---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: childes_clm_context_30
  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. -->

# childes_clm_context_30

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: 3.3503

## 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: 16
- eval_batch_size: 16
- seed: 30
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100000
- training_steps: 400000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step  | Validation Loss |
|:-------------:|:-------:|:-----:|:---------------:|
| 5.3831        | 3.5149  | 4000  | 4.0429          |
| 3.7776        | 7.0299  | 8000  | 3.5983          |
| 3.427         | 10.5448 | 12000 | 3.3933          |
| 3.1929        | 14.0598 | 16000 | 3.2864          |
| 3.0111        | 17.5747 | 20000 | 3.2382          |
| 2.865         | 21.0896 | 24000 | 3.2529          |
| 2.7295        | 24.6046 | 28000 | 3.2886          |
| 2.6194        | 28.1195 | 32000 | 3.3503          |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1