PracticalWork/Falcon3-1B-Instruct-tuned

1---2library_name: peft3license: other4base_model: tiiuae/Falcon3-1B-Instruct5tags:6- base_model:adapter:tiiuae/Falcon3-1B-Instruct7- transformers8pipeline_tag: text-generation9model-index:10- name: Falcon3-1B-Instruct-tuned11  results: []12---13 14<!-- This model card has been generated automatically according to the information the Trainer had access to. You15should probably proofread and complete it, then remove this comment. -->16 17# Falcon3-1B-Instruct-tuned18 19This model is a fine-tuned version of [tiiuae/Falcon3-1B-Instruct](https://huggingface.co/tiiuae/Falcon3-1B-Instruct) on an unknown dataset.20It achieves the following results on the evaluation set:21- Loss: 1.722822- Perplexity: 5.600123 24## Training procedure25 26### Training hyperparameters27 28The following hyperparameters were used during training:29- learning_rate: 0.00330- train_batch_size: 1231- eval_batch_size: 1232- seed: 4233- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments34- lr_scheduler_type: linear35- num_epochs: 336 37### Training results38 39| Training Loss | Epoch  | Step | Validation Loss | Perplexity |40|:-------------:|:------:|:----:|:---------------:|:----------:|41| No log        | 0      | 0    | 3.5178          | 33.7116    |42| No log        | 0.6011 | 333  | 1.8889          | 6.6122     |43| 1.9189        | 1.2022 | 666  | 1.8092          | 6.1057     |44| 1.9189        | 1.8032 | 999  | 1.7672          | 5.8541     |45| 1.7617        | 2.4043 | 1332 | 1.7440          | 5.7203     |46| 1.7617        | 3      | 1664 | 1.7228          | 5.6001     |47 48 49### Framework versions50 51- PEFT 0.16.052- Transformers 4.54.153- Pytorch 2.7.1+cu12854- Datasets 4.0.055- Tokenizers 0.21.4