Hugging Face's logo

prosecalign
/
clm7b0129-kendall-onof-ofif-corr-max-2-simpo-max1500-decay-sft-beta1.5-gamma0.5-lr5e-6

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
dd7dc9a
·
verified ·
1 Parent(s): 9cefb7c

Training in progress, step 300

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:b266be409db7d879882292a4790ace968b4aae610e8e251fee9bd6a8c6f685cf
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a425ce98380c2ecb5935299a33c336430295e361176ffeab4ecddcf898bdb319
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -28,3 +28,9 @@
28
  {"current_steps": 240, "total_steps": 1500, "loss": 6.667, "accuracy": 0.6499999761581421, "learning_rate": 4.690766700109659e-06, "epoch": 0.1739603153030715, "percentage": 16.0, "elapsed_time": "0:32:40", "remaining_time": "2:51:35", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 6.7146, "accuracy": 0.5625, "learning_rate": 4.665063509461098e-06, "epoch": 0.1812086617740328, "percentage": 16.67, "elapsed_time": "0:34:00", "remaining_time": "2:50:01", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.8070082664489746, "epoch": 0.1812086617740328, "percentage": 16.67, "elapsed_time": "0:34:30", "remaining_time": "2:52:33", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
28
  {"current_steps": 240, "total_steps": 1500, "loss": 6.667, "accuracy": 0.6499999761581421, "learning_rate": 4.690766700109659e-06, "epoch": 0.1739603153030715, "percentage": 16.0, "elapsed_time": "0:32:40", "remaining_time": "2:51:35", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 6.7146, "accuracy": 0.5625, "learning_rate": 4.665063509461098e-06, "epoch": 0.1812086617740328, "percentage": 16.67, "elapsed_time": "0:34:00", "remaining_time": "2:50:01", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.8070082664489746, "epoch": 0.1812086617740328, "percentage": 16.67, "elapsed_time": "0:34:30", "remaining_time": "2:52:33", "throughput": "0.00", "total_tokens": 0}
31
+ {"current_steps": 260, "total_steps": 1500, "loss": 6.5743, "accuracy": 0.637499988079071, "learning_rate": 4.638410650401267e-06, "epoch": 0.18845700824499412, "percentage": 17.33, "elapsed_time": "0:35:59", "remaining_time": "2:51:41", "throughput": "0.00", "total_tokens": 0}
32
+ {"current_steps": 270, "total_steps": 1500, "loss": 6.4931, "accuracy": 0.5874999761581421, "learning_rate": 4.610819813755038e-06, "epoch": 0.19570535471595543, "percentage": 18.0, "elapsed_time": "0:37:16", "remaining_time": "2:49:46", "throughput": "0.00", "total_tokens": 0}
33
+ {"current_steps": 280, "total_steps": 1500, "loss": 6.2272, "accuracy": 0.550000011920929, "learning_rate": 4.582303101775249e-06, "epoch": 0.20295370118691675, "percentage": 18.67, "elapsed_time": "0:38:32", "remaining_time": "2:47:56", "throughput": "0.00", "total_tokens": 0}
34
+ {"current_steps": 290, "total_steps": 1500, "loss": 5.7937, "accuracy": 0.7124999761581421, "learning_rate": 4.55287302283426e-06, "epoch": 0.21020204765787803, "percentage": 19.33, "elapsed_time": "0:39:45", "remaining_time": "2:45:54", "throughput": "0.00", "total_tokens": 0}
35
+ {"current_steps": 300, "total_steps": 1500, "loss": 5.741, "accuracy": 0.6875, "learning_rate": 4.522542485937369e-06, "epoch": 0.21745039412883935, "percentage": 20.0, "elapsed_time": "0:40:58", "remaining_time": "2:43:53", "throughput": "0.00", "total_tokens": 0}
36
+ {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.6990054845809937, "epoch": 0.21745039412883935, "percentage": 20.0, "elapsed_time": "0:41:28", "remaining_time": "2:45:55", "throughput": "0.00", "total_tokens": 0}