distilbert-base-uncased-finetuned-imdb

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

• Loss: 2.2527
• Model Preparation Time: 0.0018

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: 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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time
2.6809	1.0	157	2.4958	0.0018
2.5738	2.0	314	2.4353	0.0018
2.4988	3.0	471	2.4525	0.0018
2.4786	4.0	628	2.3622	0.0018
2.4465	5.0	785	2.3930	0.0018
2.4165	6.0	942	2.3718	0.0018
2.3949	7.0	1099	2.3510	0.0018
2.3756	8.0	1256	2.3534	0.0018
2.3618	9.0	1413	2.3242	0.0018
2.3631	10.0	1570	2.3137	0.0018
2.3513	11.0	1727	2.3205	0.0018
2.3443	12.0	1884	2.3488	0.0018
2.3048	13.0	2041	2.3442	0.0018
2.308	14.0	2198	2.3250	0.0018
2.2952	15.0	2355	2.2978	0.0018
2.2875	16.0	2512	2.3453	0.0018
2.2705	17.0	2669	2.2938	0.0018
2.2713	18.0	2826	2.2780	0.0018
2.2679	19.0	2983	2.2849	0.0018
2.2534	20.0	3140	2.2641	0.0018
2.2402	21.0	3297	2.2802	0.0018
2.2408	22.0	3454	2.2947	0.0018
2.2379	23.0	3611	2.2862	0.0018
2.2407	24.0	3768	2.2792	0.0018
2.2201	25.0	3925	2.2767	0.0018
2.2302	26.0	4082	2.2982	0.0018
2.2152	27.0	4239	2.2731	0.0018
2.2183	28.0	4396	2.2596	0.0018
2.2206	29.0	4553	2.2734	0.0018
2.2049	30.0	4710	2.2838	0.0018

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0