final_V1-distilbert-text-classification-model

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: 0.1494
Accuracy: 0.9672
F1: 0.8312
Precision: 0.8275
Recall: 0.8357

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: 5e-05
train_batch_size: 16
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
1.6662	0.11	50	1.6945	0.2888	0.0820	0.1958	0.1341
0.7494	0.22	100	0.6947	0.8034	0.4962	0.4949	0.5054
0.2779	0.33	150	0.4631	0.8980	0.6685	0.6550	0.6829
0.2204	0.44	200	0.3938	0.8999	0.6686	0.6659	0.6758
0.137	0.55	250	0.4153	0.9065	0.6707	0.6537	0.6898
0.1931	0.66	300	0.3093	0.9166	0.7089	0.7728	0.7046
0.1356	0.76	350	0.3384	0.9152	0.6904	0.8123	0.6978
0.1065	0.87	400	0.4172	0.9144	0.7233	0.7804	0.7174
0.105	0.98	450	0.4521	0.8852	0.7078	0.7342	0.7051
0.1275	1.09	500	0.2837	0.9262	0.7365	0.7927	0.7275
0.0754	1.2	550	0.3979	0.9180	0.7164	0.8039	0.7133
0.0861	1.31	600	0.1506	0.9604	0.8259	0.8247	0.8280
0.0514	1.42	650	0.1397	0.9664	0.8277	0.8264	0.8293
0.0536	1.53	700	0.1566	0.9642	0.8279	0.8255	0.8308
0.0351	1.64	750	0.1804	0.9620	0.8276	0.8251	0.8312
0.0862	1.75	800	0.1445	0.9655	0.8314	0.8307	0.8322
0.0461	1.86	850	0.1492	0.9669	0.8306	0.8291	0.8324
0.0663	1.97	900	0.2054	0.9604	0.8292	0.8299	0.8295
0.0482	2.07	950	0.1498	0.9655	0.8294	0.8272	0.8324
0.0299	2.18	1000	0.1657	0.9650	0.8292	0.8269	0.8321
0.0348	2.29	1050	0.1473	0.9686	0.8310	0.8291	0.8332
0.0283	2.4	1100	0.1470	0.9694	0.8333	0.8297	0.8376
0.0115	2.51	1150	0.1496	0.9691	0.8336	0.8317	0.8358
0.004	2.62	1200	0.1671	0.9650	0.8301	0.8280	0.8329
0.0054	2.73	1250	0.1560	0.9694	0.8333	0.8325	0.8343
0.0217	2.84	1300	0.1553	0.9696	0.8334	0.8326	0.8345
0.0054	2.95	1350	0.1603	0.9691	0.8332	0.8324	0.8343

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2

Loading…

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05

train_batch_size: 16

eval_batch_size: 32

seed: 42

optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

lr_scheduler_type: linear

lr_scheduler_warmup_steps: 100

num_epochs: 3

mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
1.6662	0.11	50	1.6945	0.2888	0.0820	0.1958	0.1341
0.7494	0.22	100	0.6947	0.8034	0.4962	0.4949	0.5054
0.2779	0.33	150	0.4631	0.8980	0.6685	0.6550	0.6829
0.2204	0.44	200	0.3938	0.8999	0.6686	0.6659	0.6758
0.137	0.55	250	0.4153	0.9065	0.6707	0.6537	0.6898
0.1931	0.66	300	0.3093	0.9166	0.7089	0.7728	0.7046
0.1356	0.76	350	0.3384	0.9152	0.6904	0.8123	0.6978
0.1065	0.87	400	0.4172	0.9144	0.7233	0.7804	0.7174
0.105	0.98	450	0.4521	0.8852	0.7078	0.7342	0.7051
0.1275	1.09	500	0.2837	0.9262	0.7365	0.7927	0.7275
0.0754	1.2	550	0.3979	0.9180	0.7164	0.8039	0.7133
0.0861	1.31	600	0.1506	0.9604	0.8259	0.8247	0.8280
0.0514	1.42	650	0.1397	0.9664	0.8277	0.8264	0.8293
0.0536	1.53	700	0.1566	0.9642	0.8279	0.8255	0.8308
0.0351	1.64	750	0.1804	0.9620	0.8276	0.8251	0.8312
0.0862	1.75	800	0.1445	0.9655	0.8314	0.8307	0.8322
0.0461	1.86	850	0.1492	0.9669	0.8306	0.8291	0.8324
0.0663	1.97	900	0.2054	0.9604	0.8292	0.8299	0.8295
0.0482	2.07	950	0.1498	0.9655	0.8294	0.8272	0.8324
0.0299	2.18	1000	0.1657	0.9650	0.8292	0.8269	0.8321
0.0348	2.29	1050	0.1473	0.9686	0.8310	0.8291	0.8332
0.0283	2.4	1100	0.1470	0.9694	0.8333	0.8297	0.8376
0.0115	2.51	1150	0.1496	0.9691	0.8336	0.8317	0.8358
0.004	2.62	1200	0.1671	0.9650	0.8301	0.8280	0.8329
0.0054	2.73	1250	0.1560	0.9694	0.8333	0.8325	0.8343
0.0217	2.84	1300	0.1553	0.9696	0.8334	0.8326	0.8345
0.0054	2.95	1350	0.1603	0.9691	0.8332	0.8324	0.8343

Framework versions

Transformers 4.39.3

Pytorch 2.1.2

Datasets 2.18.0

Tokenizers 0.15.2

AmirlyPhd/final_V1-distilbert-text-classification-model

final_V1-distilbert-text-classification-model

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

final_V1-distilbert-text-classification-model

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions