mistral-0.5B-base

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

• Loss: 3.8893

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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: 100
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
5.9695	0.3989	74	6.0154
5.0148	0.7978	148	5.1781
4.459	1.1941	222	4.7603
4.0585	1.5930	296	4.4421
3.8404	1.9919	370	4.2375
3.1164	2.3881	444	4.0944
2.4948	2.7871	518	3.9528
1.6126	3.1833	592	3.9094
1.5873	3.5822	666	3.8964
1.4401	3.9811	740	3.8893

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0