Update README.md

README.md

@@ -1,13 +1,47 @@
 ---
-{}
+datasets:
+- DEplain/DEplain-APA-sent
+language:
+- de
+metrics:
+- sari
+- bleu
+- bertscore
+library_name: transformers
+base_model: google/mT5-large
+pipeline_tag: text2text-generation
 ---
-# TRAINING ARGS:
-{'per_device_train_batch_size': 16,
- 'warmup_ratio': 0.1,
- 'num_train_epochs': 1}
+# Model Card for mT5-large-trimmed_deplain-apa
 
-# OPTIMIZER ARGS:
-{'lr': 0.001, 'eps': (1e-30, 0.001), 'clip_threshold': 1.0, 'decay_rate': 0.0, 'beta1': None, 'weight_decay': 0.0, 'scale_parameter': False, 'relative_step': False, 'warmup_init': False, 'differentiable': False}
+Finetuned mT5-Model for German sentence-level text-simplification.
 
-# DEVICE:
-NVIDIA A100 80GB PCIe
+## Model Details
+
+### Model Description
+
+- **Model type:** Encoder-Decoder-Transformer
+- **Language(s) (NLP):** German
+- **Finetuned from model:** google/mT5-small
+- **Task**: Text-Simplification
+
+## Training Details
+
+### Training Data
+
+[DEplain/DEplain-APA-sent](https://huggingface.co/datasets/DEplain/DEplain-APA-sent)
+
+### Training Procedure
+
+Parameter-efficient Fine-Tuning with LoRA
+
+#### Training Hyperparameters
+* Batch Size: 16
+* Epochs: 1
+* Learning Rate: 0,001
+* Optimizer: Adafactor
+
+#### LoRA Hyperparameters
+* R: 32
+* Alpha: 64
+* Dropout:
+* Target modules: all linear layers