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
d775384
·
verified ·
1 Parent(s): 52f5c58

Training in progress, step 1250

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:dcbe5c60e63a74bda1718c743a5e3df0a742995ea8da64d57c7081a949df9d74
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:183886bc502da5abdabe9d61240f4fd8556eb323e18a73b72a8770c8c6d09440
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -142,3 +142,9 @@
142
  {"current_steps": 1190, "total_steps": 1500, "loss": 1.1177, "accuracy": 0.949999988079071, "learning_rate": 5.086752049395094e-07, "epoch": 0.8625532300443961, "percentage": 79.33, "elapsed_time": "2:44:37", "remaining_time": "0:42:53", "throughput": "0.00", "total_tokens": 0}
143
  {"current_steps": 1200, "total_steps": 1500, "loss": 0.4369, "accuracy": 1.0, "learning_rate": 4.774575140626317e-07, "epoch": 0.8698015765153574, "percentage": 80.0, "elapsed_time": "2:45:55", "remaining_time": "0:41:28", "throughput": "0.00", "total_tokens": 0}
144
  {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.08837977796792984, "epoch": 0.8698015765153574, "percentage": 80.0, "elapsed_time": "2:46:25", "remaining_time": "0:41:36", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
142
  {"current_steps": 1190, "total_steps": 1500, "loss": 1.1177, "accuracy": 0.949999988079071, "learning_rate": 5.086752049395094e-07, "epoch": 0.8625532300443961, "percentage": 79.33, "elapsed_time": "2:44:37", "remaining_time": "0:42:53", "throughput": "0.00", "total_tokens": 0}
143
  {"current_steps": 1200, "total_steps": 1500, "loss": 0.4369, "accuracy": 1.0, "learning_rate": 4.774575140626317e-07, "epoch": 0.8698015765153574, "percentage": 80.0, "elapsed_time": "2:45:55", "remaining_time": "0:41:28", "throughput": "0.00", "total_tokens": 0}
144
  {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.08837977796792984, "epoch": 0.8698015765153574, "percentage": 80.0, "elapsed_time": "2:46:25", "remaining_time": "0:41:36", "throughput": "0.00", "total_tokens": 0}
145
+ {"current_steps": 1210, "total_steps": 1500, "loss": 0.4923, "accuracy": 1.0, "learning_rate": 4.4712697716573994e-07, "epoch": 0.8770499229863188, "percentage": 80.67, "elapsed_time": "2:47:51", "remaining_time": "0:40:13", "throughput": "0.00", "total_tokens": 0}
146
+ {"current_steps": 1220, "total_steps": 1500, "loss": 0.7736, "accuracy": 0.9750000238418579, "learning_rate": 4.1769689822475147e-07, "epoch": 0.8842982694572801, "percentage": 81.33, "elapsed_time": "2:49:04", "remaining_time": "0:38:48", "throughput": "0.00", "total_tokens": 0}
147
+ {"current_steps": 1230, "total_steps": 1500, "loss": 0.6428, "accuracy": 0.987500011920929, "learning_rate": 3.891801862449629e-07, "epoch": 0.8915466159282414, "percentage": 82.0, "elapsed_time": "2:50:17", "remaining_time": "0:37:22", "throughput": "0.00", "total_tokens": 0}
148
+ {"current_steps": 1240, "total_steps": 1500, "loss": 0.5315, "accuracy": 1.0, "learning_rate": 3.615893495987335e-07, "epoch": 0.8987949623992026, "percentage": 82.67, "elapsed_time": "2:51:29", "remaining_time": "0:35:57", "throughput": "0.00", "total_tokens": 0}
149
+ {"current_steps": 1250, "total_steps": 1500, "loss": 0.9809, "accuracy": 0.987500011920929, "learning_rate": 3.3493649053890325e-07, "epoch": 0.906043308870164, "percentage": 83.33, "elapsed_time": "2:52:47", "remaining_time": "0:34:33", "throughput": "0.00", "total_tokens": 0}
150
+ {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.08777090907096863, "epoch": 0.906043308870164, "percentage": 83.33, "elapsed_time": "2:53:17", "remaining_time": "0:34:39", "throughput": "0.00", "total_tokens": 0}