fr-camembert-base-finetuned

This model is a fine-tuned version of camembert-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.3301

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: 16
• eval_batch_size: 16
• 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
3.2487	1.0	124	2.8169
2.6851	2.0	248	2.6374
2.6175	3.0	372	2.6431
2.5366	4.0	496	2.4475
2.4529	5.0	620	2.4647
2.4002	6.0	744	2.4846
2.3914	7.0	868	2.4187
2.3439	8.0	992	2.4819
2.2797	9.0	1116	2.3769
2.3065	10.0	1240	2.4536
2.2499	11.0	1364	2.4079
2.2254	12.0	1488	2.3755
2.218	13.0	1612	2.3189
2.2059	14.0	1736	2.3628
2.158	15.0	1860	2.4482
2.1871	16.0	1984	2.3020
2.154	17.0	2108	2.3485
2.1906	18.0	2232	2.4602
2.1853	19.0	2356	2.2482
2.1334	20.0	2480	2.3699

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3