Hugging Face's logo

prosecalign
/
clm7b0129-wds-0.8-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files
xet
Community
ziansu commited on
Commit
df1382e
·
verified ·
1 Parent(s): e913b50

Training in progress, step 450

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:a8c479ae0ffd5ebfb1066ec4cf6988e1f55d04a12e9d1b477dc4e357cfcc3f00
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084e6c50b03baf002be8e4062afcc45294b54b0673f510c4e122572121eb5fa8
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -46,3 +46,9 @@
46
  {"current_steps": 390, "total_steps": 1500, "loss": 4.6813, "accuracy": 0.5874999761581421, "learning_rate": 4.211367764821722e-06, "epoch": 0.3200656544932294, "percentage": 26.0, "elapsed_time": "0:50:53", "remaining_time": "2:24:50", "throughput": "0.00", "total_tokens": 0}
47
  {"current_steps": 400, "total_steps": 1500, "loss": 4.3764, "accuracy": 0.737500011920929, "learning_rate": 4.172826515897146e-06, "epoch": 0.3282724661469019, "percentage": 26.67, "elapsed_time": "0:52:03", "remaining_time": "2:23:10", "throughput": "0.00", "total_tokens": 0}
48
  {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.5019229650497437, "epoch": 0.3282724661469019, "percentage": 26.67, "elapsed_time": "0:52:30", "remaining_time": "2:24:22", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
46
  {"current_steps": 390, "total_steps": 1500, "loss": 4.6813, "accuracy": 0.5874999761581421, "learning_rate": 4.211367764821722e-06, "epoch": 0.3200656544932294, "percentage": 26.0, "elapsed_time": "0:50:53", "remaining_time": "2:24:50", "throughput": "0.00", "total_tokens": 0}
47
  {"current_steps": 400, "total_steps": 1500, "loss": 4.3764, "accuracy": 0.737500011920929, "learning_rate": 4.172826515897146e-06, "epoch": 0.3282724661469019, "percentage": 26.67, "elapsed_time": "0:52:03", "remaining_time": "2:23:10", "throughput": "0.00", "total_tokens": 0}
48
  {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.5019229650497437, "epoch": 0.3282724661469019, "percentage": 26.67, "elapsed_time": "0:52:30", "remaining_time": "2:24:22", "throughput": "0.00", "total_tokens": 0}
49
+ {"current_steps": 410, "total_steps": 1500, "loss": 4.0575, "accuracy": 0.7250000238418579, "learning_rate": 4.133551509975264e-06, "epoch": 0.33647927780057446, "percentage": 27.33, "elapsed_time": "0:53:54", "remaining_time": "2:23:19", "throughput": "0.00", "total_tokens": 0}
50
+ {"current_steps": 420, "total_steps": 1500, "loss": 3.9082, "accuracy": 0.762499988079071, "learning_rate": 4.093559974371725e-06, "epoch": 0.344686089454247, "percentage": 28.0, "elapsed_time": "0:55:05", "remaining_time": "2:21:39", "throughput": "0.00", "total_tokens": 0}
51
+ {"current_steps": 430, "total_steps": 1500, "loss": 3.6948, "accuracy": 0.800000011920929, "learning_rate": 4.052869450695776e-06, "epoch": 0.3528929011079196, "percentage": 28.67, "elapsed_time": "0:56:17", "remaining_time": "2:20:04", "throughput": "0.00", "total_tokens": 0}
52
+ {"current_steps": 440, "total_steps": 1500, "loss": 3.7709, "accuracy": 0.7875000238418579, "learning_rate": 4.011497787155938e-06, "epoch": 0.36109971276159214, "percentage": 29.33, "elapsed_time": "0:57:31", "remaining_time": "2:18:34", "throughput": "0.00", "total_tokens": 0}
53
+ {"current_steps": 450, "total_steps": 1500, "loss": 3.6878, "accuracy": 0.8374999761581421, "learning_rate": 3.969463130731183e-06, "epoch": 0.3693065244152647, "percentage": 30.0, "elapsed_time": "0:58:40", "remaining_time": "2:16:55", "throughput": "0.00", "total_tokens": 0}
54
+ {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.43350929021835327, "epoch": 0.3693065244152647, "percentage": 30.0, "elapsed_time": "0:59:07", "remaining_time": "2:17:56", "throughput": "0.00", "total_tokens": 0}