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: 2.9524

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: 0.01
• 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
3.6485	1.0	6	3.2312
3.1316	2.0	12	2.9996
3.037	3.0	18	3.0512
3.0193	4.0	24	3.0006
2.9967	5.0	30	2.9620
2.9847	6.0	36	2.9710
2.9765	7.0	42	2.9646
2.9729	8.0	48	2.9598
2.9755	9.0	54	2.9601
2.9644	10.0	60	2.9621
2.967	11.0	66	2.9609
2.9713	12.0	72	2.9563
2.9704	13.0	78	2.9534
2.9708	14.0	84	2.9552
2.9582	15.0	90	2.9530
2.9729	16.0	96	2.9547
2.9628	17.0	102	2.9576
2.9621	18.0	108	2.9559
2.968	19.0	114	2.9524
2.9663	20.0	120	2.9556
2.9609	21.0	126	2.9534
2.9661	22.0	132	2.9523
2.9563	23.0	138	2.9593
2.9656	24.0	144	2.9551
2.9604	25.0	150	2.9534
2.9694	26.0	156	2.9525
2.9636	27.0	162	2.9522
2.9561	28.0	168	2.9535
2.9762	29.0	174	2.9548
2.962	30.0	180	2.9530
2.9537	31.0	186	2.9501
2.9592	32.0	192	2.9513
2.9695	33.0	198	2.9519
2.9664	34.0	204	2.9527
2.9594	35.0	210	2.9532
2.9582	36.0	216	2.9529
2.9718	37.0	222	2.9533
2.9563	38.0	228	2.9530
2.9599	39.0	234	2.9525
2.9615	40.0	240	2.9524

Framework versions

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