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
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
d946825
·
verified ·
1 Parent(s): 4b5d90e

Training in progress, step 350

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:a425ce98380c2ecb5935299a33c336430295e361176ffeab4ecddcf898bdb319
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a7a520373f138bb236cd642a1ccafb049449ab3dd41944526c9b0af107b5bbe
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -34,3 +34,9 @@
34
  {"current_steps": 290, "total_steps": 1500, "loss": 5.7937, "accuracy": 0.7124999761581421, "learning_rate": 4.55287302283426e-06, "epoch": 0.21020204765787803, "percentage": 19.33, "elapsed_time": "0:39:45", "remaining_time": "2:45:54", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 5.741, "accuracy": 0.6875, "learning_rate": 4.522542485937369e-06, "epoch": 0.21745039412883935, "percentage": 20.0, "elapsed_time": "0:40:58", "remaining_time": "2:43:53", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.6990054845809937, "epoch": 0.21745039412883935, "percentage": 20.0, "elapsed_time": "0:41:28", "remaining_time": "2:45:55", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
34
  {"current_steps": 290, "total_steps": 1500, "loss": 5.7937, "accuracy": 0.7124999761581421, "learning_rate": 4.55287302283426e-06, "epoch": 0.21020204765787803, "percentage": 19.33, "elapsed_time": "0:39:45", "remaining_time": "2:45:54", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 5.741, "accuracy": 0.6875, "learning_rate": 4.522542485937369e-06, "epoch": 0.21745039412883935, "percentage": 20.0, "elapsed_time": "0:40:58", "remaining_time": "2:43:53", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.6990054845809937, "epoch": 0.21745039412883935, "percentage": 20.0, "elapsed_time": "0:41:28", "remaining_time": "2:45:55", "throughput": "0.00", "total_tokens": 0}
37
+ {"current_steps": 310, "total_steps": 1500, "loss": 5.3005, "accuracy": 0.625, "learning_rate": 4.491324795060491e-06, "epoch": 0.22469874059980066, "percentage": 20.67, "elapsed_time": "0:42:55", "remaining_time": "2:44:45", "throughput": "0.00", "total_tokens": 0}
38
+ {"current_steps": 320, "total_steps": 1500, "loss": 5.2832, "accuracy": 0.6625000238418579, "learning_rate": 4.4592336433146e-06, "epoch": 0.23194708707076198, "percentage": 21.33, "elapsed_time": "0:44:06", "remaining_time": "2:42:38", "throughput": "0.00", "total_tokens": 0}
39
+ {"current_steps": 330, "total_steps": 1500, "loss": 5.1977, "accuracy": 0.6875, "learning_rate": 4.426283106939474e-06, "epoch": 0.2391954335417233, "percentage": 22.0, "elapsed_time": "0:45:18", "remaining_time": "2:40:37", "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}