llama-nli-fr

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1193

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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_ratio: 0.03
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.0868	0.3192	100	1.1299
1.0057	0.6385	200	1.1173
1.0172	0.9577	300	1.1193

Framework versions

• PEFT 0.16.0
• Transformers 4.53.3
• Pytorch 2.6.0+cu124
• Datasets 4.4.1
• Tokenizers 0.21.2