Training in progress, epoch 1

README.md

@@ -0,0 +1,74 @@
+---
+base_model: csebuetnlp/banglabert
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+model-index:
+- name: banglabert-MLTC-BB1
+  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. -->
+
+# banglabert-MLTC-BB1
+
+This model is a fine-tuned version of [csebuetnlp/banglabert](https://huggingface.co/csebuetnlp/banglabert) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3670
+- F1: 0.8559
+- Roc Auc: 0.8534
+- Accuracy: 0.5681
+- Hamming Loss: 0.1465
+- Jaccard Score: 0.7481
+- Zero One Loss: 0.4319
+
+## 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: 24
+- eval_batch_size: 24
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy | Hamming Loss | Jaccard Score | Zero One Loss |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|:------------:|:-------------:|:-------------:|
+| 0.5656        | 1.0   | 49   | 0.5135          | 0.7799 | 0.7750  | 0.4113   | 0.2249       | 0.6392        | 0.5887        |
+| 0.4157        | 2.0   | 98   | 0.4203          | 0.8359 | 0.8309  | 0.5398   | 0.1690       | 0.7181        | 0.4602        |
+| 0.3652        | 3.0   | 147  | 0.3970          | 0.8507 | 0.8431  | 0.5604   | 0.1568       | 0.7401        | 0.4396        |
+| 0.3096        | 4.0   | 196  | 0.3716          | 0.8530 | 0.8489  | 0.5656   | 0.1510       | 0.7437        | 0.4344        |
+| 0.2674        | 5.0   | 245  | 0.3693          | 0.8521 | 0.8489  | 0.5527   | 0.1510       | 0.7423        | 0.4473        |
+| 0.2709        | 6.0   | 294  | 0.3660          | 0.8532 | 0.8509  | 0.5630   | 0.1491       | 0.7439        | 0.4370        |
+| 0.2208        | 7.0   | 343  | 0.3626          | 0.8550 | 0.8534  | 0.5656   | 0.1465       | 0.7467        | 0.4344        |
+| 0.2388        | 8.0   | 392  | 0.3723          | 0.8573 | 0.8541  | 0.5630   | 0.1459       | 0.7503        | 0.4370        |
+| 0.2466        | 9.0   | 441  | 0.3685          | 0.8562 | 0.8541  | 0.5656   | 0.1459       | 0.7486        | 0.4344        |
+| 0.2187        | 10.0  | 490  | 0.3670          | 0.8559 | 0.8534  | 0.5681   | 0.1465       | 0.7481        | 0.4319        |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.1.2
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "csebuetnlp/banglabert",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Personal Attack",
+    "1": "Sexism",
+    "2": "Racism",
+    "3": "hate speech"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Personal Attack": 0,
+    "Racism": 2,
+    "Sexism": 1,
+    "hate speech": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69c16340150a17ceac46947eaf5c5967c6387dc131f90952acb5282363e4109
+size 442505824

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": false,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b28a6771b1fc70d59216db92a6d00396941dccfa7469e81c8595d6a9ebd54f3
+size 5112