LLama3-finetuning – AI Model by msab97 | AlphaNeural AI

You can deploy this model and start earning money today!

msab97/
LLama3-finetuning

like

0

generated_from_trainer

meta-llama/Llama-3.2-1B

Views

No views yet

LLama3-finetuning

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3923
Accuracy: 0.8414
F1 Macro: 0.8365

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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro
1.8719	1.0	454	0.8635	0.6562	0.6261
0.9455	2.0	908	0.4734	0.8168	0.8068
0.7437	3.0	1362	0.4071	0.8366	0.8305
0.7825	4.0	1816	0.3959	0.8433	0.8391
0.6047	5.0	2270	0.3910	0.8400	0.8341

Framework versions

PEFT 0.14.0
Transformers 4.47.1
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0