Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
HuggingFaceH4
/
zephyr-7b-gemma-v0.1
like
121
Follow
Hugging Face H4
673
Text Generation
Transformers
TensorBoard
Safetensors
argilla/dpo-mix-7k
gemma
alignment-handbook
trl
dpo
Generated from Trainer
conversational
Eval Results
text-generation-inference
Inference Endpoints
arxiv:
2310.16944
License:
gemma-terms-of-use
Model card
Files
Files and versions
Metrics
Training metrics
Community
11
Train
Deploy
Use this model
87a8563
zephyr-7b-gemma-v0.1
/
all_results.json
lewtun
HF staff
Model save
87a8563
verified
9 months ago
raw
Copy download link
history
blame
Safe
196 Bytes
{
"epoch"
:
1.97
,
"train_loss"
:
0.38887147261546207
,
"train_runtime"
:
1183.8142
,
"train_samples"
:
6750
,
"train_samples_per_second"
:
11.404
,
"train_steps_per_second"
:
0.088
}