Hugging Face's logo

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

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
7f293ba
·
verified ·
1 Parent(s): bcfc006

Training in progress, step 350

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 sha256:42602a023da910239730c2d92fae8b24f0ac23ff53f0f5823b7dd2836b8881b4
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:861fce42fc1edb745eb484e80f94be8baf83b03312cef3811d98fea932cff773
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -34,3 +34,9 @@
34
  {"current_steps": 290, "total_steps": 1500, "loss": 0.6192, "accuracy": 0.612500011920929, "learning_rate": 4.55287302283426e-06, "epoch": 0.24924795874516545, "percentage": 19.33, "elapsed_time": "0:38:45", "remaining_time": "2:41:43", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 0.5721, "accuracy": 0.612500011920929, "learning_rate": 4.522542485937369e-06, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:40:00", "remaining_time": "2:40:03", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5730626583099365, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:40:26", "remaining_time": "2:41:45", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
34
  {"current_steps": 290, "total_steps": 1500, "loss": 0.6192, "accuracy": 0.612500011920929, "learning_rate": 4.55287302283426e-06, "epoch": 0.24924795874516545, "percentage": 19.33, "elapsed_time": "0:38:45", "remaining_time": "2:41:43", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 0.5721, "accuracy": 0.612500011920929, "learning_rate": 4.522542485937369e-06, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:40:00", "remaining_time": "2:40:03", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5730626583099365, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:40:26", "remaining_time": "2:41:45", "throughput": "0.00", "total_tokens": 0}
37
+ {"current_steps": 310, "total_steps": 1500, "loss": 0.5091, "accuracy": 0.762499988079071, "learning_rate": 4.491324795060491e-06, "epoch": 0.2664374731413838, "percentage": 20.67, "elapsed_time": "0:41:47", "remaining_time": "2:40:26", "throughput": "0.00", "total_tokens": 0}
38
+ {"current_steps": 320, "total_steps": 1500, "loss": 0.5352, "accuracy": 0.675000011920929, "learning_rate": 4.4592336433146e-06, "epoch": 0.2750322303394929, "percentage": 21.33, "elapsed_time": "0:43:02", "remaining_time": "2:38:43", "throughput": "0.00", "total_tokens": 0}
39
+ {"current_steps": 330, "total_steps": 1500, "loss": 0.5397, "accuracy": 0.6000000238418579, "learning_rate": 4.426283106939474e-06, "epoch": 0.28362698753760207, "percentage": 22.0, "elapsed_time": "0:44:19", "remaining_time": "2:37:10", "throughput": "0.00", "total_tokens": 0}
40
+ {"current_steps": 340, "total_steps": 1500, "loss": 0.4817, "accuracy": 0.699999988079071, "learning_rate": 4.3924876391293915e-06, "epoch": 0.2922217447357112, "percentage": 22.67, "elapsed_time": "0:45:39", "remaining_time": "2:35:46", "throughput": "0.00", "total_tokens": 0}
41
+ {"current_steps": 350, "total_steps": 1500, "loss": 0.5098, "accuracy": 0.574999988079071, "learning_rate": 4.357862063693486e-06, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:46:54", "remaining_time": "2:34:08", "throughput": "0.00", "total_tokens": 0}
42
+ {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5162621736526489, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:47:20", "remaining_time": "2:35:32", "throughput": "0.00", "total_tokens": 0}