Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.9-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
3cdbc81
·
verified ·
1 Parent(s): 4cf4134

Training in progress, step 400

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +6 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0222416e1ec9d0120a5a4314348666fdd6ac0492a111cb2eb970f19aaedef4b9
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4536ef2974aa09ce1e948c88ab1bb493563e6b259d6d8b5d99fdcfed4854e70
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -40,3 +40,9 @@
40
  {"current_steps": 340, "total_steps": 1500, "loss": 0.4718, "accuracy": 0.7749999761581421, "learning_rate": 4.3924876391293915e-06, "epoch": 0.27447023208879917, "percentage": 22.67, "elapsed_time": "0:47:39", "remaining_time": "2:42:35", "throughput": "0.00", "total_tokens": 0}
41
  {"current_steps": 350, "total_steps": 1500, "loss": 0.4909, "accuracy": 0.7124999761581421, "learning_rate": 4.357862063693486e-06, "epoch": 0.28254288597376387, "percentage": 23.33, "elapsed_time": "0:48:53", "remaining_time": "2:40:37", "throughput": "0.00", "total_tokens": 0}
42
  {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.44899094104766846, "epoch": 0.28254288597376387, "percentage": 23.33, "elapsed_time": "0:49:23", "remaining_time": "2:42:15", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
40
  {"current_steps": 340, "total_steps": 1500, "loss": 0.4718, "accuracy": 0.7749999761581421, "learning_rate": 4.3924876391293915e-06, "epoch": 0.27447023208879917, "percentage": 22.67, "elapsed_time": "0:47:39", "remaining_time": "2:42:35", "throughput": "0.00", "total_tokens": 0}
41
  {"current_steps": 350, "total_steps": 1500, "loss": 0.4909, "accuracy": 0.7124999761581421, "learning_rate": 4.357862063693486e-06, "epoch": 0.28254288597376387, "percentage": 23.33, "elapsed_time": "0:48:53", "remaining_time": "2:40:37", "throughput": "0.00", "total_tokens": 0}
42
  {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.44899094104766846, "epoch": 0.28254288597376387, "percentage": 23.33, "elapsed_time": "0:49:23", "remaining_time": "2:42:15", "throughput": "0.00", "total_tokens": 0}
43
+ {"current_steps": 360, "total_steps": 1500, "loss": 0.4561, "accuracy": 0.737500011920929, "learning_rate": 4.322421568553529e-06, "epoch": 0.29061553985872857, "percentage": 24.0, "elapsed_time": "0:50:45", "remaining_time": "2:40:45", "throughput": "0.00", "total_tokens": 0}
44
+ {"current_steps": 370, "total_steps": 1500, "loss": 0.4305, "accuracy": 0.737500011920929, "learning_rate": 4.286181699082008e-06, "epoch": 0.29868819374369326, "percentage": 24.67, "elapsed_time": "0:52:03", "remaining_time": "2:38:59", "throughput": "0.00", "total_tokens": 0}
45
+ {"current_steps": 380, "total_steps": 1500, "loss": 0.4358, "accuracy": 0.737500011920929, "learning_rate": 4.249158351283414e-06, "epoch": 0.3067608476286579, "percentage": 25.33, "elapsed_time": "0:53:18", "remaining_time": "2:37:07", "throughput": "0.00", "total_tokens": 0}
46
+ {"current_steps": 390, "total_steps": 1500, "loss": 0.4565, "accuracy": 0.7250000238418579, "learning_rate": 4.211367764821722e-06, "epoch": 0.3148335015136226, "percentage": 26.0, "elapsed_time": "0:54:37", "remaining_time": "2:35:29", "throughput": "0.00", "total_tokens": 0}
47
+ {"current_steps": 400, "total_steps": 1500, "loss": 0.408, "accuracy": 0.887499988079071, "learning_rate": 4.172826515897146e-06, "epoch": 0.3229061553985873, "percentage": 26.67, "elapsed_time": "0:55:56", "remaining_time": "2:33:51", "throughput": "0.00", "total_tokens": 0}
48
+ {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.38578492403030396, "epoch": 0.3229061553985873, "percentage": 26.67, "elapsed_time": "0:56:26", "remaining_time": "2:35:13", "throughput": "0.00", "total_tokens": 0}