tinyllama-lora-squad_4_5e-04_3_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: 0.0059

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: 0.0005
• 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: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.7668	0.2998	743	0.0067
0.006	0.5997	1486	0.0063
0.0059	0.8995	2229	0.0057
0.0043	1.1994	2972	0.0059
0.0038	1.4992	3715	0.0056
0.0039	1.7990	4458	0.0054
0.0031	2.0989	5201	0.0058
0.002	2.3987	5944	0.0061
0.0018	2.6985	6687	0.0061
0.0019	2.9984	7430	0.0059

Framework versions

• PEFT 0.14.0
• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1