015-microsoft-deberta-v3-base-finetuned-yahoo-80_20

This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.0709
F1: 0.2744
Accuracy: 0.35
Precision: 0.2452
Recall: 0.35
System Ram Used: 3.9663
System Ram Total: 83.4807
Gpu Ram Allocated: 2.0874
Gpu Ram Cached: 6.8516
Gpu Ram Total: 39.5640
Gpu Utilization: 14
Disk Space Used: 24.7820
Disk Space Total: 78.1898

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: 32
eval_batch_size: 32
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	F1	Accuracy	Precision	Recall	System Ram Used	System Ram Total	Gpu Ram Allocated	Gpu Ram Cached	Gpu Ram Total	Gpu Utilization	Disk Space Used	Disk Space Total
2.3062	2.0	6	2.3028	0.025	0.1	0.0143	0.1	3.9009	83.4807	2.0874	6.8398	39.5640	51	24.7819	78.1898
2.304	4.0	12	2.3020	0.0722	0.15	0.0625	0.15	3.9032	83.4807	2.0873	6.8418	39.5640	56	24.7819	78.1898
2.2892	6.0	18	2.2997	0.0111	0.05	0.0063	0.05	3.9136	83.4807	2.0874	6.8418	39.5640	62	24.7819	78.1898
2.2729	8.0	24	2.2947	0.0190	0.1	0.0105	0.1	3.9411	83.4807	2.0873	6.8418	39.5640	56	24.7819	78.1898
2.2108	10.0	30	2.2843	0.0521	0.15	0.0333	0.15	3.9439	83.4807	2.0873	6.8418	39.5640	60	24.7819	78.1898
2.1482	12.0	36	2.2660	0.1417	0.2	0.1643	0.2	3.9451	83.4807	2.0873	6.8418	39.5640	48	24.7819	78.1898
2.0203	14.0	42	2.2328	0.2086	0.3	0.1617	0.3	3.9597	83.4807	2.0874	6.8418	39.5640	52	24.7819	78.1898
1.8707	16.0	48	2.2030	0.2019	0.3	0.1533	0.3	3.9691	83.4807	2.0873	6.8418	39.5640	55	24.7819	78.1898
1.701	18.0	54	2.1741	0.2638	0.35	0.2483	0.35	3.9705	83.4807	2.0873	6.8418	39.5640	58	24.7819	78.1898
1.5493	20.0	60	2.1379	0.2967	0.35	0.3	0.35	3.9699	83.4807	2.0874	6.8516	39.5640	57	24.7819	78.1898
1.4073	22.0	66	2.1232	0.2244	0.3	0.1952	0.3	3.9711	83.4807	2.0873	6.8516	39.5640	51	24.7819	78.1898
1.2447	24.0	72	2.1096	0.2344	0.3	0.2119	0.3	3.9705	83.4807	2.0873	6.8516	39.5640	49	24.7819	78.1898
1.155	26.0	78	2.0978	0.3178	0.4	0.3119	0.4	3.9663	83.4807	2.0874	6.8516	39.5640	56	24.7819	78.1898
1.0522	28.0	84	2.0805	0.2744	0.35	0.2452	0.35	3.9661	83.4807	2.0873	6.8516	39.5640	63	24.7820	78.1898
0.9741	30.0	90	2.0735	0.2744	0.35	0.2452	0.35	3.9575	83.4807	2.0873	6.8516	39.5640	59	24.7820	78.1898
0.9042	32.0	96	2.0793	0.2744	0.35	0.2452	0.35	3.9661	83.4807	2.0873	6.8516	39.5640	50	24.7820	78.1898
0.8497	34.0	102	2.0769	0.2744	0.35	0.2452	0.35	3.9654	83.4807	2.0874	6.8516	39.5640	58	24.7820	78.1898
0.8228	36.0	108	2.0736	0.2744	0.35	0.2452	0.35	3.9660	83.4807	2.0873	6.8516	39.5640	60	24.7820	78.1898
0.7908	38.0	114	2.0717	0.2744	0.35	0.2452	0.35	3.9659	83.4807	2.0873	6.8516	39.5640	59	24.7820	78.1898
0.7998	40.0	120	2.0709	0.2744	0.35	0.2452	0.35	3.9661	83.4807	2.0873	6.8516	39.5640	59	24.7820	78.1898

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3

diogopaes10/015-microsoft-deberta-v3-base-finetuned-yahoo-80_20

015-microsoft-deberta-v3-base-finetuned-yahoo-80_20

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Seed this model