TuringGame/Llama-3.2-1B-Instruct-classifier

1---2library_name: transformers3license: llama3.24base_model: meta-llama/Llama-3.2-1B-Instruct5tags:6- generated_from_trainer7metrics:8- accuracy9- f110model-index:11- name: Llama-3.2-1B-Instruct-classifier12  results: []13---14 15<!-- This model card has been generated automatically according to the information the Trainer had access to. You16should probably proofread and complete it, then remove this comment. -->17 18# Llama-3.2-1B-Instruct-classifier19 20This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on an unknown dataset.21It achieves the following results on the evaluation set:22- Loss: 0.216023- Accuracy: 0.930824- F1: 0.862125 26## Model description27 28More information needed29 30## Intended uses & limitations31 32More information needed33 34## Training and evaluation data35 36More information needed37 38## Training procedure39 40### Training hyperparameters41 42The following hyperparameters were used during training:43- learning_rate: 2e-0544- train_batch_size: 3245- eval_batch_size: 3246- seed: 4247- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments48- lr_scheduler_type: linear49- num_epochs: 250 51### Training results52 53| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |54|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|55| No log        | 0      | 0    | 1.0194          | 0.4524   | 0.3310 |56| No log        | 0.2020 | 79   | 0.3185          | 0.8804   | 0.7508 |57| No log        | 0.4041 | 158  | 0.2728          | 0.8948   | 0.7989 |58| No log        | 0.6061 | 237  | 0.2436          | 0.9006   | 0.8110 |59| No log        | 0.8082 | 316  | 0.2251          | 0.8963   | 0.7895 |60| No log        | 1.0102 | 395  | 0.2713          | 0.8905   | 0.81   |61| No log        | 1.2123 | 474  | 0.3203          | 0.9020   | 0.8162 |62| 0.3016        | 1.4143 | 553  | 0.2289          | 0.9164   | 0.8324 |63| 0.3016        | 1.6164 | 632  | 0.2306          | 0.9280   | 0.8641 |64| 0.3016        | 1.8184 | 711  | 0.2160          | 0.9308   | 0.8621 |65 66 67### Framework versions68 69- Transformers 4.53.370- Pytorch 2.6.0+cu12471- Datasets 4.0.072- Tokenizers 0.21.273