Mathildeholst/Good-generator

1---2library_name: transformers3license: apache-2.04base_model: HuggingFaceTB/SmolLM2-135M5tags:6- generated_from_trainer7model-index:8- name: Good-generator9  results: []10---11 12<!-- This model card has been generated automatically according to the information the Trainer had access to. You13should probably proofread and complete it, then remove this comment. -->14 15# Good-generator16 17This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M) on an unknown dataset.18It achieves the following results on the evaluation set:19- Loss: 2.426720 21## Model description22 23More information needed24 25## Intended uses & limitations26 27More information needed28 29## Training and evaluation data30 31More information needed32 33## Training procedure34 35### Training hyperparameters36 37The following hyperparameters were used during training:38- learning_rate: 0.000339- train_batch_size: 840- eval_batch_size: 841- seed: 4242- gradient_accumulation_steps: 1643- total_train_batch_size: 12844- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments45- lr_scheduler_type: cosine46- lr_scheduler_warmup_ratio: 0.1247- num_epochs: 148 49### Training results50 51| Training Loss | Epoch  | Step | Validation Loss |52|:-------------:|:------:|:----:|:---------------:|53| 3.3182        | 0.1067 | 25   | 2.9325          |54| 2.7389        | 0.2133 | 50   | 2.7289          |55| 2.6049        | 0.32   | 75   | 2.6352          |56| 2.4956        | 0.4267 | 100  | 2.5653          |57| 2.4569        | 0.5333 | 125  | 2.5161          |58| 2.4627        | 0.64   | 150  | 2.4759          |59| 2.3903        | 0.7467 | 175  | 2.4464          |60| 2.3572        | 0.8533 | 200  | 2.4319          |61| 2.3607        | 0.96   | 225  | 2.4267          |62 63 64### Framework versions65 66- Transformers 4.57.167- Pytorch 2.8.0+cu12668- Datasets 4.0.069- Tokenizers 0.22.170