End of training

README.md

@@ -1,99 +1,92 @@
----
-license: apache-2.0
-base_model: distilbert-base-uncased
-tags:
-- generated_from_trainer
-datasets:
-- conll2002
-metrics:
-- precision
-- recall
-- f1
-- accuracy
-model-index:
-- name: distilbert-base-uncased-finetuned-ner
-  results:
-  - task:
-      name: Token Classification
-      type: token-classification
-    dataset:
-      name: conll2002
-      type: conll2002
-      config: es
-      split: validation
-      args: es
-    metrics:
-    - name: Precision
-      type: precision
-      value: 0.7348668280871671
-    - name: Recall
-      type: recall
-      value: 0.7311491206938088
-    - name: F1
-      type: f1
-      value: 0.733003260475788
-    - name: Accuracy
-      type: accuracy
-      value: 0.94996285742796
----
-
-<!-- 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-base-uncased-finetuned-ner
-
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2002 dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.2347
-- Precision: 0.7349
-- Recall: 0.7311
-- F1: 0.7330
-- Accuracy: 0.9500
-
-## 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: 10
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.3477        | 1.0   | 521  | 0.2581          | 0.6392    | 0.5888 | 0.6130 | 0.9270   |
-| 0.1883        | 2.0   | 1042 | 0.2224          | 0.6617    | 0.6644 | 0.6631 | 0.9370   |
-| 0.1339        | 3.0   | 1563 | 0.2079          | 0.7044    | 0.7021 | 0.7033 | 0.9431   |
-| 0.1039        | 4.0   | 2084 | 0.2040          | 0.7017    | 0.7221 | 0.7118 | 0.9446   |
-| 0.0835        | 5.0   | 2605 | 0.2126          | 0.7306    | 0.7166 | 0.7235 | 0.9486   |
-| 0.0647        | 6.0   | 3126 | 0.2221          | 0.7220    | 0.7198 | 0.7209 | 0.9478   |
-| 0.0536        | 7.0   | 3647 | 0.2258          | 0.7198    | 0.7244 | 0.7221 | 0.9480   |
-| 0.0443        | 8.0   | 4168 | 0.2319          | 0.7047    | 0.7334 | 0.7188 | 0.9469   |
-| 0.0375        | 9.0   | 4689 | 0.2350          | 0.7182    | 0.7315 | 0.7248 | 0.9482   |
-| 0.0349        | 10.0  | 5210 | 0.2347          | 0.7349    | 0.7311 | 0.7330 | 0.9500   |
-
-
-### Framework versions
-
-- Transformers 4.43.3
-- Pytorch 2.4.0
-- Datasets 2.20.0
-- Tokenizers 0.19.1
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- conll2002
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: distilbert-base-uncased-finetuned-ner
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: conll2002
+      type: conll2002
+      config: es
+      split: validation
+      args: es
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.6434803981811479
+    - name: Recall
+      type: recall
+      value: 0.6306913996627319
+    - name: F1
+      type: f1
+      value: 0.6370217166494313
+    - name: Accuracy
+      type: accuracy
+      value: 0.9318683268102846
+---
+
+<!-- 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-base-uncased-finetuned-ner
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2002 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2428
+- Precision: 0.6435
+- Recall: 0.6307
+- F1: 0.6370
+- Accuracy: 0.9319
+
+## 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: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.3631        | 1.0   | 521  | 0.2718          | 0.5847    | 0.5858 | 0.5852 | 0.9219   |
+| 0.2056        | 2.0   | 1042 | 0.2428          | 0.6435    | 0.6307 | 0.6370 | 0.9319   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.0.2
+- Tokenizers 0.19.1

config.json

@@ -1,46 +1,46 @@
-{
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
-  "architectures": [
-    "DistilBertForTokenClassification"
-  ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
-  "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,
-  "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
-  },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.46.0",
-  "vocab_size": 30522
-}
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "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,
+  "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
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69c2a2a4936c24f523d64acb76c708dfb5046ee9a4f2547706f8eec10db63578
+oid sha256:41cb9663a1212572b4031bc7b0e93a474cbf4de749a17597743de0a8181a1041
 size 265491548

runs/Oct31_15-11-25_689617b4c2be/events.out.tfevents.1730387494.689617b4c2be.926.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55fbfa4ce963b387db14a1358b523644e1e104fb64a70d9519602af86dfc4869
+size 5452

runs/Oct31_15-57-33_689617b4c2be/events.out.tfevents.1730390267.689617b4c2be.926.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de98b22c45d6efc478c039412dce7f19a6d88b0aece64fc57f61e501b155c496
+size 5452

runs/Oct31_16-03-43_689617b4c2be/events.out.tfevents.1730390629.689617b4c2be.926.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cec753517f056425c1dd4bc6bf6b91f9443f0c1cda475c7d9a686b47e45c91b
+size 6961

runs/Oct31_16-03-43_689617b4c2be/events.out.tfevents.1730390861.689617b4c2be.926.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:729fe31cd0665de0681fde56f59048e221c9a4f5f104e9aac857fb44c1b5aee7
+size 560

special_tokens_map.json

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

tokenizer_config.json

@@ -1,55 +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": false,
-  "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": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
-}
+{
+  "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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b672c47872089ffbe799121118fb9417f54a338c9d57802f9ce9418a5359ad
-size 5304
+oid sha256:0256419f60ea6707f88e2c0168ac3622c8b3884f47d5f12774490f810edae845
+size 5240