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
3f369fe
·
verified ·
1 Parent(s): 45d0b76

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 sha256:607b07a7a5dbee4002f453eb4b2786c26f0a3417a28ae62925c6ae7851adc1b0
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de479425ba6fa800a974d4edb9ef5e6c7d087b6bf9a24112f87301ac900545ef
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -82,3 +82,9 @@
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}
 
 
 
 
 
 
 
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}
85
+ {"current_steps": 710, "total_steps": 1500, "loss": 1.7604, "accuracy": 0.9125000238418579, "learning_rate": 2.70919460833079e-06, "epoch": 0.5146325994382531, "percentage": 47.33, "elapsed_time": "1:38:10", "remaining_time": "1:49:14", "throughput": "0.00", "total_tokens": 0}
86
+ {"current_steps": 720, "total_steps": 1500, "loss": 1.2509, "accuracy": 0.9750000238418579, "learning_rate": 2.6569762988232838e-06, "epoch": 0.5218809459092144, "percentage": 48.0, "elapsed_time": "1:39:29", "remaining_time": "1:47:47", "throughput": "0.00", "total_tokens": 0}
87
+ {"current_steps": 730, "total_steps": 1500, "loss": 1.2837, "accuracy": 0.925000011920929, "learning_rate": 2.604689134322999e-06, "epoch": 0.5291292923801758, "percentage": 48.67, "elapsed_time": "1:40:45", "remaining_time": "1:46:16", "throughput": "0.00", "total_tokens": 0}
88
+ {"current_steps": 740, "total_steps": 1500, "loss": 1.2981, "accuracy": 0.9624999761581421, "learning_rate": 2.5523560497083927e-06, "epoch": 0.5363776388511371, "percentage": 49.33, "elapsed_time": "1:41:59", "remaining_time": "1:44:44", "throughput": "0.00", "total_tokens": 0}
89
+ {"current_steps": 750, "total_steps": 1500, "loss": 1.1198, "accuracy": 0.9750000238418579, "learning_rate": 2.5e-06, "epoch": 0.5436259853220984, "percentage": 50.0, "elapsed_time": "1:43:18", "remaining_time": "1:43:18", "throughput": "0.00", "total_tokens": 0}
90
+ {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.15141016244888306, "epoch": 0.5436259853220984, "percentage": 50.0, "elapsed_time": "1:43:48", "remaining_time": "1:43:48", "throughput": "0.00", "total_tokens": 0}