---
library_name: transformers
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: counterfactual_seed-21_1e-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. -->

# counterfactual_seed-21_1e-3

This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1823
- Accuracy: 0.4006

## 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: 0.001
- train_batch_size: 32
- eval_batch_size: 64
- seed: 21
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- 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: linear
- lr_scheduler_warmup_steps: 32000
- num_epochs: 20.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step  | Validation Loss | Accuracy |
|:-------------:|:-------:|:-----:|:---------------:|:--------:|
| 5.989         | 0.9994  | 1486  | 4.4159          | 0.2934   |
| 4.3089        | 1.9992  | 2972  | 3.9080          | 0.3322   |
| 3.7012        | 2.9991  | 4458  | 3.6264          | 0.3562   |
| 3.5317        | 3.9996  | 5945  | 3.4692          | 0.3708   |
| 3.3115        | 4.9994  | 7431  | 3.3732          | 0.3799   |
| 3.2381        | 5.9992  | 8917  | 3.3111          | 0.3859   |
| 3.1324        | 6.9991  | 10403 | 3.2706          | 0.3900   |
| 3.0931        | 7.9996  | 11890 | 3.2468          | 0.3921   |
| 3.0318        | 8.9994  | 13376 | 3.2260          | 0.3944   |
| 3.0079        | 9.9992  | 14862 | 3.2155          | 0.3960   |
| 2.9696        | 10.9991 | 16348 | 3.2068          | 0.3968   |
| 2.9483        | 11.9996 | 17835 | 3.2019          | 0.3973   |
| 2.9289        | 12.9994 | 19321 | 3.2017          | 0.3978   |
| 2.9089        | 13.9992 | 20807 | 3.1979          | 0.3988   |
| 2.9           | 14.9991 | 22293 | 3.1900          | 0.3990   |
| 2.8805        | 15.9996 | 23780 | 3.1883          | 0.3997   |
| 2.8807        | 16.9994 | 25266 | 3.1876          | 0.3999   |
| 2.8605        | 17.9992 | 26752 | 3.1893          | 0.3999   |
| 2.8688        | 18.9991 | 28238 | 3.1880          | 0.4002   |
| 2.8484        | 19.9962 | 29720 | 3.1823          | 0.4006   |


### Framework versions

- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.20.0