walia_ii_amharic_sum_normalized

This model is a fine-tuned version of israel/LLAMA-Walia-II on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.5518

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
2.739	0.4913	400	2.7388
2.6434	0.9826	800	2.6399
2.5789	1.4729	1200	2.5918
2.5649	1.9642	1600	2.5651
2.5446	2.4544	2000	2.5543
2.5434	2.9457	2400	2.5518

Framework versions

• PEFT 0.14.1.dev0
• Transformers 4.57.1
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.22.1