End of training

README.md

@@ -1,92 +1,92 @@
----
-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: 0.641320474777448
-    - name: Recall
-      type: recall
-      value: 0.6247892074198989
-    - name: F1
-      type: f1
-      value: 0.6329469188529592
-    - name: Accuracy
-      type: accuracy
-      value: 0.9310811260297363
----
-
-<!-- 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: 0.2434
-- Precision: 0.6413
-- Recall: 0.6248
-- F1: 0.6329
-- Accuracy: 0.9311
-
-## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- num_epochs: 2
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.3551        | 1.0   | 521  | 0.2708          | 0.5957    | 0.5858 | 0.5907 | 0.9230   |
-| 0.2055        | 2.0   | 1042 | 0.2434          | 0.6413    | 0.6248 | 0.6329 | 0.9311   |
-
-
-### Framework versions
-
-- Transformers 4.46.0
-- Pytorch 2.5.0+cpu
-- Datasets 3.0.2
-- Tokenizers 0.20.1
+---
+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: 0.6296160430423087
+    - name: Recall
+      type: recall
+      value: 0.6202119971091303
+    - name: F1
+      type: f1
+      value: 0.6248786407766991
+    - name: Accuracy
+      type: accuracy
+      value: 0.9305489339527457
+---
+
+<!-- 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: 0.2451
+- Precision: 0.6296
+- Recall: 0.6202
+- F1: 0.6249
+- Accuracy: 0.9305
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.3571        | 1.0   | 521  | 0.2721          | 0.5804    | 0.5771 | 0.5787 | 0.9217   |
+| 0.203         | 2.0   | 1042 | 0.2451          | 0.6296    | 0.6202 | 0.6249 | 0.9305   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- 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 sha256:73cf7fab8e5b803930a2d2d566cfdf6d927d74f0c55ceb6a8ce5c70aad91d57b
+oid sha256:8cc0b5aac94ebd2af7064b8ead3a2edc93a2f884df50bcca6296764f1a29cbd3
 size 265491548

runs/Nov11_14-36-33_d40eef0cc704/events.out.tfevents.1731335865.d40eef0cc704.1072.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6607899d8cc1a8a234a9c706829ec45f955fd1a7705690b9238c5d3c6e6706e7
+size 5241

runs/Nov11_14-47-25_d40eef0cc704/events.out.tfevents.1731336464.d40eef0cc704.1072.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3288f6ea2a6d3566c36edbd34ba491b1cbe4294a257cc696cbdee9fda518f624
+size 6934

runs/Nov11_14-47-25_d40eef0cc704/events.out.tfevents.1731336895.d40eef0cc704.1072.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9dd8d18ff0b7625e886763a8b61bc13ff667c8235f97bd11bc17a385c5ad87e
+size 560

runs/Nov11_15-04-18_d40eef0cc704/events.out.tfevents.1731337488.d40eef0cc704.1072.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62074adc6e851a6d7cac66d409957ec47c01340475d6b5a9cb0feb893fcd4711
+size 6961

runs/Nov11_15-04-18_d40eef0cc704/events.out.tfevents.1731337776.d40eef0cc704.1072.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ef970d9422bdd9dc80fd89da9c83b70fbefaac18418d487f829660e0d827f3
+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:c1a95d483891ca2e1d2d5f557054c431944d773136d8ba105b8cfa181ca23fa4
-size 5304
+oid sha256:a16046f98ba3bf21e6d8b4679e588239388f9553d15b79141824316311248f96
+size 5240