SmolLM_360M_Instruct_qlora_nf4-plaba

This model is a fine-tuned version of HuggingFaceTB/SmolLM-360M-Instruct on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 1.8521

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: 0.001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.8889	2	2.0708
No log	1.7778	4	2.0152
No log	2.6667	6	1.9361
No log	4.0	9	1.8851
1.9803	4.8889	11	1.8728
1.9803	5.7778	13	1.8640
1.9803	6.6667	15	1.8571
1.9803	8.0	18	1.8525
1.8574	8.8889	20	1.8521

Framework versions

• PEFT 0.10.0
• Transformers 4.40.0
• Pytorch 2.1.0
• Datasets 2.18.0
• Tokenizers 0.19.1