yakazimir/smollm_1_7B_ultrachat_v2

HuggingFaceTB/SmolLM2-1.7B

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-1.7B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2902

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-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• total_eval_batch_size: 64
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.3939	0.2463	200	1.3921
1.2806	0.4926	400	1.3156
1.2827	0.7389	600	1.2938
1.2807	0.9852	800	1.2902

Framework versions

• Transformers 4.48.3
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.21.0