t5_es_weight_4_4

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

• Loss: 0.0214
• Accuracy: 0.9955
• F1: 0.9958

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: 0.0001
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 64
• total_train_batch_size: 4096
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.7125	6.8817	50	0.6708	0.662	0.7245
0.6147	13.7634	100	0.4378	0.897	0.8985
0.2517	20.6452	150	0.0903	0.9705	0.9721
0.0614	27.5269	200	0.0484	0.986	0.9868
0.0283	34.4086	250	0.0329	0.9895	0.9901
0.0156	41.2903	300	0.0228	0.9935	0.9939
0.008	48.1720	350	0.0188	0.996	0.9962
0.0041	55.0538	400	0.0194	0.996	0.9962
0.0026	61.9355	450	0.0209	0.996	0.9962
0.0018	68.8172	500	0.0232	0.9955	0.9958
0.0017	75.6989	550	0.0219	0.9955	0.9958
0.0009	82.5806	600	0.0222	0.9955	0.9958
0.0005	89.4624	650	0.0270	0.9955	0.9958
0.0005	96.3441	700	0.0214	0.9955	0.9958

Framework versions

• Transformers 4.40.0
• Pytorch 2.4.1+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1