local_distilbert_finetune_model

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: 0.2154
• Precision: 0.5
• Recall: 0.5
• F1: 0.5
• Accuracy: 0.9231

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	1	0.8718	0.0	0.0	0.0	0.7692
No log	2.0	2	0.8088	0.0	0.0	0.0	0.7692
No log	3.0	3	0.7507	0.0	0.0	0.0	0.7692
No log	4.0	4	0.6957	0.0	0.0	0.0	0.7692
No log	5.0	5	0.6445	0.0	0.0	0.0	0.7692
No log	6.0	6	0.5982	0.0	0.0	0.0	0.7692
No log	7.0	7	0.5559	0.0	0.0	0.0	0.7692
No log	8.0	8	0.5177	0.0	0.0	0.0	0.7692
No log	9.0	9	0.4832	0.0	0.0	0.0	0.8462
No log	10.0	10	0.4523	0.5	0.5	0.5	0.9231
No log	11.0	11	0.4243	0.5	0.5	0.5	0.9231
No log	12.0	12	0.3996	0.5	0.5	0.5	0.9231
No log	13.0	13	0.3778	0.5	0.5	0.5	0.9231
No log	14.0	14	0.3592	0.5	0.5	0.5	0.9231
No log	15.0	15	0.3428	0.5	0.5	0.5	0.9231
No log	16.0	16	0.3293	0.5	0.5	0.5	0.9231
No log	17.0	17	0.3180	0.5	0.5	0.5	0.9231
No log	18.0	18	0.3087	0.5	0.5	0.5	0.9231
No log	19.0	19	0.3003	0.5	0.5	0.5	0.9231
No log	20.0	20	0.2933	0.5	0.5	0.5	0.9231
No log	21.0	21	0.2865	0.5	0.5	0.5	0.9231
No log	22.0	22	0.2807	0.5	0.5	0.5	0.9231
No log	23.0	23	0.2755	0.5	0.5	0.5	0.9231
No log	24.0	24	0.2689	0.5	0.5	0.5	0.9231
No log	25.0	25	0.2628	0.5	0.5	0.5	0.9231
No log	26.0	26	0.2573	0.5	0.5	0.5	0.9231
No log	27.0	27	0.2528	0.5	0.5	0.5	0.9231
No log	28.0	28	0.2487	0.5	0.5	0.5	0.9231
No log	29.0	29	0.2451	0.5	0.5	0.5	0.9231
No log	30.0	30	0.2420	0.5	0.5	0.5	0.9231
No log	31.0	31	0.2392	0.5	0.5	0.5	0.9231
No log	32.0	32	0.2363	0.5	0.5	0.5	0.9231
No log	33.0	33	0.2335	0.5	0.5	0.5	0.9231
No log	34.0	34	0.2310	0.5	0.5	0.5	0.9231
No log	35.0	35	0.2288	0.5	0.5	0.5	0.9231
No log	36.0	36	0.2267	0.5	0.5	0.5	0.9231
No log	37.0	37	0.2247	0.5	0.5	0.5	0.9231
No log	38.0	38	0.2230	0.5	0.5	0.5	0.9231
No log	39.0	39	0.2216	0.5	0.5	0.5	0.9231
No log	40.0	40	0.2205	0.5	0.5	0.5	0.9231
No log	41.0	41	0.2196	0.5	0.5	0.5	0.9231
No log	42.0	42	0.2187	0.5	0.5	0.5	0.9231
No log	43.0	43	0.2180	0.5	0.5	0.5	0.9231
No log	44.0	44	0.2173	0.5	0.5	0.5	0.9231
No log	45.0	45	0.2168	0.5	0.5	0.5	0.9231
No log	46.0	46	0.2163	0.5	0.5	0.5	0.9231
No log	47.0	47	0.2159	0.5	0.5	0.5	0.9231
No log	48.0	48	0.2157	0.5	0.5	0.5	0.9231
No log	49.0	49	0.2155	0.5	0.5	0.5	0.9231
No log	50.0	50	0.2154	0.5	0.5	0.5	0.9231

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2