Saving model gmra_google-bert/bert-base-uncased_12112024T103207

README.md

@@ -0,0 +1,95 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: bert-base-uncased_12112024T103207
+  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. -->
+
+# bert-base-uncased_12112024T103207
+
+This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4280
+- F1: 0.8755
+- Learning Rate: 0.0
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 600
+- num_epochs: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | F1     | Rate   |
+|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
+| No log        | 0.9942  | 86   | 1.7552          | 0.1858 | 0.0000 |
+| No log        | 2.0     | 173  | 1.6269          | 0.3187 | 0.0000 |
+| No log        | 2.9942  | 259  | 1.4885          | 0.4438 | 0.0000 |
+| No log        | 4.0     | 346  | 1.3478          | 0.4980 | 0.0000 |
+| No log        | 4.9942  | 432  | 1.1903          | 0.5445 | 0.0000 |
+| 1.5065        | 6.0     | 519  | 1.0219          | 0.5810 | 0.0000 |
+| 1.5065        | 6.9942  | 605  | 0.9065          | 0.6140 | 1e-05  |
+| 1.5065        | 8.0     | 692  | 0.7955          | 0.6526 | 0.0000 |
+| 1.5065        | 8.9942  | 778  | 0.6876          | 0.7032 | 0.0000 |
+| 1.5065        | 10.0    | 865  | 0.6171          | 0.7536 | 0.0000 |
+| 1.5065        | 10.9942 | 951  | 0.5734          | 0.7612 | 0.0000 |
+| 0.7171        | 12.0    | 1038 | 0.4960          | 0.8147 | 0.0000 |
+| 0.7171        | 12.9942 | 1124 | 0.4820          | 0.8358 | 0.0000 |
+| 0.7171        | 14.0    | 1211 | 0.4557          | 0.8445 | 0.0000 |
+| 0.7171        | 14.9942 | 1297 | 0.4596          | 0.8524 | 0.0000 |
+| 0.7171        | 16.0    | 1384 | 0.4299          | 0.8651 | 0.0000 |
+| 0.7171        | 16.9942 | 1470 | 0.4426          | 0.8671 | 6e-06  |
+| 0.2382        | 18.0    | 1557 | 0.4280          | 0.8755 | 0.0000 |
+| 0.2382        | 18.9942 | 1643 | 0.4517          | 0.8728 | 0.0000 |
+| 0.2382        | 20.0    | 1730 | 0.4473          | 0.8761 | 0.0000 |
+| 0.2382        | 20.9942 | 1816 | 0.4599          | 0.8798 | 0.0000 |
+| 0.2382        | 22.0    | 1903 | 0.4927          | 0.8777 | 0.0000 |
+| 0.2382        | 22.9942 | 1989 | 0.4768          | 0.8819 | 0.0000 |
+| 0.0713        | 24.0    | 2076 | 0.4970          | 0.8808 | 0.0000 |
+| 0.0713        | 24.9942 | 2162 | 0.5031          | 0.8808 | 0.0000 |
+| 0.0713        | 26.0    | 2249 | 0.4807          | 0.8845 | 7e-07  |
+| 0.0713        | 26.9942 | 2335 | 0.4959          | 0.8825 | 4e-07  |
+| 0.0713        | 28.0    | 2422 | 0.5034          | 0.8818 | 2e-07  |
+| 0.0344        | 28.9942 | 2508 | 0.5037          | 0.8818 | 0.0    |
+| 0.0344        | 29.8266 | 2580 | 0.5037          | 0.8824 | 0.0    |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "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": "acknowledgement",
+    "1": "change_request",
+    "2": "critical",
+    "3": "discussion_participation",
+    "4": "discussion_trigger",
+    "5": "reference"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "acknowledgement": 0,
+    "change_request": 1,
+    "critical": 2,
+    "discussion_participation": 3,
+    "discussion_trigger": 4,
+    "reference": 5
+  },
+  "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": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a303cc1712b64b17fbc68be34aef719c48465a13ea88e1fac84abea0534a41
+size 437970952

runs/Nov12_05-02-07_3e71c030542d/events.out.tfevents.1731387735.3e71c030542d.617.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb3cc7d7ee2b55ba33f8a0b5183988a8851ca2dadee288760717c5d9717f5c5
+size 18089

runs/Nov12_05-02-07_3e71c030542d/events.out.tfevents.1731391002.3e71c030542d.617.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb92733fda0e9e2c8939837e8f429c4c4dda32a025e355031a001f585b5b1379
+size 463

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

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab30dd2797da110549b6af87c493271819f7f06eca5a7bce49dd46e9a3bb98c0
+size 5240