Hugging Face's logo

prosecalign
/
clm7b0129-cds-0.8-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
5bd621d
·
verified ·
1 Parent(s): 174678f

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 sha256:921a2cf022e997eef29a2d1a0b81ff032e005ce9bb58db0f1de38fede016b8bc
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19daadb3a75f2d3e0ea7e18013279dce4803b3d0523487e96586bd50074abaa1
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -28,3 +28,9 @@
28
  {"current_steps": 240, "total_steps": 1500, "loss": 7.012, "accuracy": 0.625, "learning_rate": 4.690766700109659e-06, "epoch": 0.19696347968814115, "percentage": 16.0, "elapsed_time": "0:31:30", "remaining_time": "2:45:25", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 6.7812, "accuracy": 0.5375000238418579, "learning_rate": 4.665063509461098e-06, "epoch": 0.2051702913418137, "percentage": 16.67, "elapsed_time": "0:32:43", "remaining_time": "2:43:39", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.8434350490570068, "epoch": 0.2051702913418137, "percentage": 16.67, "elapsed_time": "0:33:09", "remaining_time": "2:45:49", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
28
  {"current_steps": 240, "total_steps": 1500, "loss": 7.012, "accuracy": 0.625, "learning_rate": 4.690766700109659e-06, "epoch": 0.19696347968814115, "percentage": 16.0, "elapsed_time": "0:31:30", "remaining_time": "2:45:25", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 6.7812, "accuracy": 0.5375000238418579, "learning_rate": 4.665063509461098e-06, "epoch": 0.2051702913418137, "percentage": 16.67, "elapsed_time": "0:32:43", "remaining_time": "2:43:39", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.8434350490570068, "epoch": 0.2051702913418137, "percentage": 16.67, "elapsed_time": "0:33:09", "remaining_time": "2:45:49", "throughput": "0.00", "total_tokens": 0}
31
+ {"current_steps": 260, "total_steps": 1500, "loss": 6.6024, "accuracy": 0.5625, "learning_rate": 4.638410650401267e-06, "epoch": 0.21337710299548626, "percentage": 17.33, "elapsed_time": "0:34:33", "remaining_time": "2:44:46", "throughput": "0.00", "total_tokens": 0}
32
+ {"current_steps": 270, "total_steps": 1500, "loss": 6.7377, "accuracy": 0.612500011920929, "learning_rate": 4.610819813755038e-06, "epoch": 0.2215839146491588, "percentage": 18.0, "elapsed_time": "0:35:45", "remaining_time": "2:42:53", "throughput": "0.00", "total_tokens": 0}
33
+ {"current_steps": 280, "total_steps": 1500, "loss": 6.6463, "accuracy": 0.6875, "learning_rate": 4.582303101775249e-06, "epoch": 0.22979072630283134, "percentage": 18.67, "elapsed_time": "0:36:58", "remaining_time": "2:41:06", "throughput": "0.00", "total_tokens": 0}
34
+ {"current_steps": 290, "total_steps": 1500, "loss": 6.2424, "accuracy": 0.5249999761581421, "learning_rate": 4.55287302283426e-06, "epoch": 0.23799753795650389, "percentage": 19.33, "elapsed_time": "0:38:07", "remaining_time": "2:39:04", "throughput": "0.00", "total_tokens": 0}
35
+ {"current_steps": 300, "total_steps": 1500, "loss": 6.3458, "accuracy": 0.5375000238418579, "learning_rate": 4.522542485937369e-06, "epoch": 0.24620434961017645, "percentage": 20.0, "elapsed_time": "0:39:20", "remaining_time": "2:37:22", "throughput": "0.00", "total_tokens": 0}
36
+ {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.7593368887901306, "epoch": 0.24620434961017645, "percentage": 20.0, "elapsed_time": "0:39:46", "remaining_time": "2:39:06", "throughput": "0.00", "total_tokens": 0}