Zetavg's workspace
Runs
106
Name
7 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
_name_or_path
adafactor
adam_beta1
adam_beta2
adam_epsilon
add_cross_attention
all_params_count
architectures
auto_find_batch_size
bf16
bf16_full_eval
bos_token_id
chunk_size_feed_forward
cutoff_len
data_seed
dataloader_drop_last
dataloader_num_workers
dataloader_pin_memory
ddp_bucket_cap_mb
ddp_find_unused_parameters
ddp_timeout
debug
deepspeed
disable_tqdm
diversity_penalty
do_eval
do_predict
do_sample
do_train
early_stopping
encoder_no_repeat_ngram_size
eos_token_id
eval_accumulation_steps
eval_batch_size
eval_delay
eval_steps
evaluation_strategy
fp16
fp16_backend
fp16_full_eval
fp16_opt_level
frozen_params
fsdp
fsdp_config
Finished
-
zetavg
group:ta01
3h 30m 59s
-
zh-tw-llm-dv/zh-tw-llm-ta01-pythia-6.9b-ta8000-v1-a2_1_embeddings-h100-t003-e574b6
false
0.9
0.999
1.0000e-8
false
6970556416
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
-
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Finished
-
zetavg
group:ta01
train:a2_1_embeddings
10h 13m 57s
-
zh-tw-llm-dv/zh-tw-llm-ta01-pythia-6.9b-ta8000-v1-a_1_embeddings-h100-t015-792f7c
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
250
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Crashed
-
zetavg
group:ta01
train:a2_1_embeddings
28m 31s
-
zh-tw-llm-dv/zh-tw-llm-ta01-pythia-6.9b-ta8000-v1-a_1_embeddings-h100-t015-792f7c
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Crashed
-
zetavg
group:ta01
train:a2_1_embeddings
1m 49s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Finished
-
zetavg
group:ta01
3h 25m 29s
-
zh-tw-llm-dv/zh-tw-llm-ta01-pythia-6.9b-ta8000-v1-a_1_embeddings-h100-t015-792f7c
false
0.9
0.999
1.0000e-8
false
6970556416
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
-
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Crashed
-
zetavg
group:ta01
4m 36s
-
zh-tw-llm-dv/zh-tw-llm-ta01-pythia-6.9b-ta8000-v1-a_1_embeddings-h100-t015-792f7c
false
0.9
0.999
1.0000e-8
false
6945390592
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
100
steps
false
auto
false
O1
-
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Finished
-
zetavg
group:ta01
train:a_1_embeddings
13h 9m 26s
-
EleutherAI/pythia-6.9b
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Crashed
-
zetavg
group:ta01
train:a_1_embeddings
8m 34s
-
EleutherAI/pythia-6.9b
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Failed
-
zetavg
group:ta01
train:a_1_embeddings
25s
-
EleutherAI/pythia-6.9b
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
true
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Crashed
-
zetavg
group:ta01
train:a_1_embeddings
4m 56s
-
EleutherAI/pythia-6.9b
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Crashed
-
zetavg
group:ta01
train:a_1_embeddings
11m 31s
-
EleutherAI/pythia-6.9b
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Failed
-
zetavg
group:ta01
train:a_1_embeddings
10m 43s
-
EleutherAI/pythia-6.9b
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Failed
-
zetavg
group:ta01
train:a_1_embeddings
18m 29s
-
EleutherAI/pythia-6.9b
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Crashed
-
zetavg
group:ta01
train:a_1_embeddings
24m 29s
-
EleutherAI/pythia-6.9b
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Finished
-
zetavg
group:ta01
