Hugging Face's logo

prosecalign
/
phi3m0128-cds-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
343332f
·
verified ·
1 Parent(s): 41c2cdb

Training in progress, step 750

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 sha256:1d425bc219a9d654d836fee0b4aa2ca86744dd40b8005ba8f3882e419b82dad4
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:633361ccdfdd139aa9f945143ab1df72e94551665506ce7bd77f575842b21b87
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -82,3 +82,9 @@
82
  {"current_steps": 690, "total_steps": 1500, "loss": 0.2861, "accuracy": 0.925000011920929, "learning_rate": 2.813333083910761e-06, "epoch": 0.6127886323268206, "percentage": 46.0, "elapsed_time": "1:33:41", "remaining_time": "1:49:58", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 0.2885, "accuracy": 0.887499988079071, "learning_rate": 2.761321158169134e-06, "epoch": 0.6216696269982238, "percentage": 46.67, "elapsed_time": "1:34:56", "remaining_time": "1:48:30", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.26512712240219116, "epoch": 0.6216696269982238, "percentage": 46.67, "elapsed_time": "1:35:22", "remaining_time": "1:48:59", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
82
  {"current_steps": 690, "total_steps": 1500, "loss": 0.2861, "accuracy": 0.925000011920929, "learning_rate": 2.813333083910761e-06, "epoch": 0.6127886323268206, "percentage": 46.0, "elapsed_time": "1:33:41", "remaining_time": "1:49:58", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 0.2885, "accuracy": 0.887499988079071, "learning_rate": 2.761321158169134e-06, "epoch": 0.6216696269982238, "percentage": 46.67, "elapsed_time": "1:34:56", "remaining_time": "1:48:30", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.26512712240219116, "epoch": 0.6216696269982238, "percentage": 46.67, "elapsed_time": "1:35:22", "remaining_time": "1:48:59", "throughput": "0.00", "total_tokens": 0}
85
+ {"current_steps": 710, "total_steps": 1500, "loss": 0.2078, "accuracy": 0.9624999761581421, "learning_rate": 2.70919460833079e-06, "epoch": 0.6305506216696269, "percentage": 47.33, "elapsed_time": "1:36:48", "remaining_time": "1:47:42", "throughput": "0.00", "total_tokens": 0}
86
+ {"current_steps": 720, "total_steps": 1500, "loss": 0.2346, "accuracy": 0.9375, "learning_rate": 2.6569762988232838e-06, "epoch": 0.6394316163410302, "percentage": 48.0, "elapsed_time": "1:38:07", "remaining_time": "1:46:18", "throughput": "0.00", "total_tokens": 0}
87
+ {"current_steps": 730, "total_steps": 1500, "loss": 0.2354, "accuracy": 0.925000011920929, "learning_rate": 2.604689134322999e-06, "epoch": 0.6483126110124334, "percentage": 48.67, "elapsed_time": "1:39:24", "remaining_time": "1:44:51", "throughput": "0.00", "total_tokens": 0}
88
+ {"current_steps": 740, "total_steps": 1500, "loss": 0.231, "accuracy": 0.8999999761581421, "learning_rate": 2.5523560497083927e-06, "epoch": 0.6571936056838366, "percentage": 49.33, "elapsed_time": "1:40:38", "remaining_time": "1:43:22", "throughput": "0.00", "total_tokens": 0}
89
+ {"current_steps": 750, "total_steps": 1500, "loss": 0.2332, "accuracy": 0.875, "learning_rate": 2.5e-06, "epoch": 0.6660746003552398, "percentage": 50.0, "elapsed_time": "1:41:53", "remaining_time": "1:41:53", "throughput": "0.00", "total_tokens": 0}
90
+ {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.2521994411945343, "epoch": 0.6660746003552398, "percentage": 50.0, "elapsed_time": "1:42:19", "remaining_time": "1:42:19", "throughput": "0.00", "total_tokens": 0}