Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.8-kendall-onof-decrease-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files
xet
Community
ziansu commited on
Commit
7860cb0
·
verified ·
1 Parent(s): 05c0fdc

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:f24a7a47f45120cb86768cf6d416ae531f4243bc100226f511003c46a6d16e7b
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb783137ac0455c07887ce9b914c24aa889fa47415a26329b0f8efa3321b008b
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -34,3 +34,9 @@
34
  {"current_steps": 290, "total_steps": 1500, "loss": 0.6685, "accuracy": 0.6000000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.24924795874516545, "percentage": 19.33, "elapsed_time": "0:38:10", "remaining_time": "2:39:16", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 0.6009, "accuracy": 0.625, "learning_rate": 4.522542485937369e-06, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:39:25", "remaining_time": "2:37:41", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5855891704559326, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:39:51", "remaining_time": "2:39:24", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
34
  {"current_steps": 290, "total_steps": 1500, "loss": 0.6685, "accuracy": 0.6000000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.24924795874516545, "percentage": 19.33, "elapsed_time": "0:38:10", "remaining_time": "2:39:16", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 0.6009, "accuracy": 0.625, "learning_rate": 4.522542485937369e-06, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:39:25", "remaining_time": "2:37:41", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5855891704559326, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:39:51", "remaining_time": "2:39:24", "throughput": "0.00", "total_tokens": 0}
37
+ {"current_steps": 310, "total_steps": 1500, "loss": 0.512, "accuracy": 0.75, "learning_rate": 4.491324795060491e-06, "epoch": 0.2664374731413838, "percentage": 20.67, "elapsed_time": "0:41:11", "remaining_time": "2:38:08", "throughput": "0.00", "total_tokens": 0}
38
+ {"current_steps": 320, "total_steps": 1500, "loss": 0.5405, "accuracy": 0.6499999761581421, "learning_rate": 4.4592336433146e-06, "epoch": 0.2750322303394929, "percentage": 21.33, "elapsed_time": "0:42:25", "remaining_time": "2:36:25", "throughput": "0.00", "total_tokens": 0}
39
+ {"current_steps": 330, "total_steps": 1500, "loss": 0.5335, "accuracy": 0.637499988079071, "learning_rate": 4.426283106939474e-06, "epoch": 0.28362698753760207, "percentage": 22.0, "elapsed_time": "0:43:40", "remaining_time": "2:34:51", "throughput": "0.00", "total_tokens": 0}
40
+ {"current_steps": 340, "total_steps": 1500, "loss": 0.4903, "accuracy": 0.7124999761581421, "learning_rate": 4.3924876391293915e-06, "epoch": 0.2922217447357112, "percentage": 22.67, "elapsed_time": "0:44:52", "remaining_time": "2:33:06", "throughput": "0.00", "total_tokens": 0}
41
+ {"current_steps": 350, "total_steps": 1500, "loss": 0.5249, "accuracy": 0.5625, "learning_rate": 4.357862063693486e-06, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:46:04", "remaining_time": "2:31:22", "throughput": "0.00", "total_tokens": 0}
42
+ {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5171241760253906, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:46:29", "remaining_time": "2:32:46", "throughput": "0.00", "total_tokens": 0}