NER-bert-large-wnut-v1

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+mnist_test.csv filter=lfs diff=lfs merge=lfs -text
+mnist_train_small.csv filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,131 @@
+---
+license: apache-2.0
+base_model: bert-large-uncased
+tags:
+- generated_from_trainer
+datasets:
+- wnut_17
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: sample_data
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: wnut_17
+      type: wnut_17
+      config: wnut_17
+      split: validation
+      args: wnut_17
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.7290715372907154
+    - name: Recall
+      type: recall
+      value: 0.5729665071770335
+    - name: F1
+      type: f1
+      value: 0.6416610850636303
+    - name: Accuracy
+      type: accuracy
+      value: 0.9602644796236252
+---
+
+<!-- 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. -->
+
+# sample_data
+
+This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the wnut_17 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2684
+- Precision: 0.7291
+- Recall: 0.5730
+- F1: 0.6417
+- Accuracy: 0.9603
+
+## 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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.6403        | 0.12  | 25   | 0.4914          | 0.0       | 0.0    | 0.0    | 0.9205   |
+| 0.334         | 0.23  | 50   | 0.4539          | 0.0       | 0.0    | 0.0    | 0.9205   |
+| 0.2346        | 0.35  | 75   | 0.3556          | 0.4118    | 0.0419 | 0.0760 | 0.9236   |
+| 0.2352        | 0.47  | 100  | 0.2936          | 0.4337    | 0.2464 | 0.3143 | 0.9341   |
+| 0.1725        | 0.59  | 125  | 0.2898          | 0.4983    | 0.3421 | 0.4057 | 0.9372   |
+| 0.1449        | 0.7   | 150  | 0.2858          | 0.4606    | 0.3493 | 0.3973 | 0.9399   |
+| 0.1548        | 0.82  | 175  | 0.2487          | 0.5699    | 0.3900 | 0.4631 | 0.9435   |
+| 0.1429        | 0.94  | 200  | 0.3071          | 0.6888    | 0.3469 | 0.4614 | 0.9415   |
+| 0.1506        | 1.06  | 225  | 0.2252          | 0.4820    | 0.4952 | 0.4885 | 0.9465   |
+| 0.1196        | 1.17  | 250  | 0.2512          | 0.5463    | 0.4940 | 0.5188 | 0.9485   |
+| 0.1062        | 1.29  | 275  | 0.2916          | 0.6395    | 0.4605 | 0.5355 | 0.9495   |
+| 0.0983        | 1.41  | 300  | 0.2402          | 0.6199    | 0.5443 | 0.5796 | 0.9497   |
+| 0.1068        | 1.53  | 325  | 0.2470          | 0.6018    | 0.4773 | 0.5324 | 0.9504   |
+| 0.0879        | 1.64  | 350  | 0.2360          | 0.6468    | 0.5586 | 0.5995 | 0.9511   |
+| 0.0928        | 1.76  | 375  | 0.2267          | 0.6126    | 0.5467 | 0.5777 | 0.9514   |
+| 0.1045        | 1.88  | 400  | 0.2258          | 0.6934    | 0.5060 | 0.5851 | 0.9542   |
+| 0.0933        | 2.0   | 425  | 0.2403          | 0.6954    | 0.5108 | 0.5890 | 0.9547   |
+| 0.0497        | 2.11  | 450  | 0.2539          | 0.6460    | 0.5371 | 0.5865 | 0.9554   |
+| 0.0607        | 2.23  | 475  | 0.3065          | 0.7293    | 0.4737 | 0.5743 | 0.9523   |
+| 0.0857        | 2.35  | 500  | 0.2565          | 0.6770    | 0.4964 | 0.5728 | 0.9545   |
+| 0.0513        | 2.46  | 525  | 0.2569          | 0.6931    | 0.5323 | 0.6022 | 0.9569   |
+| 0.0697        | 2.58  | 550  | 0.2273          | 0.7193    | 0.5670 | 0.6341 | 0.9566   |
+| 0.0446        | 2.7   | 575  | 0.2361          | 0.6348    | 0.5634 | 0.5970 | 0.9580   |
+| 0.0498        | 2.82  | 600  | 0.2544          | 0.7109    | 0.5323 | 0.6088 | 0.9579   |
+| 0.0464        | 2.93  | 625  | 0.2576          | 0.7237    | 0.5514 | 0.6259 | 0.9589   |
+| 0.0441        | 3.05  | 650  | 0.2691          | 0.7321    | 0.5490 | 0.6275 | 0.9586   |
+| 0.0524        | 3.17  | 675  | 0.2368          | 0.6947    | 0.5825 | 0.6337 | 0.9603   |
+| 0.0335        | 3.29  | 700  | 0.2488          | 0.6991    | 0.5670 | 0.6262 | 0.9594   |
+| 0.0349        | 3.4   | 725  | 0.2564          | 0.7084    | 0.5347 | 0.6094 | 0.9580   |
+| 0.026         | 3.52  | 750  | 0.2523          | 0.7085    | 0.5610 | 0.6262 | 0.9594   |
+| 0.0314        | 3.64  | 775  | 0.2647          | 0.7335    | 0.5467 | 0.6265 | 0.9584   |
+| 0.0213        | 3.76  | 800  | 0.2551          | 0.7032    | 0.5754 | 0.6329 | 0.9603   |
+| 0.0312        | 3.87  | 825  | 0.2470          | 0.7034    | 0.5957 | 0.6451 | 0.9606   |
+| 0.0313        | 3.99  | 850  | 0.2693          | 0.7421    | 0.5610 | 0.6390 | 0.9598   |
+| 0.0243        | 4.11  | 875  | 0.2699          | 0.7345    | 0.5658 | 0.6392 | 0.9598   |
+| 0.0289        | 4.23  | 900  | 0.2535          | 0.7143    | 0.5682 | 0.6329 | 0.9603   |
+| 0.0226        | 4.34  | 925  | 0.2581          | 0.7205    | 0.5706 | 0.6368 | 0.9602   |
+| 0.0173        | 4.46  | 950  | 0.2644          | 0.7145    | 0.5718 | 0.6352 | 0.9601   |
+| 0.0139        | 4.58  | 975  | 0.2705          | 0.7164    | 0.5682 | 0.6338 | 0.9600   |
+| 0.0243        | 4.69  | 1000 | 0.2615          | 0.7116    | 0.5813 | 0.6399 | 0.9606   |
+| 0.0222        | 4.81  | 1025 | 0.2642          | 0.7229    | 0.5742 | 0.64   | 0.9606   |
+| 0.0112        | 4.93  | 1050 | 0.2684          | 0.7291    | 0.5730 | 0.6417 | 0.9603   |
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3

