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: 0.1169

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss
2.9502	1.0	6	2.2802
2.0549	2.0	12	1.7738
1.5997	3.0	18	1.4024
1.2779	4.0	24	1.1706
1.0815	5.0	30	1.0180
0.9888	6.0	36	0.9056
0.8501	7.0	42	0.8061
0.8250	8.0	48	0.7222
0.7338	9.0	54	0.6823
0.6561	10.0	60	0.6417
0.6298	11.0	66	0.6212
0.6047	12.0	72	0.5623
0.5525	13.0	78	0.5455
0.5400	14.0	84	0.4992
0.5045	15.0	90	0.4876
0.4888	16.0	96	0.4948
0.4609	17.0	102	0.4694
0.4535	18.0	108	0.4192
0.4206	19.0	114	0.4057
0.4170	20.0	120	0.3800
0.3543	21.0	126	0.3535
0.3753	22.0	132	0.3321
0.3173	23.0	138	0.3216
0.3158	24.0	144	0.2960
0.3168	25.0	150	0.2865
0.2720	26.0	156	0.2633
0.2552	27.0	162	0.2425
0.2640	28.0	168	0.2167
0.2276	29.0	174	0.1935
0.2228	30.0	180	0.1803
0.2011	31.0	186	0.1693
0.1959	32.0	192	0.1507
0.1897	33.0	198	0.1418
0.1649	34.0	204	0.1337
0.1770	35.0	210	0.1313
0.1466	36.0	216	0.1262
0.1632	37.0	222	0.1231
0.1553	38.0	228	0.1192
0.1453	39.0	234	0.1173
0.1475	40.0	240	0.1169

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cpu
• Datasets 4.0.0
• Tokenizers 0.22.2