Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.75-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
840114d
·
verified ·
1 Parent(s): 88acbba

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 sha256:3eec8b85745fa04266c7ba212539220ce1bc93dd4bf3d7268ebb3202146b3669
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e033097391818d41f822f327481d8c8487a12392be9a83a89a46f929f30318e6
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -58,3 +58,9 @@
58
  {"current_steps": 490, "total_steps": 1500, "loss": 0.3238, "accuracy": 0.925000011920929, "learning_rate": 3.795067523432826e-06, "epoch": 0.4351687388987567, "percentage": 32.67, "elapsed_time": "1:08:15", "remaining_time": "2:20:41", "throughput": "0.00", "total_tokens": 0}
59
  {"current_steps": 500, "total_steps": 1500, "loss": 0.3052, "accuracy": 0.875, "learning_rate": 3.7500000000000005e-06, "epoch": 0.44404973357015987, "percentage": 33.33, "elapsed_time": "1:09:35", "remaining_time": "2:19:10", "throughput": "0.00", "total_tokens": 0}
60
  {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.324949711561203, "epoch": 0.44404973357015987, "percentage": 33.33, "elapsed_time": "1:10:02", "remaining_time": "2:20:04", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
58
  {"current_steps": 490, "total_steps": 1500, "loss": 0.3238, "accuracy": 0.925000011920929, "learning_rate": 3.795067523432826e-06, "epoch": 0.4351687388987567, "percentage": 32.67, "elapsed_time": "1:08:15", "remaining_time": "2:20:41", "throughput": "0.00", "total_tokens": 0}
59
  {"current_steps": 500, "total_steps": 1500, "loss": 0.3052, "accuracy": 0.875, "learning_rate": 3.7500000000000005e-06, "epoch": 0.44404973357015987, "percentage": 33.33, "elapsed_time": "1:09:35", "remaining_time": "2:19:10", "throughput": "0.00", "total_tokens": 0}
60
  {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.324949711561203, "epoch": 0.44404973357015987, "percentage": 33.33, "elapsed_time": "1:10:02", "remaining_time": "2:20:04", "throughput": "0.00", "total_tokens": 0}
61
+ {"current_steps": 510, "total_steps": 1500, "loss": 0.3185, "accuracy": 0.862500011920929, "learning_rate": 3.7043841852542884e-06, "epoch": 0.45293072824156305, "percentage": 34.0, "elapsed_time": "1:11:24", "remaining_time": "2:18:36", "throughput": "0.00", "total_tokens": 0}
62
+ {"current_steps": 520, "total_steps": 1500, "loss": 0.3148, "accuracy": 0.875, "learning_rate": 3.658240087799655e-06, "epoch": 0.46181172291296624, "percentage": 34.67, "elapsed_time": "1:12:44", "remaining_time": "2:17:06", "throughput": "0.00", "total_tokens": 0}
63
+ {"current_steps": 530, "total_steps": 1500, "loss": 0.3191, "accuracy": 0.9375, "learning_rate": 3.611587947962319e-06, "epoch": 0.4706927175843694, "percentage": 35.33, "elapsed_time": "1:14:02", "remaining_time": "2:15:31", "throughput": "0.00", "total_tokens": 0}
64
+ {"current_steps": 540, "total_steps": 1500, "loss": 0.276, "accuracy": 0.8999999761581421, "learning_rate": 3.564448228912682e-06, "epoch": 0.47957371225577267, "percentage": 36.0, "elapsed_time": "1:15:23", "remaining_time": "2:14:01", "throughput": "0.00", "total_tokens": 0}
65
+ {"current_steps": 550, "total_steps": 1500, "loss": 0.3257, "accuracy": 0.9375, "learning_rate": 3.516841607689501e-06, "epoch": 0.48845470692717585, "percentage": 36.67, "elapsed_time": "1:16:40", "remaining_time": "2:12:25", "throughput": "0.00", "total_tokens": 0}
66
+ {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.30456680059432983, "epoch": 0.48845470692717585, "percentage": 36.67, "elapsed_time": "1:17:07", "remaining_time": "2:13:12", "throughput": "0.00", "total_tokens": 0}