Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ShenaoZ
/
0.01_ablation_3iters_bs256_nodpo_iter_1
like
0
Text Generation
Transformers
Safetensors
updated
original
mistral
alignment-handbook
Generated from Trainer
trl
dpo
conversational
text-generation-inference
License:
mit
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
78b33ad
0.01_ablation_3iters_bs256_nodpo_iter_1
/
train_results.json
ShenaoZ
Model save
6c9d6b3
verified
over 1 year ago
raw
Copy download link
history
blame
Safe
195 Bytes
{
"epoch"
:
0.99
,
"train_loss"
:
0.5758069738557067
,
"train_runtime"
:
4666.8235
,
"train_samples"
:
20378
,
"train_samples_per_second"
:
4.367
,
"train_steps_per_second"
:
0.017
}