myproject

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

• Loss: 10.7401
• Accuracy: 0.3585

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 70

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	60	6.8412	0.3585
No log	2.0	120	7.0381	0.3585
No log	3.0	180	7.2302	0.3585
No log	4.0	240	7.3315	0.3585
No log	5.0	300	7.5093	0.3585
No log	6.0	360	7.6537	0.3585
No log	7.0	420	7.7774	0.3585
No log	8.0	480	7.8459	0.3585
2.4126	9.0	540	7.9683	0.3585
2.4126	10.0	600	8.0727	0.3585
2.4126	11.0	660	8.1432	0.3585
2.4126	12.0	720	8.2632	0.3585
2.4126	13.0	780	8.3617	0.3585
2.4126	14.0	840	8.3888	0.3585
2.4126	15.0	900	8.4802	0.3585
2.4126	16.0	960	8.6048	0.3585
1.3107	17.0	1020	8.6832	0.3585
1.3107	18.0	1080	8.7031	0.3585
1.3107	19.0	1140	8.8062	0.3585
1.3107	20.0	1200	8.9172	0.3585
1.3107	21.0	1260	8.9063	0.3585
1.3107	22.0	1320	9.0786	0.3585
1.3107	23.0	1380	9.1961	0.3585
1.3107	24.0	1440	9.1986	0.3585
0.6626	25.0	1500	9.2499	0.3585
0.6626	26.0	1560	9.2925	0.3585
0.6626	27.0	1620	9.4094	0.3585
0.6626	28.0	1680	9.4204	0.3585
0.6626	29.0	1740	9.5304	0.3585
0.6626	30.0	1800	9.5006	0.3585
0.6626	31.0	1860	9.6281	0.3585
0.6626	32.0	1920	9.6695	0.3585
0.6626	33.0	1980	9.6979	0.3585
0.3334	34.0	2040	9.8019	0.3585
0.3334	35.0	2100	9.8644	0.3585
0.3334	36.0	2160	9.8489	0.3585
0.3334	37.0	2220	9.8635	0.3585
0.3334	38.0	2280	9.9720	0.3585
0.3334	39.0	2340	10.0142	0.3585
0.3334	40.0	2400	10.1065	0.3585
0.3334	41.0	2460	10.1095	0.3585
0.1755	42.0	2520	10.1453	0.3585
0.1755	43.0	2580	10.1601	0.3585
0.1755	44.0	2640	10.2449	0.3585
0.1755	45.0	2700	10.2644	0.3585
0.1755	46.0	2760	10.2791	0.3585
0.1755	47.0	2820	10.3368	0.3585
0.1755	48.0	2880	10.3840	0.3585
0.1755	49.0	2940	10.3765	0.3585
0.1048	50.0	3000	10.4580	0.3585
0.1048	51.0	3060	10.4575	0.3585
0.1048	52.0	3120	10.4835	0.3585
0.1048	53.0	3180	10.5889	0.3585
0.1048	54.0	3240	10.5074	0.3585
0.1048	55.0	3300	10.5430	0.3585
0.1048	56.0	3360	10.5594	0.3585
0.1048	57.0	3420	10.6237	0.3585
0.1048	58.0	3480	10.6025	0.3585
0.0744	59.0	3540	10.6312	0.3585
0.0744	60.0	3600	10.6667	0.3585
0.0744	61.0	3660	10.6999	0.3585
0.0744	62.0	3720	10.6992	0.3585
0.0744	63.0	3780	10.6985	0.3585
0.0744	64.0	3840	10.7162	0.3585
0.0744	65.0	3900	10.7121	0.3585
0.0744	66.0	3960	10.7050	0.3585
0.06	67.0	4020	10.7263	0.3585
0.06	68.0	4080	10.7295	0.3585
0.06	69.0	4140	10.7384	0.3585
0.06	70.0	4200	10.7401	0.3585

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.1+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0