sentiment-lora-r16a2d0.2-0

This model is a fine-tuned version of indolem/indobert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2895
• Accuracy: 0.8647
• Precision: 0.8352
• Recall: 0.8417
• F1: 0.8383

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: 30
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.5604	1.0	122	0.4996	0.7268	0.6671	0.6592	0.6627
0.4842	2.0	244	0.4520	0.7544	0.7169	0.7462	0.7247
0.4079	3.0	366	0.3749	0.8321	0.7963	0.8062	0.8009
0.3378	4.0	488	0.3624	0.8471	0.8184	0.8068	0.8122
0.3146	5.0	610	0.3620	0.8471	0.8130	0.8393	0.8235
0.2935	6.0	732	0.3518	0.8496	0.8158	0.8386	0.8253
0.2842	7.0	854	0.3307	0.8647	0.8346	0.8442	0.8391
0.267	8.0	976	0.3191	0.8622	0.8333	0.8350	0.8341
0.2598	9.0	1098	0.3174	0.8672	0.8393	0.8410	0.8402
0.2557	10.0	1220	0.3076	0.8647	0.8367	0.8367	0.8367
0.2341	11.0	1342	0.3144	0.8697	0.8411	0.8478	0.8443
0.2352	12.0	1464	0.3135	0.8672	0.8385	0.8435	0.8409
0.2335	13.0	1586	0.3035	0.8722	0.8445	0.8496	0.8470
0.232	14.0	1708	0.3012	0.8697	0.8404	0.8503	0.8451
0.221	15.0	1830	0.3050	0.8672	0.8372	0.8485	0.8425
0.216	16.0	1952	0.3016	0.8697	0.8399	0.8528	0.8458
0.2096	17.0	2074	0.2881	0.8697	0.8419	0.8453	0.8436
0.2184	18.0	2196	0.2966	0.8697	0.8393	0.8553	0.8465
0.2134	19.0	2318	0.2884	0.8672	0.8385	0.8435	0.8409
0.2077	20.0	2440	0.2895	0.8647	0.8352	0.8417	0.8383

Framework versions

• Transformers 4.39.3
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.15.2