scenario-KD-SCR-PO-CDF-EN-FROM-EN-D2_data-en-cardiff_eng_only66

This model is a fine-tuned version of haryoaw/scenario-MDBT-TCR_data-en-cardiff_eng_only on the None dataset. It achieves the following results on the evaluation set:

• Loss: 533.0406
• Accuracy: 0.3444
• F1: 0.2711

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: 8
• eval_batch_size: 32
• seed: 66
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.7391	100	631.4247	0.3302	0.2694
No log	3.4783	200	605.5723	0.3413	0.2651
No log	5.2174	300	589.1194	0.3369	0.2521
No log	6.9565	400	580.2668	0.3501	0.2633
574.1509	8.6957	500	571.8079	0.3254	0.2189
574.1509	10.4348	600	564.8586	0.3360	0.2072
574.1509	12.1739	700	559.2232	0.3417	0.2567
574.1509	13.9130	800	552.7770	0.3391	0.2289
574.1509	15.6522	900	549.6864	0.3333	0.2295
468.9151	17.3913	1000	545.1831	0.3338	0.2429
468.9151	19.1304	1100	541.3506	0.3466	0.2794
468.9151	20.8696	1200	538.9130	0.3355	0.2612
468.9151	22.6087	1300	537.2876	0.3470	0.2807
468.9151	24.3478	1400	535.7286	0.3426	0.2346
433.9469	26.0870	1500	533.7326	0.3492	0.2730
433.9469	27.8261	1600	533.2730	0.3338	0.2553
433.9469	29.5652	1700	533.0406	0.3444	0.2711

Framework versions

• Transformers 4.44.2
• Pytorch 2.1.1+cu121
• Datasets 2.14.5
• Tokenizers 0.19.1