Hugging Face's logo

prosecalign
/
phi3m0128-kendall-onof-neg_if-corr-max-2-simpo-max1500-decay-sft0.2-beta1.5-gamma0.5-lr5e-6

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
5d3aa7e
·
verified ·
1 Parent(s): 35e259c

Training in progress, step 450

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 sha256:0cbdfddfc70ba8b65ee9e24badb483de40c05c45aa4b9e7d953c9962e5a994cd
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2411ef6f36f9737d6f3c5fa254f29de53cfc28862732a6ac79929468c8740ff
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -46,3 +46,9 @@
46
  {"current_steps": 390, "total_steps": 1500, "loss": 0.4259, "accuracy": 0.6499999761581421, "learning_rate": 4.211367764821722e-06, "epoch": 0.2968036529680365, "percentage": 26.0, "elapsed_time": "0:53:08", "remaining_time": "2:31:13", "throughput": "0.00", "total_tokens": 0}
47
  {"current_steps": 400, "total_steps": 1500, "loss": 0.4167, "accuracy": 0.7124999761581421, "learning_rate": 4.172826515897146e-06, "epoch": 0.30441400304414, "percentage": 26.67, "elapsed_time": "0:54:19", "remaining_time": "2:29:22", "throughput": "0.00", "total_tokens": 0}
48
  {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.4080003499984741, "epoch": 0.30441400304414, "percentage": 26.67, "elapsed_time": "0:54:50", "remaining_time": "2:30:47", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
46
  {"current_steps": 390, "total_steps": 1500, "loss": 0.4259, "accuracy": 0.6499999761581421, "learning_rate": 4.211367764821722e-06, "epoch": 0.2968036529680365, "percentage": 26.0, "elapsed_time": "0:53:08", "remaining_time": "2:31:13", "throughput": "0.00", "total_tokens": 0}
47
  {"current_steps": 400, "total_steps": 1500, "loss": 0.4167, "accuracy": 0.7124999761581421, "learning_rate": 4.172826515897146e-06, "epoch": 0.30441400304414, "percentage": 26.67, "elapsed_time": "0:54:19", "remaining_time": "2:29:22", "throughput": "0.00", "total_tokens": 0}
48
  {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.4080003499984741, "epoch": 0.30441400304414, "percentage": 26.67, "elapsed_time": "0:54:50", "remaining_time": "2:30:47", "throughput": "0.00", "total_tokens": 0}
49
+ {"current_steps": 410, "total_steps": 1500, "loss": 0.3834, "accuracy": 0.8125, "learning_rate": 4.133551509975264e-06, "epoch": 0.3120243531202435, "percentage": 27.33, "elapsed_time": "0:56:13", "remaining_time": "2:29:27", "throughput": "0.00", "total_tokens": 0}
50
+ {"current_steps": 420, "total_steps": 1500, "loss": 0.397, "accuracy": 0.7124999761581421, "learning_rate": 4.093559974371725e-06, "epoch": 0.319634703196347, "percentage": 28.0, "elapsed_time": "0:57:28", "remaining_time": "2:27:48", "throughput": "0.00", "total_tokens": 0}
51
+ {"current_steps": 430, "total_steps": 1500, "loss": 0.3623, "accuracy": 0.7875000238418579, "learning_rate": 4.052869450695776e-06, "epoch": 0.3272450532724505, "percentage": 28.67, "elapsed_time": "0:58:45", "remaining_time": "2:26:13", "throughput": "0.00", "total_tokens": 0}
52
+ {"current_steps": 440, "total_steps": 1500, "loss": 0.3786, "accuracy": 0.7875000238418579, "learning_rate": 4.011497787155938e-06, "epoch": 0.334855403348554, "percentage": 29.33, "elapsed_time": "1:00:03", "remaining_time": "2:24:40", "throughput": "0.00", "total_tokens": 0}
53
+ {"current_steps": 450, "total_steps": 1500, "loss": 0.3948, "accuracy": 0.762499988079071, "learning_rate": 3.969463130731183e-06, "epoch": 0.3424657534246575, "percentage": 30.0, "elapsed_time": "1:01:19", "remaining_time": "2:23:04", "throughput": "0.00", "total_tokens": 0}
54
+ {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.3748260736465454, "epoch": 0.3424657534246575, "percentage": 30.0, "elapsed_time": "1:01:49", "remaining_time": "2:24:16", "throughput": "0.00", "total_tokens": 0}