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
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
2b4f41a
·
verified ·
1 Parent(s): 73ff368

Training in progress, step 300

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:baf8d899504b31aa88914bfb3f8ef2feb95c0337a42c24e27bf49d3f3935979b
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3723d7a38a8c8710653f37f912461e0112b9c9676394cbf49f046e933d47ce4d
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -28,3 +28,9 @@
28
  {"current_steps": 240, "total_steps": 1500, "loss": 0.7877, "accuracy": 0.675000011920929, "learning_rate": 4.690766700109659e-06, "epoch": 0.2205122315378431, "percentage": 16.0, "elapsed_time": "0:32:56", "remaining_time": "2:52:54", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 0.7902, "accuracy": 0.5874999761581421, "learning_rate": 4.665063509461098e-06, "epoch": 0.22970024118525326, "percentage": 16.67, "elapsed_time": "0:34:14", "remaining_time": "2:51:10", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7682384252548218, "epoch": 0.22970024118525326, "percentage": 16.67, "elapsed_time": "0:34:38", "remaining_time": "2:53:12", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
28
  {"current_steps": 240, "total_steps": 1500, "loss": 0.7877, "accuracy": 0.675000011920929, "learning_rate": 4.690766700109659e-06, "epoch": 0.2205122315378431, "percentage": 16.0, "elapsed_time": "0:32:56", "remaining_time": "2:52:54", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 0.7902, "accuracy": 0.5874999761581421, "learning_rate": 4.665063509461098e-06, "epoch": 0.22970024118525326, "percentage": 16.67, "elapsed_time": "0:34:14", "remaining_time": "2:51:10", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7682384252548218, "epoch": 0.22970024118525326, "percentage": 16.67, "elapsed_time": "0:34:38", "remaining_time": "2:53:12", "throughput": "0.00", "total_tokens": 0}
31
+ {"current_steps": 260, "total_steps": 1500, "loss": 0.6911, "accuracy": 0.6499999761581421, "learning_rate": 4.638410650401267e-06, "epoch": 0.23888825083266338, "percentage": 17.33, "elapsed_time": "0:36:00", "remaining_time": "2:51:42", "throughput": "0.00", "total_tokens": 0}
32
+ {"current_steps": 270, "total_steps": 1500, "loss": 0.6774, "accuracy": 0.625, "learning_rate": 4.610819813755038e-06, "epoch": 0.2480762604800735, "percentage": 18.0, "elapsed_time": "0:37:16", "remaining_time": "2:49:50", "throughput": "0.00", "total_tokens": 0}
33
+ {"current_steps": 280, "total_steps": 1500, "loss": 0.628, "accuracy": 0.6875, "learning_rate": 4.582303101775249e-06, "epoch": 0.25726427012748365, "percentage": 18.67, "elapsed_time": "0:38:34", "remaining_time": "2:48:04", "throughput": "0.00", "total_tokens": 0}
34
+ {"current_steps": 290, "total_steps": 1500, "loss": 0.5988, "accuracy": 0.7250000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.2664522797748938, "percentage": 19.33, "elapsed_time": "0:39:52", "remaining_time": "2:46:21", "throughput": "0.00", "total_tokens": 0}
35
+ {"current_steps": 300, "total_steps": 1500, "loss": 0.5927, "accuracy": 0.6625000238418579, "learning_rate": 4.522542485937369e-06, "epoch": 0.2756402894223039, "percentage": 20.0, "elapsed_time": "0:41:07", "remaining_time": "2:44:29", "throughput": "0.00", "total_tokens": 0}
36
+ {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5978505611419678, "epoch": 0.2756402894223039, "percentage": 20.0, "elapsed_time": "0:41:31", "remaining_time": "2:46:07", "throughput": "0.00", "total_tokens": 0}