Training in progress, step 500

README.md

@@ -0,0 +1,94 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- conll2003
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: NER_Pittsburgh_TAA
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: conll2003
+      type: conll2003
+      config: conll2003
+      split: validation
+      args: conll2003
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9395179124281291
+    - name: Recall
+      type: recall
+      value: 0.9505537532162435
+    - name: F1
+      type: f1
+      value: 0.9450036145248291
+    - name: Accuracy
+      type: accuracy
+      value: 0.9864965764849795
+---
+
+<!-- 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. -->
+
+# NER_Pittsburgh_TAA
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the conll2003 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0805
+- Precision: 0.9395
+- Recall: 0.9506
+- F1: 0.9450
+- Accuracy: 0.9865
+
+## 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: 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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 439  | 0.0774          | 0.9424    | 0.9455 | 0.9439 | 0.9855   |
+| 0.0061        | 2.0   | 878  | 0.0741          | 0.9399    | 0.9475 | 0.9437 | 0.9863   |
+| 0.0042        | 3.0   | 1317 | 0.0784          | 0.9355    | 0.9479 | 0.9417 | 0.9855   |
+| 0.0026        | 4.0   | 1756 | 0.0789          | 0.9409    | 0.9490 | 0.9449 | 0.9865   |
+| 0.0016        | 5.0   | 2195 | 0.0805          | 0.9395    | 0.9506 | 0.9450 | 0.9865   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "bert-base-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": 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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c400f9e65518022416c893a432f83c102bd3fb05198c8dc834b04d76d2c7cb
+size 435617620

runs/Jun13_14-46-08_53e1e73118f7/events.out.tfevents.1718290024.53e1e73118f7.799.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4434b8bff8529875fc0522605d1cf083c25f2e8b247fe8b4d7d0e0598b729e
+size 11950

runs/Jun13_15-19-20_53e1e73118f7/events.out.tfevents.1718292293.53e1e73118f7.799.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbce30628f17456a0c00ec6434641c44bdde63032a8fc40493cb1700755ae0c4
+size 8783

runs/Jun13_15-41-46_53e1e73118f7/events.out.tfevents.1718293312.53e1e73118f7.799.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6bfc29a053e2647eed71fcfde2146321a3868102043e2e8440f3de22978de88
+size 5908

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 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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 sha256:8df73856452951645b6402b472e34ee2cd9bbe8738af52c6418520d7ebde9c9b
+size 5112