Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.75-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
17d96cf
·
verified ·
1 Parent(s): 47fd30b

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 sha256:3d80f2c648a0aca0e72371b2c69b66f6dc19cfe220178a7db24f7be8e742472e
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a58f228bd505214dc3dd6604e8f062c0981998cf7833146d9ec90da5cc2d121f
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -148,3 +148,9 @@
148
  {"current_steps": 1240, "total_steps": 1500, "loss": 0.195, "accuracy": 0.925000011920929, "learning_rate": 3.615893495987335e-07, "epoch": 1.1012433392539964, "percentage": 82.67, "elapsed_time": "2:48:32", "remaining_time": "0:35:20", "throughput": "0.00", "total_tokens": 0}
149
  {"current_steps": 1250, "total_steps": 1500, "loss": 0.1571, "accuracy": 0.949999988079071, "learning_rate": 3.3493649053890325e-07, "epoch": 1.1101243339253997, "percentage": 83.33, "elapsed_time": "2:49:50", "remaining_time": "0:33:58", "throughput": "0.00", "total_tokens": 0}
150
  {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.2080618292093277, "epoch": 1.1101243339253997, "percentage": 83.33, "elapsed_time": "2:50:15", "remaining_time": "0:34:03", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
148
  {"current_steps": 1240, "total_steps": 1500, "loss": 0.195, "accuracy": 0.925000011920929, "learning_rate": 3.615893495987335e-07, "epoch": 1.1012433392539964, "percentage": 82.67, "elapsed_time": "2:48:32", "remaining_time": "0:35:20", "throughput": "0.00", "total_tokens": 0}
149
  {"current_steps": 1250, "total_steps": 1500, "loss": 0.1571, "accuracy": 0.949999988079071, "learning_rate": 3.3493649053890325e-07, "epoch": 1.1101243339253997, "percentage": 83.33, "elapsed_time": "2:49:50", "remaining_time": "0:33:58", "throughput": "0.00", "total_tokens": 0}
150
  {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.2080618292093277, "epoch": 1.1101243339253997, "percentage": 83.33, "elapsed_time": "2:50:15", "remaining_time": "0:34:03", "throughput": "0.00", "total_tokens": 0}
151
+ {"current_steps": 1260, "total_steps": 1500, "loss": 0.2137, "accuracy": 0.9125000238418579, "learning_rate": 3.092332998903416e-07, "epoch": 1.119005328596803, "percentage": 84.0, "elapsed_time": "2:51:36", "remaining_time": "0:32:41", "throughput": "0.00", "total_tokens": 0}
152
+ {"current_steps": 1270, "total_steps": 1500, "loss": 0.2259, "accuracy": 0.949999988079071, "learning_rate": 2.844910519219632e-07, "epoch": 1.1278863232682061, "percentage": 84.67, "elapsed_time": "2:52:51", "remaining_time": "0:31:18", "throughput": "0.00", "total_tokens": 0}
153
+ {"current_steps": 1280, "total_steps": 1500, "loss": 0.1657, "accuracy": 0.9624999761581421, "learning_rate": 2.6072059940146775e-07, "epoch": 1.1367673179396092, "percentage": 85.33, "elapsed_time": "2:54:07", "remaining_time": "0:29:55", "throughput": "0.00", "total_tokens": 0}
154
+ {"current_steps": 1290, "total_steps": 1500, "loss": 0.1965, "accuracy": 0.949999988079071, "learning_rate": 2.3793236883495164e-07, "epoch": 1.1456483126110124, "percentage": 86.0, "elapsed_time": "2:55:26", "remaining_time": "0:28:33", "throughput": "0.00", "total_tokens": 0}
155
+ {"current_steps": 1300, "total_steps": 1500, "loss": 0.174, "accuracy": 0.987500011920929, "learning_rate": 2.1613635589349756e-07, "epoch": 1.1545293072824157, "percentage": 86.67, "elapsed_time": "2:56:45", "remaining_time": "0:27:11", "throughput": "0.00", "total_tokens": 0}
156
+ {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.20604319870471954, "epoch": 1.1545293072824157, "percentage": 86.67, "elapsed_time": "2:57:10", "remaining_time": "0:27:15", "throughput": "0.00", "total_tokens": 0}