78 lines
2.2 KiB
Markdown
78 lines
2.2 KiB
Markdown
---
|
|
library_name: transformers
|
|
tags:
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: Aris-293M
|
|
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. -->
|
|
|
|
# Aris-293M
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 3.2572
|
|
|
|
## 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: 0.0002
|
|
- train_batch_size: 2
|
|
- eval_batch_size: 2
|
|
- seed: 42
|
|
- distributed_type: multi-GPU
|
|
- num_devices: 2
|
|
- gradient_accumulation_steps: 16
|
|
- total_train_batch_size: 64
|
|
- total_eval_batch_size: 4
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
- lr_scheduler_type: cosine
|
|
- lr_scheduler_warmup_steps: 200
|
|
- training_steps: 7630
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss |
|
|
|:-------------:|:------:|:----:|:---------------:|
|
|
| 4.8587 | 0.0655 | 500 | 4.8854 |
|
|
| 4.1492 | 0.1311 | 1000 | 4.1392 |
|
|
| 3.8591 | 0.1966 | 1500 | 3.8450 |
|
|
| 3.7696 | 0.2621 | 2000 | 3.6781 |
|
|
| 3.5556 | 0.3277 | 2500 | 3.5741 |
|
|
| 3.5234 | 0.3932 | 3000 | 3.4973 |
|
|
| 3.4189 | 0.4587 | 3500 | 3.4381 |
|
|
| 3.4178 | 0.5242 | 4000 | 3.3871 |
|
|
| 3.3873 | 0.5898 | 4500 | 3.3499 |
|
|
| 3.3054 | 0.6553 | 5000 | 3.3194 |
|
|
| 3.3168 | 0.7208 | 5500 | 3.2948 |
|
|
| 3.2871 | 0.7864 | 6000 | 3.2781 |
|
|
| 3.2399 | 0.8519 | 6500 | 3.2660 |
|
|
| 3.2484 | 0.9174 | 7000 | 3.2593 |
|
|
| 3.2665 | 0.9830 | 7500 | 3.2572 |
|
|
| 3.2976 | 1.0 | 7630 | 3.2572 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 5.12.1
|
|
- Pytorch 2.4.1+cu124
|
|
- Datasets 5.0.0
|
|
- Tokenizers 0.22.2
|