frett/distilroberta-base_task2-2_macrof1

1---2license: apache-2.03base_model: distilroberta-base4tags:5- generated_from_trainer6model-index:7- name: distilroberta-base_task2-2_macrof18  results: []9---10 11<!-- This model card has been generated automatically according to the information the Trainer had access to. You12should probably proofread and complete it, then remove this comment. -->13 14# distilroberta-base_task2-2_macrof115 16This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset.17It achieves the following results on the evaluation set:18- Loss: 0.620319- Macro F1: 0.309020 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: 1e-0639- train_batch_size: 1040- eval_batch_size: 841- seed: 4242- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0843- lr_scheduler_type: linear44- lr_scheduler_warmup_steps: 50045- num_epochs: 1046 47### Training results48 49| Training Loss | Epoch | Step | Validation Loss | Macro F1 |50|:-------------:|:-----:|:----:|:---------------:|:--------:|51| 0.6541        | 1.0   | 553  | 0.6474          | 0.2768   |52| 0.7044        | 2.0   | 1106 | 0.6376          | 0.2768   |53| 0.6615        | 3.0   | 1659 | 0.6390          | 0.2768   |54| 0.6289        | 4.0   | 2212 | 0.6355          | 0.2768   |55| 0.5047        | 5.0   | 2765 | 0.6372          | 0.2841   |56| 0.5894        | 6.0   | 3318 | 0.6296          | 0.2983   |57| 0.5401        | 7.0   | 3871 | 0.6203          | 0.3090   |58| 0.7215        | 8.0   | 4424 | 0.6263          | 0.3080   |59| 0.6368        | 9.0   | 4977 | 0.6370          | 0.3033   |60| 0.4872        | 10.0  | 5530 | 0.6349          | 0.3024   |61 62 63### Framework versions64 65- Transformers 4.41.166- Pytorch 2.3.0+cu12167- Datasets 2.19.168- Tokenizers 0.19.169