Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.8-kendall-onof-decrease-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files
xet
Community
ziansu commited on
Commit
b8b6e1a
·
verified ·
1 Parent(s): 8263c69

Training in progress, step 400

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:fb783137ac0455c07887ce9b914c24aa889fa47415a26329b0f8efa3321b008b
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16c89cc9c6eeee8ca994b86c0bb1e7cd5f01a58b6ff9b44219e32e3d455b5776
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -40,3 +40,9 @@
40
  {"current_steps": 340, "total_steps": 1500, "loss": 0.4903, "accuracy": 0.7124999761581421, "learning_rate": 4.3924876391293915e-06, "epoch": 0.2922217447357112, "percentage": 22.67, "elapsed_time": "0:44:52", "remaining_time": "2:33:06", "throughput": "0.00", "total_tokens": 0}
41
  {"current_steps": 350, "total_steps": 1500, "loss": 0.5249, "accuracy": 0.5625, "learning_rate": 4.357862063693486e-06, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:46:04", "remaining_time": "2:31:22", "throughput": "0.00", "total_tokens": 0}
42
  {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5171241760253906, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:46:29", "remaining_time": "2:32:46", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
40
  {"current_steps": 340, "total_steps": 1500, "loss": 0.4903, "accuracy": 0.7124999761581421, "learning_rate": 4.3924876391293915e-06, "epoch": 0.2922217447357112, "percentage": 22.67, "elapsed_time": "0:44:52", "remaining_time": "2:33:06", "throughput": "0.00", "total_tokens": 0}
41
  {"current_steps": 350, "total_steps": 1500, "loss": 0.5249, "accuracy": 0.5625, "learning_rate": 4.357862063693486e-06, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:46:04", "remaining_time": "2:31:22", "throughput": "0.00", "total_tokens": 0}
42
  {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5171241760253906, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:46:29", "remaining_time": "2:32:46", "throughput": "0.00", "total_tokens": 0}
43
+ {"current_steps": 360, "total_steps": 1500, "loss": 0.5067, "accuracy": 0.675000011920929, "learning_rate": 4.322421568553529e-06, "epoch": 0.3094112591319295, "percentage": 24.0, "elapsed_time": "0:47:46", "remaining_time": "2:31:15", "throughput": "0.00", "total_tokens": 0}
44
+ {"current_steps": 370, "total_steps": 1500, "loss": 0.4726, "accuracy": 0.800000011920929, "learning_rate": 4.286181699082008e-06, "epoch": 0.31800601633003867, "percentage": 24.67, "elapsed_time": "0:48:58", "remaining_time": "2:29:34", "throughput": "0.00", "total_tokens": 0}
45
+ {"current_steps": 380, "total_steps": 1500, "loss": 0.4801, "accuracy": 0.6625000238418579, "learning_rate": 4.249158351283414e-06, "epoch": 0.3266007735281478, "percentage": 25.33, "elapsed_time": "0:50:12", "remaining_time": "2:27:57", "throughput": "0.00", "total_tokens": 0}
46
+ {"current_steps": 390, "total_steps": 1500, "loss": 0.4585, "accuracy": 0.5874999761581421, "learning_rate": 4.211367764821722e-06, "epoch": 0.33519553072625696, "percentage": 26.0, "elapsed_time": "0:51:21", "remaining_time": "2:26:11", "throughput": "0.00", "total_tokens": 0}
47
+ {"current_steps": 400, "total_steps": 1500, "loss": 0.4771, "accuracy": 0.675000011920929, "learning_rate": 4.172826515897146e-06, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:52:33", "remaining_time": "2:24:30", "throughput": "0.00", "total_tokens": 0}
48
+ {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.47841358184814453, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:52:58", "remaining_time": "2:25:41", "throughput": "0.00", "total_tokens": 0}