train:a_1_embeddings
39m 47s
-
EleutherAI/pythia-6.9b
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Crashed
-
zetavg
group:ta01
train:a_1_embeddings
18m 39s
-
EleutherAI/pythia-6.9b
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Failed
-
zetavg
group:ta01
train:a_1_embeddings
8s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Finished
-
zetavg
group:ta01
train:a_1_embeddings
2h 7m 40s
-
EleutherAI/pythia-6.9b
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Failed
-
zetavg
group:ta01
train:a_1_embeddings
3m 34s
-
EleutherAI/pythia-6.9b
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.post_attention_layernorm.weight","gpt_neox.layers.0.post_attention_layernorm.bias","gpt_neox.layers.0.attention.query_key_value.weight","gpt_neox.layers.0.attention.query_key_value.bias","gpt_neox.layers.0.attention.dense.weight","gpt_neox.layers.0.attention.dense.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.post_attention_layernorm.weight","gpt_neox.layers.1.post_attention_layernorm.bias","gpt_neox.layers.1.attention.query_key_value.weight","gpt_neox.layers.1.attention.query_key_value.bias","gpt_neox.layers.1.attention.dense.weight","gpt_neox.layers.1.attention.dense.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.post_attention_layernorm.weight","gpt_neox.layers.2.post_attention_layernorm.bias","gpt_neox.layers.2.attention.query_key_value.weight","gpt_neox.layers.2.attention.query_key_value.bias","gpt_neox.layers.2.attention.dense.weight","gpt_neox.layers.2.attention.dense.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.post_attention_layernorm.weight","gpt_neox.layers.3.post_attention_layernorm.bias","gpt_neox.layers.3.attention.query_key_value.weight","gpt_neox.layers.3.attention.query_key_value.bias","gpt_neox.layers.3.attention.dense.weight","gpt_neox.layers.3.attention.dense.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.post_attention_layernorm.weight","gpt_neox.layers.4.post_attention_layernorm.bias","gpt_neox.layers.4.attention.query_key_value.weight","gpt_neox.layers.4.attention.query_key_value.bias","gpt_neox.layers.4.attention.dense.weight","gpt_neox.layers.4.attention.dense.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.post_attention_layernorm.weight","gpt_neox.layers.5.post_attention_layernorm.bias","gpt_neox.layers.5.attention.query_key_value.weight","gpt_neox.layers.5.attention.query_key_value.bias","gpt_neox.layers.5.attention.dense.weight","gpt_neox.layers.5.attention.dense.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.post_attention_layernorm.weight","gpt_neox.layers.6.post_attention_layernorm.bias","gpt_neox.layers.6.attention.query_key_value.weight","gpt_neox.layers.6.attention.query_key_value.bias","gpt_neox.layers.6.attention.dense.weight","gpt_neox.layers.6.attention.dense.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.post_attention_layernorm.weight","gpt_neox.layers.7.post_attention_layernorm.bias","gpt_neox.layers.7.attention.query_key_value.weight","gpt_neox.layers.7.attention.query_key_value.bias","gpt_neox.layers.7.attention.dense.weight","gpt_neox.layers.7.attention.dense.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.post_attention_layernorm.weight","gpt_neox.layers.8.post_attention_layernorm.bias","gpt_neox.layers.8.attention.query_key_value.weight","gpt_neox.layers.8.attention.query_key_value.bias","gpt_neox.layers.8.attention.dense.weight","gpt_neox.layers.8.attention.dense.