Hugging Face's logo

prosecalign
/
clm7b0129-kendall-onof-ofif-corr-max-2-simpo-max1500-decay-sft-beta1.5-gamma0.5-lr5e-6

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
c8a293a
·
verified ·
1 Parent(s): aa3579a

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 sha256:9a7a520373f138bb236cd642a1ccafb049449ab3dd41944526c9b0af107b5bbe
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b30ac6751c045ed92611c88c626e1042849316e294b20a22f67f1ed48479733
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -40,3 +40,9 @@
40
  {"current_steps": 340, "total_steps": 1500, "loss": 4.7181, "accuracy": 0.625, "learning_rate": 4.3924876391293915e-06, "epoch": 0.2464437800126846, "percentage": 22.67, "elapsed_time": "0:46:31", "remaining_time": "2:38:45", "throughput": "0.00", "total_tokens": 0}
41
  {"current_steps": 350, "total_steps": 1500, "loss": 4.6111, "accuracy": 0.675000011920929, "learning_rate": 4.357862063693486e-06, "epoch": 0.2536921264836459, "percentage": 23.33, "elapsed_time": "0:47:45", "remaining_time": "2:36:54", "throughput": "0.00", "total_tokens": 0}
42
  {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.571855366230011, "epoch": 0.2536921264836459, "percentage": 23.33, "elapsed_time": "0:48:15", "remaining_time": "2:38:34", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
40
  {"current_steps": 340, "total_steps": 1500, "loss": 4.7181, "accuracy": 0.625, "learning_rate": 4.3924876391293915e-06, "epoch": 0.2464437800126846, "percentage": 22.67, "elapsed_time": "0:46:31", "remaining_time": "2:38:45", "throughput": "0.00", "total_tokens": 0}
41
  {"current_steps": 350, "total_steps": 1500, "loss": 4.6111, "accuracy": 0.675000011920929, "learning_rate": 4.357862063693486e-06, "epoch": 0.2536921264836459, "percentage": 23.33, "elapsed_time": "0:47:45", "remaining_time": "2:36:54", "throughput": "0.00", "total_tokens": 0}
42
  {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.571855366230011, "epoch": 0.2536921264836459, "percentage": 23.33, "elapsed_time": "0:48:15", "remaining_time": "2:38:34", "throughput": "0.00", "total_tokens": 0}
43
+ {"current_steps": 360, "total_steps": 1500, "loss": 4.8991, "accuracy": 0.6625000238418579, "learning_rate": 4.322421568553529e-06, "epoch": 0.2609404729546072, "percentage": 24.0, "elapsed_time": "0:49:40", "remaining_time": "2:37:19", "throughput": "0.00", "total_tokens": 0}
44
+ {"current_steps": 370, "total_steps": 1500, "loss": 4.6471, "accuracy": 0.637499988079071, "learning_rate": 4.286181699082008e-06, "epoch": 0.26818881942556855, "percentage": 24.67, "elapsed_time": "0:50:54", "remaining_time": "2:35:27", "throughput": "0.00", "total_tokens": 0}
45
+ {"current_steps": 380, "total_steps": 1500, "loss": 4.4326, "accuracy": 0.637499988079071, "learning_rate": 4.249158351283414e-06, "epoch": 0.27543716589652983, "percentage": 25.33, "elapsed_time": "0:52:08", "remaining_time": "2:33:42", "throughput": "0.00", "total_tokens": 0}
46
+ {"current_steps": 390, "total_steps": 1500, "loss": 4.3874, "accuracy": 0.824999988079071, "learning_rate": 4.211367764821722e-06, "epoch": 0.2826855123674912, "percentage": 26.0, "elapsed_time": "0:53:27", "remaining_time": "2:32:09", "throughput": "0.00", "total_tokens": 0}
47
+ {"current_steps": 400, "total_steps": 1500, "loss": 4.2388, "accuracy": 0.6875, "learning_rate": 4.172826515897146e-06, "epoch": 0.28993385883845246, "percentage": 26.67, "elapsed_time": "0:54:42", "remaining_time": "2:30:25", "throughput": "0.00", "total_tokens": 0}
48
+ {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.49557629227638245, "epoch": 0.28993385883845246, "percentage": 26.67, "elapsed_time": "0:55:12", "remaining_time": "2:31:49", "throughput": "0.00", "total_tokens": 0}