End of training

README.md

@@ -0,0 +1,75 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: uniBERT.distilBERT.3
+  results: []
+---
+
+<!-- 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. -->
+
+# uniBERT.distilBERT.3
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7293
+- Accuracy: (0.4772117962466488,)
+- F1: (0.4693132851587397,)
+- Precision: (0.5442146665454255,)
+- Recall: 0.4772
+
+## 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: 64
+- 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 | Accuracy               | F1                     | Precision              | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:----------------------:|:----------------------:|:------:|
+| 2.9412        | 1.0   | 210  | 2.7539          | (0.19302949061662197,) | (0.1603618689364134,)  | (0.1948027475862202,)  | 0.1930 |
+| 2.1163        | 2.0   | 420  | 2.1123          | (0.30831099195710454,) | (0.2886576454762518,)  | (0.34306886958718397,) | 0.3083 |
+| 1.5605        | 3.0   | 630  | 1.9332          | (0.35924932975871315,) | (0.3408370919837017,)  | (0.4437777540758143,)  | 0.3592 |
+| 1.2042        | 4.0   | 840  | 1.7857          | (0.4262734584450402,)  | (0.4114641689723971,)  | (0.5423496541710991,)  | 0.4263 |
+| 0.9317        | 5.0   | 1050 | 1.7584          | (0.4262734584450402,)  | (0.41517951297641825,) | (0.5270241126881486,)  | 0.4263 |
+| 0.7497        | 6.0   | 1260 | 1.7334          | (0.46380697050938335,) | (0.4616472194616382,)  | (0.5561767348377945,)  | 0.4638 |
+| 0.6484        | 7.0   | 1470 | 1.7148          | (0.48257372654155495,) | (0.47743545933365816,) | (0.5507046992541056,)  | 0.4826 |
+| 0.5396        | 8.0   | 1680 | 1.7341          | (0.47989276139410186,) | (0.4727261312495505,)  | (0.5529949943706518,)  | 0.4799 |
+| 0.4599        | 9.0   | 1890 | 1.7252          | (0.4772117962466488,)  | (0.47031578431963555,) | (0.5474190199916943,)  | 0.4772 |
+| 0.427         | 10.0  | 2100 | 1.7293          | (0.4772117962466488,)  | (0.4693132851587397,)  | (0.5442146665454255,)  | 0.4772 |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,146 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-1",
+    "2": "I-1",
+    "3": "B-2",
+    "4": "I-2",
+    "5": "B-3",
+    "6": "I-3",
+    "7": "B-4",
+    "8": "I-4",
+    "9": "B-5",
+    "10": "I-5",
+    "11": "B-6",
+    "12": "I-6",
+    "13": "B-7",
+    "14": "I-7",
+    "15": "B-8",
+    "16": "I-8",
+    "17": "B-9",
+    "18": "I-9",
+    "19": "B-10",
+    "20": "I-10",
+    "21": "B-11",
+    "22": "I-11",
+    "23": "B-12",
+    "24": "I-12",
+    "25": "B-13",
+    "26": "I-13",
+    "27": "B-14",
+    "28": "I-14",
+    "29": "B-15",
+    "30": "I-15",
+    "31": "B-16",
+    "32": "I-16",
+    "33": "B-17",
+    "34": "I-17",
+    "35": "B-18",
+    "36": "I-18",
+    "37": "B-19",
+    "38": "I-19",
+    "39": "B-20",
+    "40": "I-20",
+    "41": "B-21",
+    "42": "I-21",
+    "43": "B-22",
+    "44": "I-22",
+    "45": "B-23",
+    "46": "I-23",
+    "47": "B-24",
+    "48": "I-24",
+    "49": "B-25",
+    "50": "I-25",
+    "51": "B-26",
+    "52": "I-26",
+    "53": "B-27",
+    "54": "I-27",
+    "55": "B-28",
+    "56": "I-28",
+    "57": "B-29",
+    "58": "I-29"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-1": 1,
+    "B-10": 19,
+    "B-11": 21,
+    "B-12": 23,
+    "B-13": 25,
+    "B-14": 27,
+    "B-15": 29,
+    "B-16": 31,
+    "B-17": 33,
+    "B-18": 35,
+    "B-19": 37,
+    "B-2": 3,
+    "B-20": 39,
+    "B-21": 41,
+    "B-22": 43,
+    "B-23": 45,
+    "B-24": 47,
+    "B-25": 49,
+    "B-26": 51,
+    "B-27": 53,
+    "B-28": 55,
+    "B-29": 57,
+    "B-3": 5,
+    "B-4": 7,
+    "B-5": 9,
+    "B-6": 11,
+    "B-7": 13,
+    "B-8": 15,
+    "B-9": 17,
+    "I-1": 2,
+    "I-10": 20,
+    "I-11": 22,
+    "I-12": 24,
+    "I-13": 26,
+    "I-14": 28,
+    "I-15": 30,
+    "I-16": 32,
+    "I-17": 34,
+    "I-18": 36,
+    "I-19": 38,
+    "I-2": 4,
+    "I-20": 40,
+    "I-21": 42,
+    "I-22": 44,
+    "I-23": 46,
+    "I-24": 48,
+    "I-25": 50,
+    "I-26": 52,
+    "I-27": 54,
+    "I-28": 56,
+    "I-29": 58,
+    "I-3": 6,
+    "I-4": 8,
+    "I-5": 10,
+    "I-6": 12,
+    "I-7": 14,
+    "I-8": 16,
+    "I-9": 18,
+    "O": 0
+  },
+  "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": "4.39.3",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7daff445d7fe99591b72990488ea92eb24e2add7d7ddf69ad1aaff6aecd9e175
+size 265645356

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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf7c6d867bba75f747690845f89030974d54fff583a906720f3977ad3f0bdad5
+size 4856