Gemma2b-Sentiment-12k-20240322 – AI Model by sahil-theloops | AlphaNeural AI

You can deploy this model and start earning money today!

sahil-theloops/
Gemma2b-Sentiment-12k-20240322

like

0

generated_from_trainer

google/gemma-2b-it

Views

No views yet

logs

This model is a fine-tuned version of google/gemma-2b-it on the generator dataset. It achieves the following results on the evaluation set:

Loss: 0.6382

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: 0.0002
train_batch_size: 1
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.7393	0.45	112	0.6998
0.6937	0.9	224	0.6506
0.6017	1.35	336	0.6331
0.6384	1.8	448	0.6193
0.5111	2.25	560	0.6176
0.523	2.7	672	0.6123
0.4642	3.15	784	0.6265
0.4888	3.6	896	0.6219
0.4547	4.05	1008	0.6330
0.4343	4.5	1120	0.6379
0.4664	4.96	1232	0.6382

Framework versions

PEFT 0.10.1.dev0
Transformers 4.38.2
Pytorch 2.1.2+cu121
Datasets 2.18.0
Tokenizers 0.15.2