tinyllama-lora-squad_4_3e-05_2_lora4_qk

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0071

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: 3e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• 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: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.6845	0.1998	495	0.0120
0.0106	0.3995	990	0.0097
0.0091	0.5993	1485	0.0088
0.0084	0.7990	1980	0.0080
0.0074	0.9988	2475	0.0077
0.0067	1.1985	2970	0.0076
0.0065	1.3983	3465	0.0073
0.0064	1.5981	3960	0.0072
0.0067	1.7978	4455	0.0071
0.0065	1.9976	4950	0.0071

Framework versions

• PEFT 0.16.0
• Transformers 4.53.2
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.2