Asap-zzhou's workspace
Runs
28
Name
0 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
_attn_implementation_autoset
_name_or_path
accelerator_config.dispatch_batches
accelerator_config.even_batches
accelerator_config.non_blocking
accelerator_config.split_batches
accelerator_config.use_seedable_sampler
activation_type
adafactor
adam_beta1
adam_beta2
adam_epsilon
add_cross_attention
alibi
alibi_bias_max
architectures
attention_dropout
attention_layer_norm
attention_layer_norm_with_affine
auto_find_batch_size
auto_map.AutoConfig
auto_map.AutoModel
auto_map.AutoModelForCausalLM
average_tokens_across_devices
batch_eval_metrics
bf16
bf16_full_eval
bias
bias_for_layer_norm
block_group_size
block_type
chunk_size_feed_forward
d_model
dataloader_drop_last
dataloader_num_workers
dataloader_persistent_workers
dataloader_pin_memory
ddp_timeout
debug
disable_tqdm
diversity_penalty
do_eval
do_predict
do_sample
Crashed
asap-zzhou
2d 15h 22m 17s
-
-
["/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-base","/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-large"]
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
ModernBertForMaskedLM
0
-
-
false
-
-
-
true
false
true
false
-
-
-
-
0
-
false
0
false
true
1800
-
false
0
[false,true]
false
false
Crashed
asap-zzhou
32s
-
-
/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-base
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["ModernBertForMaskedLM"]
0
-
-
false
-
-
-
true
false
true
false
-
-
-
-
0
-
false
0
false
true
1800
[]
false
0
true
false
false
Crashed
asap-zzhou
3m 1s
-
-
/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-base
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["ModernBertForMaskedLM"]
0
-
-
false
-
-
-
true
false
true
false
-
-
-
-
0
-
false
0
false
true
1800
[]
false
0
true
false
false
Crashed
asap-zzhou
5m 16s
-
-
/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-base
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["ModernBertForMaskedLM"]
0
-
-
false
-
-
-
true
false
true
false
-
-
-
-
0
-
false
0
false
true
1800
[]
false
0
true
false
false
Crashed
asap-zzhou
6h 37m 8s
-
-
/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-large
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["ModernBertForMaskedLM"]
0
-
-
false
-
-
-
true
false
true
false
-
-
-
-
0
-
false
0
false
true
1800
[]
false
0
false
false
false
Finished
asap-zzhou
8m 36s
-
-
["/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-large","models/ModernBERT-large/openwebtext/steps-200000-bs-1024-len-1024/checkpoint-18000","models/ModernBERT-large/wikitext-103-v1/epochs-20-bs-512-len-512/checkpoint-final"]
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
ModernBertForMaskedLM
0
-
-
false
-
-
-
true
false
true
false
-
-
-
-
0
-
false
0
false
true
1800
-
false
0
true
false
false
Finished
asap-zzhou
8m 34s
-
-
models/ModernBERT-large/openwebtext/steps-200000-bs-1024-len-1024/checkpoint-18000
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["ModernBertForMaskedLM"]
0
-
-
false
-
-
-
true
false
true
false
-
-
-
-
0
-
false
0
false
true
1800
[]
false
0
true
false
false
Finished
asap-zzhou
8m 35s
-
-
models/ModernBERT-large/wikitext-103-v1/epochs-20-bs-512-len-512/checkpoint-final
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["ModernBertForMaskedLM"]
0
-
-
false
-
-
-
true
false
true
false
-
-
-
-
0
-
false
0
false
true
1800
[]
false
0
true
false
false
Finished
asap-zzhou
8m 25s
-
-
/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-large
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["ModernBertForMaskedLM"]
0
-
-
false
-
-
-
true
false
true
false
-
-
-
-
0
-
false
0
false
true
1800
[]
false
0
true
false
false
Finished
asap-zzhou
2d 15h 34m 20s
-
-
["/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-base","/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-large","models/ModernBERT-base/opc-sft-stage1/epochs-10-bs-384-len-1024/checkpoint-final"]
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
ModernBertForMaskedLM
0
-
-
false
-
-
-
true
false
true
false
-
-
-
-
0
-
false
0
false
true
1800
-
false
0
true
false
false
Finished
asap-zzhou
1d 15h 56m 9s
-
-
