Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
ShenaoZ
/
0.01_withdpo_4iters_bs256_5102lr_misit_iter_1
like
0
Text Generation
Transformers
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
d8311bc
0.01_withdpo_4iters_bs256_5102lr_misit_iter_1
/
all_results.json
ShenaoZ
Model save
3b9105d
verified
9 months ago
raw
Copy download link
history
blame
194 Bytes
{
"epoch"
:
0.99
,
"train_loss"
:
0.5465719497809975
,
"train_runtime"
:
1938.7154
,
"train_samples"
:
15283
,
"train_samples_per_second"
:
7.883
,
"train_steps_per_second"
:
0.03
}