camembert_squadFR_question_answering_tools_fr

This model is a fine-tuned version of etalab-ia/camembert-base-squadFR-fquad-piaf on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7066
• Learning Rate: 0.0001

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: 24
• eval_batch_size: 192
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 60

Training results

Training Loss	Epoch	Step	Validation Loss	Rate
No log	1.0	7	1.8851	0.0001
No log	2.0	14	1.0053	0.0001
No log	3.0	21	1.4041	0.0001
No log	4.0	28	1.0443	0.0001
No log	5.0	35	0.9649	0.0001
No log	6.0	42	1.6062	9e-05
No log	7.0	49	1.3678	0.0001
No log	8.0	56	1.2775	0.0001
No log	9.0	63	1.1872	0.0001
No log	10.0	70	1.4032	0.0001
No log	11.0	77	1.7370	0.0001
No log	12.0	84	2.1178	8e-05
No log	13.0	91	1.7708	0.0001
No log	14.0	98	1.7846	0.0001
No log	15.0	105	1.7066	0.0001

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.14.1