Flan_t5

This model is a fine-tuned version of google/flan-t5-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	126	nan
No log	2.0	252	nan
No log	3.0	378	nan
0.0	4.0	504	nan
0.0	5.0	630	nan
0.0	6.0	756	nan
0.0	7.0	882	nan
0.0	8.0	1008	nan
0.0	9.0	1134	nan
0.0	10.0	1260	nan
0.0	11.0	1386	nan
0.0	12.0	1512	nan
0.0	13.0	1638	nan
0.0	14.0	1764	nan
0.0	15.0	1890	nan
0.0	16.0	2016	nan
0.0	17.0	2142	nan
0.0	18.0	2268	nan
0.0	19.0	2394	nan
0.0	20.0	2520	nan

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1