my_awesome_qa_model

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

• Loss: 5.7197

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
No log	1.0	9	5.6727
No log	2.0	18	4.7499
No log	3.0	27	4.0555
No log	4.0	36	3.6859
No log	5.0	45	3.7884
No log	6.0	54	3.8482
No log	7.0	63	3.9977
No log	8.0	72	4.3411
No log	9.0	81	4.6886
No log	10.0	90	4.6630
No log	11.0	99	4.7296
No log	12.0	108	4.6999
No log	13.0	117	4.8416
No log	14.0	126	4.9140
No log	15.0	135	4.7755
No log	16.0	144	4.9881
No log	17.0	153	5.0003
No log	18.0	162	5.0493
No log	19.0	171	5.2228
No log	20.0	180	5.2716
No log	21.0	189	5.1830
No log	22.0	198	5.1855
No log	23.0	207	5.1763
No log	24.0	216	5.4629
No log	25.0	225	5.4778
No log	26.0	234	5.4658
No log	27.0	243	5.4926
No log	28.0	252	5.5078
No log	29.0	261	5.7624
No log	30.0	270	5.5743
No log	31.0	279	5.6203
No log	32.0	288	5.5513
No log	33.0	297	5.5641
No log	34.0	306	5.6943
No log	35.0	315	5.6849
No log	36.0	324	5.6235
No log	37.0	333	5.6985
No log	38.0	342	5.6973
No log	39.0	351	5.6863
No log	40.0	360	5.6592
No log	41.0	369	5.7277
No log	42.0	378	5.7641
No log	43.0	387	5.7648
No log	44.0	396	5.7564
No log	45.0	405	5.7573
No log	46.0	414	5.7402
No log	47.0	423	5.7205
No log	48.0	432	5.7104
No log	49.0	441	5.7145
No log	50.0	450	5.7197

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2