Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
YYYYYYibo
/
zephyr-7b-lora-64-no-quant-2k
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
c4a0a32
zephyr-7b-lora-64-no-quant-2k
/
all_results.json
YYYYYYibo
Model save
c4a0a32
verified
7 months ago
raw
Copy download link
history
blame
Safe
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.6621483755417359
,
"train_runtime"
:
6542.6499
,
"train_samples"
:
20000
,
"train_samples_per_second"
:
3.057
,
"train_steps_per_second"
:
0.012
}