Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.8-kendall-onof-neg_if-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
0579691
·
verified ·
1 Parent(s): 402aeb4

Training in progress, step 300

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:cfdf030d9f653cfe09bf2f374b2aa77ef8852890deb390006cde083903588695
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42602a023da910239730c2d92fae8b24f0ac23ff53f0f5823b7dd2836b8881b4
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -28,3 +28,9 @@
28
  {"current_steps": 240, "total_steps": 1500, "loss": 0.7787, "accuracy": 0.6499999761581421, "learning_rate": 4.690766700109659e-06, "epoch": 0.20627417275461968, "percentage": 16.0, "elapsed_time": "0:31:52", "remaining_time": "2:47:23", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 0.7776, "accuracy": 0.625, "learning_rate": 4.665063509461098e-06, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:08", "remaining_time": "2:45:43", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7469337582588196, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:34", "remaining_time": "2:47:50", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
28
  {"current_steps": 240, "total_steps": 1500, "loss": 0.7787, "accuracy": 0.6499999761581421, "learning_rate": 4.690766700109659e-06, "epoch": 0.20627417275461968, "percentage": 16.0, "elapsed_time": "0:31:52", "remaining_time": "2:47:23", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 0.7776, "accuracy": 0.625, "learning_rate": 4.665063509461098e-06, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:08", "remaining_time": "2:45:43", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7469337582588196, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:34", "remaining_time": "2:47:50", "throughput": "0.00", "total_tokens": 0}
31
+ {"current_steps": 260, "total_steps": 1500, "loss": 0.6981, "accuracy": 0.7124999761581421, "learning_rate": 4.638410650401267e-06, "epoch": 0.22346368715083798, "percentage": 17.33, "elapsed_time": "0:34:55", "remaining_time": "2:46:33", "throughput": "0.00", "total_tokens": 0}
32
+ {"current_steps": 270, "total_steps": 1500, "loss": 0.7174, "accuracy": 0.7250000238418579, "learning_rate": 4.610819813755038e-06, "epoch": 0.23205844434894715, "percentage": 18.0, "elapsed_time": "0:36:11", "remaining_time": "2:44:54", "throughput": "0.00", "total_tokens": 0}
33
+ {"current_steps": 280, "total_steps": 1500, "loss": 0.6972, "accuracy": 0.6625000238418579, "learning_rate": 4.582303101775249e-06, "epoch": 0.2406532015470563, "percentage": 18.67, "elapsed_time": "0:37:27", "remaining_time": "2:43:14", "throughput": "0.00", "total_tokens": 0}
34
+ {"current_steps": 290, "total_steps": 1500, "loss": 0.6192, "accuracy": 0.612500011920929, "learning_rate": 4.55287302283426e-06, "epoch": 0.24924795874516545, "percentage": 19.33, "elapsed_time": "0:38:45", "remaining_time": "2:41:43", "throughput": "0.00", "total_tokens": 0}
35
+ {"current_steps": 300, "total_steps": 1500, "loss": 0.5721, "accuracy": 0.612500011920929, "learning_rate": 4.522542485937369e-06, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:40:00", "remaining_time": "2:40:03", "throughput": "0.00", "total_tokens": 0}
36
+ {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5730626583099365, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:40:26", "remaining_time": "2:41:45", "throughput": "0.00", "total_tokens": 0}