Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
fay-ong
/
llama-3-8b-finetuned
like
1
PEFT
TensorBoard
Safetensors
llama
llama-factory
lora
unsloth
Generated from Trainer
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
8ea8288
llama-3-8b-finetuned
/
all_results.json
fay-ong
End of training
8ea8288
verified
5 months ago
raw
Copy download link
history
blame
Safe
209 Bytes
{
"epoch"
:
2.0
,
"total_flos"
:
1.4149166716420096e+16
,
"train_loss"
:
0.18670074969530107
,
"train_runtime"
:
1345.2529
,
"train_samples_per_second"
:
0.743
,
"train_steps_per_second"
:
0.186
}