Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.1-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
48e0a6d
·
verified ·
1 Parent(s): 5efff69

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 sha256:02968de258f5c279029d05c6f569f4c63102f30327ddc271d57b2dd514fa40f9
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4ff2bfb1cdcae75b29b397ca79830a371c02bf2122fc473b26c5a7fe4175043
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -148,3 +148,9 @@
148
  {"current_steps": 1240, "total_steps": 1500, "loss": 0.1335, "accuracy": 0.987500011920929, "learning_rate": 3.615893495987335e-07, "epoch": 1.9448695310967237, "percentage": 82.67, "elapsed_time": "2:47:06", "remaining_time": "0:35:02", "throughput": "0.00", "total_tokens": 0}
149
  {"current_steps": 1250, "total_steps": 1500, "loss": 0.1712, "accuracy": 0.9750000238418579, "learning_rate": 3.3493649053890325e-07, "epoch": 1.9605650382577986, "percentage": 83.33, "elapsed_time": "2:48:20", "remaining_time": "0:33:40", "throughput": "0.00", "total_tokens": 0}
150
  {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.15064650774002075, "epoch": 1.9605650382577986, "percentage": 83.33, "elapsed_time": "2:48:34", "remaining_time": "0:33:42", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
148
  {"current_steps": 1240, "total_steps": 1500, "loss": 0.1335, "accuracy": 0.987500011920929, "learning_rate": 3.615893495987335e-07, "epoch": 1.9448695310967237, "percentage": 82.67, "elapsed_time": "2:47:06", "remaining_time": "0:35:02", "throughput": "0.00", "total_tokens": 0}
149
  {"current_steps": 1250, "total_steps": 1500, "loss": 0.1712, "accuracy": 0.9750000238418579, "learning_rate": 3.3493649053890325e-07, "epoch": 1.9605650382577986, "percentage": 83.33, "elapsed_time": "2:48:20", "remaining_time": "0:33:40", "throughput": "0.00", "total_tokens": 0}
150
  {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.15064650774002075, "epoch": 1.9605650382577986, "percentage": 83.33, "elapsed_time": "2:48:34", "remaining_time": "0:33:42", "throughput": "0.00", "total_tokens": 0}
151
+ {"current_steps": 1260, "total_steps": 1500, "loss": 0.1332, "accuracy": 0.949999988079071, "learning_rate": 3.092332998903416e-07, "epoch": 1.976260545418874, "percentage": 84.0, "elapsed_time": "2:49:57", "remaining_time": "0:32:22", "throughput": "0.00", "total_tokens": 0}
152
+ {"current_steps": 1270, "total_steps": 1500, "loss": 0.1687, "accuracy": 0.949999988079071, "learning_rate": 2.844910519219632e-07, "epoch": 1.991956052579949, "percentage": 84.67, "elapsed_time": "2:51:16", "remaining_time": "0:31:01", "throughput": "0.00", "total_tokens": 0}
153
+ {"current_steps": 1280, "total_steps": 1500, "loss": 0.1344, "accuracy": 0.9589040875434875, "learning_rate": 2.6072059940146775e-07, "epoch": 2.00627820286443, "percentage": 85.33, "elapsed_time": "2:52:26", "remaining_time": "0:29:38", "throughput": "0.00", "total_tokens": 0}
154
+ {"current_steps": 1290, "total_steps": 1500, "loss": 0.163, "accuracy": 0.949999988079071, "learning_rate": 2.3793236883495164e-07, "epoch": 2.021973710025505, "percentage": 86.0, "elapsed_time": "2:53:40", "remaining_time": "0:28:16", "throughput": "0.00", "total_tokens": 0}
155
+ {"current_steps": 1300, "total_steps": 1500, "loss": 0.1749, "accuracy": 1.0, "learning_rate": 2.1613635589349756e-07, "epoch": 2.0376692171865805, "percentage": 86.67, "elapsed_time": "2:54:59", "remaining_time": "0:26:55", "throughput": "0.00", "total_tokens": 0}
156
+ {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.14751878380775452, "epoch": 2.0376692171865805, "percentage": 86.67, "elapsed_time": "2:55:13", "remaining_time": "0:26:57", "throughput": "0.00", "total_tokens": 0}