|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: out_3 |
|
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. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
# out_3 |
|
|
|
This model was trained from scratch on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6039 |
|
|
|
## 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: 5e-06 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- total_eval_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 150 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.9036 | 0.0 | 1 | 0.8492 | |
|
| 0.6255 | 0.07 | 79 | 0.6767 | |
|
| 0.6044 | 0.13 | 158 | 0.6644 | |
|
| 0.671 | 0.2 | 237 | 0.6563 | |
|
| 0.6385 | 0.27 | 316 | 0.6504 | |
|
| 0.6546 | 0.33 | 395 | 0.6428 | |
|
| 0.6005 | 0.4 | 474 | 0.6368 | |
|
| 0.5888 | 0.47 | 553 | 0.6311 | |
|
| 0.6194 | 0.53 | 632 | 0.6251 | |
|
| 0.6163 | 0.6 | 711 | 0.6197 | |
|
| 0.5947 | 0.67 | 790 | 0.6152 | |
|
| 0.6138 | 0.73 | 869 | 0.6102 | |
|
| 0.6154 | 0.8 | 948 | 0.6071 | |
|
| 0.6333 | 0.87 | 1027 | 0.6051 | |
|
| 0.6063 | 0.93 | 1106 | 0.6041 | |
|
| 0.5804 | 1.0 | 1185 | 0.6039 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
