initial commit

README.md

@@ -0,0 +1,98 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- wikiann_sk
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: output_dir
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: wikiann_sk
+      type: wikiann_sk
+      args: sk
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9327115256495669
+    - name: Recall
+      type: recall
+      value: 0.9470124013528749
+    - name: F1
+      type: f1
+      value: 0.9398075632132469
+    - name: Accuracy
+      type: accuracy
+      value: 0.9785228256835333
+---
+
+# output_dir
+
+This model is a fine-tuned version of [gerulata/slovakbert](https://huggingface.co/gerulata/slovakbert) on the wikiann_sk dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1600
+- Precision: 0.9327
+- Recall: 0.9470
+- F1: 0.9398
+- Accuracy: 0.9785
+
+## 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: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.2342        | 1.0   | 625  | 0.1233          | 0.8891    | 0.9076 | 0.8982 | 0.9667   |
+| 0.1114        | 2.0   | 1250 | 0.1079          | 0.9118    | 0.9269 | 0.9193 | 0.9725   |
+| 0.0817        | 3.0   | 1875 | 0.1093          | 0.9173    | 0.9315 | 0.9243 | 0.9747   |
+| 0.0438        | 4.0   | 2500 | 0.1076          | 0.9188    | 0.9353 | 0.9270 | 0.9743   |
+| 0.028         | 5.0   | 3125 | 0.1230          | 0.9143    | 0.9387 | 0.9264 | 0.9744   |
+| 0.0256        | 6.0   | 3750 | 0.1204          | 0.9246    | 0.9423 | 0.9334 | 0.9765   |
+| 0.018         | 7.0   | 4375 | 0.1332          | 0.9292    | 0.9416 | 0.9353 | 0.9770   |
+| 0.0107        | 8.0   | 5000 | 0.1339          | 0.9280    | 0.9427 | 0.9353 | 0.9769   |
+| 0.0079        | 9.0   | 5625 | 0.1368          | 0.9326    | 0.9442 | 0.9383 | 0.9785   |
+| 0.0065        | 10.0  | 6250 | 0.1490          | 0.9284    | 0.9445 | 0.9364 | 0.9772   |
+| 0.0061        | 11.0  | 6875 | 0.1566          | 0.9328    | 0.9433 | 0.9380 | 0.9778   |
+| 0.0031        | 12.0  | 7500 | 0.1555          | 0.9339    | 0.9473 | 0.9406 | 0.9787   |
+| 0.0024        | 13.0  | 8125 | 0.1548          | 0.9349    | 0.9462 | 0.9405 | 0.9787   |
+| 0.0015        | 14.0  | 8750 | 0.1562          | 0.9330    | 0.9469 | 0.9399 | 0.9788   |
+| 0.0013        | 15.0  | 9375 | 0.1600          | 0.9327    | 0.9470 | 0.9398 | 0.9785   |
+
+
+### Framework versions
+
+- Transformers 4.13.0.dev0
+- Pytorch 1.10.0+cu113
+- Datasets 1.15.1
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "gerulata/slovakbert",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50264
+}

pytorch-model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fbd8a2479c99e55f5906e5e46438562b27e5b5ec36829d0216824b91d41d690
+size 496323313

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "model_max_length": 512, "name_or_path": "gerulata/slovakbert", "tokenizer_class": "RobertaTokenizer"}