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: 0.9187

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
3.3655	1.0	6	2.7160
2.3592	2.0	12	2.0612
1.8523	3.0	18	1.6791
1.6426	4.0	24	1.7810
1.7065	5.0	30	1.9239
1.6284	6.0	36	1.5635
1.5577	7.0	42	1.6272
1.5439	8.0	48	1.5541
1.5291	9.0	54	1.5177
1.4973	10.0	60	1.4948
1.4944	11.0	66	1.4746
1.4896	12.0	72	1.4857
1.4825	13.0	78	1.4613
1.4419	14.0	84	1.4153
1.4351	15.0	90	1.3887
1.3585	16.0	96	1.3681
1.3454	17.0	102	1.3402
1.3419	18.0	108	1.3145
1.2937	19.0	114	1.3013
1.3193	20.0	120	1.3074
1.2909	21.0	126	1.2146
1.2114	22.0	132	1.1740
1.1971	23.0	138	1.1854
1.175	24.0	144	1.2008
1.1643	25.0	150	1.0863
1.1425	26.0	156	1.1085
1.1197	27.0	162	1.0871
1.0919	28.0	168	1.1259
1.0798	29.0	174	1.0877
1.0937	30.0	180	1.0704
1.0625	31.0	186	1.0540
1.0688	32.0	192	1.0596
1.0514	33.0	198	1.0648
1.066	34.0	204	1.0433
1.0302	35.0	210	1.0098
1.0291	36.0	216	0.9593
1.0629	37.0	222	0.9388
0.9886	38.0	228	0.9264
0.9615	39.0	234	0.9218
0.9775	40.0	240	0.9187

Framework versions

• Transformers 4.45.0
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.20.3