NorthernTribe-Research/maasai-project-storage/training_runs/20260619T225710Z/model_output - Storage Bucket

maasai-en-mt-staging

This model is a fine-tuned version of Qwen/Qwen2.5-3B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.7846

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: 0.0002
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 0.03
• training_steps: 800

Training results

Training Loss	Epoch	Step	Validation Loss
2.5781	0.3794	100	2.5126
2.2593	0.7588	200	2.2396
1.9743	1.1366	300	2.1062
1.8846	1.5160	400	2.0034
1.8152	1.8954	500	1.9168
1.5970	2.2732	600	1.8696
1.5604	2.6526	700	1.8172
1.5004	3.0304	800	1.7846

Framework versions

• PEFT 0.18.1
• Transformers 5.4.0
• Pytorch 2.5.1+cu118
• Datasets 4.8.4
• Tokenizers 0.22.2