q2

This model is a fine-tuned version of samhitmantrala/q1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0001

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: 70

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1	0.0032
No log	2.0	2	0.0025
No log	3.0	3	0.0020
No log	4.0	4	0.0017
No log	5.0	5	0.0014
No log	6.0	6	0.0012
No log	7.0	7	0.0010
No log	8.0	8	0.0009
No log	9.0	9	0.0007
No log	10.0	10	0.0006
No log	11.0	11	0.0006
No log	12.0	12	0.0005
No log	13.0	13	0.0004
No log	14.0	14	0.0004
No log	15.0	15	0.0003
No log	16.0	16	0.0003
No log	17.0	17	0.0003
No log	18.0	18	0.0002
No log	19.0	19	0.0002
No log	20.0	20	0.0002
No log	21.0	21	0.0002
No log	22.0	22	0.0002
No log	23.0	23	0.0002
No log	24.0	24	0.0001
No log	25.0	25	0.0001
No log	26.0	26	0.0001
No log	27.0	27	0.0001
No log	28.0	28	0.0001
No log	29.0	29	0.0001
No log	30.0	30	0.0001
No log	31.0	31	0.0001
No log	32.0	32	0.0001
No log	33.0	33	0.0001
No log	34.0	34	0.0001
No log	35.0	35	0.0001
No log	36.0	36	0.0001
No log	37.0	37	0.0001
No log	38.0	38	0.0001
No log	39.0	39	0.0001
No log	40.0	40	0.0001
No log	41.0	41	0.0001
No log	42.0	42	0.0001
No log	43.0	43	0.0001
No log	44.0	44	0.0001
No log	45.0	45	0.0001
No log	46.0	46	0.0001
No log	47.0	47	0.0001
No log	48.0	48	0.0001
No log	49.0	49	0.0001
No log	50.0	50	0.0001
No log	51.0	51	0.0001
No log	52.0	52	0.0001
No log	53.0	53	0.0001
No log	54.0	54	0.0001
No log	55.0	55	0.0001
No log	56.0	56	0.0001
No log	57.0	57	0.0001
No log	58.0	58	0.0001
No log	59.0	59	0.0001
No log	60.0	60	0.0001
No log	61.0	61	0.0001
No log	62.0	62	0.0001
No log	63.0	63	0.0001
No log	64.0	64	0.0001
No log	65.0	65	0.0001
No log	66.0	66	0.0001
No log	67.0	67	0.0001
No log	68.0	68	0.0001
No log	69.0	69	0.0001
No log	70.0	70	0.0001

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2