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
64fd0f1
·
verified ·
1 Parent(s): 7fdd16c

Training in progress, step 1150

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:be6a452ea262292ea28f67eb353d402a3d23cb22335c8edcc56c90298ec6e395
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65f3c26e6a2c627831484cf95c99e6c04fe575c4fc38ba35af97ae42fb1e227d
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -130,3 +130,9 @@
130
  {"current_steps": 1090, "total_steps": 1500, "loss": 0.1982, "accuracy": 0.9333333373069763, "learning_rate": 8.664484900247363e-07, "epoch": 1.000918800964741, "percentage": 72.67, "elapsed_time": "2:30:53", "remaining_time": "0:56:45", "throughput": "0.00", "total_tokens": 0}
131
  {"current_steps": 1100, "total_steps": 1500, "loss": 0.2476, "accuracy": 0.925000011920929, "learning_rate": 8.271734841028553e-07, "epoch": 1.0101068106121511, "percentage": 73.33, "elapsed_time": "2:32:09", "remaining_time": "0:55:19", "throughput": "0.00", "total_tokens": 0}
132
  {"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.2056656777858734, "epoch": 1.0101068106121511, "percentage": 73.33, "elapsed_time": "2:32:33", "remaining_time": "0:55:28", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
130
  {"current_steps": 1090, "total_steps": 1500, "loss": 0.1982, "accuracy": 0.9333333373069763, "learning_rate": 8.664484900247363e-07, "epoch": 1.000918800964741, "percentage": 72.67, "elapsed_time": "2:30:53", "remaining_time": "0:56:45", "throughput": "0.00", "total_tokens": 0}
131
  {"current_steps": 1100, "total_steps": 1500, "loss": 0.2476, "accuracy": 0.925000011920929, "learning_rate": 8.271734841028553e-07, "epoch": 1.0101068106121511, "percentage": 73.33, "elapsed_time": "2:32:09", "remaining_time": "0:55:19", "throughput": "0.00", "total_tokens": 0}
132
  {"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.2056656777858734, "epoch": 1.0101068106121511, "percentage": 73.33, "elapsed_time": "2:32:33", "remaining_time": "0:55:28", "throughput": "0.00", "total_tokens": 0}
133
+ {"current_steps": 1110, "total_steps": 1500, "loss": 0.1984, "accuracy": 0.925000011920929, "learning_rate": 7.886322351782782e-07, "epoch": 1.0192948202595613, "percentage": 74.0, "elapsed_time": "2:33:57", "remaining_time": "0:54:05", "throughput": "0.00", "total_tokens": 0}
134
+ {"current_steps": 1120, "total_steps": 1500, "loss": 0.186, "accuracy": 0.949999988079071, "learning_rate": 7.508416487165862e-07, "epoch": 1.0284828299069715, "percentage": 74.67, "elapsed_time": "2:35:12", "remaining_time": "0:52:39", "throughput": "0.00", "total_tokens": 0}
135
+ {"current_steps": 1130, "total_steps": 1500, "loss": 0.1932, "accuracy": 0.949999988079071, "learning_rate": 7.138183009179922e-07, "epoch": 1.0376708395543814, "percentage": 75.33, "elapsed_time": "2:36:30", "remaining_time": "0:51:14", "throughput": "0.00", "total_tokens": 0}
136
+ {"current_steps": 1140, "total_steps": 1500, "loss": 0.2186, "accuracy": 0.9624999761581421, "learning_rate": 6.775784314464717e-07, "epoch": 1.0468588492017916, "percentage": 76.0, "elapsed_time": "2:37:49", "remaining_time": "0:49:50", "throughput": "0.00", "total_tokens": 0}
137
+ {"current_steps": 1150, "total_steps": 1500, "loss": 0.2127, "accuracy": 0.9750000238418579, "learning_rate": 6.421379363065142e-07, "epoch": 1.0560468588492018, "percentage": 76.67, "elapsed_time": "2:39:13", "remaining_time": "0:48:27", "throughput": "0.00", "total_tokens": 0}
138
+ {"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.20314906537532806, "epoch": 1.0560468588492018, "percentage": 76.67, "elapsed_time": "2:39:37", "remaining_time": "0:48:34", "throughput": "0.00", "total_tokens": 0}