calculator_model_test

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

• Loss: 0.1268

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: 0.001
• train_batch_size: 512
• eval_batch_size: 512
• 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
2.9786	1.0	6	2.2468
2.0116	2.0	12	1.7255
1.5628	3.0	18	1.3183
1.2273	4.0	24	1.0790
1.0219	5.0	30	0.9549
0.9147	6.0	36	0.8300
0.7993	7.0	42	0.7326
0.7256	8.0	48	0.7028
0.6677	9.0	54	0.6345
0.6369	10.0	60	0.5926
0.5883	11.0	66	0.5722
0.5506	12.0	72	0.5835
0.5504	13.0	78	0.5491
0.5232	14.0	84	0.5165
0.4977	15.0	90	0.4719
0.4754	16.0	96	0.4910
0.4706	17.0	102	0.4623
0.4659	18.0	108	0.4202
0.4186	19.0	114	0.3720
0.385	20.0	120	0.3768
0.3692	21.0	126	0.3751
0.3775	22.0	132	0.3508
0.3359	23.0	138	0.3427
0.3412	24.0	144	0.3015
0.3128	25.0	150	0.2826
0.2892	26.0	156	0.2688
0.28	27.0	162	0.2512
0.2653	28.0	168	0.2385
0.255	29.0	174	0.2275
0.249	30.0	180	0.2108
0.2316	31.0	186	0.1894
0.2184	32.0	192	0.1777
0.2057	33.0	198	0.1644
0.186	34.0	204	0.1527
0.1853	35.0	210	0.1484
0.1721	36.0	216	0.1380
0.165	37.0	222	0.1336
0.1544	38.0	228	0.1299
0.153	39.0	234	0.1288
0.158	40.0	240	0.1268

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2