["/mnt/lustrenew/mllm_aligned/shared/models/huggingface/FacebookAI/roberta-base","/mnt/lustrenew/mllm_aligned/shared/models/huggingface/FacebookAI/roberta-large","/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-base","/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-large","/mnt/lustrenew/mllm_aligned/shared/models/huggingface/google-bert/bert-base-uncased","/mnt/lustrenew/mllm_aligned/shared/models/huggingface/google-bert/bert-large-uncased"]
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["BertForMaskedLM","ModernBertForMaskedLM","RobertaForMaskedLM"]
0
-
-
false
-
-
-
true
false
true
false
none
-
-
-
0
-
false
0
false
true
1800
-
false
0
true
false
false
Crashed
Finished
asap-zzhou
3d 1h 24m 59s
-
-
["/mnt/lustrenew/mllm_aligned/shared/models/huggingface/FacebookAI/roberta-large","/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-large"]
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["ModernBertForMaskedLM","RobertaForMaskedLM"]
0
-
-
false
-
-
-
true
false
true
false
none
-
-
-
0
-
false
0
false
true
1800
-
false
0
[false,true]
false
false
Crashed
asap-zzhou
9h 9m 46s
-
-
/mnt/lustrenew/mllm_aligned/shared/models/huggingface/answerdotai/ModernBERT-large
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["ModernBertForMaskedLM"]
0
-
-
false
-
-
-
true
false
true
false
-
-
-
-
0
-
false
0
false
true
1800
[]
false
0
false
false
false
Finished
asap-zzhou
4h 29m 42s
-
-
/mnt/lustrenew/mllm_aligned/shared/models/huggingface/FacebookAI/roberta-large
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["RobertaForMaskedLM"]
-
-
-
false
-
-
-
true
false
true
false
none
-
-
-
0
-
false
0
false
true
1800
[]
false
0
true
false
false
Finished
asap-zzhou
48m 15s
-
-
/mnt/lustrenew/mllm_aligned/shared/models/huggingface/FacebookAI/roberta-large
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["RobertaForMaskedLM"]
-
-
-
false
-
-
-
true
false
true
false
none
-
-
-
0
-
false
0
false
true
1800
[]
false
0
true
false
false
Finished
asap-zzhou
36m 36s
-
-
/mnt/lustrenew/mllm_aligned/shared/models/huggingface/FacebookAI/roberta-large
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["RobertaForMaskedLM"]
-
-
-
false
-
-
-
true
false
true
false
none
-
-
-
0
-
false
0
false
true
1800
[]
false
0
true
false
false
Finished
asap-zzhou
5h 14m 35s
-
-
/mnt/lustrenew/mllm_aligned/shared/models/huggingface/FacebookAI/roberta-large
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["RobertaForMaskedLM"]
-
-
-
false
-
-
-
true
false
true
false
none
-
-
-
0
-
false
0
false
true
1800
[]
false
0
true
false
false
Crashed
Finished
asap-zzhou
1d 14h 17m 50s
-
-
["/mnt/lustrenew/mllm_aligned/shared/models/huggingface/Dream-org/Dream-v0-Base-7B","/mnt/lustrenew/mllm_aligned/shared/models/huggingface/GSAI-ML/LLaDA-8B-Base"]
-
true
false
false
true
silu
false
0.9
0.999
1.0000e-8
false
false
8
["DreamModel","LLaDAModelLM"]
0
false
true
false
["configuration_dream.DreamConfig","configuration_llada.LLaDAConfig"]
["modeling_dream.DreamModel","modeling_llada.LLaDAModelLM"]
modeling_llada.LLaDAModelLM
true
false
true
false
none
false
1
llama
0
4096
false
0
false
true
1800
-
false
0
true
false
false
Finished
asap-zzhou
16h 45m 36s
-
-
/mnt/lustrenew/mllm_aligned/shared/models/huggingface/Dream-org/Dream-v0-Base-7B
-
true
false
false
true
-
false
0.9
0.999
1.0000e-8
false
-
-
["DreamModel"]
0
-
-
false
configuration_dream.DreamConfig
modeling_dream.DreamModel
-
true
false
true
false
none
-
-
-
0
-
false
0
false
true
1800
[]
false
0
true
false
false
Finished
asap-zzhou
7h 33m 14s
-
-
/mnt/lustrenew/mllm_aligned/shared/models/huggingface/GSAI-ML/LLaDA-8B-Base
-
true
false
false
true
silu
false
0.9
0.999
1.0000e-8
false
false
8
["LLaDAModelLM"]
0
false
true
false
configuration_llada.LLaDAConfig
modeling_llada.LLaDAModelLM
modeling_llada.LLaDAModelLM
true
false
true
false
none
false
1
llama
0
4096
false
0
false
true
1800
[]
false
0
true
false
false
Crashed
asap-zzhou
7h 40m 48s
-
-
/mnt/lustrenew/mllm_aligned/shared/models/huggingface/GSAI-ML/LLaDA-8B-Base
-
true
false
false
true
silu
false
0.9
0.999
1.0000e-8
false
false
8
["LLaDAModelLM"]
0
false
true
false
configuration_llada.LLaDAConfig
modeling_llada.LLaDAModelLM
modeling_llada.LLaDAModelLM
true
false
true
false
none
false
1
llama
0
4096
false
0
false
true
1800
[]
false
0
true
false
false
1-6
of 6