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: 0.7830

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
3.427	1.0	6	2.7939
2.4109	2.0	12	2.0016
1.8545	3.0	18	1.7404
1.6739	4.0	24	1.6295
1.6169	5.0	30	1.5796
1.5292	6.0	36	1.5329
1.5561	7.0	42	1.5452
1.5104	8.0	48	1.4851
1.449	9.0	54	1.4911
1.4033	10.0	60	1.5385
1.596	11.0	66	1.4041
1.4016	12.0	72	1.4326
1.3652	13.0	78	1.4192
1.3674	14.0	84	1.3686
1.3247	15.0	90	1.3393
1.2677	16.0	96	1.2822
1.2501	17.0	102	1.4161
1.2504	18.0	108	1.2305
1.2036	19.0	114	1.2746
1.19	20.0	120	1.1341
1.1239	21.0	126	1.0830
1.0561	22.0	132	1.1285
1.1156	23.0	138	1.1040
1.0666	24.0	144	1.0544
1.0425	25.0	150	0.9969
1.0004	26.0	156	0.9607
0.9737	27.0	162	0.9564
0.9604	28.0	168	0.9418
0.9737	29.0	174	0.8994
0.9149	30.0	180	0.8790
0.9073	31.0	186	0.8659
0.896	32.0	192	0.8466
0.8752	33.0	198	0.8496
0.9161	34.0	204	0.8349
0.8831	35.0	210	0.8165
0.8352	36.0	216	0.8027
0.8305	37.0	222	0.7951
0.8242	38.0	228	0.7902
0.8416	39.0	234	0.7846
0.832	40.0	240	0.7830

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2