RoBERTa-GPT2_EmpAI_FineTuned
This model is a fine-tuned version of LuangMV97/RoBERTa-GPT2_EmpAI on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3986
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6834 | 1.0 | 3867 | 0.7001 |
| 0.4857 | 2.0 | 7734 | 0.5345 |
| 0.3553 | 3.0 | 11601 | 0.4425 |
| 0.2913 | 4.0 | 15468 | 0.4050 |
| 0.278 | 5.0 | 19335 | 0.3986 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 103
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for LuangMV97/RoBERTa-GPT2_EmpAI_FineTuned
Base model
LuangMV97/RoBERTa-GPT2_EmpAI