91fc75bb-85bd-4bab-941b-0e5ce73830fe

This model is a fine-tuned version of unsloth/SmolLM-135M-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0630

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: 0.000201
• 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	0.0001	1	0.7720
0.0227	0.0037	50	0.2198
0.0042	0.0075	100	0.1047
0.0017	0.0112	150	0.0842
0.0014	0.0149	200	0.0767
0.0011	0.0187	250	0.0720
0.0009	0.0224	300	0.0676
0.001	0.0261	350	0.0664
0.003	0.0299	400	0.0636
0.0006	0.0336	450	0.0631
0.0023	0.0373	500	0.0630

Framework versions

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