metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
model-index:
- name: jq_emo_gpt
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.941
jq_emo_gpt
This model is a fine-tuned version of distilgpt2 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.3379
- Accuracy: 0.941
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 16000
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.7328 | 1.0 | 16000 | 0.6227 | 0.899 |
0.3989 | 2.0 | 32000 | 0.4351 | 0.927 |
0.2888 | 3.0 | 48000 | 0.3162 | 0.9385 |
0.2325 | 4.0 | 64000 | 0.2936 | 0.9445 |
0.2774 | 5.0 | 80000 | 0.2903 | 0.94 |
0.1423 | 6.0 | 96000 | 0.3410 | 0.9405 |
0.1681 | 7.0 | 112000 | 0.3259 | 0.9385 |
0.1743 | 8.0 | 128000 | 0.3225 | 0.9415 |
0.1011 | 9.0 | 144000 | 0.3356 | 0.942 |
0.1138 | 10.0 | 160000 | 0.3379 | 0.941 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3