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.post_attention_layernorm.weight","gpt_neox.layers.9.post_attention_layernorm.bias","gpt_neox.layers.9.attention.query_key_value.weight","gpt_neox.layers.9.attention.query_key_value.bias","gpt_neox.layers.9.attention.dense.weight","gpt_neox.layers.9.attention.dense.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.post_attention_layernorm.weight","gpt_neox.layers.10.post_attention_layernorm.bias","gpt_neox.layers.10.attention.query_key_value.weight","gpt_neox.layers.10.attention.query_key_value.bias","gpt_neox.layers.10.attention.dense.weight","gpt_neox.layers.10.attention.dense.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.post_attention_layernorm.weight","gpt_neox.layers.11.post_attention_layernorm.bias","gpt_neox.layers.11.attention.query_key_value.weight","gpt_neox.layers.11.attention.query_key_value.bias","gpt_neox.layers.11.attention.dense.weight","gpt_neox.layers.11.attention.dense.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.post_attention_layernorm.weight","gpt_neox.layers.12.post_attention_layernorm.bias","gpt_neox.layers.12.attention.query_key_value.weight","gpt_neox.layers.12.attention.query_key_value.bias","gpt_neox.layers.12.attention.dense.weight","gpt_neox.layers.12.attention.dense.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.post_attention_layernorm.weight","gpt_neox.layers.13.post_attention_layernorm.bias","gpt_neox.layers.13.attention.query_key_value.weight","gpt_neox.layers.13.attention.query_key_value.bias","gpt_neox.layers.13.attention.dense.weight","gpt_neox.layers.13.attention.dense.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.post_attention_layernorm.weight","gpt_neox.layers.14.post_attention_layernorm.bias","gpt_neox.layers.14.attention.query_key_value.weight","gpt_neox.layers.14.attention.query_key_value.bias","gpt_neox.layers.14.attention.dense.weight","gpt_neox.layers.14.attention.dense.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.post_attention_layernorm.weight","gpt_neox.layers.15.post_attention_layernorm.bias","gpt_neox.layers.15.attention.query_key_value.weight","gpt_neox.layers.15.attention.query_key_value.bias","gpt_neox.layers.15.attention.dense.weight","gpt_neox.layers.15.attention.dense.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.post_attention_layernorm.weight","gpt_neox.layers.16.post_attention_layernorm.bias","gpt_neox.layers.16.attention.query_key_value.weight","gpt_neox.layers.16.attention.query_key_value.bias","gpt_neox.layers.16.attention.dense.weight","gpt_neox.layers.16.attention.dense.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.post_attention_layernorm.weight","gpt_neox.layers.17.post_attention_layernorm.bias","gpt_neox.layers.17.attention.query_key_value.weight","gpt_neox.layers.17.attention.query_key_value.bias","gpt_neox.layers.17.attention.dense.weight","gpt_neox.layers.17.attention.dense.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.post_attention_layernorm.weight","gpt_neox.layers.18.post_attention_layernorm.bias","gpt_neox.layers.18.attention.query_key_value.weight","gpt_neox.layers.18.attention.query_key_value.bias","gpt_neox.layers.18.attention.dense.weight","gpt_neox.layers.18.attention.dense.