metadata
license: mit
base_model: varun-v-rao/roberta-base-fp-sick
tags:
- generated_from_trainer
datasets:
- snli
metrics:
- accuracy
model-index:
- name: roberta-base-fp-sick-lora-snli-model1
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: snli
type: snli
metrics:
- name: Accuracy
type: accuracy
value: 0.8710627921154237
roberta-base-fp-sick-lora-snli-model1
This model is a fine-tuned version of varun-v-rao/roberta-base-fp-sick on the snli dataset. It achieves the following results on the evaluation set:
- Loss: 0.3422
- Accuracy: 0.8711
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 256
- eval_batch_size: 128
- seed: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4756 | 1.0 | 2146 | 0.3687 | 0.8599 |
| 0.4455 | 2.0 | 4292 | 0.3476 | 0.8686 |
| 0.4313 | 3.0 | 6438 | 0.3422 | 0.8711 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0