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
Model card Files Community
ziansu commited on
Commit
61c20d5
·
verified ·
1 Parent(s): b295cf6

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:d4536ef2974aa09ce1e948c88ab1bb493563e6b259d6d8b5d99fdcfed4854e70
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7b0c103837d6d5650fb78e822d92aa13b9cf387dc8747fbd2f6ad302cc151f
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -46,3 +46,9 @@
46
  {"current_steps": 390, "total_steps": 1500, "loss": 0.4565, "accuracy": 0.7250000238418579, "learning_rate": 4.211367764821722e-06, "epoch": 0.3148335015136226, "percentage": 26.0, "elapsed_time": "0:54:37", "remaining_time": "2:35:29", "throughput": "0.00", "total_tokens": 0}
47
  {"current_steps": 400, "total_steps": 1500, "loss": 0.408, "accuracy": 0.887499988079071, "learning_rate": 4.172826515897146e-06, "epoch": 0.3229061553985873, "percentage": 26.67, "elapsed_time": "0:55:56", "remaining_time": "2:33:51", "throughput": "0.00", "total_tokens": 0}
48
  {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.38578492403030396, "epoch": 0.3229061553985873, "percentage": 26.67, "elapsed_time": "0:56:26", "remaining_time": "2:35:13", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
46
  {"current_steps": 390, "total_steps": 1500, "loss": 0.4565, "accuracy": 0.7250000238418579, "learning_rate": 4.211367764821722e-06, "epoch": 0.3148335015136226, "percentage": 26.0, "elapsed_time": "0:54:37", "remaining_time": "2:35:29", "throughput": "0.00", "total_tokens": 0}
47
  {"current_steps": 400, "total_steps": 1500, "loss": 0.408, "accuracy": 0.887499988079071, "learning_rate": 4.172826515897146e-06, "epoch": 0.3229061553985873, "percentage": 26.67, "elapsed_time": "0:55:56", "remaining_time": "2:33:51", "throughput": "0.00", "total_tokens": 0}
48
  {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.38578492403030396, "epoch": 0.3229061553985873, "percentage": 26.67, "elapsed_time": "0:56:26", "remaining_time": "2:35:13", "throughput": "0.00", "total_tokens": 0}
49
+ {"current_steps": 410, "total_steps": 1500, "loss": 0.3894, "accuracy": 0.800000011920929, "learning_rate": 4.133551509975264e-06, "epoch": 0.33097880928355194, "percentage": 27.33, "elapsed_time": "0:57:49", "remaining_time": "2:33:44", "throughput": "0.00", "total_tokens": 0}
50
+ {"current_steps": 420, "total_steps": 1500, "loss": 0.3853, "accuracy": 0.8500000238418579, "learning_rate": 4.093559974371725e-06, "epoch": 0.33905146316851664, "percentage": 28.0, "elapsed_time": "0:59:07", "remaining_time": "2:32:02", "throughput": "0.00", "total_tokens": 0}
51
+ {"current_steps": 430, "total_steps": 1500, "loss": 0.3669, "accuracy": 0.8125, "learning_rate": 4.052869450695776e-06, "epoch": 0.34712411705348134, "percentage": 28.67, "elapsed_time": "1:00:26", "remaining_time": "2:30:24", "throughput": "0.00", "total_tokens": 0}
52
+ {"current_steps": 440, "total_steps": 1500, "loss": 0.3333, "accuracy": 0.8500000238418579, "learning_rate": 4.011497787155938e-06, "epoch": 0.35519677093844604, "percentage": 29.33, "elapsed_time": "1:01:44", "remaining_time": "2:28:44", "throughput": "0.00", "total_tokens": 0}
53
+ {"current_steps": 450, "total_steps": 1500, "loss": 0.356, "accuracy": 0.875, "learning_rate": 3.969463130731183e-06, "epoch": 0.3632694248234107, "percentage": 30.0, "elapsed_time": "1:02:58", "remaining_time": "2:26:57", "throughput": "0.00", "total_tokens": 0}
54
+ {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.33659350872039795, "epoch": 0.3632694248234107, "percentage": 30.0, "elapsed_time": "1:03:28", "remaining_time": "2:28:07", "throughput": "0.00", "total_tokens": 0}