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
c07c7b5
·
verified ·
1 Parent(s): 77eba16

Training in progress, step 1150

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:fd23206a6a0c16946f58e071ddb10743e3ca261a4165bdd2b55c0fbfbba5a665
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d0a9ad35b163273c24e20b07f258f44868d9db5a4a56a374295104d04c75c0
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -130,3 +130,9 @@
130
  {"current_steps": 1090, "total_steps": 1500, "loss": 0.6379, "accuracy": 0.9750000238418579, "learning_rate": 8.664484900247363e-07, "epoch": 0.790069765334783, "percentage": 72.67, "elapsed_time": "2:30:40", "remaining_time": "0:56:40", "throughput": "0.00", "total_tokens": 0}
131
  {"current_steps": 1100, "total_steps": 1500, "loss": 0.6618, "accuracy": 0.987500011920929, "learning_rate": 8.271734841028553e-07, "epoch": 0.7973181118057443, "percentage": 73.33, "elapsed_time": "2:31:57", "remaining_time": "0:55:15", "throughput": "0.00", "total_tokens": 0}
132
  {"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.0923290029168129, "epoch": 0.7973181118057443, "percentage": 73.33, "elapsed_time": "2:32:27", "remaining_time": "0:55:26", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
130
  {"current_steps": 1090, "total_steps": 1500, "loss": 0.6379, "accuracy": 0.9750000238418579, "learning_rate": 8.664484900247363e-07, "epoch": 0.790069765334783, "percentage": 72.67, "elapsed_time": "2:30:40", "remaining_time": "0:56:40", "throughput": "0.00", "total_tokens": 0}
131
  {"current_steps": 1100, "total_steps": 1500, "loss": 0.6618, "accuracy": 0.987500011920929, "learning_rate": 8.271734841028553e-07, "epoch": 0.7973181118057443, "percentage": 73.33, "elapsed_time": "2:31:57", "remaining_time": "0:55:15", "throughput": "0.00", "total_tokens": 0}
132
  {"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.0923290029168129, "epoch": 0.7973181118057443, "percentage": 73.33, "elapsed_time": "2:32:27", "remaining_time": "0:55:26", "throughput": "0.00", "total_tokens": 0}
133
+ {"current_steps": 1110, "total_steps": 1500, "loss": 0.5303, "accuracy": 0.987500011920929, "learning_rate": 7.886322351782782e-07, "epoch": 0.8045664582767056, "percentage": 74.0, "elapsed_time": "2:33:53", "remaining_time": "0:54:04", "throughput": "0.00", "total_tokens": 0}
134
+ {"current_steps": 1120, "total_steps": 1500, "loss": 0.9835, "accuracy": 0.987500011920929, "learning_rate": 7.508416487165862e-07, "epoch": 0.811814804747667, "percentage": 74.67, "elapsed_time": "2:35:10", "remaining_time": "0:52:38", "throughput": "0.00", "total_tokens": 0}
135
+ {"current_steps": 1130, "total_steps": 1500, "loss": 0.9257, "accuracy": 1.0, "learning_rate": 7.138183009179922e-07, "epoch": 0.8190631512186283, "percentage": 75.33, "elapsed_time": "2:36:28", "remaining_time": "0:51:14", "throughput": "0.00", "total_tokens": 0}
136
+ {"current_steps": 1140, "total_steps": 1500, "loss": 0.5027, "accuracy": 0.9750000238418579, "learning_rate": 6.775784314464717e-07, "epoch": 0.8263114976895896, "percentage": 76.0, "elapsed_time": "2:37:41", "remaining_time": "0:49:47", "throughput": "0.00", "total_tokens": 0}
137
+ {"current_steps": 1150, "total_steps": 1500, "loss": 0.7009, "accuracy": 0.987500011920929, "learning_rate": 6.421379363065142e-07, "epoch": 0.8335598441605508, "percentage": 76.67, "elapsed_time": "2:38:55", "remaining_time": "0:48:22", "throughput": "0.00", "total_tokens": 0}
138
+ {"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.09489800035953522, "epoch": 0.8335598441605508, "percentage": 76.67, "elapsed_time": "2:39:25", "remaining_time": "0:48:31", "throughput": "0.00", "total_tokens": 0}