kanishka_-_smolm-autoreg-bpe-seed_28-4bits – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
kanishka_-_smolm-autoreg-bpe-seed_28-4bits

like

0

text-generation

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

smolm-autoreg-bpe-seed_28 - bnb 4bits

Original model description:

tags:

generated_from_trainer metrics:
accuracy model-index:
name: smolm-autoreg-bpe-seed_28 results: []

smolm-autoreg-bpe-seed_28

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.4754
Accuracy: 0.4991

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: 0.003
train_batch_size: 16
eval_batch_size: 128
seed: 28
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 24000
num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.0383	1.0	2928	3.0183	0.4371
2.7202	2.0	5856	2.7841	0.4601
2.5954	3.0	8784	2.7013	0.4689
2.5123	4.0	11712	2.6403	0.4755
2.4613	5.0	14640	2.6047	0.4802
2.4261	6.0	17568	2.5919	0.4824
2.3906	7.0	20496	2.5666	0.4850
2.3601	8.0	23424	2.5550	0.4861
2.2843	9.0	26352	2.5031	0.4940
2.1392	10.0	29280	2.4754	0.4991

Framework versions

Transformers 4.38.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1