initial commit

README.md

@@ -1,3 +1,88 @@
 ---
-license: mit
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: bart-base-spelling-de
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bart-base-spelling-de
+
+This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1065
+- Cer: 0.2022
+
+## Model description
+
+This is a proof of concept spelling correction model for german.
+
+## Intended uses & limitations
+
+This is work in progress, be aware that the model can produce artifacts. 
+You can test the model using the pipeline interface:
+
+```python
+from transformers import pipeline
+
+fix_spelling = pipeline("text2text-generation",model="oliverguhr/spelling-correction-german-base")
+
+print(fix_spelling("das idst ein neuZr test",max_length=2048))
+```
+
+
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 2
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Cer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 0.2803        | 0.11  | 1000  | 0.1978          | 0.9429 |
+| 0.1688        | 0.21  | 2000  | 0.1472          | 0.9426 |
+| 0.121         | 0.32  | 3000  | 0.1381          | 0.9424 |
+| 0.1722        | 0.43  | 4000  | 0.1340          | 0.9425 |
+| 0.1502        | 0.54  | 5000  | 0.1292          | 0.9423 |
+| 0.1556        | 0.64  | 6000  | 0.1260          | 0.9424 |
+| 0.1624        | 0.75  | 7000  | 0.1246          | 0.9425 |
+| 0.1337        | 0.86  | 8000  | 0.1213          | 0.9424 |
+| 0.131         | 0.96  | 9000  | 0.1195          | 0.9423 |
+| 0.1137        | 1.07  | 10000 | 0.1178          | 0.9424 |
+| 0.0958        | 1.18  | 11000 | 0.1166          | 0.9422 |
+| 0.1067        | 1.28  | 12000 | 0.1147          | 0.9422 |
+| 0.1201        | 1.39  | 13000 | 0.1135          | 0.9423 |
+| 0.1115        | 1.5   | 14000 | 0.1111          | 0.9423 |
+| 0.1284        | 1.61  | 15000 | 0.1101          | 0.9422 |
+| 0.0947        | 1.71  | 16000 | 0.1085          | 0.9422 |
+| 0.1081        | 1.82  | 17000 | 0.1073          | 0.9422 |
+| 0.099         | 1.93  | 18000 | 0.1065          | 0.9422 |
+
+
+### Framework versions
+
+- Transformers 4.19.0.dev0
+- Pytorch 1.11.0+cu102
+- Datasets 2.1.0
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_cer": 0.20216230110383845,
+    "eval_loss": 0.10652155429124832,
+    "eval_runtime": 981.2095,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 1.019,
+    "eval_steps_per_second": 0.255,
+    "train_loss": 0.16492035415392825,
+    "train_runtime": 21638.3485,
+    "train_samples": 298969,
+    "train_samples_per_second": 27.633,
+    "train_steps_per_second": 0.863
+}

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_cer": 0.20216230110383845,
+    "eval_loss": 0.10652155429124832,
+    "eval_runtime": 981.2095,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 1.019,
+    "eval_steps_per_second": 0.255
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fafd7324572f453b2f6bbb76fae25b68a38925abefc7c36e7d107d1729d7bbf
+size 557969145

runs/May23_22-15-11_redrod/1653336920.7642183/events.out.tfevents.1653336920.redrod.73588.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd5745bc0a83afd042d29ac6b6e31ec45457d8165cfa35f612448575c097f986
+size 5381

runs/May23_22-15-11_redrod/events.out.tfevents.1653336920.redrod.73588.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a78553872f86b85f91efa5cd7976d85682af10bd1ad771e15c85936022208d44
+size 304749

runs/May23_22-15-11_redrod/events.out.tfevents.1653359540.redrod.73588.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c4603dab81d2ad2a758a6dbc983c52c3433fec1f722d29331e12b29a112a0f
+size 364

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.16492035415392825,
+    "train_runtime": 21638.3485,
+    "train_samples": 298969,
+    "train_samples_per_second": 27.633,
+    "train_steps_per_second": 0.863
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86db7474590e0d9fb8ea0e8be89b19710348e2b8b5efbd7f2dad410f64876127
+size 3311