lemonhat/Llama-3.2-3B-Instruct-t1_25k_v4_tag5

t1_25k_v4_tag5

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the t1_25k_v4_tag5 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3343

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: 5e-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 8
• total_eval_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.3365	0.1447	100	0.4070
0.3231	0.2894	200	0.3755
0.3272	0.4342	300	0.3558
0.2767	0.5789	400	0.3474
0.3235	0.7236	500	0.3418
0.3842	0.8683	600	0.3348

Framework versions

• Transformers 4.46.1
• Pytorch 2.6.0+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3