updating the repo with the fine-tuned model

README.md

@@ -0,0 +1,130 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: uwb_atcc
+  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. -->
+
+# uwb_atcc
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6191
+- Accuracy: 0.9103
+- Precision: 0.9239
+- Recall: 0.9161
+- F1: 0.9200
+- Report:               precision    recall  f1-score   support
+
+           0       0.89      0.90      0.90       463
+           1       0.92      0.92      0.92       596
+
+    accuracy                           0.91      1059
+   macro avg       0.91      0.91      0.91      1059
+weighted avg       0.91      0.91      0.91      1059
+
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 3000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Report                                                                                                                                                                                                                                                                                                                                 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
+| No log        | 3.36  | 500  | 0.2346          | 0.9207   | 0.9197    | 0.9413 | 0.9303 |               precision    recall  f1-score   support
+
+           0       0.92      0.89      0.91       463
+           1       0.92      0.94      0.93       596
+
+    accuracy                           0.92      1059
+   macro avg       0.92      0.92      0.92      1059
+weighted avg       0.92      0.92      0.92      1059
+ |
+| 0.2212        | 6.71  | 1000 | 0.3161          | 0.9046   | 0.9260    | 0.9027 | 0.9142 |               precision    recall  f1-score   support
+
+           0       0.88      0.91      0.89       463
+           1       0.93      0.90      0.91       596
+
+    accuracy                           0.90      1059
+   macro avg       0.90      0.90      0.90      1059
+weighted avg       0.91      0.90      0.90      1059
+ |
+| 0.2212        | 10.07 | 1500 | 0.4337          | 0.9065   | 0.9191    | 0.9144 | 0.9167 |               precision    recall  f1-score   support
+
+           0       0.89      0.90      0.89       463
+           1       0.92      0.91      0.92       596
+
+    accuracy                           0.91      1059
+   macro avg       0.90      0.91      0.91      1059
+weighted avg       0.91      0.91      0.91      1059
+ |
+| 0.0651        | 13.42 | 2000 | 0.4743          | 0.9178   | 0.9249    | 0.9295 | 0.9272 |               precision    recall  f1-score   support
+
+           0       0.91      0.90      0.91       463
+           1       0.92      0.93      0.93       596
+
+    accuracy                           0.92      1059
+   macro avg       0.92      0.92      0.92      1059
+weighted avg       0.92      0.92      0.92      1059
+ |
+| 0.0651        | 16.78 | 2500 | 0.5538          | 0.9103   | 0.9196    | 0.9211 | 0.9204 |               precision    recall  f1-score   support
+
+           0       0.90      0.90      0.90       463
+           1       0.92      0.92      0.92       596
+
+    accuracy                           0.91      1059
+   macro avg       0.91      0.91      0.91      1059
+weighted avg       0.91      0.91      0.91      1059
+ |
+| 0.0296        | 20.13 | 3000 | 0.6191          | 0.9103   | 0.9239    | 0.9161 | 0.9200 |               precision    recall  f1-score   support
+
+           0       0.89      0.90      0.90       463
+           1       0.92      0.92      0.92       596
+
+    accuracy                           0.91      1059
+   macro avg       0.91      0.91      0.91      1059
+weighted avg       0.91      0.91      0.91      1059
+ |
+
+
+### Framework versions
+
+- Transformers 4.24.0
+- Pytorch 1.13.0+cu117
+- Datasets 2.7.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 20.13,
+    "train_loss": 0.10527635129292806,
+    "train_runtime": 3964.4436,
+    "train_samples_per_second": 48.431,
+    "train_steps_per_second": 0.757
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "experiments/results/spk_id/bert-base-uncased/1234/uwb_atcc//",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "atco",
+    "1": "pilot"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "atco": 0,
+    "pilot": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e1125e744c982b578daf74f01675ccfefb5bc72751764b40982f3934a197a4e
+size 438005109

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 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "experiments/results/spk_id/bert-base-uncased/1234/uwb_atcc//",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 20.13,
+    "train_loss": 0.10527635129292806,
+    "train_runtime": 3964.4436,
+    "train_samples_per_second": 48.431,
+    "train_steps_per_second": 0.757
+}

