Upload 14 files

README.md

@@ -1,3 +1,82 @@
 ---
-license: gpl-3.0
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: bart-base-spelling-nl
+  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-nl
+
+This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base).
+
+It achieves the following results on the evaluation set:
+- Loss: 0.0276
+- Cer: 0.0147
+
+## Model description
+
+This is a text-to-text fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) trained on spelling correction. It leans on the excellent work by Oliver Guhr ([github](https://github.com/oliverguhr/spelling), [huggingface](https://huggingface.co/oliverguhr/spelling-correction-english-base)). Training was performed on an AWS EC2 instance (g5.xlarge) on a single GPU in about 4 hours.
+
+## Intended uses & limitations
+
+The intended use for this model is to be a component of the [Valkuil.net](https://valkuil.net) context-sensitive spelling checker. A next version of the model will be trained on more data.
+
+## Training and evaluation data
+
+The model was trained on a Dutch dataset composed of 300,000 lines of text from three public Dutch sources, downloaded from the [Opus corpus](https://opus.nlpl.eu/):
+
+- nl-europarlv7.100k.txt
+- nl-opensubtitles2016.100k.txt
+- nl-wikipedia.100k.txt
+
+
+## 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
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Cer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 0.1617        | 0.11  | 1000  | 0.0986          | 0.9241 |
+| 0.1326        | 0.21  | 2000  | 0.0676          | 0.9240 |
+| 0.09          | 0.32  | 3000  | 0.0586          | 0.9241 |
+| 0.0891        | 0.43  | 4000  | 0.0530          | 0.9240 |
+| 0.0753        | 0.54  | 5000  | 0.0491          | 0.9239 |
+| 0.069         | 0.64  | 6000  | 0.0459          | 0.9238 |
+| 0.0615        | 0.75  | 7000  | 0.0435          | 0.9238 |
+| 0.0494        | 0.86  | 8000  | 0.0409          | 0.9237 |
+| 0.0671        | 0.97  | 9000  | 0.0388          | 0.9238 |
+| 0.0425        | 1.07  | 10000 | 0.0367          | 0.9237 |
+| 0.0394        | 1.18  | 11000 | 0.0356          | 0.9237 |
+| 0.0399        | 1.29  | 12000 | 0.0344          | 0.9236 |
+| 0.0375        | 1.4   | 13000 | 0.0333          | 0.9235 |
+| 0.0409        | 1.5   | 14000 | 0.0315          | 0.9237 |
+| 0.0291        | 1.61  | 15000 | 0.0304          | 0.9236 |
+| 0.0268        | 1.72  | 16000 | 0.0293          | 0.9236 |
+| 0.0309        | 1.83  | 17000 | 0.0284          | 0.9235 |
+| 0.0362        | 1.93  | 18000 | 0.0276          | 0.9235 |
+
+
+### Framework versions
+
+- Transformers 4.27.3
+- Pytorch 2.0.0+cu117
+- Datasets 2.10.1
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_cer": 0.014650276279943154,
+    "eval_loss": 0.02764066681265831,
+    "eval_runtime": 1893.5756,
+    "eval_samples": 1998,
+    "eval_samples_per_second": 1.055,
+    "eval_steps_per_second": 0.264,
+    "train_loss": 0.07157236041639212,
+    "train_runtime": 20459.2275,
+    "train_samples": 297945,
+    "train_samples_per_second": 29.126,
+    "train_steps_per_second": 0.91
+}

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": "4.27.3",
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_cer": 0.014650276279943154,
+    "eval_loss": 0.02764066681265831,
+    "eval_runtime": 1893.5756,
+    "eval_samples": 1998,
+    "eval_samples_per_second": 1.055,
+    "eval_steps_per_second": 0.264
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.27.3"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ec838026fb8064635d2b995bbdaee79908374ba00bf32c931e3f2c58ae7740
+size 557971229

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.07157236041639212,
+    "train_runtime": 20459.2275,
+    "train_samples": 297945,
+    "train_samples_per_second": 29.126,
+    "train_steps_per_second": 0.91
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b1e317a1539f18fba060b518401be911171d875d5c3512b6969c88a588025d
+size 3707