ClaudiaRichard/mbti_models

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: sentence-transformers/paraphrase-mpnet-base-v2
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: paraphrase-mpnet-base-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. -->
+
+# paraphrase-mpnet-base-v2_mbti_full
+
+This model is a fine-tuned version of [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5933
+- F1: 0.5931
+- Roc Auc: 0.6834
+
+## 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  | 0.5755          | 0.4804 | 0.6197  |
+| 0.5774        | 2.0   | 651  | 0.5656          | 0.2262 | 0.5484  |
+| 0.5774        | 3.0   | 976  | 0.5515          | 0.3992 | 0.6041  |
+| 0.5594        | 4.0   | 1302 | 0.5487          | 0.4959 | 0.6344  |
+| 0.5352        | 5.0   | 1627 | 0.5429          | 0.5776 | 0.6775  |
+| 0.5352        | 6.0   | 1953 | 0.5557          | 0.5332 | 0.6560  |
+| 0.4996        | 7.0   | 2278 | 0.5681          | 0.5895 | 0.6837  |
+| 0.4531        | 8.0   | 2604 | 0.5793          | 0.5783 | 0.6783  |
+| 0.4531        | 9.0   | 2929 | 0.5924          | 0.5982 | 0.6882  |
+| 0.4204        | 9.98  | 3250 | 0.5970          | 0.5786 | 0.6778  |
+
+
+### Framework versions
+
+- Transformers 4.39.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-mpnet-base-v2",
+  "architectures": [
+    "MPNetForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "multi_label_classification",
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "vocab_size": 30527
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9e175071457f9c86dc34f84602f746fd150a895df057d7c6a0f9e14a75b358
+size 437981352

runs/Mar24_01-02-34_5f2b4ca659aa/events.out.tfevents.1711242155.5f2b4ca659aa.329.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73577b32de8dbed746d2c87e54c7d66dd9beee1e0455a2480d568d45f9fb2448
+size 10169

runs/Mar24_01-02-34_5f2b4ca659aa/events.out.tfevents.1711242847.5f2b4ca659aa.329.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb382a91e6bea4eb996f481ad0ff0b11cc2b1b7720032d5cdf3e50b1d7f34483
+size 456

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "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 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b162fa2aa40c2935c3cb7ccb88bdac92202222bdf305a36b3e4bd221d74380e
+size 4984