Huseinzol05's workspace
Runs
1
State
Notes
User
Tags
Created
Runtime
Sweep
_attn_implementation_autoset
_name_or_path
accelerator_config.even_batches
accelerator_config.non_blocking
accelerator_config.split_batches
accelerator_config.use_seedable_sampler
adafactor
adam_beta1
adam_beta2
adam_epsilon
add_cross_attention
architectures
attention_dropout
auto_find_batch_size
average_tokens_across_devices
batch_eval_metrics
beta
bf16
bf16_full_eval
bos_token_id
chunk_size_feed_forward
dataloader_drop_last
dataloader_num_workers
dataloader_persistent_workers
dataloader_pin_memory
ddp_find_unused_parameters
ddp_timeout
debug
disable_dropout
disable_tqdm
diversity_penalty
do_eval
do_predict
do_sample
do_train
ds3_gather_for_generation
early_stopping
encoder_no_repeat_ngram_size
eos_token_id
epsilon
eval_delay
eval_do_concat_batches
eval_on_start
eval_strategy
Crashed
-
huseinzol05
22h 18m 55s
-
true
mesolitica/Malaysian-Qwen2.5-7B-Reasoning-SFT
true
false
false
true
false
0.9
0.999
1.0000e-8
false
["Qwen2ForCausalLM"]
0
false
false
false
0.04
true
false
151643
0
false
0
false
true
false
1800
[]
false
false
0
false
false
false
true
true
false
0
151645
0.2
0
true
false
no
1-1
of 1