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
Model card Files Community
ziansu commited on
Commit
2f8f952
·
verified ·
1 Parent(s): b5f11e8

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 sha256:493f3ea7f6055a76835c90b369623909b3f40f9fd3c9de6a89faed43317fc9ab
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7715ee7642127df7a17823cdc34dc42522fae42aa3da333a5766d24d3b43ace5
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -34,3 +34,9 @@
34
  {"current_steps": 290, "total_steps": 1500, "loss": 0.5863, "accuracy": 0.6875, "learning_rate": 4.55287302283426e-06, "epoch": 0.25754884547069273, "percentage": 19.33, "elapsed_time": "0:40:15", "remaining_time": "2:47:56", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 0.5354, "accuracy": 0.75, "learning_rate": 4.522542485937369e-06, "epoch": 0.2664298401420959, "percentage": 20.0, "elapsed_time": "0:41:27", "remaining_time": "2:45:50", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5640697479248047, "epoch": 0.2664298401420959, "percentage": 20.0, "elapsed_time": "0:41:54", "remaining_time": "2:47:38", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
34
  {"current_steps": 290, "total_steps": 1500, "loss": 0.5863, "accuracy": 0.6875, "learning_rate": 4.55287302283426e-06, "epoch": 0.25754884547069273, "percentage": 19.33, "elapsed_time": "0:40:15", "remaining_time": "2:47:56", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 0.5354, "accuracy": 0.75, "learning_rate": 4.522542485937369e-06, "epoch": 0.2664298401420959, "percentage": 20.0, "elapsed_time": "0:41:27", "remaining_time": "2:45:50", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5640697479248047, "epoch": 0.2664298401420959, "percentage": 20.0, "elapsed_time": "0:41:54", "remaining_time": "2:47:38", "throughput": "0.00", "total_tokens": 0}
37
+ {"current_steps": 310, "total_steps": 1500, "loss": 0.5357, "accuracy": 0.6875, "learning_rate": 4.491324795060491e-06, "epoch": 0.2753108348134991, "percentage": 20.67, "elapsed_time": "0:43:16", "remaining_time": "2:46:06", "throughput": "0.00", "total_tokens": 0}
38
+ {"current_steps": 320, "total_steps": 1500, "loss": 0.5412, "accuracy": 0.6625000238418579, "learning_rate": 4.4592336433146e-06, "epoch": 0.2841918294849023, "percentage": 21.33, "elapsed_time": "0:44:30", "remaining_time": "2:44:08", "throughput": "0.00", "total_tokens": 0}
39
+ {"current_steps": 330, "total_steps": 1500, "loss": 0.5502, "accuracy": 0.675000011920929, "learning_rate": 4.426283106939474e-06, "epoch": 0.29307282415630553, "percentage": 22.0, "elapsed_time": "0:45:44", "remaining_time": "2:42:09", "throughput": "0.00", "total_tokens": 0}
40
+ {"current_steps": 340, "total_steps": 1500, "loss": 0.5519, "accuracy": 0.637499988079071, "learning_rate": 4.3924876391293915e-06, "epoch": 0.3019538188277087, "percentage": 22.67, "elapsed_time": "0:47:01", "remaining_time": "2:40:26", "throughput": "0.00", "total_tokens": 0}
41
+ {"current_steps": 350, "total_steps": 1500, "loss": 0.4806, "accuracy": 0.7124999761581421, "learning_rate": 4.357862063693486e-06, "epoch": 0.3108348134991119, "percentage": 23.33, "elapsed_time": "0:48:18", "remaining_time": "2:38:43", "throughput": "0.00", "total_tokens": 0}
42
+ {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.4698469638824463, "epoch": 0.3108348134991119, "percentage": 23.33, "elapsed_time": "0:48:45", "remaining_time": "2:40:11", "throughput": "0.00", "total_tokens": 0}