RKessler/BLESSRelationTrain-2

1---2license: mit3base_model: roberta-base4tags:5- generated_from_trainer6metrics:7- accuracy8model-index:9- name: BLESSRelationTrain-210  results: []11---12 13<!-- This model card has been generated automatically according to the information the Trainer had access to. You14should probably proofread and complete it, then remove this comment. -->15 16# BLESSRelationTrain-217 18This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.19It achieves the following results on the evaluation set:20- Loss: 0.628021- Accuracy: 0.847322 23## Model description24 25More information needed26 27## Intended uses & limitations28 29More information needed30 31## Training and evaluation data32 33More information needed34 35## Training procedure36 37### Training hyperparameters38 39The following hyperparameters were used during training:40- learning_rate: 5e-0541- train_batch_size: 842- eval_batch_size: 843- seed: 4244- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0845- lr_scheduler_type: linear46- num_epochs: 847 48### Training results49 50| Training Loss | Epoch | Step | Validation Loss | Accuracy |51|:-------------:|:-----:|:----:|:---------------:|:--------:|52| No log        | 0.8   | 100  | 0.6965          | 0.5      |53| No log        | 1.6   | 200  | 0.6828          | 0.5868   |54| No log        | 2.4   | 300  | 0.7161          | 0.5      |55| No log        | 3.2   | 400  | 0.6493          | 0.6377   |56| 0.6926        | 4.0   | 500  | 0.6856          | 0.5269   |57| 0.6926        | 4.8   | 600  | 0.6096          | 0.7784   |58| 0.6926        | 5.6   | 700  | 0.6265          | 0.8204   |59| 0.6926        | 6.4   | 800  | 0.8188          | 0.8054   |60| 0.6926        | 7.2   | 900  | 0.5995          | 0.8503   |61| 0.3811        | 8.0   | 1000 | 0.6280          | 0.8473   |62 63 64### Framework versions65 66- Transformers 4.34.067- Pytorch 2.1.0+cu12168- Datasets 2.14.569- Tokenizers 0.14.170