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
e441eff
·
verified ·
1 Parent(s): 20c5554

Training in progress, step 550

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 sha256:011040067210d01ccfe86f7da5a944863b3f1fe08a9f1552b905bac0c793fdc6
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99afd7d1d267e329ca99fcdaf820287cb9c75b965d648b99a019613bf2251394
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -58,3 +58,9 @@
58
  {"current_steps": 490, "total_steps": 1500, "loss": 0.2638, "accuracy": 0.9375, "learning_rate": 3.795067523432826e-06, "epoch": 0.3955600403632694, "percentage": 32.67, "elapsed_time": "1:08:41", "remaining_time": "2:21:35", "throughput": "0.00", "total_tokens": 0}
59
  {"current_steps": 500, "total_steps": 1500, "loss": 0.2592, "accuracy": 0.8999999761581421, "learning_rate": 3.7500000000000005e-06, "epoch": 0.4036326942482341, "percentage": 33.33, "elapsed_time": "1:09:57", "remaining_time": "2:19:54", "throughput": "0.00", "total_tokens": 0}
60
  {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.3161226809024811, "epoch": 0.4036326942482341, "percentage": 33.33, "elapsed_time": "1:10:27", "remaining_time": "2:20:54", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
58
  {"current_steps": 490, "total_steps": 1500, "loss": 0.2638, "accuracy": 0.9375, "learning_rate": 3.795067523432826e-06, "epoch": 0.3955600403632694, "percentage": 32.67, "elapsed_time": "1:08:41", "remaining_time": "2:21:35", "throughput": "0.00", "total_tokens": 0}
59
  {"current_steps": 500, "total_steps": 1500, "loss": 0.2592, "accuracy": 0.8999999761581421, "learning_rate": 3.7500000000000005e-06, "epoch": 0.4036326942482341, "percentage": 33.33, "elapsed_time": "1:09:57", "remaining_time": "2:19:54", "throughput": "0.00", "total_tokens": 0}
60
  {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.3161226809024811, "epoch": 0.4036326942482341, "percentage": 33.33, "elapsed_time": "1:10:27", "remaining_time": "2:20:54", "throughput": "0.00", "total_tokens": 0}
61
+ {"current_steps": 510, "total_steps": 1500, "loss": 0.2772, "accuracy": 0.925000011920929, "learning_rate": 3.7043841852542884e-06, "epoch": 0.4117053481331988, "percentage": 34.0, "elapsed_time": "1:11:48", "remaining_time": "2:19:23", "throughput": "0.00", "total_tokens": 0}
62
+ {"current_steps": 520, "total_steps": 1500, "loss": 0.2724, "accuracy": 0.925000011920929, "learning_rate": 3.658240087799655e-06, "epoch": 0.41977800201816345, "percentage": 34.67, "elapsed_time": "1:13:06", "remaining_time": "2:17:46", "throughput": "0.00", "total_tokens": 0}
63
+ {"current_steps": 530, "total_steps": 1500, "loss": 0.2616, "accuracy": 0.949999988079071, "learning_rate": 3.611587947962319e-06, "epoch": 0.42785065590312815, "percentage": 35.33, "elapsed_time": "1:14:21", "remaining_time": "2:16:05", "throughput": "0.00", "total_tokens": 0}
64
+ {"current_steps": 540, "total_steps": 1500, "loss": 0.2954, "accuracy": 0.8374999761581421, "learning_rate": 3.564448228912682e-06, "epoch": 0.43592330978809285, "percentage": 36.0, "elapsed_time": "1:15:39", "remaining_time": "2:14:30", "throughput": "0.00", "total_tokens": 0}
65
+ {"current_steps": 550, "total_steps": 1500, "loss": 0.26, "accuracy": 0.887499988079071, "learning_rate": 3.516841607689501e-06, "epoch": 0.4439959636730575, "percentage": 36.67, "elapsed_time": "1:16:55", "remaining_time": "2:12:52", "throughput": "0.00", "total_tokens": 0}
66
+ {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.28268176317214966, "epoch": 0.4439959636730575, "percentage": 36.67, "elapsed_time": "1:17:25", "remaining_time": "2:13:44", "throughput": "0.00", "total_tokens": 0}