floor_model

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5275

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	2	7.1063
No log	2.0	4	5.9058
No log	3.0	6	5.7194
No log	4.0	8	5.4093
No log	5.0	10	5.0095
No log	6.0	12	4.6585
No log	7.0	14	4.3100
No log	8.0	16	3.7773
No log	9.0	18	3.2896
No log	10.0	20	2.8048
No log	11.0	22	2.2923
No log	12.0	24	1.7918
No log	13.0	26	1.3847
No log	14.0	28	1.0383
No log	15.0	30	0.8697
No log	16.0	32	0.7580
No log	17.0	34	0.6656
No log	18.0	36	0.6772
No log	19.0	38	0.7125
No log	20.0	40	0.6898
No log	21.0	42	0.6570
No log	22.0	44	0.6096
No log	23.0	46	0.5863
No log	24.0	48	0.6213
No log	25.0	50	0.6869
No log	26.0	52	0.6249
No log	27.0	54	0.5709
No log	28.0	56	0.5503
No log	29.0	58	0.5259
No log	30.0	60	0.4970
No log	31.0	62	0.4952
No log	32.0	64	0.4939
No log	33.0	66	0.4870
No log	34.0	68	0.4967
No log	35.0	70	0.5093
No log	36.0	72	0.5106
No log	37.0	74	0.5250
No log	38.0	76	0.5376
No log	39.0	78	0.5508
No log	40.0	80	0.5488
No log	41.0	82	0.5445
No log	42.0	84	0.5540
No log	43.0	86	0.5534
No log	44.0	88	0.5520
No log	45.0	90	0.5393
No log	46.0	92	0.5328
No log	47.0	94	0.5280
No log	48.0	96	0.5266
No log	49.0	98	0.5274
No log	50.0	100	0.5275

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0