ClaudiaRichard/mbti_classification_v3/

README.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+base_model: sentence-transformers/bert-base-nli-mean-tokens
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: mbti-bert-nli-finetuned_v2
+  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. -->
+
+# mbti-bert-nli-finetuned_v2
+
+This model is a fine-tuned version of [sentence-transformers/bert-base-nli-mean-tokens](https://huggingface.co/sentence-transformers/bert-base-nli-mean-tokens) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5429
+- F1: 0.5231
+- Roc Auc: 0.6546
+
+## 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: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | F1     | Roc Auc |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
+| 0.5413        | 1.0   | 5948  | 0.5385          | 0.5721 | 0.6766  |
+| 0.5046        | 2.0   | 11896 | 0.5429          | 0.5231 | 0.6546  |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "sentence-transformers/bert-base-nli-mean-tokens",
+  "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": "I/E",
+    "1": "N/S",
+    "2": "T/F",
+    "3": "J/P"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "I/E": 0,
+    "J/P": 3,
+    "N/S": 1,
+    "T/F": 2
+  },
+  "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": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "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 sha256:58ef3aa03770f35fbaf1b091c2f611136d95cda6b6068939ff2116fd002ca2df
+size 437964800

runs/Feb25_06-51-31_d45e614e63bd/events.out.tfevents.1708843901.d45e614e63bd.218.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380baf1f3fc6099bb07fa85a0a53cff23d7c11aa14c1ff4aa11c3ee643eda529
+size 14182

runs/Feb25_06-51-31_d45e614e63bd/events.out.tfevents.1708848999.d45e614e63bd.218.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec9b119fc1b789d73baaa76a8b1edc303bef75a873ddc1f12d30acf7aeb01bf0
+size 3864

runs/Feb25_06-51-31_d45e614e63bd/events.out.tfevents.1708849065.d45e614e63bd.218.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8bccfec5d54008199c02715191c4015e59d9772135f841d1c88374a9976d50
+size 3864

runs/Feb25_06-51-31_d45e614e63bd/events.out.tfevents.1708849097.d45e614e63bd.218.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cdc37eddf8c1b8921bb23d96e97fe528861c5e053b24835b705bb155f420e1b
+size 3864

runs/Feb25_06-51-31_d45e614e63bd/events.out.tfevents.1708849138.d45e614e63bd.218.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ed449046fb96efcfd5befdde5ecf4d1ce3bf463073ffa5f2bdf84ed774d8e6
+size 3864

runs/Feb25_08-19-37_d45e614e63bd/events.out.tfevents.1708849219.d45e614e63bd.218.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0eaf9f5c0b40e55c0ba3c68e8953b8ddfe84a9cc688ab809405c7a46956dcfe
+size 3864

runs/Feb25_08-19-37_d45e614e63bd/events.out.tfevents.1708849302.d45e614e63bd.218.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37d65a4a71af86dbea95fafee972e63865e9119a9500e5d97c0b13e35d8571ee
+size 3864

runs/Feb25_08-23-44_d45e614e63bd/events.out.tfevents.1708849445.d45e614e63bd.218.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993892ae53981668a47ba93027e7a3dbfd0d6175230d4bb1ace35a1d5ef00ecd
+size 3864

runs/Feb25_08-23-44_d45e614e63bd/events.out.tfevents.1708849600.d45e614e63bd.218.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d1de8f635eb293981994a2e8c1e82413f1600d72d213addbf68f9c32662ecb2
+size 3864

runs/Feb25_08-23-44_d45e614e63bd/events.out.tfevents.1708849640.d45e614e63bd.218.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0fba3cfce144f43f38bde00bffc93fda15377aa8a48b58d77f6de4cf717c73
+size 3864

runs/Feb25_08-23-44_d45e614e63bd/events.out.tfevents.1708849673.d45e614e63bd.218.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1286c507657c8062be0536b86813406bf0d53bb470587ff48a7ff2d7863f5997
+size 3864

runs/Feb25_08-23-44_d45e614e63bd/events.out.tfevents.1708850122.d45e614e63bd.218.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:983b42872f9f7400ea2a6ffb390cc7097a55f340809fb9a5dd43377bba3e8cec
+size 4846

runs/Feb25_08-23-44_d45e614e63bd/events.out.tfevents.1708850152.d45e614e63bd.218.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:031f564d0967b45db0be752802ea750be02f9d16008a652a8a7b1328687fbe70
+size 4846

runs/Feb25_08-23-44_d45e614e63bd/events.out.tfevents.1708850251.d45e614e63bd.218.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e544320aed0eae881cf01bd013ad158b2dad42ae4607cb60a54bc9d2f1c6fa
+size 7167

runs/Feb25_08-23-44_d45e614e63bd/events.out.tfevents.1708851357.d45e614e63bd.218.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cdd89e656b57257862b36d65eee400f74978b10b8f65c6e9c32bf6a05dfbcc4
+size 10757

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 +1,58 @@
+{
+  "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]",
+  "device": "cpu",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "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 sha256:677e2ad17fab37138f1296425d320385fc66509b523879d6c0ce8947b645c178
+size 4920