metadata

tags:
  - generated_from_trainer
datasets:
  - uonlp/CulturaX
metrics:
  - accuracy
model-index:
  - name: gpt2+morf_s0-30-x-2_cx-en_00000-00009_50k
    results:
      - task:
          name: Causal Language Modeling
          type: text-generation
        dataset:
          name: uonlp/CulturaX en
          type: uonlp/CulturaX
          args: en
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.4329592727693433
license: mit
language:
  - en

gpt2+morf_s0-30-x-2_cx-en_00000-00009_50k

This model is a fine-tuned version of on the uonlp/CulturaX en dataset. It achieves the following results on the evaluation set:

Loss: 2.8423
Accuracy: 0.4330

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: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.6569	0.03	10000	3.5764	0.3502
3.4317	0.06	20000	3.3581	0.3727
3.3161	0.09	30000	3.2447	0.3848
3.2463	0.13	40000	3.1761	0.3924
3.1897	0.16	50000	3.1277	0.3977
3.152	0.19	60000	3.0910	0.4022
3.1341	0.22	70000	3.0575	0.4060
3.1006	0.25	80000	3.0363	0.4084
3.0806	0.28	90000	3.0118	0.4115
3.0555	0.31	100000	2.9919	0.4138
3.038	0.34	110000	2.9786	0.4156
3.0291	0.38	120000	2.9651	0.4171
3.0182	0.41	130000	2.9499	0.4191
3.0145	0.44	140000	2.9381	0.4205
2.9891	0.47	150000	2.9272	0.4219
2.9836	0.5	160000	2.9191	0.4230
2.9717	0.53	170000	2.9103	0.4241
2.9651	0.56	180000	2.9039	0.4250
2.9615	0.59	190000	2.8971	0.4258
2.9556	0.63	200000	2.8882	0.4269
2.9452	0.66	210000	2.8825	0.4277
2.9412	0.69	220000	2.8766	0.4284
2.9402	0.72	230000	2.8722	0.4290
2.9299	0.75	240000	2.8675	0.4296
2.9302	0.78	250000	2.8623	0.4304
2.9165	0.81	260000	2.8585	0.4308
2.915	0.84	270000	2.8537	0.4314
2.92	0.88	280000	2.8506	0.4319
2.9186	0.91	290000	2.8484	0.4321
2.9084	0.94	300000	2.8458	0.4325
2.9142	0.97	310000	2.8438	0.4327

Framework versions

Transformers 4.37.1
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.1