metadata

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: []

llama-3.2-amharic-32k-1024-v6

This model is a fine-tuned version of 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