finetuning-sentiment-model-tweet-OLDsamples

This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment-latest on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3200
• Accuracy Percentage: 0.7738
• Accuracy Number: 65.0
• F1: 0.7878
• Precision: 0.7738
• Recall: 0.7738

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: 5e-05
• train_batch_size: 32
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Percentage	Accuracy Number	F1	Precision	Recall
0.5465	1.0	11	0.5817	0.7857	66.0	0.7854	0.7857	0.7857
0.351	2.0	22	0.4817	0.7976	67.0	0.7930	0.7976	0.7976
0.1612	3.0	33	1.0279	0.75	63.0	0.7618	0.75	0.75
0.0734	4.0	44	1.0266	0.7857	66.0	0.7968	0.7857	0.7857
0.0303	5.0	55	0.8942	0.8095	68.0	0.8150	0.8095	0.8095
0.0083	6.0	66	1.1278	0.8095	68.0	0.8177	0.8095	0.8095
0.0028	7.0	77	1.2560	0.7738	65.0	0.7878	0.7738	0.7738
0.0012	8.0	88	1.2988	0.7738	65.0	0.7878	0.7738	0.7738
0.001	9.0	99	1.3170	0.7857	66.0	0.7997	0.7857	0.7857
0.001	10.0	110	1.3200	0.7738	65.0	0.7878	0.7738	0.7738

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3