---
base_model: final_models/focus_bur_phi_after_focus_reinit
tags:
- generated_from_trainer
datasets:
- mc4
model-index:
- name: focus_bur_phi_focus_trained
  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. -->

# focus_bur_phi_focus_trained

This model is a fine-tuned version of [final_models/focus_bur_phi_after_focus_reinit](https://huggingface.co/final_models/focus_bur_phi_after_focus_reinit) on the mc4 my dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8202

## 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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 2000
- num_epochs: 6.0

### Training results

| Training Loss | Epoch | Step   | Validation Loss |
|:-------------:|:-----:|:------:|:---------------:|
| 1.5881        | 1.0   | 24415  | 2.1758          |
| 1.8           | 2.0   | 48830  | 2.0561          |
| 2.4986        | 3.0   | 73245  | 1.9480          |
| 0.9893        | 4.0   | 97660  | 1.8157          |
| 1.0487        | 5.0   | 122075 | 1.7515          |
| 0.8305        | 6.0   | 146490 | 1.8202          |


### Framework versions

- Transformers 4.44.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.19.1