init

README.md

@@ -1,3 +1,95 @@
----
-license: mit
----
+---
+tags:
+- generated_from_trainer
+datasets:
+- universal_dependencies
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: distilbert-final-upos
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: universal_dependencies sk_snk
+      type: universal_dependencies
+      args: sk_snk
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9771104035797263
+    - name: Recall
+      type: recall
+      value: 0.9785418821096173
+    - name: F1
+      type: f1
+      value: 0.9778256189451022
+    - name: Accuracy
+      type: accuracy
+      value: 0.9800851200513933
+---
+
+<!-- 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. -->
+
+# distilbert-final-upos
+
+This model is a fine-tuned version of [../../../../distilbert-final](https://huggingface.co/../../../../distilbert-final) on the universal_dependencies sk_snk dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1207
+- Precision: 0.9771
+- Recall: 0.9785
+- F1: 0.9778
+- Accuracy: 0.9801
+
+## 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: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 266  | 0.2168          | 0.9570    | 0.9554 | 0.9562 | 0.9610   |
+| 0.3935        | 2.0   | 532  | 0.1416          | 0.9723    | 0.9736 | 0.9730 | 0.9740   |
+| 0.3935        | 3.0   | 798  | 0.1236          | 0.9722    | 0.9735 | 0.9728 | 0.9747   |
+| 0.0664        | 4.0   | 1064 | 0.1195          | 0.9722    | 0.9741 | 0.9732 | 0.9766   |
+| 0.0664        | 5.0   | 1330 | 0.1160          | 0.9764    | 0.9772 | 0.9768 | 0.9789   |
+| 0.0377        | 6.0   | 1596 | 0.1194          | 0.9763    | 0.9776 | 0.9770 | 0.9790   |
+| 0.0377        | 7.0   | 1862 | 0.1188          | 0.9740    | 0.9755 | 0.9748 | 0.9777   |
+| 0.024         | 8.0   | 2128 | 0.1188          | 0.9762    | 0.9777 | 0.9769 | 0.9793   |
+| 0.024         | 9.0   | 2394 | 0.1207          | 0.9774    | 0.9789 | 0.9781 | 0.9802   |
+| 0.0184        | 10.0  | 2660 | 0.1207          | 0.9771    | 0.9785 | 0.9778 | 0.9801   |
+
+
+### Framework versions
+
+- Transformers 4.17.0.dev0
+- Pytorch 1.10.0
+- Datasets 1.16.1
+- Tokenizers 0.11.0

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "../../../../distilbert-final",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NOUN",
+    "1": "PUNCT",
+    "2": "ADP",
+    "3": "NUM",
+    "4": "SYM",
+    "5": "SCONJ",
+    "6": "ADJ",
+    "7": "PART",
+    "8": "DET",
+    "9": "CCONJ",
+    "10": "PROPN",
+    "11": "PRON",
+    "12": "X",
+    "13": "_",
+    "14": "ADV",
+    "15": "INTJ",
+    "16": "VERB",
+    "17": "AUX"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ADJ": 6,
+    "ADP": 2,
+    "ADV": 14,
+    "AUX": 17,
+    "CCONJ": 9,
+    "DET": 8,
+    "INTJ": 15,
+    "NOUN": 0,
+    "NUM": 3,
+    "PART": 7,
+    "PRON": 11,
+    "PROPN": 10,
+    "PUNCT": 1,
+    "SCONJ": 5,
+    "SYM": 4,
+    "VERB": 16,
+    "X": 12,
+    "_": 13
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "output_hidden_states": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0.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:e6784532c47008fbf125471cdc7f891415634ad80da4d6c52dbd879f41389802
+size 326208945

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 @@
+{"errors": "replace", "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"}, "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"}, "unk_token": {"content": "<unk>", "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"}, "add_prefix_space": true, "trim_offsets": true, "special_tokens_map_file": null, "model_max_length": 512, "name_or_path": "../../../../distilbert-final", "tokenizer_class": "RobertaTokenizer"}