8d088fb3-28c5-4e4e-a7d5-ddfaadc1064c

This model is a fine-tuned version of unsloth/SmolLM2-360M-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7453

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: 0.00021
• 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	0.0000	1	2.5578
1.7976	0.0015	50	2.0161
1.5856	0.0029	100	1.9200
1.6293	0.0044	150	1.8517
1.5918	0.0059	200	1.8128
1.4642	0.0073	250	1.7846
1.522	0.0088	300	1.7801
1.5238	0.0103	350	1.7666
1.5004	0.0117	400	1.7521
1.6255	0.0132	450	1.7463
1.4193	0.0147	500	1.7453

Framework versions

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