bloomz_lora_mn

This model is a fine-tuned version of bigscience/bloomz-3b on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.4090

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: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 500
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.938	0.1820	1000	2.9015
2.6901	0.3641	2000	2.7353
2.5543	0.5461	3000	2.5426
2.4624	0.7282	4000	2.4493
2.4762	0.9102	5000	2.4090

Framework versions

• PEFT 0.14.0
• Transformers 4.45.0
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.20.3