5b93413b-7a81-4dca-a6b8-a94e7e50fce7

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

• Loss: 0.7737

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: 10
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100
• training_steps: 7000

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0007	1	1.2054
0.9425	0.3430	500	0.9315
0.9202	0.6860	1000	0.8849
0.8687	1.0291	1500	0.8518
0.8354	1.3721	2000	0.8317
0.8244	1.7151	2500	0.8181
0.7854	2.0581	3000	0.8035
0.7883	2.4011	3500	0.7945
0.7697	2.7441	4000	0.7866
0.7577	3.0872	4500	0.7821
0.7594	3.4302	5000	0.7772
0.7453	3.7732	5500	0.7731
0.7461	4.1163	6000	0.7755
0.7604	4.4593	6500	0.7726
0.7341	4.8023	7000	0.7737

Framework versions

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