|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: GPT2_five_function_53 |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# GPT2_five_function_53 |
|
|
|
|
|
This model was trained from scratch on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.6064 |
|
|
- Accuracy: 0.4052 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 128 |
|
|
- eval_batch_size: 128 |
|
|
- seed: 53 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 10000 |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
|
| 4.7541 | 1.0 | 6408 | 4.5598 | 0.3268 | |
|
|
| 4.1833 | 2.0 | 12816 | 4.0602 | 0.3599 | |
|
|
| 3.9344 | 3.0 | 19224 | 3.8742 | 0.3767 | |
|
|
| 3.8132 | 4.0 | 25632 | 3.7790 | 0.3858 | |
|
|
| 3.7206 | 5.0 | 32040 | 3.7182 | 0.3915 | |
|
|
| 3.6507 | 6.0 | 38448 | 3.6788 | 0.3954 | |
|
|
| 3.5926 | 7.0 | 44856 | 3.6508 | 0.3991 | |
|
|
| 3.5419 | 8.0 | 51264 | 3.6279 | 0.4019 | |
|
|
| 3.499 | 9.0 | 57672 | 3.6127 | 0.4039 | |
|
|
| 3.4548 | 10.0 | 64080 | 3.6064 | 0.4052 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.30.2 |
|
|
- Pytorch 2.9.1+cu128 |
|
|
- Datasets 4.1.1 |
|
|
- Tokenizers 0.13.3 |
|
|
|
