metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: helsinki-opus-de-en-fine-tuned-wmt16-finetuned-src-to-trg
    results: []

helsinki-opus-de-en-fine-tuned-wmt16-finetuned-src-to-trg

This model is a fine-tuned version of mariav/helsinki-opus-de-en-fine-tuned-wmt16 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.9684
Rouge1: 63.4933
Rouge2: 31.4582
Rougel: 60.1644
Rougelsum: 60.1675
Gen Len: 23.6657
Bleu-1: 63.2918
Bleu-2: 44.1514
Bleu-3: 31.6161
Bleu-4: 23.2357
Meteor: 0.5330

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: 5
eval_batch_size: 5
seed: 7575
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len	Bleu-1	Bleu-2	Bleu-3	Bleu-4	Meteor
0.7348	1.0	1189	0.9407	61.8229	29.2612	58.4443	58.4242	25.6717	60.1910	40.8083	28.4530	20.4451	0.5069
0.7794	2.0	2378	0.8899	62.6968	30.8608	59.6691	59.7023	22.2829	60.8908	42.4421	30.4327	22.2917	0.5153
0.6464	3.0	3567	0.8960	63.399	31.2227	60.0505	60.0958	24.0847	62.5712	43.4595	30.9384	22.7195	0.5269
0.5419	4.0	4756	0.9126	63.4944	30.9818	60.1074	60.095	22.9259	61.9100	42.9890	30.6511	22.4916	0.5242
0.4666	5.0	5945	0.9249	63.9576	31.6972	60.6369	60.6662	23.708	63.1527	44.3529	32.3818	24.4188	0.5339
0.4009	6.0	7134	0.9534	63.6549	32.2835	60.3324	60.344	23.4327	63.0061	44.5392	32.1776	23.9321	0.5342
0.3523	7.0	8323	0.9684	63.4933	31.4582	60.1644	60.1675	23.6657	63.2918	44.1514	31.6161	23.2357	0.5330

Framework versions

Transformers 4.30.1
Pytorch 2.0.1+cu118
Datasets 2.12.0
Tokenizers 0.13.3