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_B
+  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_B
+
+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: 0.0293
+- Precision: 0.9456
+- Recall: 0.9531
+- F1: 0.9493
+- Accuracy: 0.9931
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0134        | 1.0   | 8205  | 0.0208          | 0.9466    | 0.9488 | 0.9477 | 0.9929   |
+| 0.0067        | 2.0   | 16410 | 0.0237          | 0.9453    | 0.9528 | 0.9490 | 0.9931   |
+| 0.0031        | 3.0   | 24615 | 0.0293          | 0.9456    | 0.9531 | 0.9493 | 0.9931   |
+
+
+### 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": 0.9935278438152871,
+    "test_f1": 0.9598040065909288,
+    "test_loss": 0.01882234774529934,
+    "test_precision": 0.955618874929845,
+    "test_recall": 0.9640259570576194,
+    "test_runtime": 81.9799,
+    "test_samples_per_second": 401.415,
+    "test_steps_per_second": 12.552
+}

config.json

@@ -0,0 +1,51 @@
+{
+  "_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-DIS": 9,
+    "B-LOC": 5,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-ANIM": 8,
+    "I-DIS": 10,
+    "I-LOC": 6,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "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-DIS",
+    "10": "I-DIS"
+  },
+  "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:ce3b4f7ad9da7c15ae6227b25d98d54412c5d4d6d20399ed143b0aa5017576fb
+size 260809820

runs/Dec12_12-39-24_c4d84df77466/events.out.tfevents.1702384777.c4d84df77466.1779.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd3a135bdf08664992ccd16b6da2ee29dc936b82c50f4bfb2ca6f2454ad12801
+size 14080

runs/Dec12_12-39-24_c4d84df77466/events.out.tfevents.1702389843.c4d84df77466.1779.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575caae150c2044e618a1cd03173a634b2ac4d2d6b5cc597de16581ff1048ec5
+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": 0.9935278438152871,
+    "test_f1": 0.9598040065909288,
+    "test_loss": 0.01882234774529934,
+    "test_precision": 0.955618874929845,
+    "test_recall": 0.9640259570576194,
+    "test_runtime": 81.9799,
+    "test_samples_per_second": 401.415,
+    "test_steps_per_second": 12.552
+}

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 sha256:1d482643fdfb74f2fbe5881a3377393243656172e65fb831f0b083bfe156b32b
+size 4600