model

This model is a fine-tuned version of cmarkea/distilcamembert-base on the allocine dataset. It achieves the following results on the evaluation set:

• Loss: 2.0254

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20.0

Training results

Training Loss	Epoch	Step	Validation Loss
2.4388	1.0	157	2.1637
2.288	2.0	314	2.1697
2.2444	3.0	471	2.1150
2.2166	4.0	628	2.0906
2.1754	5.0	785	2.0899
2.1604	6.0	942	2.0797
2.1299	7.0	1099	2.0589
2.1195	8.0	1256	2.0178
2.1258	9.0	1413	2.0348
2.1071	10.0	1570	2.0090
2.0888	11.0	1727	2.0047
2.0792	12.0	1884	2.0219
2.0687	13.0	2041	2.0080
2.0527	14.0	2198	2.0298
2.0589	15.0	2355	1.9869
2.0518	16.0	2512	2.0152
2.0409	17.0	2669	2.0247
2.0507	18.0	2826	1.9928
2.0366	19.0	2983	2.0175
2.0386	20.0	3140	1.9487

Framework versions

• Transformers 4.21.2
• Pytorch 1.12.1+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1