Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
yyx123
/
Yi-6B-zhihu7
like
0
PEFT
Safetensors
zhihu
llama
alignment-handbook
Generated from Trainer
trl
sft
4-bit precision
bitsandbytes
License:
other
Model card
Files
Files and versions
Community
Train
Use this model
11aae5b
Yi-6B-zhihu7
/
eval_results.json
yyx123
Model save
11aae5b
verified
7 months ago
raw
Copy download link
history
blame
Safe
188 Bytes
{
"epoch"
:
20.0
,
"eval_loss"
:
2.5970427989959717
,
"eval_runtime"
:
173.4328
,
"eval_samples"
:
2561
,
"eval_samples_per_second"
:
4.417
,
"eval_steps_per_second"
:
1.107
}