Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO-2
/
phi-2-irepo-chatml-v16-i1
like
0
Follow
DUAL-GPO-2
2
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
8fb66c8
phi-2-irepo-chatml-v16-i1
/
all_results.json
lole25
Model save
b6f6aaa
verified
6 months ago
raw
Copy download link
history
blame
Safe
195 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.19580436278230104
,
"train_runtime"
:
2618.6186
,
"train_samples"
:
10000
,
"train_samples_per_second"
:
3.819
,
"train_steps_per_second"
:
0.119
}