Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.9-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
8765978
·
verified ·
1 Parent(s): f7d6817

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 sha256:9c57f4ca7305d11afa28f049e0e4b21d4108dfaecbf9c199d6a04aebfd654db6
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0222416e1ec9d0120a5a4314348666fdd6ac0492a111cb2eb970f19aaedef4b9
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -34,3 +34,9 @@
34
  {"current_steps": 290, "total_steps": 1500, "loss": 0.5544, "accuracy": 0.6000000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.2341069626639758, "percentage": 19.33, "elapsed_time": "0:40:29", "remaining_time": "2:48:55", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 0.4968, "accuracy": 0.800000011920929, "learning_rate": 4.522542485937369e-06, "epoch": 0.24217961654894046, "percentage": 20.0, "elapsed_time": "0:41:47", "remaining_time": "2:47:08", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.4899609684944153, "epoch": 0.24217961654894046, "percentage": 20.0, "elapsed_time": "0:42:17", "remaining_time": "2:49:08", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
34
  {"current_steps": 290, "total_steps": 1500, "loss": 0.5544, "accuracy": 0.6000000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.2341069626639758, "percentage": 19.33, "elapsed_time": "0:40:29", "remaining_time": "2:48:55", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 0.4968, "accuracy": 0.800000011920929, "learning_rate": 4.522542485937369e-06, "epoch": 0.24217961654894046, "percentage": 20.0, "elapsed_time": "0:41:47", "remaining_time": "2:47:08", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.4899609684944153, "epoch": 0.24217961654894046, "percentage": 20.0, "elapsed_time": "0:42:17", "remaining_time": "2:49:08", "throughput": "0.00", "total_tokens": 0}
37
+ {"current_steps": 310, "total_steps": 1500, "loss": 0.5372, "accuracy": 0.699999988079071, "learning_rate": 4.491324795060491e-06, "epoch": 0.25025227043390513, "percentage": 20.67, "elapsed_time": "0:43:41", "remaining_time": "2:47:41", "throughput": "0.00", "total_tokens": 0}
38
+ {"current_steps": 320, "total_steps": 1500, "loss": 0.4974, "accuracy": 0.6875, "learning_rate": 4.4592336433146e-06, "epoch": 0.25832492431886983, "percentage": 21.33, "elapsed_time": "0:44:59", "remaining_time": "2:45:52", "throughput": "0.00", "total_tokens": 0}
39
+ {"current_steps": 330, "total_steps": 1500, "loss": 0.4777, "accuracy": 0.75, "learning_rate": 4.426283106939474e-06, "epoch": 0.26639757820383453, "percentage": 22.0, "elapsed_time": "0:46:21", "remaining_time": "2:44:22", "throughput": "0.00", "total_tokens": 0}
40
+ {"current_steps": 340, "total_steps": 1500, "loss": 0.4718, "accuracy": 0.7749999761581421, "learning_rate": 4.3924876391293915e-06, "epoch": 0.27447023208879917, "percentage": 22.67, "elapsed_time": "0:47:39", "remaining_time": "2:42:35", "throughput": "0.00", "total_tokens": 0}
41
+ {"current_steps": 350, "total_steps": 1500, "loss": 0.4909, "accuracy": 0.7124999761581421, "learning_rate": 4.357862063693486e-06, "epoch": 0.28254288597376387, "percentage": 23.33, "elapsed_time": "0:48:53", "remaining_time": "2:40:37", "throughput": "0.00", "total_tokens": 0}
42
+ {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.44899094104766846, "epoch": 0.28254288597376387, "percentage": 23.33, "elapsed_time": "0:49:23", "remaining_time": "2:42:15", "throughput": "0.00", "total_tokens": 0}