End of training

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+base_model: distilbert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: distilbert_system_A
+  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. -->
+
+# distilbert_system_A
+
+This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0547
+- Precision: 0.8996
+- Recall: 0.9132
+- F1: 0.9063
+- Accuracy: 0.9850
+
+## 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0278        | 1.0   | 8205  | 0.0434          | 0.8992    | 0.8977 | 0.8984 | 0.9843   |
+| 0.0161        | 2.0   | 16410 | 0.0477          | 0.9067    | 0.9065 | 0.9066 | 0.9851   |
+| 0.0097        | 3.0   | 24615 | 0.0547          | 0.8996    | 0.9132 | 0.9063 | 0.9850   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "test_accuracy": 0.9894704992435703,
+    "test_f1": 0.9351623370314959,
+    "test_loss": 0.02968989498913288,
+    "test_precision": 0.93195724575943,
+    "test_recall": 0.9383895496198089,
+    "test_runtime": 86.156,
+    "test_samples_per_second": 381.958,
+    "test_steps_per_second": 11.943
+}

config.json

@@ -0,0 +1,91 @@
+{
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "B-ANIM": 7,
+    "B-BIO": 9,
+    "B-CEL": 11,
+    "B-DIS": 13,
+    "B-EVE": 15,
+    "B-FOOD": 17,
+    "B-INST": 19,
+    "B-LOC": 5,
+    "B-MEDIA": 21,
+    "B-MYTH": 23,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "B-PLANT": 25,
+    "B-TIME": 27,
+    "B-VEHI": 29,
+    "I-ANIM": 8,
+    "I-BIO": 10,
+    "I-CEL": 12,
+    "I-DIS": 14,
+    "I-EVE": 16,
+    "I-FOOD": 18,
+    "I-INST": 20,
+    "I-LOC": 6,
+    "I-MEDIA": 22,
+    "I-MYTH": 24,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "I-PLANT": 26,
+    "I-TIME": 28,
+    "I-VEHI": 30,
+    "O": 0
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-ANIM",
+    "8": "I-ANIM",
+    "9": "B-BIO",
+    "10": "I-BIO",
+    "11": "B-CEL",
+    "12": "I-CEL",
+    "13": "B-DIS",
+    "14": "I-DIS",
+    "15": "B-EVE",
+    "16": "I-EVE",
+    "17": "B-FOOD",
+    "18": "I-FOOD",
+    "19": "B-INST",
+    "20": "I-INST",
+    "21": "B-MEDIA",
+    "22": "I-MEDIA",
+    "23": "B-MYTH",
+    "24": "I-MYTH",
+    "25": "B-PLANT",
+    "26": "I-PLANT",
+    "27": "B-TIME",
+    "28": "I-TIME",
+    "29": "B-VEHI",
+    "30": "I-VEHI"
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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": "4.35.2",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee975ea43c2a4ee4adb112738ae55dc4f8e88725de5b1a3ad49fc5bdbc54d4f
+size 260871348

runs/Dec12_14-48-39_a84a099a6836/events.out.tfevents.1702392525.a84a099a6836.170.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4351cb152c88983cdcd1cfde326bd0988c2d68401b850dc4e68f08a25cb2433a
+size 14836

runs/Dec12_14-48-39_a84a099a6836/events.out.tfevents.1702397678.a84a099a6836.170.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba31a8994ec988a9bf6d1da9fda1840fae0c0f0b3e07f16cc8a54cd7ee2bade6
+size 569

special_tokens_map.json

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

test_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "test_accuracy": 0.9894704992435703,
+    "test_f1": 0.9351623370314959,
+    "test_loss": 0.02968989498913288,
+    "test_precision": 0.93195724575943,
+    "test_recall": 0.9383895496198089,
+    "test_runtime": 86.156,
+    "test_samples_per_second": 381.958,
+    "test_steps_per_second": 11.943
+}

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": false,
+  "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:b5b65fa37b02c351ae9ff3be097393f68d392645a0c9e0030899908c3ae88519
+size 4600