Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
ondevicellm
/
tinyllama_mole_sft_router05_lr1e-4_ep3
like
0
Text Generation
Transformers
TensorBoard
Safetensors
HuggingFaceH4/ultrachat_200k
mixtralmole
alignment-handbook
trl
sft
Generated from Trainer
conversational
custom_code
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
e3c4c99
tinyllama_mole_sft_router05_lr1e-4_ep3
/
eval_results.json
hushell
Model save
b2f9a13
verified
7 months ago
raw
Copy download link
history
blame
No virus
187 Bytes
{
"epoch"
:
3.0
,
"eval_loss"
:
2.10353946685791
,
"eval_runtime"
:
435.0953
,
"eval_samples"
:
23110
,
"eval_samples_per_second"
:
37.155
,
"eval_steps_per_second"
:
1.163
}