Training in progress, epoch 1

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: cc-by-4.0
+base_model: NbAiLab/nb-bert-base
+tags:
+- generated_from_trainer
+model-index:
+- name: nbbert_ED1
+  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. -->
+
+# nbbert_ED1
+
+This model is a fine-tuned version of [NbAiLab/nb-bert-base](https://huggingface.co/NbAiLab/nb-bert-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4147
+- F1-score: 0.8769
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1-score |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 69   | 0.7063          | 0.3425   |
+| No log        | 2.0   | 138  | 0.6562          | 0.4700   |
+| No log        | 3.0   | 207  | 0.5758          | 0.8114   |
+| No log        | 4.0   | 276  | 0.4802          | 0.8441   |
+| No log        | 5.0   | 345  | 0.4557          | 0.8096   |
+| No log        | 6.0   | 414  | 0.4620          | 0.8597   |
+| No log        | 7.0   | 483  | 0.4147          | 0.8769   |
+| 0.4906        | 8.0   | 552  | 0.5979          | 0.8442   |
+| 0.4906        | 9.0   | 621  | 0.6290          | 0.8432   |
+| 0.4906        | 10.0  | 690  | 0.5401          | 0.8443   |
+| 0.4906        | 11.0  | 759  | 0.5805          | 0.8606   |
+| 0.4906        | 12.0  | 828  | 0.6075          | 0.8688   |
+| 0.4906        | 13.0  | 897  | 0.7802          | 0.8436   |
+| 0.4906        | 14.0  | 966  | 0.7530          | 0.8432   |
+| 0.1795        | 15.0  | 1035 | 0.6979          | 0.8606   |
+| 0.1795        | 16.0  | 1104 | 0.7619          | 0.8524   |
+| 0.1795        | 17.0  | 1173 | 0.7760          | 0.8525   |
+| 0.1795        | 18.0  | 1242 | 0.8060          | 0.8525   |
+| 0.1795        | 19.0  | 1311 | 0.8363          | 0.8525   |
+| 0.1795        | 20.0  | 1380 | 0.8305          | 0.8525   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "NbAiLab/nb-bert-base",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "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": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf258dfa5085ef89081136609396e0681bcef8cf2859bcb0d59e28e4e904aa0
+size 711443456

runs/Sep10_11-44-42_0159380eb78d/events.out.tfevents.1725968708.0159380eb78d.1698.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae93f9289a561ba0a63ed66529d86ae75ca05ff9554b24230684e7116ca8ecf
+size 12424

runs/Sep10_11-44-42_0159380eb78d/events.out.tfevents.1725969479.0159380eb78d.1698.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:616bb690eb2004a6441acfb36ffb3cc8ba277f4628b2ca7e41de8eaaf52cfa61
+size 411

runs/Sep12_07-42-17_22700fec697b/events.out.tfevents.1726126950.22700fec697b.1983.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5aaba41d3d4edd2db5ccbdebedfc909085e3aa087f32e47873cb3931670b26
+size 5511

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 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "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:e8a5be6e362a7d4174e13dbe753816693dbe3bdc45e43ac2f3d8a82f7264b178
+size 5304