DipeshY/distilbert-finetuned-disaster-entity

fine_tune_results

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

• Loss: 0.0821

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: 40

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1	0.5517
No log	2.0	2	0.4685
No log	3.0	3	0.4025
No log	4.0	4	0.3522
No log	5.0	5	0.3154
No log	6.0	6	0.2895
No log	7.0	7	0.2715
No log	8.0	8	0.2579
No log	9.0	9	0.2464
No log	10.0	10	0.2362
No log	11.0	11	0.2270
No log	12.0	12	0.2188
No log	13.0	13	0.2114
No log	14.0	14	0.2049
No log	15.0	15	0.1988
No log	16.0	16	0.1926
No log	17.0	17	0.1862
No log	18.0	18	0.1793
No log	19.0	19	0.1720
No log	20.0	20	0.1644
No log	21.0	21	0.1565
No log	22.0	22	0.1485
No log	23.0	23	0.1406
No log	24.0	24	0.1330
No log	25.0	25	0.1259
No log	26.0	26	0.1193
No log	27.0	27	0.1133
No log	28.0	28	0.1080
No log	29.0	29	0.1032
No log	30.0	30	0.0991
No log	31.0	31	0.0955
No log	32.0	32	0.0925
No log	33.0	33	0.0900
No log	34.0	34	0.0878
No log	35.0	35	0.0860
No log	36.0	36	0.0847
No log	37.0	37	0.0836
No log	38.0	38	0.0828
No log	39.0	39	0.0823
No log	40.0	40	0.0821

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cpu
• Datasets 2.10.1
• Tokenizers 0.13.2