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
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
b9856be
·
verified ·
1 Parent(s): 97a60b2

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 sha256:02719bb80dbc90787c545ba0f09351e14bd53f9ba0609b526f3303df45964ca6
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f55ed3dc0e43341f4eda69f628b4169dd703e8656c89a736da1dc449ede06cb4
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -82,3 +82,9 @@
82
  {"current_steps": 690, "total_steps": 1500, "loss": 1.0845, "accuracy": 0.9750000238418579, "learning_rate": 2.813333083910761e-06, "epoch": 0.5662700041034058, "percentage": 46.0, "elapsed_time": "1:30:22", "remaining_time": "1:46:05", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 1.112, "accuracy": 1.0, "learning_rate": 2.761321158169134e-06, "epoch": 0.5744768157570784, "percentage": 46.67, "elapsed_time": "1:31:30", "remaining_time": "1:44:34", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.15530110895633698, "epoch": 0.5744768157570784, "percentage": 46.67, "elapsed_time": "1:31:56", "remaining_time": "1:45:04", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
82
  {"current_steps": 690, "total_steps": 1500, "loss": 1.0845, "accuracy": 0.9750000238418579, "learning_rate": 2.813333083910761e-06, "epoch": 0.5662700041034058, "percentage": 46.0, "elapsed_time": "1:30:22", "remaining_time": "1:46:05", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 1.112, "accuracy": 1.0, "learning_rate": 2.761321158169134e-06, "epoch": 0.5744768157570784, "percentage": 46.67, "elapsed_time": "1:31:30", "remaining_time": "1:44:34", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.15530110895633698, "epoch": 0.5744768157570784, "percentage": 46.67, "elapsed_time": "1:31:56", "remaining_time": "1:45:04", "throughput": "0.00", "total_tokens": 0}
85
+ {"current_steps": 710, "total_steps": 1500, "loss": 0.9868, "accuracy": 0.987500011920929, "learning_rate": 2.70919460833079e-06, "epoch": 0.582683627410751, "percentage": 47.33, "elapsed_time": "1:33:21", "remaining_time": "1:43:52", "throughput": "0.00", "total_tokens": 0}
86
+ {"current_steps": 720, "total_steps": 1500, "loss": 1.141, "accuracy": 0.987500011920929, "learning_rate": 2.6569762988232838e-06, "epoch": 0.5908904390644235, "percentage": 48.0, "elapsed_time": "1:34:33", "remaining_time": "1:42:25", "throughput": "0.00", "total_tokens": 0}
87
+ {"current_steps": 730, "total_steps": 1500, "loss": 0.9563, "accuracy": 0.9750000238418579, "learning_rate": 2.604689134322999e-06, "epoch": 0.599097250718096, "percentage": 48.67, "elapsed_time": "1:35:41", "remaining_time": "1:40:56", "throughput": "0.00", "total_tokens": 0}
88
+ {"current_steps": 740, "total_steps": 1500, "loss": 0.8511, "accuracy": 0.987500011920929, "learning_rate": 2.5523560497083927e-06, "epoch": 0.6073040623717686, "percentage": 49.33, "elapsed_time": "1:36:51", "remaining_time": "1:39:28", "throughput": "0.00", "total_tokens": 0}
89
+ {"current_steps": 750, "total_steps": 1500, "loss": 0.8016, "accuracy": 0.9750000238418579, "learning_rate": 2.5e-06, "epoch": 0.6155108740254411, "percentage": 50.0, "elapsed_time": "1:38:00", "remaining_time": "1:38:00", "throughput": "0.00", "total_tokens": 0}
90
+ {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.13788874447345734, "epoch": 0.6155108740254411, "percentage": 50.0, "elapsed_time": "1:38:26", "remaining_time": "1:38:26", "throughput": "0.00", "total_tokens": 0}