llama-fin

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2086

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: 0.0003
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• 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
• lr_scheduler_warmup_steps: 1000
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
3.0634	0.1593	5000	1.6380
1.5345	0.3185	10000	1.4842
1.4255	0.4778	15000	1.4151
1.3929	0.6370	20000	1.3720
1.3462	0.7963	25000	1.3367
1.3094	0.9555	30000	1.3087
1.2835	1.1148	35000	1.2838
1.2534	1.2740	40000	1.2605
1.2303	1.4333	45000	1.2407
1.2187	1.5926	50000	1.2244
1.2001	1.7518	55000	1.2133
1.1937	1.9111	60000	1.2086

Framework versions

• Transformers 4.51.3
• Pytorch 2.1.0+cu118
• Datasets 3.5.0
• Tokenizers 0.21.1