framing_classification_longformer_30_augmented_multi_undersampled_second

This model is a fine-tuned version of allenai/longformer-base-4096 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3928
• Accuracy: 0.9452
• F1: 0.9479
• Precision: 0.9496
• Recall: 0.9468

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: 1
• eval_batch_size: 1
• seed: 42
• 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	Precision	Recall
0.7779	1.0	11979	0.7469	0.8671	0.8587	0.8727	0.8604
0.5767	2.0	23958	0.6461	0.9025	0.8972	0.9102	0.8975
0.4894	3.0	35937	0.5479	0.9218	0.9208	0.9254	0.9200
0.5261	4.0	47916	0.4513	0.9238	0.9238	0.9294	0.9212
0.4559	5.0	59895	0.4831	0.9225	0.9219	0.9285	0.9205
0.4335	6.0	71874	0.6019	0.9138	0.9132	0.9211	0.9123
0.4899	7.0	83853	0.4653	0.9299	0.9295	0.9356	0.9264
0.5907	8.0	95832	0.4006	0.9419	0.9437	0.9494	0.9403
0.5436	9.0	107811	0.4034	0.9472	0.9494	0.9525	0.9479
0.3722	10.0	119790	0.4336	0.9385	0.9391	0.9433	0.9386
0.443	11.0	131769	0.4519	0.9332	0.9365	0.9375	0.9363
0.3867	12.0	143748	0.4657	0.9232	0.9268	0.9242	0.9301
0.3362	13.0	155727	0.4739	0.9305	0.9336	0.9327	0.9353
0.3106	14.0	167706	0.4533	0.9399	0.9404	0.9445	0.9386
0.3265	15.0	179685	0.3928	0.9452	0.9479	0.9496	0.9468
0.2352	16.0	191664	0.4770	0.9238	0.9279	0.9251	0.9320
0.2962	17.0	203643	0.4575	0.9345	0.9383	0.9390	0.9377
0.3453	18.0	215622	0.6071	0.9152	0.9203	0.9174	0.9253
0.1919	19.0	227601	0.5484	0.9238	0.9280	0.9260	0.9313
0.1667	20.0	239580	0.4992	0.9325	0.9358	0.9359	0.9363
0.1111	21.0	251559	0.5727	0.9272	0.9319	0.9292	0.9358
0.1705	22.0	263538	0.5028	0.9345	0.9392	0.9385	0.9401
0.1745	23.0	275517	0.5244	0.9345	0.9389	0.9387	0.9394
0.1366	24.0	287496	0.5165	0.9345	0.9393	0.9370	0.9423
0.1031	25.0	299475	0.5479	0.9339	0.9382	0.9368	0.9399
0.0851	26.0	311454	0.6036	0.9345	0.9386	0.9378	0.9396
0.125	27.0	323433	0.5253	0.9385	0.9424	0.9419	0.9430
0.1193	28.0	335412	0.5650	0.9352	0.9394	0.9376	0.9415
0.067	29.0	347391	0.5818	0.9352	0.9395	0.9376	0.9418
0.0219	30.0	359370	0.5994	0.9359	0.9402	0.9385	0.9423

Framework versions

• Transformers 4.32.0.dev0
• Pytorch 2.0.1
• Datasets 2.14.4
• Tokenizers 0.13.3