Saving model gmra_google-bert/bert-base-uncased_12112024T130600

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_12112024T130600
+  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_12112024T130600
+
+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: 1.2744
+- F1: 0.4792
+- 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   | 1.8801          | 0.0859 | 0.0000 |
+| No log        | 2.0     | 173  | 1.8639          | 0.1526 | 0.0000 |
+| No log        | 2.9942  | 259  | 1.7658          | 0.3384 | 0.0000 |
+| No log        | 4.0     | 346  | 1.5763          | 0.4250 | 0.0000 |
+| No log        | 4.9942  | 432  | 1.3998          | 0.4554 | 0.0000 |
+| 1.5137        | 6.0     | 519  | 1.3179          | 0.4529 | 0.0000 |
+| 1.5137        | 6.9942  | 605  | 1.3344          | 0.4610 | 1e-05  |
+| 1.5137        | 8.0     | 692  | 1.2744          | 0.4792 | 0.0000 |
+| 1.5137        | 8.9942  | 778  | 1.3345          | 0.4778 | 0.0000 |
+| 1.5137        | 10.0    | 865  | 1.3757          | 0.4794 | 0.0000 |
+| 1.5137        | 10.9942 | 951  | 1.4471          | 0.4857 | 0.0000 |
+| 0.6472        | 12.0    | 1038 | 1.5127          | 0.4885 | 0.0000 |
+| 0.6472        | 12.9942 | 1124 | 1.6826          | 0.4786 | 0.0000 |
+| 0.6472        | 14.0    | 1211 | 1.6606          | 0.4938 | 0.0000 |
+| 0.6472        | 14.9942 | 1297 | 1.8626          | 0.4945 | 0.0000 |
+| 0.6472        | 16.0    | 1384 | 1.9157          | 0.4965 | 0.0000 |
+| 0.6472        | 16.9942 | 1470 | 1.9586          | 0.5034 | 6e-06  |
+| 0.179         | 18.0    | 1557 | 1.9809          | 0.5039 | 0.0000 |
+| 0.179         | 18.9942 | 1643 | 2.1634          | 0.5057 | 0.0000 |
+| 0.179         | 20.0    | 1730 | 2.3241          | 0.4995 | 0.0000 |
+| 0.179         | 20.9942 | 1816 | 2.3038          | 0.5037 | 0.0000 |
+| 0.179         | 22.0    | 1903 | 2.3403          | 0.5091 | 0.0000 |
+| 0.179         | 22.9942 | 1989 | 2.3770          | 0.5044 | 0.0000 |
+| 0.0501        | 24.0    | 2076 | 2.5511          | 0.4936 | 0.0000 |
+| 0.0501        | 24.9942 | 2162 | 2.5529          | 0.4976 | 0.0000 |
+| 0.0501        | 26.0    | 2249 | 2.5132          | 0.5041 | 7e-07  |
+| 0.0501        | 26.9942 | 2335 | 2.5330          | 0.5049 | 4e-07  |
+| 0.0501        | 28.0    | 2422 | 2.5368          | 0.4989 | 2e-07  |
+| 0.0248        | 28.9942 | 2508 | 2.5301          | 0.4973 | 0.0    |
+| 0.0248        | 29.8266 | 2580 | 2.5316          | 0.4973 | 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 sha256:11cc82272431a02a7d631e2f35d5d330aa5b76d064cfe8c06d0e2e86f143ad40
+size 437970952

runs/Nov12_07-36-00_76676af845b7/events.out.tfevents.1731396971.76676af845b7.236.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04052cb136f01f5a918c4dea968d1a44d2d13811c6c6a7f3f1e4c0a2aafbf94
+size 18089

runs/Nov12_07-36-00_76676af845b7/events.out.tfevents.1731399814.76676af845b7.236.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb8566155b3cb83a6effde9dcb2d622030e797d8652e4880acfed456d4cf5cc5
+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 sha256:4f68e0f7ff0bb1d723d7e68a5aecc0d30101307b9b4fc414cbda368904dd0910
+size 5240