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
e87e472
·
verified ·
1 Parent(s): 9a46696

Training in progress, step 1350

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 sha256:94ebccd7741337cc28a9b8aa42e38fbc8e04cf920e987eb0f1664b87dabf3b0a
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70820fbc26ccf27443d6c53330482120e4bc434be5198734599ee0212dfd9ad5
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -154,3 +154,9 @@
154
  {"current_steps": 1290, "total_steps": 1500, "loss": 0.2191, "accuracy": 0.9375, "learning_rate": 2.3793236883495164e-07, "epoch": 1.1846789939129436, "percentage": 86.0, "elapsed_time": "2:58:54", "remaining_time": "0:29:07", "throughput": "0.00", "total_tokens": 0}
155
  {"current_steps": 1300, "total_steps": 1500, "loss": 0.2523, "accuracy": 0.9375, "learning_rate": 2.1613635589349756e-07, "epoch": 1.1938670035603538, "percentage": 86.67, "elapsed_time": "3:00:11", "remaining_time": "0:27:43", "throughput": "0.00", "total_tokens": 0}
156
  {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.20123924314975739, "epoch": 1.1938670035603538, "percentage": 86.67, "elapsed_time": "3:00:36", "remaining_time": "0:27:47", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
154
  {"current_steps": 1290, "total_steps": 1500, "loss": 0.2191, "accuracy": 0.9375, "learning_rate": 2.3793236883495164e-07, "epoch": 1.1846789939129436, "percentage": 86.0, "elapsed_time": "2:58:54", "remaining_time": "0:29:07", "throughput": "0.00", "total_tokens": 0}
155
  {"current_steps": 1300, "total_steps": 1500, "loss": 0.2523, "accuracy": 0.9375, "learning_rate": 2.1613635589349756e-07, "epoch": 1.1938670035603538, "percentage": 86.67, "elapsed_time": "3:00:11", "remaining_time": "0:27:43", "throughput": "0.00", "total_tokens": 0}
156
  {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.20123924314975739, "epoch": 1.1938670035603538, "percentage": 86.67, "elapsed_time": "3:00:36", "remaining_time": "0:27:47", "throughput": "0.00", "total_tokens": 0}
157
+ {"current_steps": 1310, "total_steps": 1500, "loss": 0.2, "accuracy": 0.9624999761581421, "learning_rate": 1.95342121028749e-07, "epoch": 1.2030550132077638, "percentage": 87.33, "elapsed_time": "3:01:59", "remaining_time": "0:26:23", "throughput": "0.00", "total_tokens": 0}
158
+ {"current_steps": 1320, "total_steps": 1500, "loss": 0.1589, "accuracy": 0.9750000238418579, "learning_rate": 1.7555878527937164e-07, "epoch": 1.212243022855174, "percentage": 88.0, "elapsed_time": "3:03:12", "remaining_time": "0:24:58", "throughput": "0.00", "total_tokens": 0}
159
+ {"current_steps": 1330, "total_steps": 1500, "loss": 0.1793, "accuracy": 0.9624999761581421, "learning_rate": 1.567950262702714e-07, "epoch": 1.2214310325025841, "percentage": 88.67, "elapsed_time": "3:04:30", "remaining_time": "0:23:35", "throughput": "0.00", "total_tokens": 0}
160
+ {"current_steps": 1340, "total_steps": 1500, "loss": 0.1779, "accuracy": 0.9624999761581421, "learning_rate": 1.3905907440629752e-07, "epoch": 1.2306190421499943, "percentage": 89.33, "elapsed_time": "3:05:50", "remaining_time": "0:22:11", "throughput": "0.00", "total_tokens": 0}
161
+ {"current_steps": 1350, "total_steps": 1500, "loss": 0.1736, "accuracy": 0.987500011920929, "learning_rate": 1.223587092621162e-07, "epoch": 1.2398070517974045, "percentage": 90.0, "elapsed_time": "3:07:07", "remaining_time": "0:20:47", "throughput": "0.00", "total_tokens": 0}
162
+ {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.19999442994594574, "epoch": 1.2398070517974045, "percentage": 90.0, "elapsed_time": "3:07:31", "remaining_time": "0:20:50", "throughput": "0.00", "total_tokens": 0}