mehdie/fine_tuned_emBERT

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model: morten-j/Mehdie_Extended-mBERT
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- precision
+- recall
+model-index:
+- name: fine_tuned_emBERT
+  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. -->
+
+# fine_tuned_emBERT
+
+This model is a fine-tuned version of [morten-j/Mehdie_Extended-mBERT](https://huggingface.co/morten-j/Mehdie_Extended-mBERT) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2085
+- F1: 0.6316
+- F5: 0.6072
+- Precision: 0.7059
+- Recall: 0.5714
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | F5     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 38   | 0.2641          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 2.0   | 76   | 0.2444          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 3.0   | 114  | 0.2411          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 4.0   | 152  | 0.2419          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 5.0   | 190  | 0.1799          | 0.4375 | 0.3994 | 0.5833    | 0.35   |
+| No log        | 6.0   | 228  | 0.2493          | 0.4444 | 0.4641 | 0.4       | 0.5    |
+| No log        | 7.0   | 266  | 0.2708          | 0.4444 | 0.4641 | 0.4       | 0.5    |
+| No log        | 8.0   | 304  | 0.2356          | 0.5517 | 0.4819 | 0.8889    | 0.4    |
+| No log        | 9.0   | 342  | 0.2139          | 0.5333 | 0.4731 | 0.8       | 0.4    |
+| No log        | 10.0  | 380  | 0.2477          | 0.4444 | 0.3754 | 0.8571    | 0.3    |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "morten-j/Mehdie_Extended-mBERT",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NO_MATCH",
+    "1": "MATCH"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "MATCH": 1,
+    "NO_MATCH": 0
+  },
+  "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": "4.38.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105879
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c292e4be3c83eea7764cf7cd851a7d2a51b94a284d204995ad625f3ec82f28a
+size 669455360

runs/May16_08-40-00_yoga/events.out.tfevents.1715841601.yoga.7230.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6be76123f5a1cc056f79eae730f08be0d40d092b8f9edb33a8846b3a12cd1864
+size 9845

runs/May16_08-40-00_yoga/events.out.tfevents.1715841688.yoga.7230.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:184a4598c95646261d529bc44352b274b1ea7a7bc0bd90624e3cba84ea22ce53
+size 554

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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:cf78b44e18668153d6ba469cc16394f3c6d1d51e64a3383c0a9cfa235df72b66
+size 4920