metadata

license: apache-2.0
tags:
  - text-classification
  - generated_from_trainer
datasets:
  - xnli
metrics:
  - accuracy
model-index:
  - name: xnli_m_bert_only_en_single_gpu
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: xnli
          type: xnli
          config: en
          split: train
          args: en
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.810843373493976

xnli_m_bert_only_en_single_gpu

This model is a fine-tuned version of bert-base-multilingual-cased on the xnli dataset. It achieves the following results on the evaluation set:

Loss: 0.5306
Accuracy: 0.8108

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8884	0.04	1000	0.7743	0.6703
0.782	0.08	2000	0.7029	0.7060
0.7479	0.12	3000	0.7366	0.6880
0.7348	0.16	4000	0.6722	0.7285
0.721	0.2	5000	0.6802	0.7237
0.7097	0.24	6000	0.6801	0.7217
0.6978	0.29	7000	0.6051	0.7643
0.6924	0.33	8000	0.6793	0.7357
0.6807	0.37	9000	0.6604	0.7502
0.6636	0.41	10000	0.6309	0.7430
0.6616	0.45	11000	0.6039	0.7490
0.6561	0.49	12000	0.6051	0.7610
0.6545	0.53	13000	0.6354	0.7454
0.644	0.57	14000	0.6064	0.7466
0.6446	0.61	15000	0.6052	0.7554
0.6414	0.65	16000	0.6365	0.7422
0.6311	0.69	17000	0.6118	0.7546
0.6187	0.73	18000	0.5973	0.7538
0.619	0.77	19000	0.5863	0.7570
0.6108	0.81	20000	0.6212	0.7490
0.6136	0.86	21000	0.5810	0.7695
0.6018	0.9	22000	0.5799	0.7731
0.6198	0.94	23000	0.5548	0.7723
0.6047	0.98	24000	0.5964	0.7622
0.5636	1.02	25000	0.5805	0.7851
0.5267	1.06	26000	0.5540	0.7795
0.5067	1.1	27000	0.5388	0.7855
0.5304	1.14	28000	0.5482	0.7799
0.5332	1.18	29000	0.5290	0.7859
0.5154	1.22	30000	0.5475	0.7799
0.524	1.26	31000	0.5305	0.7900
0.5236	1.3	32000	0.5691	0.7871
0.5154	1.34	33000	0.5642	0.7739
0.5248	1.39	34000	0.5590	0.7643
0.5077	1.43	35000	0.6064	0.7715
0.5147	1.47	36000	0.5343	0.7948
0.5041	1.51	37000	0.5375	0.7867
0.5054	1.55	38000	0.5660	0.7727
0.5053	1.59	39000	0.5479	0.7859
0.5009	1.63	40000	0.5080	0.7960
0.5081	1.67	41000	0.5139	0.7920
0.5013	1.71	42000	0.5385	0.7904
0.4972	1.75	43000	0.5257	0.7928
0.4987	1.79	44000	0.5056	0.8020
0.4863	1.83	45000	0.5030	0.8004
0.5	1.87	46000	0.5157	0.7980
0.4926	1.91	47000	0.5505	0.7924
0.4893	1.96	48000	0.5286	0.8004
0.4755	2.0	49000	0.5216	0.8036
0.3855	2.04	50000	0.6087	0.7884
0.3731	2.08	51000	0.5485	0.8064
0.3698	2.12	52000	0.5398	0.8080
0.3702	2.16	53000	0.5454	0.8
0.3688	2.2	54000	0.5512	0.8068
0.3683	2.24	55000	0.5423	0.8060
0.3704	2.28	56000	0.5383	0.8084
0.3758	2.32	57000	0.5398	0.8161
0.3781	2.36	58000	0.5481	0.8088
0.3697	2.4	59000	0.5465	0.8056
0.3706	2.44	60000	0.5488	0.7988
0.3704	2.49	61000	0.5395	0.8052
0.3648	2.53	62000	0.5463	0.8068
0.36	2.57	63000	0.5400	0.8052
0.3661	2.61	64000	0.5542	0.8068
0.3555	2.65	65000	0.5424	0.8044
0.3551	2.69	66000	0.5269	0.8124
0.3608	2.73	67000	0.5382	0.8129
0.35	2.77	68000	0.5461	0.8108
0.3457	2.81	69000	0.5477	0.8084
0.3516	2.85	70000	0.5345	0.8104
0.3499	2.89	71000	0.5344	0.8129
0.3513	2.93	72000	0.5279	0.8120
0.3442	2.97	73000	0.5306	0.8108

Framework versions

Transformers 4.24.0
Pytorch 1.13.0
Datasets 2.6.1
Tokenizers 0.13.1