Hugging Face's logo

IeBoytsov
/
ox-llms-sula-10-profiles-sft

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
alignment-handbook
trl
sft
conversational
text-generation-inference
4-bit precision
bitsandbytes
Model card Files
xet
 Community
IeBoytsov commited on
Commit
9d0c442
·
verified ·
1 Parent(s): e0c8127

Model save

Browse files
Files changed (3) hide show
  1. all_results.json +12 -0
  2. train_results.json +12 -0
  3. trainer_state.json +0 -0
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "entropy": 0.1506435771783193,
3
+ "epoch": 1.0,
4
+ "mean_token_accuracy": 0.9381802678108215,
5
+ "num_tokens": 24937449.0,
6
+ "total_flos": 1.3805074115628892e+18,
7
+ "train_loss": 0.1824477752374585,
8
+ "train_runtime": 6615.9277,
9
+ "train_samples": 35223,
10
+ "train_samples_per_second": 5.324,
11
+ "train_steps_per_second": 0.333
12
+ }
train_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "entropy": 0.1506435771783193,
3
+ "epoch": 1.0,
4
+ "mean_token_accuracy": 0.9381802678108215,
5
+ "num_tokens": 24937449.0,
6
+ "total_flos": 1.3805074115628892e+18,
7
+ "train_loss": 0.1824477752374585,
8
+ "train_runtime": 6615.9277,
9
+ "train_samples": 35223,
10
+ "train_samples_per_second": 5.324,
11
+ "train_steps_per_second": 0.333
12
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff