---
library_name: transformers
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: llama_1b_step2_batch_v3
  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. -->

# llama_1b_step2_batch_v3

This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3241

## 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: 5e-05
- train_batch_size: 4
- eval_batch_size: 40
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.174         | 0.0682 | 50   | 1.1018          |
| 0.8332        | 0.1363 | 100  | 0.8992          |
| 0.6499        | 0.2045 | 150  | 0.7669          |
| 0.823         | 0.2727 | 200  | 0.6721          |
| 0.6367        | 0.3408 | 250  | 0.6062          |
| 0.7465        | 0.4090 | 300  | 0.5634          |
| 0.3689        | 0.4772 | 350  | 0.5195          |
| 0.4012        | 0.5453 | 400  | 0.4824          |
| 0.3911        | 0.6135 | 450  | 0.4470          |
| 0.4325        | 0.6817 | 500  | 0.4248          |
| 0.338         | 0.7498 | 550  | 0.4069          |
| 0.3274        | 0.8180 | 600  | 0.3879          |
| 0.3937        | 0.8862 | 650  | 0.3740          |
| 0.2884        | 0.9543 | 700  | 0.3620          |
| 0.2069        | 1.0225 | 750  | 0.3641          |
| 0.1866        | 1.0907 | 800  | 0.3545          |
| 0.2269        | 1.1588 | 850  | 0.3532          |
| 0.2287        | 1.2270 | 900  | 0.3479          |
| 0.2592        | 1.2952 | 950  | 0.3415          |
| 0.191         | 1.3633 | 1000 | 0.3361          |
| 0.2337        | 1.4315 | 1050 | 0.3346          |
| 0.2271        | 1.4997 | 1100 | 0.3321          |
| 0.2411        | 1.5678 | 1150 | 0.3279          |
| 0.2503        | 1.6360 | 1200 | 0.3271          |
| 0.2475        | 1.7042 | 1250 | 0.3259          |
| 0.191         | 1.7723 | 1300 | 0.3254          |
| 0.1946        | 1.8405 | 1350 | 0.3246          |
| 0.2598        | 1.9087 | 1400 | 0.3242          |
| 0.157         | 1.9768 | 1450 | 0.3241          |


### Framework versions

- Transformers 4.46.0
- Pytorch 2.1.0+cu118
- Datasets 3.0.2
- Tokenizers 0.20.1