amazon_rev_trained_RObert_model

This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9028
• Accuracy: 0.8049

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	47	0.4212	0.8049
No log	2.0	94	0.6644	0.7561
No log	3.0	141	1.3246	0.7317
No log	4.0	188	0.6812	0.8049
No log	5.0	235	1.2917	0.7561
No log	6.0	282	1.1877	0.8293
No log	7.0	329	1.2476	0.8049
No log	8.0	376	1.3675	0.8049
No log	9.0	423	1.4784	0.7805
No log	10.0	470	1.2681	0.8537
0.1642	11.0	517	1.9347	0.7561
0.1642	12.0	564	1.7068	0.8049
0.1642	13.0	611	2.0000	0.7561
0.1642	14.0	658	2.0884	0.7561
0.1642	15.0	705	1.4458	0.8293
0.1642	16.0	752	1.9728	0.7317
0.1642	17.0	799	1.7737	0.8049
0.1642	18.0	846	2.1893	0.7561
0.1642	19.0	893	2.1955	0.7561
0.1642	20.0	940	2.1964	0.7561
0.1642	21.0	987	2.1856	0.7561
0.0088	22.0	1034	2.1928	0.7561
0.0088	23.0	1081	2.1536	0.7561
0.0088	24.0	1128	2.1206	0.7561
0.0088	25.0	1175	2.1292	0.7561
0.0088	26.0	1222	2.2903	0.7561
0.0088	27.0	1269	2.2995	0.7561
0.0088	28.0	1316	2.2882	0.7561
0.0088	29.0	1363	2.2781	0.7561
0.0088	30.0	1410	2.3034	0.7561
0.0088	31.0	1457	2.2885	0.7561
0.0041	32.0	1504	2.0640	0.7805
0.0041	33.0	1551	2.1061	0.7805
0.0041	34.0	1598	1.6638	0.8293
0.0041	35.0	1645	1.7633	0.8049
0.0041	36.0	1692	1.7837	0.8049
0.0041	37.0	1739	1.8168	0.8049
0.0041	38.0	1786	1.8107	0.8049
0.0041	39.0	1833	1.8074	0.8049
0.0041	40.0	1880	1.8366	0.8049
0.0041	41.0	1927	1.8463	0.8049
0.0041	42.0	1974	1.8614	0.8049
0.0045	43.0	2021	1.8757	0.8049
0.0045	44.0	2068	1.8854	0.8049
0.0045	45.0	2115	1.8975	0.8049
0.0045	46.0	2162	1.8942	0.8049
0.0045	47.0	2209	1.8989	0.8049
0.0045	48.0	2256	1.9027	0.8049
0.0045	49.0	2303	1.9030	0.8049
0.0045	50.0	2350	1.9028	0.8049

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1
• Datasets 2.19.1
• Tokenizers 0.20.1