add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,76 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- null
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model_index:
+- name: roberta-base-finetuned-ner
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.9914674251177673
+---
+
+<!-- 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. -->
+
+# roberta-base-finetuned-ner
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0381
+- Precision: 0.9469
+- Recall: 0.9530
+- F1: 0.9500
+- Accuracy: 0.9915
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.1328        | 1.0   | 753  | 0.0492          | 0.9143    | 0.9308 | 0.9225 | 0.9884   |
+| 0.0301        | 2.0   | 1506 | 0.0378          | 0.9421    | 0.9474 | 0.9448 | 0.9910   |
+| 0.0185        | 3.0   | 2259 | 0.0381          | 0.9469    | 0.9530 | 0.9500 | 0.9915   |
+
+
+### Framework versions
+
+- Transformers 4.9.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "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": "4.9.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b296faa3bcfaa20a4c49af551e12468ff671d8db91750f86957ee1d5dc10ef9c
+size 496332529

runs/Aug18_03-31-20_06dc742a3f46/1629257513.6828794/events.out.tfevents.1629257513.06dc742a3f46.75.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5046c30e9261a5858a1723a7bba38df71fc9b2eb8116fbe1c64e777758d68ba
+size 4187

runs/Aug18_03-31-20_06dc742a3f46/events.out.tfevents.1629257513.06dc742a3f46.75.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050c4b6c474b6d77dc0081722519ef4d9bab83cbfd0d4736a661af19ef6ee744
+size 5740

runs/Aug18_03-31-20_06dc742a3f46/events.out.tfevents.1629257961.06dc742a3f46.75.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85213b7f3bf8a897202127f86cff825579215bf593310e99a29c8ac90477bbae
+size 512

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 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5b8b4c5ef34e933157268e5f0eb3202e3b52a32991d9d6b20edf63b55464d1
+size 2671