metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: GPT2_five_function_within_boundary_53
results: []
GPT2_five_function_within_boundary_53
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.6819
- Accuracy: 0.3937
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 |
|---|---|---|---|---|
| 4.8403 | 1.0 | 6408 | 4.6563 | 0.3079 |
| 4.2687 | 2.0 | 12816 | 4.1422 | 0.3458 |
| 4.016 | 3.0 | 19224 | 3.9519 | 0.3632 |
| 3.8939 | 4.0 | 25632 | 3.8525 | 0.3735 |
| 3.8002 | 5.0 | 32040 | 3.7941 | 0.3787 |
| 3.7294 | 6.0 | 38448 | 3.7532 | 0.3843 |
| 3.6702 | 7.0 | 44856 | 3.7277 | 0.3876 |
| 3.6188 | 8.0 | 51264 | 3.7051 | 0.3901 |
| 3.5761 | 9.0 | 57672 | 3.6879 | 0.3927 |
| 3.5318 | 10.0 | 64080 | 3.6819 | 0.3937 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.11.0+cu126
- Datasets 4.1.1
- Tokenizers 0.13.3