Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.75-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
d532e05
·
verified ·
1 Parent(s): 4d014ce

Training in progress, step 1300

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:eae7f2daf1236faffca9b1a84a013a46591ccf3ae4c2b2ceea55d05faf0cd57c
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c5cb1d31f209236b975d2637605e163c1b02a6b96acf10c7f8e04f0f1dcd5c
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -148,3 +148,9 @@
148
  {"current_steps": 1240, "total_steps": 1500, "loss": 0.1784, "accuracy": 0.949999988079071, "learning_rate": 3.615893495987335e-07, "epoch": 1.1012433392539964, "percentage": 82.67, "elapsed_time": "2:53:45", "remaining_time": "0:36:26", "throughput": "0.00", "total_tokens": 0}
149
  {"current_steps": 1250, "total_steps": 1500, "loss": 0.1609, "accuracy": 0.9624999761581421, "learning_rate": 3.3493649053890325e-07, "epoch": 1.1101243339253997, "percentage": 83.33, "elapsed_time": "2:55:07", "remaining_time": "0:35:01", "throughput": "0.00", "total_tokens": 0}
150
  {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.20066653192043304, "epoch": 1.1101243339253997, "percentage": 83.33, "elapsed_time": "2:55:33", "remaining_time": "0:35:06", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
148
  {"current_steps": 1240, "total_steps": 1500, "loss": 0.1784, "accuracy": 0.949999988079071, "learning_rate": 3.615893495987335e-07, "epoch": 1.1012433392539964, "percentage": 82.67, "elapsed_time": "2:53:45", "remaining_time": "0:36:26", "throughput": "0.00", "total_tokens": 0}
149
  {"current_steps": 1250, "total_steps": 1500, "loss": 0.1609, "accuracy": 0.9624999761581421, "learning_rate": 3.3493649053890325e-07, "epoch": 1.1101243339253997, "percentage": 83.33, "elapsed_time": "2:55:07", "remaining_time": "0:35:01", "throughput": "0.00", "total_tokens": 0}
150
  {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.20066653192043304, "epoch": 1.1101243339253997, "percentage": 83.33, "elapsed_time": "2:55:33", "remaining_time": "0:35:06", "throughput": "0.00", "total_tokens": 0}
151
+ {"current_steps": 1260, "total_steps": 1500, "loss": 0.1991, "accuracy": 0.887499988079071, "learning_rate": 3.092332998903416e-07, "epoch": 1.119005328596803, "percentage": 84.0, "elapsed_time": "2:57:04", "remaining_time": "0:33:43", "throughput": "0.00", "total_tokens": 0}
152
+ {"current_steps": 1270, "total_steps": 1500, "loss": 0.2242, "accuracy": 0.9750000238418579, "learning_rate": 2.844910519219632e-07, "epoch": 1.1278863232682061, "percentage": 84.67, "elapsed_time": "2:58:22", "remaining_time": "0:32:18", "throughput": "0.00", "total_tokens": 0}
153
+ {"current_steps": 1280, "total_steps": 1500, "loss": 0.1869, "accuracy": 0.949999988079071, "learning_rate": 2.6072059940146775e-07, "epoch": 1.1367673179396092, "percentage": 85.33, "elapsed_time": "2:59:41", "remaining_time": "0:30:52", "throughput": "0.00", "total_tokens": 0}
154
+ {"current_steps": 1290, "total_steps": 1500, "loss": 0.2117, "accuracy": 0.949999988079071, "learning_rate": 2.3793236883495164e-07, "epoch": 1.1456483126110124, "percentage": 86.0, "elapsed_time": "3:01:05", "remaining_time": "0:29:28", "throughput": "0.00", "total_tokens": 0}
155
+ {"current_steps": 1300, "total_steps": 1500, "loss": 0.1628, "accuracy": 0.9624999761581421, "learning_rate": 2.1613635589349756e-07, "epoch": 1.1545293072824157, "percentage": 86.67, "elapsed_time": "3:02:23", "remaining_time": "0:28:03", "throughput": "0.00", "total_tokens": 0}
156
+ {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.19974029064178467, "epoch": 1.1545293072824157, "percentage": 86.67, "elapsed_time": "3:02:50", "remaining_time": "0:28:07", "throughput": "0.00", "total_tokens": 0}