flan-t5-small-gigatrue

This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.1229

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: 0.0003
• train_batch_size: 256
• eval_batch_size: 256
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
2.5659	0.2030	3000	2.1724
2.4802	0.4059	6000	2.1500
2.4581	0.6089	9000	2.1390
2.4493	0.8119	12000	2.1325
2.4436	1.0148	15000	2.1282
2.4398	1.2178	18000	2.1255
2.437	1.4207	21000	2.1246
2.434	1.6237	24000	2.1246
2.4337	1.8267	27000	2.1226
2.4337	2.0296	30000	2.1228
2.4314	2.2326	33000	2.1234
2.4332	2.4356	36000	2.1232
2.4327	2.6385	39000	2.1230
2.4329	2.8415	42000	2.1229

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1
• Datasets 3.2.0
• Tokenizers 0.20.3