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.13422818791946,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.36,
+      "eval_accuracy": 0.9206798866855525,
+      "eval_f1": 0.9303482587064678,
+      "eval_loss": 0.2345595508813858,
+      "eval_precision": 0.919672131147541,
+      "eval_recall": 0.9412751677852349,
+      "eval_report": "              precision    recall  f1-score   support\n\n           0       0.92      0.89      0.91       463\n           1       0.92      0.94      0.93       596\n\n    accuracy                           0.92      1059\n   macro avg       0.92      0.92      0.92      1059\nweighted avg       0.92      0.92      0.92      1059\n",
+      "eval_runtime": 8.0364,
+      "eval_samples_per_second": 131.775,
+      "eval_steps_per_second": 8.337,
+      "step": 500
+    },
+    {
+      "epoch": 6.71,
+      "learning_rate": 4e-05,
+      "loss": 0.2212,
+      "step": 1000
+    },
+    {
+      "epoch": 6.71,
+      "eval_accuracy": 0.9046270066100094,
+      "eval_f1": 0.9141886151231945,
+      "eval_loss": 0.31608325242996216,
+      "eval_precision": 0.9259896729776248,
+      "eval_recall": 0.9026845637583892,
+      "eval_report": "              precision    recall  f1-score   support\n\n           0       0.88      0.91      0.89       463\n           1       0.93      0.90      0.91       596\n\n    accuracy                           0.90      1059\n   macro avg       0.90      0.90      0.90      1059\nweighted avg       0.91      0.90      0.90      1059\n",
+      "eval_runtime": 8.0054,
+      "eval_samples_per_second": 132.285,
+      "eval_steps_per_second": 8.369,
+      "step": 1000
+    },
+    {
+      "epoch": 10.07,
+      "eval_accuracy": 0.9065155807365439,
+      "eval_f1": 0.9167367535744324,
+      "eval_loss": 0.43374723196029663,
+      "eval_precision": 0.9190556492411467,
+      "eval_recall": 0.9144295302013423,
+      "eval_report": "              precision    recall  f1-score   support\n\n           0       0.89      0.90      0.89       463\n           1       0.92      0.91      0.92       596\n\n    accuracy                           0.91      1059\n   macro avg       0.90      0.91      0.91      1059\nweighted avg       0.91      0.91      0.91      1059\n",
+      "eval_runtime": 8.0154,
+      "eval_samples_per_second": 132.12,
+      "eval_steps_per_second": 8.359,
+      "step": 1500
+    },
+    {
+      "epoch": 13.42,
+      "learning_rate": 2e-05,
+      "loss": 0.0651,
+      "step": 2000
+    },
+    {
+      "epoch": 13.42,
+      "eval_accuracy": 0.9178470254957507,
+      "eval_f1": 0.9271966527196652,
+      "eval_loss": 0.47431105375289917,
+      "eval_precision": 0.9248747913188647,
+      "eval_recall": 0.9295302013422819,
+      "eval_report": "              precision    recall  f1-score   support\n\n           0       0.91      0.90      0.91       463\n           1       0.92      0.93      0.93       596\n\n    accuracy                           0.92      1059\n   macro avg       0.92      0.92      0.92      1059\nweighted avg       0.92      0.92      0.92      1059\n",
+      "eval_runtime": 8.0135,
+      "eval_samples_per_second": 132.152,
+      "eval_steps_per_second": 8.361,
+      "step": 2000
+    },
+    {
+      "epoch": 16.78,
+      "eval_accuracy": 0.9102927289896129,
+      "eval_f1": 0.9203688181056161,
+      "eval_loss": 0.5537705421447754,
+      "eval_precision": 0.9195979899497487,
+      "eval_recall": 0.9211409395973155,
+      "eval_report": "              precision    recall  f1-score   support\n\n           0       0.90      0.90      0.90       463\n           1       0.92      0.92      0.92       596\n\n    accuracy                           0.91      1059\n   macro avg       0.91      0.91      0.91      1059\nweighted avg       0.91      0.91      0.91      1059\n",
+      "eval_runtime": 8.0263,
+      "eval_samples_per_second": 131.941,
+      "eval_steps_per_second": 8.348,
+      "step": 2500
+    },
+    {
+      "epoch": 20.13,
+      "learning_rate": 0.0,
+      "loss": 0.0296,
+      "step": 3000
+    },
+    {
+      "epoch": 20.13,
+      "eval_accuracy": 0.9102927289896129,
+      "eval_f1": 0.9199663016006739,
+      "eval_loss": 0.6190621256828308,
+      "eval_precision": 0.9238578680203046,
+      "eval_recall": 0.9161073825503355,
+      "eval_report": "              precision    recall  f1-score   support\n\n           0       0.89      0.90      0.90       463\n           1       0.92      0.92      0.92       596\n\n    accuracy                           0.91      1059\n   macro avg       0.91      0.91      0.91      1059\nweighted avg       0.91      0.91      0.91      1059\n",
+      "eval_runtime": 8.0249,
+      "eval_samples_per_second": 131.965,
+      "eval_steps_per_second": 8.349,
+      "step": 3000
+    },
+    {
+      "epoch": 20.13,
+      "step": 3000,
+      "total_flos": 5.04436515336192e+16,
+      "train_loss": 0.10527635129292806,
+      "train_runtime": 3964.4436,
+      "train_samples_per_second": 48.431,
+      "train_steps_per_second": 0.757
+    }
+  ],
+  "max_steps": 3000,
+  "num_train_epochs": 21,
+  "total_flos": 5.04436515336192e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:766182c45bbaddf86724696e93caca89d45786b72cab46c2a9020624460ca63e
+size 3451