---
library_name: transformers
license: llama3.2
base_model: yosefw/llama-3.2-amharic-32k-1024-v6
tags:
- generated_from_trainer
model-index:
- name: llama-3.2-amharic-32k-1024-v6
  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-3.2-amharic-32k-1024-v6

This model is a fine-tuned version of [yosefw/llama-3.2-amharic-32k-1024-v6](https://huggingface.co/yosefw/llama-3.2-amharic-32k-1024-v6) on an unknown dataset.
It achieves the following results on the evaluation set:
- eval_loss: 4.0369
- eval_model_preparation_time: 0.0027
- eval_runtime: 25.3096
- eval_samples_per_second: 102.53
- eval_steps_per_second: 6.44
- epoch: 4.5197
- step: 18898

## 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: 0.00012
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 200
- num_epochs: 6

### Framework versions

- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3