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
81ccf68
·
verified ·
1 Parent(s): 9cd35a4

Training in progress, step 250

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 sha256:79387fe1fa1a86683dcaeefe38022b992b6089822c0fad02214bc28a04683b06
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b266be409db7d879882292a4790ace968b4aae610e8e251fee9bd6a8c6f685cf
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -22,3 +22,9 @@
22
  {"current_steps": 190, "total_steps": 1500, "loss": 6.9941, "accuracy": 0.5874999761581421, "learning_rate": 4.804657878971252e-06, "epoch": 0.13771858294826492, "percentage": 12.67, "elapsed_time": "0:25:45", "remaining_time": "2:57:32", "throughput": "0.00", "total_tokens": 0}
23
  {"current_steps": 200, "total_steps": 1500, "loss": 7.0413, "accuracy": 0.6499999761581421, "learning_rate": 4.783863644106502e-06, "epoch": 0.14496692941922623, "percentage": 13.33, "elapsed_time": "0:26:59", "remaining_time": "2:55:24", "throughput": "0.00", "total_tokens": 0}
24
  {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8543878793716431, "epoch": 0.14496692941922623, "percentage": 13.33, "elapsed_time": "0:27:29", "remaining_time": "2:58:41", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
22
  {"current_steps": 190, "total_steps": 1500, "loss": 6.9941, "accuracy": 0.5874999761581421, "learning_rate": 4.804657878971252e-06, "epoch": 0.13771858294826492, "percentage": 12.67, "elapsed_time": "0:25:45", "remaining_time": "2:57:32", "throughput": "0.00", "total_tokens": 0}
23
  {"current_steps": 200, "total_steps": 1500, "loss": 7.0413, "accuracy": 0.6499999761581421, "learning_rate": 4.783863644106502e-06, "epoch": 0.14496692941922623, "percentage": 13.33, "elapsed_time": "0:26:59", "remaining_time": "2:55:24", "throughput": "0.00", "total_tokens": 0}
24
  {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8543878793716431, "epoch": 0.14496692941922623, "percentage": 13.33, "elapsed_time": "0:27:29", "remaining_time": "2:58:41", "throughput": "0.00", "total_tokens": 0}
25
+ {"current_steps": 210, "total_steps": 1500, "loss": 6.882, "accuracy": 0.5874999761581421, "learning_rate": 4.762067631165049e-06, "epoch": 0.15221527589018755, "percentage": 14.0, "elapsed_time": "0:28:57", "remaining_time": "2:57:50", "throughput": "0.00", "total_tokens": 0}
26
+ {"current_steps": 220, "total_steps": 1500, "loss": 6.9158, "accuracy": 0.699999988079071, "learning_rate": 4.7392794005985324e-06, "epoch": 0.15946362236114886, "percentage": 14.67, "elapsed_time": "0:30:10", "remaining_time": "2:55:35", "throughput": "0.00", "total_tokens": 0}
27
+ {"current_steps": 230, "total_steps": 1500, "loss": 6.8503, "accuracy": 0.699999988079071, "learning_rate": 4.715508948078037e-06, "epoch": 0.16671196883211017, "percentage": 15.33, "elapsed_time": "0:31:25", "remaining_time": "2:53:29", "throughput": "0.00", "total_tokens": 0}
28
+ {"current_steps": 240, "total_steps": 1500, "loss": 6.667, "accuracy": 0.6499999761581421, "learning_rate": 4.690766700109659e-06, "epoch": 0.1739603153030715, "percentage": 16.0, "elapsed_time": "0:32:40", "remaining_time": "2:51:35", "throughput": "0.00", "total_tokens": 0}
29
+ {"current_steps": 250, "total_steps": 1500, "loss": 6.7146, "accuracy": 0.5625, "learning_rate": 4.665063509461098e-06, "epoch": 0.1812086617740328, "percentage": 16.67, "elapsed_time": "0:34:00", "remaining_time": "2:50:01", "throughput": "0.00", "total_tokens": 0}
30
+ {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.8070082664489746, "epoch": 0.1812086617740328, "percentage": 16.67, "elapsed_time": "0:34:30", "remaining_time": "2:52:33", "throughput": "0.00", "total_tokens": 0}