Wing-lian's workspace
Runs
7
State
Notes
User
Tags
Created
Runtime
Sweep
_name_or_path
adafactor
adam_beta1
adam_beta2
adam_epsilon
add_cross_attention
architectures
attention_dropout
auto_find_batch_size
bench_dataset
bench_source_max_len
bench_split
bf16
bf16_full_eval
bos_token_id
chunk_size_feed_forward
dataloader_drop_last
dataloader_num_workers
dataloader_persistent_workers
dataloader_pin_memory
dataloader_prefetch_factor
ddp_find_unused_parameters
ddp_timeout
debug
deepspeed
disable_tqdm
diversity_penalty
do_bench_eval
do_eval
do_predict
do_sample
do_train
early_stopping
encoder_no_repeat_ngram_size
eos_token_id
eval_accumulation_steps
eval_delay
eval_sample_packing
eval_steps
evaluation_strategy
fp16
fp16_backend
fp16_full_eval
fp16_opt_level
Finished
wing-lian
9h 49m 20s
-
mistralai/Mixtral-8x7B-v0.1
false
0.9
0.95
0.00001
false
["MixtralForCausalLM"]
0
false
pharaouk/dharma-1/dharma_1_mini.json
2048
eval
true
false
1
0
false
8
false
true
4
false
1800
[]
deepspeed/zero2.json
false
0
false
true
false
false
false
false
0
32000
1
0
true
0.05
steps
false
auto
false
O1
Crashed
wing-lian
32m 1s
-
mistralai/Mixtral-8x7B-v0.1
false
0.9
0.999
1.0000e-8
false
["MixtralForCausalLM"]
0
false
pharaouk/dharma-1/dharma_1_mini.json
2048
eval
true
false
1
0
false
8
false
true
4
false
1800
[]
deepspeed/zero2.json
false
0
false
true
false
false
false
false
0
32000
1
0
true
0.05
steps
false
auto
false
O1
Crashed
wing-lian
8s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Crashed
wing-lian
9m
-
mistralai/Mixtral-8x7B-v0.1
false
0.9
0.999
1.0000e-8
false
["MixtralForCausalLM"]
0
false
pharaouk/dharma-1/dharma_1_mini.json
2048
eval
true
false
1
0
false
8
false
true
4
false
1800
[]
deepspeed/zero2.json
false
0
false
true
false
false
false
false
0
32000
2
0
true
0.05
steps
false
auto
false
O1
Crashed
wing-lian
1m 46s
-
mistralai/Mixtral-8x7B-v0.1
false
0.9
0.999
1.0000e-8
false
["MixtralForCausalLM"]
0
false
pharaouk/dharma-1/dharma_1_mini.json
2048
eval
true
false
1
0
false
8
false
true
4
false
1800
[]
deepspeed/zero2.json
false
0
false
true
false
false
false
false
0
32000
2
0
true
0.05
steps
false
auto
false
O1
Crashed
wing-lian
7s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Crashed
wing-lian
3m 25s
-
mistralai/Mixtral-8x7B-v0.1
false
0.9
0.999
1.0000e-8
false
["MixtralForCausalLM"]
0
false
pharaouk/dharma-1/dharma_1_mini.json
2048
eval
true
false
1
0
false
0
false
true
-
false
1800
[]
deepspeed/zero2.json
false
0
false
true
false
false
false
false
0
32000
2
0
true
0.05
steps
false
auto
false
O1
1-7
of 7