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: 0.7408

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
3.4176	1.0	6	2.8127
2.4296	2.0	12	2.0690
1.8443	3.0	18	1.6885
1.6666	4.0	24	1.5769
1.5906	5.0	30	1.5903
1.5582	6.0	36	1.5658
1.5621	7.0	42	1.5468
1.5217	8.0	48	1.5043
1.4893	9.0	54	1.4836
1.4929	10.0	60	1.4403
1.4309	11.0	66	1.4263
1.4353	12.0	72	1.3740
1.3626	13.0	78	1.2495
1.2713	14.0	84	1.2969
1.2557	15.0	90	1.2570
1.2188	16.0	96	1.1866
1.1469	17.0	102	1.1291
1.1023	18.0	108	1.0906
1.0688	19.0	114	1.0346
1.0314	20.0	120	1.1635
1.0971	21.0	126	1.1421
1.0944	22.0	132	0.9807
1.0208	23.0	138	1.0720
1.0365	24.0	144	0.9644
0.97	25.0	150	0.9323
0.9316	26.0	156	0.8888
0.9112	27.0	162	0.9156
0.8913	28.0	168	0.9113
0.8733	29.0	174	0.8876
0.8755	30.0	180	0.8725
0.8578	31.0	186	0.8051
0.8409	32.0	192	0.8311
0.8363	33.0	198	0.7970
0.803	34.0	204	0.7995
0.8088	35.0	210	0.7723
0.7882	36.0	216	0.7635
0.7851	37.0	222	0.7551
0.7775	38.0	228	0.7460
0.7979	39.0	234	0.7429
0.7852	40.0	240	0.7408

Framework versions

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