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
c28c0f8
·
verified ·
1 Parent(s): 5698286

Training in progress, step 700

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:f68ce168241fb3faec874c5a2443c093347e6963fa70c07806dbd311ababcfc9
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:607b07a7a5dbee4002f453eb4b2786c26f0a3417a28ae62925c6ae7851adc1b0
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -76,3 +76,9 @@
76
  {"current_steps": 640, "total_steps": 1500, "loss": 1.7631, "accuracy": 0.9750000238418579, "learning_rate": 3.0708771752766397e-06, "epoch": 0.46389417414152395, "percentage": 42.67, "elapsed_time": "1:28:06", "remaining_time": "1:58:24", "throughput": "0.00", "total_tokens": 0}
77
  {"current_steps": 650, "total_steps": 1500, "loss": 1.5531, "accuracy": 0.987500011920929, "learning_rate": 3.019779227044398e-06, "epoch": 0.4711425206124853, "percentage": 43.33, "elapsed_time": "1:29:22", "remaining_time": "1:56:51", "throughput": "0.00", "total_tokens": 0}
78
  {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.21141496300697327, "epoch": 0.4711425206124853, "percentage": 43.33, "elapsed_time": "1:29:52", "remaining_time": "1:57:31", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
76
  {"current_steps": 640, "total_steps": 1500, "loss": 1.7631, "accuracy": 0.9750000238418579, "learning_rate": 3.0708771752766397e-06, "epoch": 0.46389417414152395, "percentage": 42.67, "elapsed_time": "1:28:06", "remaining_time": "1:58:24", "throughput": "0.00", "total_tokens": 0}
77
  {"current_steps": 650, "total_steps": 1500, "loss": 1.5531, "accuracy": 0.987500011920929, "learning_rate": 3.019779227044398e-06, "epoch": 0.4711425206124853, "percentage": 43.33, "elapsed_time": "1:29:22", "remaining_time": "1:56:51", "throughput": "0.00", "total_tokens": 0}
78
  {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.21141496300697327, "epoch": 0.4711425206124853, "percentage": 43.33, "elapsed_time": "1:29:52", "remaining_time": "1:57:31", "throughput": "0.00", "total_tokens": 0}
79
+ {"current_steps": 660, "total_steps": 1500, "loss": 1.3669, "accuracy": 0.987500011920929, "learning_rate": 2.9684532864643123e-06, "epoch": 0.4783908670834466, "percentage": 44.0, "elapsed_time": "1:31:18", "remaining_time": "1:56:12", "throughput": "0.00", "total_tokens": 0}
80
+ {"current_steps": 670, "total_steps": 1500, "loss": 1.8781, "accuracy": 0.9624999761581421, "learning_rate": 2.9169218667902562e-06, "epoch": 0.4856392135544079, "percentage": 44.67, "elapsed_time": "1:32:32", "remaining_time": "1:54:39", "throughput": "0.00", "total_tokens": 0}
81
+ {"current_steps": 680, "total_steps": 1500, "loss": 1.2831, "accuracy": 0.949999988079071, "learning_rate": 2.8652075714060296e-06, "epoch": 0.4928875600253692, "percentage": 45.33, "elapsed_time": "1:33:46", "remaining_time": "1:53:05", "throughput": "0.00", "total_tokens": 0}
82
+ {"current_steps": 690, "total_steps": 1500, "loss": 1.0306, "accuracy": 0.9750000238418579, "learning_rate": 2.813333083910761e-06, "epoch": 0.5001359064963306, "percentage": 46.0, "elapsed_time": "1:35:02", "remaining_time": "1:51:34", "throughput": "0.00", "total_tokens": 0}
83
+ {"current_steps": 700, "total_steps": 1500, "loss": 1.1941, "accuracy": 0.987500011920929, "learning_rate": 2.761321158169134e-06, "epoch": 0.5073842529672918, "percentage": 46.67, "elapsed_time": "1:36:13", "remaining_time": "1:49:58", "throughput": "0.00", "total_tokens": 0}
84
+ {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.1846819519996643, "epoch": 0.5073842529672918, "percentage": 46.67, "elapsed_time": "1:36:44", "remaining_time": "1:50:33", "throughput": "0.00", "total_tokens": 0}