ClaudiaRichard/mbti_models

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: sentence-transformers/all-MiniLM-L12-v2
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: all-MiniLM-L12-v2_mbti_full
+  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. -->
+
+# all-MiniLM-L12-v2_mbti_full
+
+This model is a fine-tuned version of [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6163
+- F1: 0.6302
+- Roc Auc: 0.7108
+
+## 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: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
+| No log        | 1.0   | 325  | 0.5453          | 0.4591 | 0.6226  |
+| 0.5606        | 2.0   | 651  | 0.5234          | 0.6248 | 0.7090  |
+| 0.5606        | 3.0   | 976  | 0.5217          | 0.6148 | 0.7054  |
+| 0.4918        | 4.0   | 1302 | 0.5307          | 0.5912 | 0.6932  |
+| 0.4152        | 5.0   | 1627 | 0.5459          | 0.6262 | 0.7116  |
+| 0.4152        | 6.0   | 1953 | 0.5793          | 0.6234 | 0.7087  |
+| 0.3484        | 7.0   | 2278 | 0.5958          | 0.6378 | 0.7161  |
+| 0.293         | 8.0   | 2604 | 0.6076          | 0.6405 | 0.7177  |
+| 0.293         | 9.0   | 2929 | 0.6186          | 0.6362 | 0.7143  |
+| 0.2592        | 9.98  | 3250 | 0.6262          | 0.6365 | 0.7149  |
+
+
+### Framework versions
+
+- Transformers 4.39.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "sentence-transformers/all-MiniLM-L12-v2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "I/E",
+    "1": "N/S",
+    "2": "T/F",
+    "3": "J/P"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "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": "4.39.1",
+  "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:d95ca9dc66328c6e240903f33d1ea9edf190e8210084e3b3f5b584ffef39cc68
+size 133469456

runs/Mar24_00-42-13_5f2b4ca659aa/events.out.tfevents.1711240934.5f2b4ca659aa.329.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3f943ff45b0a793e87c2624dc53639415538009bd8814087332733351443f5
+size 5275

runs/Mar24_00-43-34_5f2b4ca659aa/events.out.tfevents.1711241014.5f2b4ca659aa.329.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373c73a59a8f3250838bf3ec69373bb3f79922c5b94b4637002b298787b681e5
+size 10208

runs/Mar24_00-52-19_5f2b4ca659aa/events.out.tfevents.1711241539.5f2b4ca659aa.329.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82f3c65a2eef1a68903e8f2087ce7f15e9c9522b5b366bfba404856f7c853978
+size 4908

runs/Mar24_00-53-29_5f2b4ca659aa/events.out.tfevents.1711241609.5f2b4ca659aa.329.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a9275ff2b08b1430638a7ecff887d39e871097b81be26e8e2136f12aa5cdf8
+size 10208

runs/Mar24_00-53-29_5f2b4ca659aa/events.out.tfevents.1711242141.5f2b4ca659aa.329.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fd78f7f8b230fa6768ef2a0cac0212787efd14d835e1f8623550a25faf439a0
+size 456

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 +1,64 @@
+{
+  "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": true,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9273432df763454b82b0fc04dc87a24b1b9ff4a772c13094f19b9f1f6cfdd7ef
+size 4984