smol_llama_x

This model is a fine-tuned version of Isotonic/smol_llama-4x220M-MoE on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.5906
• Accuracy: 0.6799

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	211	1.4545	0.6908
No log	2.0	422	1.4871	0.6881
1.4748	3.0	633	1.5353	0.6841
1.4748	4.0	844	1.5906	0.6799

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2