scenario-KD-SCR-CDF-ALL-D2_data-cardiffnlp_tweet_sentiment_multilingual_all55

This model is a fine-tuned version of haryoaw/scenario-MDBT-TCR_data-cardiffnlp_tweet_sentiment_multilingual_all on the tweet_sentiment_multilingual dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Accuracy: 0.3333
• F1: 0.1667

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: 32
• seed: 55
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.0358	1.09	500	nan	0.3333	0.1667
0.0	2.17	1000	nan	0.3333	0.1667
0.0	3.26	1500	nan	0.3333	0.1667
0.0	4.35	2000	nan	0.3333	0.1667
0.0	5.43	2500	nan	0.3333	0.1667
0.0	6.52	3000	nan	0.3333	0.1667
0.0	7.61	3500	nan	0.3333	0.1667
0.0	8.7	4000	nan	0.3333	0.1667
0.0	9.78	4500	nan	0.3333	0.1667
0.0	10.87	5000	nan	0.3333	0.1667
0.0	11.96	5500	nan	0.3333	0.1667
0.0	13.04	6000	nan	0.3333	0.1667
0.0	14.13	6500	nan	0.3333	0.1667
0.0	15.22	7000	nan	0.3333	0.1667
0.0	16.3	7500	nan	0.3333	0.1667
0.0	17.39	8000	nan	0.3333	0.1667
0.0	18.48	8500	nan	0.3333	0.1667
0.0	19.57	9000	nan	0.3333	0.1667
0.0	20.65	9500	nan	0.3333	0.1667
0.0	21.74	10000	nan	0.3333	0.1667
0.0	22.83	10500	nan	0.3333	0.1667
0.0	23.91	11000	nan	0.3333	0.1667
0.0	25.0	11500	nan	0.3333	0.1667
0.0	26.09	12000	nan	0.3333	0.1667
0.0	27.17	12500	nan	0.3333	0.1667
0.0	28.26	13000	nan	0.3333	0.1667
0.0	29.35	13500	nan	0.3333	0.1667
0.0	30.43	14000	nan	0.3333	0.1667
0.0	31.52	14500	nan	0.3333	0.1667
0.0	32.61	15000	nan	0.3333	0.1667
0.0	33.7	15500	nan	0.3333	0.1667
0.0	34.78	16000	nan	0.3333	0.1667
0.0	35.87	16500	nan	0.3333	0.1667
0.0	36.96	17000	nan	0.3333	0.1667
0.0	38.04	17500	nan	0.3333	0.1667
0.0	39.13	18000	nan	0.3333	0.1667
0.0	40.22	18500	nan	0.3333	0.1667
0.0	41.3	19000	nan	0.3333	0.1667
0.0	42.39	19500	nan	0.3333	0.1667
0.0	43.48	20000	nan	0.3333	0.1667
0.0	44.57	20500	nan	0.3333	0.1667
0.0	45.65	21000	nan	0.3333	0.1667
0.0	46.74	21500	nan	0.3333	0.1667
0.0	47.83	22000	nan	0.3333	0.1667
0.0	48.91	22500	nan	0.3333	0.1667
0.0	50.0	23000	nan	0.3333	0.1667

Framework versions

• Transformers 4.33.3
• Pytorch 2.1.1+cu121
• Datasets 2.14.5
• Tokenizers 0.13.3