llama2-violencia_genero – AI Model by MelisaO | AlphaNeural AI

You can deploy this model and start earning money today!

MelisaO/
llama2-violencia_genero

like

0

generated_from_trainer

meta-llama/Llama-2-7b-chat-hf

Views

No views yet

llama2-violencia_genero

This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 11.5478

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: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	3	12.5506
No log	2.0	6	12.5186
No log	3.0	9	12.3555
14.4441	4.0	12	12.1632
14.4441	5.0	15	12.0007
14.4441	6.0	18	11.7902
13.8938	7.0	21	11.6535
13.8938	8.0	24	11.5517
13.8938	9.0	27	11.5325
13.5263	10.0	30	11.5478

Framework versions

PEFT 0.14.0
Transformers 4.49.0
Pytorch 2.6.0+cu118
Datasets 3.3.2
Tokenizers 0.21.0