metadata
license: apache-2.0
base_model: allenai/longformer-base-4096
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
model-index:
- name: my_awesome_model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: test
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.95528
my_awesome_model
This model is a fine-tuned version of allenai/longformer-base-4096 on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.2141
- Accuracy: 0.9553
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3358 | 0.32 | 1000 | 0.2286 | 0.9349 |
| 0.2658 | 0.64 | 2000 | 0.2036 | 0.9447 |
| 0.2392 | 0.96 | 3000 | 0.2294 | 0.9504 |
| 0.1648 | 1.28 | 4000 | 0.2288 | 0.9518 |
| 0.1477 | 1.6 | 5000 | 0.2190 | 0.9532 |
| 0.1404 | 1.92 | 6000 | 0.2141 | 0.9553 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1