fro-distil-xlstm

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

• Loss: 6.9495

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: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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: 0.1
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
24.8787	0.32	100	6.9945
24.5002	0.64	200	6.9865
24.668	0.96	300	6.9007
23.6867	1.2784	400	6.9811
23.7862	1.5984	500	6.9604
24.0215	1.9184	600	6.9495

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0