---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: 4M-ACT
  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. -->

# 4M-ACT

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: 0.2253

## 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: 0.0003
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- training_steps: 2000

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 3.5504        | 0.0135 | 200  | 3.3654          |
| 1.0185        | 0.0270 | 400  | 0.9663          |
| 0.4490        | 0.0404 | 600  | 0.4422          |
| 0.3504        | 0.0539 | 800  | 0.3512          |
| 0.3106        | 0.0674 | 1000 | 0.3083          |
| 0.2867        | 0.0809 | 1200 | 0.2812          |
| 0.2550        | 0.0944 | 1400 | 0.2564          |
| 0.2600        | 0.1079 | 1600 | 0.2609          |
| 0.2334        | 0.1213 | 1800 | 0.2323          |
| 0.2238        | 0.1348 | 2000 | 0.2253          |


### Framework versions

- Transformers 5.15.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 5.0.1
- Tokenizers 0.22.2