anscombe.json

@@ -0,0 +1,49 @@
+[
+  {"Series":"I", "X":10.0, "Y":8.04},
+  {"Series":"I", "X":8.0, "Y":6.95},
+  {"Series":"I", "X":13.0, "Y":7.58},
+  {"Series":"I", "X":9.0, "Y":8.81},
+  {"Series":"I", "X":11.0, "Y":8.33},
+  {"Series":"I", "X":14.0, "Y":9.96},
+  {"Series":"I", "X":6.0, "Y":7.24},
+  {"Series":"I", "X":4.0, "Y":4.26},
+  {"Series":"I", "X":12.0, "Y":10.84},
+  {"Series":"I", "X":7.0, "Y":4.81},
+  {"Series":"I", "X":5.0, "Y":5.68},
+
+  {"Series":"II", "X":10.0, "Y":9.14},
+  {"Series":"II", "X":8.0, "Y":8.14},
+  {"Series":"II", "X":13.0, "Y":8.74},
+  {"Series":"II", "X":9.0, "Y":8.77},
+  {"Series":"II", "X":11.0, "Y":9.26},
+  {"Series":"II", "X":14.0, "Y":8.10},
+  {"Series":"II", "X":6.0, "Y":6.13},
+  {"Series":"II", "X":4.0, "Y":3.10},
+  {"Series":"II", "X":12.0, "Y":9.13},
+  {"Series":"II", "X":7.0, "Y":7.26},
+  {"Series":"II", "X":5.0, "Y":4.74},
+
+  {"Series":"III", "X":10.0, "Y":7.46},
+  {"Series":"III", "X":8.0, "Y":6.77},
+  {"Series":"III", "X":13.0, "Y":12.74},
+  {"Series":"III", "X":9.0, "Y":7.11},
+  {"Series":"III", "X":11.0, "Y":7.81},
+  {"Series":"III", "X":14.0, "Y":8.84},
+  {"Series":"III", "X":6.0, "Y":6.08},
+  {"Series":"III", "X":4.0, "Y":5.39},
+  {"Series":"III", "X":12.0, "Y":8.15},
+  {"Series":"III", "X":7.0, "Y":6.42},
+  {"Series":"III", "X":5.0, "Y":5.73},
+
+  {"Series":"IV", "X":8.0, "Y":6.58},
+  {"Series":"IV", "X":8.0, "Y":5.76},
+  {"Series":"IV", "X":8.0, "Y":7.71},
+  {"Series":"IV", "X":8.0, "Y":8.84},
+  {"Series":"IV", "X":8.0, "Y":8.47},
+  {"Series":"IV", "X":8.0, "Y":7.04},
+  {"Series":"IV", "X":8.0, "Y":5.25},
+  {"Series":"IV", "X":19.0, "Y":12.50},
+  {"Series":"IV", "X":8.0, "Y":5.56},
+  {"Series":"IV", "X":8.0, "Y":7.91},
+  {"Series":"IV", "X":8.0, "Y":6.89}
+]

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-corporation",
+    "2": "I-corporation",
+    "3": "B-creative-work",
+    "4": "I-creative-work",
+    "5": "B-group",
+    "6": "I-group",
+    "7": "B-location",
+    "8": "I-location",
+    "9": "B-person",
+    "10": "I-person",
+    "11": "B-product",
+    "12": "I-product"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-corporation": 1,
+    "B-creative-work": 3,
+    "B-group": 5,
+    "B-location": 7,
+    "B-person": 9,
+    "B-product": 11,
+    "I-corporation": 2,
+    "I-creative-work": 4,
+    "I-group": 6,
+    "I-location": 8,
+    "I-person": 10,
+    "I-product": 12,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

mnist_test.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c292478d94ec3a01461bdfa82eb0885d262eb09e615679b2d69dedb6ad09e7
+size 18289443

mnist_train_small.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef64781aa03180f4f5ce504314f058f5d0227277df86060473d973cf43b033e
+size 36523880

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae9c83d13291be565ef89cbe180235243c8689318b96b4d9110159413b6ce0a
+size 1336556201

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df789abcb23d846539f6371973af479722c2fa03f3c133903a9334565c80156
+size 4027