metadata

library_name: transformers
license: apache-2.0
base_model: google/flan-t5-large
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
model-index:
  - name: flanT5_Task1
    results: []

flanT5_Task1

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: 1.6498
Accuracy: 0.8047
Precision: 0.8229
Recall: 0.7765
F1 score: 0.7990

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: 1
eval_batch_size: 1
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Accuracy	F1 score	Precision	Recall	Validation Loss
1.0024	0.4205	2500	0.76	0.7530	0.7756	0.7318	0.8479
1.0808	0.8410	5000	0.7553	0.7620	0.7416	0.7835	0.8954
1.0927	1.2616	7500	0.7682	0.7411	0.8393	0.6635	1.0011
0.8823	1.6821	10000	0.7847	0.7738	0.8151	0.7365	0.8913
0.8154	2.1026	12500	0.7929	0.7822	0.8251	0.7435	0.8291
0.6981	2.5231	15000	0.9793	0.7929	0.8152	0.7576	0.7854
0.6452	2.9437	17500	0.9164	0.8035	0.8564	0.7294	0.7878
0.4567	3.3642	20000	1.0961	0.8153	0.8418	0.7765	0.8078
0.4245	3.7847	22500	1.2257	0.8153	0.8268	0.7976	0.8120
0.3159	4.2052	25000	1.4984	0.8047	0.8047	0.8047	0.8047
0.2152	4.6257	27500	1.6498	0.8047	0.8229	0.7765	0.7990

Framework versions

Transformers 4.48.3
Pytorch 2.3.0+cu121
Datasets 3.2.0
Tokenizers 0.21.0