rationale_model_e3_save5000_f3

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

• Loss: 1.9449

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.7548	0.1907	1000	1.9449
1.3912	0.3814	2000	2.0170
0.9994	0.5721	3000	2.1840
0.6462	0.7628	4000	2.3842
0.3791	0.9535	5000	2.7062
0.2017	1.1442	6000	2.9006
0.1723	1.3349	7000	3.0643
0.1449	1.5256	8000	3.2089
0.1292	1.7162	9000	3.3468
0.1177	1.9069	10000	3.4686
0.0996	2.0976	11000	3.5735
0.0966	2.2883	12000	3.6707
0.0913	2.4790	13000	3.7954
0.0916	2.6697	14000	3.9067
0.0859	2.8604	15000	3.9867

Framework versions

• Transformers 4.45.0
• Pytorch 2.3.0
• Datasets 2.14.4
• Tokenizers 0.20.3