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.post_attention_layernorm.weight","gpt_neox.layers.19.post_attention_layernorm.bias","gpt_neox.layers.19.attention.query_key_value.weight","gpt_neox.layers.19.attention.query_key_value.bias","gpt_neox.layers.19.attention.dense.weight","gpt_neox.layers.19.attention.dense.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.post_attention_layernorm.weight","gpt_neox.layers.20.post_attention_layernorm.bias","gpt_neox.layers.20.attention.query_key_value.weight","gpt_neox.layers.20.attention.query_key_value.bias","gpt_neox.layers.20.attention.dense.weight","gpt_neox.layers.20.attention.dense.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.post_attention_layernorm.weight","gpt_neox.layers.21.post_attention_layernorm.bias","gpt_neox.layers.21.attention.query_key_value.weight","gpt_neox.layers.21.attention.query_key_value.bias","gpt_neox.layers.21.attention.dense.weight","gpt_neox.layers.21.attention.dense.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.post_attention_layernorm.weight","gpt_neox.layers.22.post_attention_layernorm.bias","gpt_neox.layers.22.attention.query_key_value.weight","gpt_neox.layers.22.attention.query_key_value.bias","gpt_neox.layers.22.attention.dense.weight","gpt_neox.layers.22.attention.dense.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.post_attention_layernorm.weight","gpt_neox.layers.23.post_attention_layernorm.bias","gpt_neox.layers.23.attention.query_key_value.weight","gpt_neox.layers.23.attention.query_key_value.bias","gpt_neox.layers.23.attention.dense.weight","gpt_neox.layers.23.attention.dense.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.post_attention_layernorm.weight","gpt_neox.layers.24.post_attention_layernorm.bias","gpt_neox.layers.24.attention.query_key_value.weight","gpt_neox.layers.24.attention.query_key_value.bias","gpt_neox.layers.24.attention.dense.weight","gpt_neox.layers.24.attention.dense.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.post_attention_layernorm.weight","gpt_neox.layers.25.post_attention_layernorm.bias","gpt_neox.layers.25.attention.query_key_value.weight","gpt_neox.layers.25.attention.query_key_value.bias","gpt_neox.layers.25.attention.dense.weight","gpt_neox.layers.25.attention.dense.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.post_attention_layernorm.weight","gpt_neox.layers.26.post_attention_layernorm.bias","gpt_neox.layers.26.attention.query_key_value.weight","gpt_neox.layers.26.attention.query_key_value.bias","gpt_neox.layers.26.attention.dense.weight","gpt_neox.layers.26.attention.dense.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.post_attention_layernorm.weight","gpt_neox.layers.27.post_attention_layernorm.bias","gpt_neox.layers.27.attention.query_key_value.weight","gpt_neox.layers.27.attention.query_key_value.bias","gpt_neox.layers.27.attention.dense.weight","gpt_neox.layers.27.attention.dense.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.post_attention_layernorm.weight","gpt_neox.layers.28.post_attention_layernorm.bias","gpt_neox.layers.28.attention.query_key_value.weight","gpt_neox.layers.28.attention.query_key_value.bias","gpt_neox.layers.28.attention.dense.weight","gpt_neox.layers.28.attention.dense.