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
5620bb5
·
verified ·
1 Parent(s): c2ce9f0

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 sha256:22f681d6e2a105aed52fb10818ea3c735174a290794d44cef202e385c8b8d96b
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ded9effaf26b814fa2662f4f5f5fc018391f7e8695803e30a06e8986d4d894
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -28,3 +28,9 @@
28
  {"current_steps": 240, "total_steps": 1500, "loss": 6.9879, "accuracy": 0.637499988079071, "learning_rate": 4.690766700109659e-06, "epoch": 0.19696347968814115, "percentage": 16.0, "elapsed_time": "0:30:53", "remaining_time": "2:42:12", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 6.7357, "accuracy": 0.6000000238418579, "learning_rate": 4.665063509461098e-06, "epoch": 0.2051702913418137, "percentage": 16.67, "elapsed_time": "0:32:05", "remaining_time": "2:40:27", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.8405817747116089, "epoch": 0.2051702913418137, "percentage": 16.67, "elapsed_time": "0:32:31", "remaining_time": "2:42:38", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
28
  {"current_steps": 240, "total_steps": 1500, "loss": 6.9879, "accuracy": 0.637499988079071, "learning_rate": 4.690766700109659e-06, "epoch": 0.19696347968814115, "percentage": 16.0, "elapsed_time": "0:30:53", "remaining_time": "2:42:12", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 6.7357, "accuracy": 0.6000000238418579, "learning_rate": 4.665063509461098e-06, "epoch": 0.2051702913418137, "percentage": 16.67, "elapsed_time": "0:32:05", "remaining_time": "2:40:27", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.8405817747116089, "epoch": 0.2051702913418137, "percentage": 16.67, "elapsed_time": "0:32:31", "remaining_time": "2:42:38", "throughput": "0.00", "total_tokens": 0}
31
+ {"current_steps": 260, "total_steps": 1500, "loss": 6.6048, "accuracy": 0.574999988079071, "learning_rate": 4.638410650401267e-06, "epoch": 0.21337710299548626, "percentage": 17.33, "elapsed_time": "0:33:55", "remaining_time": "2:41:49", "throughput": "0.00", "total_tokens": 0}
32
+ {"current_steps": 270, "total_steps": 1500, "loss": 6.6403, "accuracy": 0.6000000238418579, "learning_rate": 4.610819813755038e-06, "epoch": 0.2215839146491588, "percentage": 18.0, "elapsed_time": "0:35:08", "remaining_time": "2:40:07", "throughput": "0.00", "total_tokens": 0}
33
+ {"current_steps": 280, "total_steps": 1500, "loss": 6.4767, "accuracy": 0.6875, "learning_rate": 4.582303101775249e-06, "epoch": 0.22979072630283134, "percentage": 18.67, "elapsed_time": "0:36:23", "remaining_time": "2:38:35", "throughput": "0.00", "total_tokens": 0}
34
+ {"current_steps": 290, "total_steps": 1500, "loss": 6.2071, "accuracy": 0.4749999940395355, "learning_rate": 4.55287302283426e-06, "epoch": 0.23799753795650389, "percentage": 19.33, "elapsed_time": "0:37:36", "remaining_time": "2:36:53", "throughput": "0.00", "total_tokens": 0}
35
+ {"current_steps": 300, "total_steps": 1500, "loss": 6.1801, "accuracy": 0.5874999761581421, "learning_rate": 4.522542485937369e-06, "epoch": 0.24620434961017645, "percentage": 20.0, "elapsed_time": "0:38:47", "remaining_time": "2:35:09", "throughput": "0.00", "total_tokens": 0}
36
+ {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.738965630531311, "epoch": 0.24620434961017645, "percentage": 20.0, "elapsed_time": "0:39:13", "remaining_time": "2:36:53", "throughput": "0.00", "total_tokens": 0}