distilbert-base-uncased-finetuned-squad-linear-v3 – AI Model by goryden | AlphaNeural AI

You can deploy this model and start earning money today!

goryden/
distilbert-base-uncased-finetuned-squad-linear-v3

like

0

generated_from_trainer

distilbert/distilbert-base-uncased

Views

No views yet

Visualize in Weights & Biases

distilbert-base-uncased-finetuned-squad-linear-v3

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: 5.3795

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: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
4.6466	1.0	1384	4.5685
4.4435	2.0	2768	4.4266
4.2618	3.0	4152	4.3409
4.1056	4.0	5536	4.2640
4.009	5.0	6920	4.2542
3.8868	6.0	8304	4.2373
3.7923	7.0	9688	4.2827
3.7058	8.0	11072	4.3045
3.6021	9.0	12456	4.3316
3.5198	10.0	13840	4.4002
3.4235	11.0	15224	4.3556
3.3517	12.0	16608	4.4455
3.2419	13.0	17992	4.5226
3.1657	14.0	19376	4.6344
3.0952	15.0	20760	4.7090
3.0292	16.0	22144	4.7006
2.9471	17.0	23528	4.8139
2.8799	18.0	24912	4.8523
2.8182	19.0	26296	4.9372
2.7611	20.0	27680	4.9981
2.7128	21.0	29064	5.0938
2.6537	22.0	30448	5.1496
2.6061	23.0	31832	5.1768
2.5528	24.0	33216	5.1544
2.5202	25.0	34600	5.2163
2.4748	26.0	35984	5.2345
2.4695	27.0	37368	5.3142
2.4317	28.0	38752	5.4011
2.4071	29.0	40136	5.3698
2.3855	30.0	41520	5.3795

Framework versions

Transformers 4.42.3
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1