morten-j/fine_tuned_mBERT

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model: google-bert/bert-base-multilingual-cased
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- precision
+- recall
+model-index:
+- name: fine_tuned_bert
+  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_bert
+
+This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1299
+- F1: 0.8444
+- F5: 0.8373
+- Precision: 0.8636
+- Recall: 0.8261
+
+## 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
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | F5     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 33   | 0.3776          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 2.0   | 66   | 0.2996          | 0.4    | 0.3359 | 0.8       | 0.2667 |
+| No log        | 3.0   | 99   | 0.2137          | 0.7273 | 0.7534 | 0.6667    | 0.8    |
+| No log        | 4.0   | 132  | 0.2161          | 0.6429 | 0.6258 | 0.6923    | 0.6    |
+| No log        | 5.0   | 165  | 0.2367          | 0.6154 | 0.5812 | 0.7273    | 0.5333 |
+| No log        | 6.0   | 198  | 0.1997          | 0.7451 | 0.6980 | 0.9048    | 0.6333 |
+| No log        | 7.0   | 231  | 0.2023          | 0.8000 | 0.8    | 0.8       | 0.8    |
+| No log        | 8.0   | 264  | 0.2011          | 0.8070 | 0.7911 | 0.8519    | 0.7667 |
+| No log        | 9.0   | 297  | 0.2196          | 0.7857 | 0.7648 | 0.8462    | 0.7333 |
+| No log        | 10.0  | 330  | 0.2509          | 0.7667 | 0.7667 | 0.7667    | 0.7667 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.3.0a0+ebedce2
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "google-bert/bert-base-multilingual-cased",
+  "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": "4.38.2",
+  "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 sha256:6419468d93b5db3d518b2e34cd051f682e0bc5817a64e724892ec9761e909e2c
+size 711443456

runs/Apr15_15-02-52_a256-t4-04.srv.aau.dk/events.out.tfevents.1713186177.a256-t4-04.srv.aau.dk.34830.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf1886184220167cee13417465ca618af575d80ee211b379b3e7da9404c0965
+size 9894

runs/Apr15_15-02-52_a256-t4-04.srv.aau.dk/events.out.tfevents.1713186338.a256-t4-04.srv.aau.dk.34830.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4da46271cd0c945b20fff2deac4c5da9ceec8a8fd876e66333690d2d33f455
+size 506

runs/Apr16_09-06-18_nv-ai-03.srv.aau.dk/events.out.tfevents.1713251179.nv-ai-03.srv.aau.dk.3544529.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e9872c93764dd75ddf60307310d2d385d9043c1337067f284f04e91fed75e0
+size 9789

runs/Apr16_09-06-18_nv-ai-03.srv.aau.dk/events.out.tfevents.1713251251.nv-ai-03.srv.aau.dk.3544529.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9d14cad31bc8c1056e75c5f6988e028a6b59031f8bbcf6d4958f3cc9c723ca
+size 506

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": false,
+  "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 sha256:8458d0b4c7131a631dbec08b3fc5893f2e8d12cd0d4fd705696c396d91befbf2
+size 4920