ClaudiaRichard/mbti_models

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: sentence-transformers/nli-roberta-base-v2
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: nli-roberta-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. -->
+
+# nli-roberta-base-v2_mbti_full
+
+This model is a fine-tuned version of [sentence-transformers/nli-roberta-base-v2](https://huggingface.co/sentence-transformers/nli-roberta-base-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5563
+- F1: 0.5888
+- Roc Auc: 0.6803
+
+## 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  | 0.5830          | 0.4804 | 0.6197  |
+| 0.5793        | 2.0   | 651  | 0.5773          | 0.0    | 0.5     |
+| 0.5793        | 3.0   | 976  | 0.5772          | 0.0    | 0.5     |
+| 0.5783        | 4.0   | 1302 | 0.5774          | 0.0    | 0.5     |
+| 0.5772        | 5.0   | 1627 | 0.5692          | 0.5181 | 0.6399  |
+| 0.5772        | 6.0   | 1953 | 0.5563          | 0.3637 | 0.5904  |
+| 0.5587        | 7.0   | 2278 | 0.5488          | 0.5498 | 0.6651  |
+| 0.5371        | 8.0   | 2604 | 0.5513          | 0.5917 | 0.6857  |
+| 0.5371        | 9.0   | 2929 | 0.5563          | 0.6021 | 0.6906  |
+| 0.5139        | 9.98  | 3250 | 0.5622          | 0.5661 | 0.6723  |
+
+
+### Framework versions
+
+- Transformers 4.39.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "sentence-transformers/nli-roberta-base-v2",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389e7ab6d2cbd874919128f2a8cd72b1a7eeff3fda37e82114cd232622820594
+size 498618976

runs/Mar24_01-14-40_5f2b4ca659aa/events.out.tfevents.1711242881.5f2b4ca659aa.329.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4dae5cf8324f64aec8c7912598a76be9b3bd068e478143cbc5e7a20aabdb748
+size 10264

runs/Mar24_01-14-40_5f2b4ca659aa/events.out.tfevents.1711243625.5f2b4ca659aa.329.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0011dedad92afa2a47fb77ea08432372e13d967466cc9b99b46d14aaa157d02
+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 +1,57 @@
+{
+  "add_prefix_space": false,
+  "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
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f29cca1846e2d0a04db05ff92008af4c5f8119e98413d623db79ff31a6a6498
+size 4984