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.post_attention_layernorm.weight","gpt_neox.layers.29.post_attention_layernorm.bias","gpt_neox.layers.29.attention.query_key_value.weight","gpt_neox.layers.29.attention.query_key_value.bias","gpt_neox.layers.29.attention.dense.weight","gpt_neox.layers.29.attention.dense.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.post_attention_layernorm.weight","gpt_neox.layers.30.post_attention_layernorm.bias","gpt_neox.layers.30.attention.query_key_value.weight","gpt_neox.layers.30.attention.query_key_value.bias","gpt_neox.layers.30.attention.dense.weight","gpt_neox.layers.30.attention.dense.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.post_attention_layernorm.weight","gpt_neox.layers.31.post_attention_layernorm.bias","gpt_neox.layers.31.attention.query_key_value.weight","gpt_neox.layers.31.attention.query_key_value.bias","gpt_neox.layers.31.attention.dense.weight","gpt_neox.layers.31.attention.dense.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
Failed
-
zetavg
group:ta01
4m 12s
-
EleutherAI/pythia-6.9b
false
0.9
0.999
1.0000e-8
false
6920224768
["GPTNeoXForCausalLM"]
true
false
false
0
0
-
None
false
0
true
None
None
1800
[]
None
false
0
true
false
false
false
false
0
0
None
8
0
500
steps
false
auto
false
O1
["gpt_neox.layers.0.input_layernorm.weight","gpt_neox.layers.0.input_layernorm.bias","gpt_neox.layers.0.mlp.dense_h_to_4h.weight","gpt_neox.layers.0.mlp.dense_h_to_4h.bias","gpt_neox.layers.0.mlp.dense_4h_to_h.weight","gpt_neox.layers.0.mlp.dense_4h_to_h.bias","gpt_neox.layers.1.input_layernorm.weight","gpt_neox.layers.1.input_layernorm.bias","gpt_neox.layers.1.mlp.dense_h_to_4h.weight","gpt_neox.layers.1.mlp.dense_h_to_4h.bias","gpt_neox.layers.1.mlp.dense_4h_to_h.weight","gpt_neox.layers.1.mlp.dense_4h_to_h.bias","gpt_neox.layers.2.input_layernorm.weight","gpt_neox.layers.2.input_layernorm.bias","gpt_neox.layers.2.mlp.dense_h_to_4h.weight","gpt_neox.layers.2.mlp.dense_h_to_4h.bias","gpt_neox.layers.2.mlp.dense_4h_to_h.weight","gpt_neox.layers.2.mlp.dense_4h_to_h.bias","gpt_neox.layers.3.input_layernorm.weight","gpt_neox.layers.3.input_layernorm.bias","gpt_neox.layers.3.mlp.dense_h_to_4h.weight","gpt_neox.layers.3.mlp.dense_h_to_4h.bias","gpt_neox.layers.3.mlp.dense_4h_to_h.weight","gpt_neox.layers.3.mlp.dense_4h_to_h.bias","gpt_neox.layers.4.input_layernorm.weight","gpt_neox.layers.4.input_layernorm.bias","gpt_neox.layers.4.mlp.dense_h_to_4h.weight","gpt_neox.layers.4.mlp.dense_h_to_4h.bias","gpt_neox.layers.4.mlp.dense_4h_to_h.weight","gpt_neox.layers.4.mlp.dense_4h_to_h.bias","gpt_neox.layers.5.input_layernorm.weight","gpt_neox.layers.5.input_layernorm.bias","gpt_neox.layers.5.mlp.dense_h_to_4h.weight","gpt_neox.layers.5.mlp.dense_h_to_4h.bias","gpt_neox.layers.5.mlp.dense_4h_to_h.weight","gpt_neox.layers.5.mlp.dense_4h_to_h.bias","gpt_neox.layers.6.input_layernorm.weight","gpt_neox.layers.6.input_layernorm.bias","gpt_neox.layers.6.mlp.dense_h_to_4h.weight","gpt_neox.layers.6.mlp.dense_h_to_4h.bias","gpt_neox.layers.6.mlp.dense_4h_to_h.weight","gpt_neox.layers.6.mlp.dense_4h_to_h.bias","gpt_neox.layers.7.input_layernorm.weight","gpt_neox.layers.7.input_layernorm.bias","gpt_neox.layers.7.mlp.dense_h_to_4h.weight","gpt_neox.layers.7.mlp.dense_h_to_4h.bias","