Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.7-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
239da26
·
verified ·
1 Parent(s): c1b3140

Training in progress, step 750

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 sha256:186cd96a41c3447887c7913bca1d768b158b800658d05f0641f9056a5fcf0f84
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d2c89b623a0bac2650e986b11ebeefe08ead2d78de6bbef304fb1dc41de899
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -82,3 +82,9 @@
82
  {"current_steps": 690, "total_steps": 1500, "loss": 0.2808, "accuracy": 0.925000011920929, "learning_rate": 2.813333083910761e-06, "epoch": 0.633972665671299, "percentage": 46.0, "elapsed_time": "1:35:27", "remaining_time": "1:52:03", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 0.2808, "accuracy": 0.8999999761581421, "learning_rate": 2.761321158169134e-06, "epoch": 0.6431606753187091, "percentage": 46.67, "elapsed_time": "1:36:46", "remaining_time": "1:50:36", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.26070258021354675, "epoch": 0.6431606753187091, "percentage": 46.67, "elapsed_time": "1:37:11", "remaining_time": "1:51:04", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
82
  {"current_steps": 690, "total_steps": 1500, "loss": 0.2808, "accuracy": 0.925000011920929, "learning_rate": 2.813333083910761e-06, "epoch": 0.633972665671299, "percentage": 46.0, "elapsed_time": "1:35:27", "remaining_time": "1:52:03", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 0.2808, "accuracy": 0.8999999761581421, "learning_rate": 2.761321158169134e-06, "epoch": 0.6431606753187091, "percentage": 46.67, "elapsed_time": "1:36:46", "remaining_time": "1:50:36", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.26070258021354675, "epoch": 0.6431606753187091, "percentage": 46.67, "elapsed_time": "1:37:11", "remaining_time": "1:51:04", "throughput": "0.00", "total_tokens": 0}
85
+ {"current_steps": 710, "total_steps": 1500, "loss": 0.2565, "accuracy": 0.9125000238418579, "learning_rate": 2.70919460833079e-06, "epoch": 0.6523486849661192, "percentage": 47.33, "elapsed_time": "1:38:39", "remaining_time": "1:49:46", "throughput": "0.00", "total_tokens": 0}
86
+ {"current_steps": 720, "total_steps": 1500, "loss": 0.2321, "accuracy": 0.9125000238418579, "learning_rate": 2.6569762988232838e-06, "epoch": 0.6615366946135294, "percentage": 48.0, "elapsed_time": "1:39:55", "remaining_time": "1:48:15", "throughput": "0.00", "total_tokens": 0}
87
+ {"current_steps": 730, "total_steps": 1500, "loss": 0.2812, "accuracy": 0.9375, "learning_rate": 2.604689134322999e-06, "epoch": 0.6707247042609394, "percentage": 48.67, "elapsed_time": "1:41:16", "remaining_time": "1:46:49", "throughput": "0.00", "total_tokens": 0}
88
+ {"current_steps": 740, "total_steps": 1500, "loss": 0.2603, "accuracy": 0.9375, "learning_rate": 2.5523560497083927e-06, "epoch": 0.6799127139083496, "percentage": 49.33, "elapsed_time": "1:42:34", "remaining_time": "1:45:20", "throughput": "0.00", "total_tokens": 0}
89
+ {"current_steps": 750, "total_steps": 1500, "loss": 0.2348, "accuracy": 0.862500011920929, "learning_rate": 2.5e-06, "epoch": 0.6891007235557597, "percentage": 50.0, "elapsed_time": "1:43:52", "remaining_time": "1:43:52", "throughput": "0.00", "total_tokens": 0}
90
+ {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.25226154923439026, "epoch": 0.6891007235557597, "percentage": 50.0, "elapsed_time": "1:44:16", "remaining_time": "1:44:16", "throughput": "0.00", "total_tokens": 0}