Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
YYYYYYibo
/
zephyr-7b-lora-64-no-quant-6k
like
0
PEFT
TensorBoard
Safetensors
updated
original
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
a4272c2
zephyr-7b-lora-64-no-quant-6k
/
train_results.json
YYYYYYibo
Model save
b9ebb3a
verified
7 months ago
raw
Copy download link
history
blame
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.6080600586758942
,
"train_runtime"
:
20828.337
,
"train_samples"
:
61135
,
"train_samples_per_second"
:
2.935
,
"train_steps_per_second"
:
0.011
}