gpt_neox.layers.7.mlp.dense_4h_to_h.weight","gpt_neox.layers.7.mlp.dense_4h_to_h.bias","gpt_neox.layers.8.input_layernorm.weight","gpt_neox.layers.8.input_layernorm.bias","gpt_neox.layers.8.mlp.dense_h_to_4h.weight","gpt_neox.layers.8.mlp.dense_h_to_4h.bias","gpt_neox.layers.8.mlp.dense_4h_to_h.weight","gpt_neox.layers.8.mlp.dense_4h_to_h.bias","gpt_neox.layers.9.input_layernorm.weight","gpt_neox.layers.9.input_layernorm.bias","gpt_neox.layers.9.mlp.dense_h_to_4h.weight","gpt_neox.layers.9.mlp.dense_h_to_4h.bias","gpt_neox.layers.9.mlp.dense_4h_to_h.weight","gpt_neox.layers.9.mlp.dense_4h_to_h.bias","gpt_neox.layers.10.input_layernorm.weight","gpt_neox.layers.10.input_layernorm.bias","gpt_neox.layers.10.mlp.dense_h_to_4h.weight","gpt_neox.layers.10.mlp.dense_h_to_4h.bias","gpt_neox.layers.10.mlp.dense_4h_to_h.weight","gpt_neox.layers.10.mlp.dense_4h_to_h.bias","gpt_neox.layers.11.input_layernorm.weight","gpt_neox.layers.11.input_layernorm.bias","gpt_neox.layers.11.mlp.dense_h_to_4h.weight","gpt_neox.layers.11.mlp.dense_h_to_4h.bias","gpt_neox.layers.11.mlp.dense_4h_to_h.weight","gpt_neox.layers.11.mlp.dense_4h_to_h.bias","gpt_neox.layers.12.input_layernorm.weight","gpt_neox.layers.12.input_layernorm.bias","gpt_neox.layers.12.mlp.dense_h_to_4h.weight","gpt_neox.layers.12.mlp.dense_h_to_4h.bias","gpt_neox.layers.12.mlp.dense_4h_to_h.weight","gpt_neox.layers.12.mlp.dense_4h_to_h.bias","gpt_neox.layers.13.input_layernorm.weight","gpt_neox.layers.13.input_layernorm.bias","gpt_neox.layers.13.mlp.dense_h_to_4h.weight","gpt_neox.layers.13.mlp.dense_h_to_4h.bias","gpt_neox.layers.13.mlp.dense_4h_to_h.weight","gpt_neox.layers.13.mlp.dense_4h_to_h.bias","gpt_neox.layers.14.input_layernorm.weight","gpt_neox.layers.14.input_layernorm.bias","gpt_neox.layers.14.mlp.dense_h_to_4h.weight","gpt_neox.layers.14.mlp.dense_h_to_4h.bias","gpt_neox.layers.14.mlp.dense_4h_to_h.weight","gpt_neox.layers.14.mlp.dense_4h_to_h.bias","gpt_neox.layers.15.input_layernorm.weight","gpt_neox.layers.15.input_layernorm.bias","gpt_neox.layers.15.mlp.dense_h_to_4h.weight","gpt_neox.layers.15.mlp.dense_h_to_4h.bias","gpt_neox.layers.15.mlp.dense_4h_to_h.weight","gpt_neox.layers.15.mlp.dense_4h_to_h.bias","gpt_neox.layers.16.input_layernorm.weight","gpt_neox.layers.16.input_layernorm.bias","gpt_neox.layers.16.mlp.dense_h_to_4h.weight","gpt_neox.layers.16.mlp.dense_h_to_4h.bias","gpt_neox.layers.16.mlp.dense_4h_to_h.weight","gpt_neox.layers.16.mlp.dense_4h_to_h.bias","gpt_neox.layers.17.input_layernorm.weight","gpt_neox.layers.17.input_layernorm.bias","gpt_neox.layers.17.mlp.dense_h_to_4h.weight","gpt_neox.layers.17.mlp.dense_h_to_4h.bias","gpt_neox.layers.17.mlp.dense_4h_to_h.weight","gpt_neox.layers.17.mlp.dense_4h_to_h.bias","gpt_neox.layers.18.input_layernorm.weight","gpt_neox.layers.18.input_layernorm.bias","gpt_neox.layers.18.mlp.dense_h_to_4h.weight","gpt_neox.layers.18.mlp.dense_h_to_4h.bias","gpt_neox.layers.18.mlp.dense_4h_to_h.weight","gpt_neox.layers.18.mlp.dense_4h_to_h.bias","gpt_neox.layers.19.input_layernorm.weight","gpt_neox.layers.19.input_layernorm.bias","gpt_neox.layers.19.mlp.dense_h_to_4h.weight","gpt_neox.layers.19.mlp.dense_h_to_4h.bias","gpt_neox.layers.19.mlp.dense_4h_to_h.weight","gpt_neox.layers.19.mlp.dense_4h_to_h.bias","gpt_neox.layers.20.input_layernorm.weight","gpt_neox.layers.20.input_layernorm.bias","gpt_neox.layers.20.mlp.dense_h_to_4h.weight","gpt_neox.layers.20.mlp.dense_h_to_4h.bias","gpt_neox.layers.20.mlp.dense_4h_to_h.weight","gpt_neox.layers.20.mlp.dense_4h_to_h.bias","gpt_neox.layers.21.input_layernorm.weight","gpt_neox.layers.21.input_layernorm.bias","gpt_neox.layers.21.mlp.dense_h_to_4h.weight","gpt_neox.layers.21.mlp.dense_h_to_4h.bias","gpt_neox.layers.21.mlp.dense_4h_to_h.weight","gpt_neox.layers.21.mlp.dense_4h_to_h.bias","gpt_neox.layers.22.input_layernorm.weight","gpt_neox.layers.22.input_layernorm.bias","gpt_neox.layers.22.mlp.dense_h_to_4h.weight","gpt_neox.layers.22.mlp.dense_h_to_4h.bias","gpt_neox.layers.22.mlp.dense_4h_to_h.weight","gpt_neox.layers.22.mlp.dense_4h_to_h.bias","gpt_neox.layers.23.input_layernorm.weight","gpt_neox.layers.23.input_layernorm.bias","gpt_neox.layers.23.mlp.dense_h_to_4h.weight","gpt_neox.layers.23.mlp.dense_h_to_4h.bias","gpt_neox.layers.23.mlp.dense_4h_to_h.weight","gpt_neox.layers.23.mlp.dense_4h_to_h.bias","gpt_neox.layers.24.input_layernorm.weight","gpt_neox.layers.24.input_layernorm.bias","gpt_neox.layers.24.mlp.dense_h_to_4h.weight","gpt_neox.layers.24.mlp.dense_h_to_4h.bias","gpt_neox.layers.24.mlp.dense_4h_to_h.weight","gpt_neox.layers.24.mlp.dense_4h_to_h.bias","gpt_neox.layers.25.input_layernorm.weight","gpt_neox.layers.25.input_layernorm.bias","gpt_neox.layers.25.mlp.dense_h_to_4h.weight","gpt_neox.layers.25.mlp.dense_h_to_4h.bias","gpt_neox.layers.25.mlp.dense_4h_to_h.weight","gpt_neox.layers.25.mlp.dense_4h_to_h.bias","gpt_neox.layers.26.input_layernorm.weight","gpt_neox.layers.26.input_layernorm.bias","gpt_neox.layers.26.mlp.dense_h_to_4h.weight","gpt_neox.layers.26.mlp.dense_h_to_4h.bias","gpt_neox.layers.26.mlp.dense_4h_to_h.weight","gpt_neox.layers.26.mlp.dense_4h_to_h.bias","gpt_neox.layers.27.input_layernorm.weight","gpt_neox.layers.27.input_layernorm.bias","gpt_neox.layers.27.mlp.dense_h_to_4h.weight","gpt_neox.layers.27.mlp.dense_h_to_4h.bias","gpt_neox.layers.27.mlp.dense_4h_to_h.weight","gpt_neox.layers.27.mlp.dense_4h_to_h.bias","gpt_neox.layers.28.input_layernorm.weight","gpt_neox.layers.28.input_layernorm.bias","gpt_neox.layers.28.mlp.dense_h_to_4h.weight","gpt_neox.layers.28.mlp.dense_h_to_4h.bias","gpt_neox.layers.28.mlp.dense_4h_to_h.weight","gpt_neox.layers.28.mlp.dense_4h_to_h.bias","gpt_neox.layers.29.input_layernorm.weight","gpt_neox.layers.29.input_layernorm.bias","gpt_neox.layers.29.mlp.dense_h_to_4h.weight","gpt_neox.layers.29.mlp.dense_h_to_4h.bias","gpt_neox.layers.29.mlp.dense_4h_to_h.weight","gpt_neox.layers.29.mlp.dense_4h_to_h.bias","gpt_neox.layers.30.input_layernorm.weight","gpt_neox.layers.30.input_layernorm.bias","gpt_neox.layers.30.mlp.dense_h_to_4h.weight","gpt_neox.layers.30.mlp.dense_h_to_4h.bias","gpt_neox.layers.30.mlp.dense_4h_to_h.weight","gpt_neox.layers.30.mlp.dense_4h_to_h.bias","gpt_neox.layers.31.input_layernorm.weight","gpt_neox.layers.31.input_layernorm.bias","gpt_neox.layers.31.mlp.dense_h_to_4h.weight","gpt_neox.layers.31.mlp.dense_h_to_4h.bias","gpt_neox.layers.31.mlp.dense_4h_to_h.weight","gpt_neox.layers.31.mlp.dense_4h_to_h.bias","gpt_neox.final_layer_norm.weight","gpt_neox.final_layer_norm.bias"]
[]
{'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}
1-20
of 106