rerun-09-19-2024-experiment-distill-tree-babylm2024-58-2

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

• Loss: 2.6157

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: 0.00025
• train_batch_size: 64
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 200
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
10.104	1.0	2065	10.4130
5.2452	2.0	4130	5.7628
3.9297	3.0	6195	4.3714
3.3837	4.0	8260	3.7472
2.84	5.0	10325	3.3064
2.6592	6.0	12390	3.0392
2.3847	7.0	14455	2.8177
2.2605	8.0	16520	2.6904
2.1446	9.0	18585	2.6290
2.1841	10.0	20650	2.6157

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.4.0+cu121
• Tokenizers 0.19.1