stojchet_-_jnkto3-jsft8-8bits – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
stojchet_-_jnkto3-jsft8-8bits

like

0

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

jnkto3-jsft8 - bnb 8bits

Model creator: https://huggingface.co/stojchet/
Original model: https://huggingface.co/stojchet/jnkto3-jsft8/

Original model description:

license: other base_model: stojchet/jnkto3 tags:

trl
sft
generated_from_trainer datasets:
generator model-index:
name: jnkto3-jsft8 results: []

Visualize in Weights & Biases

jnkto3-jsft8

This model is a fine-tuned version of stojchet/jnkto3 on the generator dataset. It achieves the following results on the evaluation set:

Loss: 1.1923

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 200
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.0714	2.56	100	1.1923

Framework versions

Transformers 4.43.0.dev0
Pytorch 2.2.2+cu121
Datasets 2.19.2
Tokenizers 0.19.1