62a42452-4d9f-48bb-8b96-3e8f06178c30

This model is a fine-tuned version of unsloth/SmolLM-1.7B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.5584

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: 0.000211
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0007	1	3.4471
3.0201	0.0329	50	3.0048
2.7222	0.0658	100	2.8511
2.6578	0.0987	150	2.7651
2.5535	0.1316	200	2.7146
2.5642	0.1645	250	2.6533
2.5087	0.1974	300	2.6221
2.5043	0.2303	350	2.5962
2.5099	0.2632	400	2.5703
2.5141	0.2962	450	2.5609
2.4894	0.3291	500	2.5584

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1