Model save

README.md

@@ -0,0 +1,68 @@
+---
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: roberta-base-goodreads-bookgenres-Description_cls-6e
+  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. -->
+
+# roberta-base-goodreads-bookgenres-Description_cls-6e
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2130
+- F1: 0.6717
+
+## 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: 4e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-10
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.04
+- num_epochs: 6.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.3118        | 1.0   | 62   | 0.2885          | 0.3362 |
+| 0.2676        | 2.0   | 124  | 0.2511          | 0.4882 |
+| 0.2325        | 3.0   | 186  | 0.2272          | 0.6093 |
+| 0.2127        | 4.0   | 248  | 0.2181          | 0.6591 |
+| 0.1978        | 5.0   | 310  | 0.2140          | 0.6686 |
+| 0.1817        | 6.0   | 372  | 0.2130          | 0.6717 |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.2.0.dev20231001+cu121
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "History & Politics",
+    "1": "Health & Medicine",
+    "2": "Mystery & Thriller",
+    "3": "Arts & Design",
+    "4": "Self-Help & Wellness",
+    "5": "Sports & Recreation",
+    "6": "Non-Fiction",
+    "7": "Science Fiction & Fantasy",
+    "8": "Countries & Geography",
+    "9": "Other",
+    "10": "Nature & Environment",
+    "11": "Business & Finance",
+    "12": "Romance",
+    "13": "Philosophy & Religion",
+    "14": "Literature & Fiction",
+    "15": "Science & Technology",
+    "16": "Children & Young Adult",
+    "17": "Food & Cooking"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Arts & Design": 3,
+    "Business & Finance": 11,
+    "Children & Young Adult": 16,
+    "Countries & Geography": 8,
+    "Food & Cooking": 17,
+    "Health & Medicine": 1,
+    "History & Politics": 0,
+    "Literature & Fiction": 14,
+    "Mystery & Thriller": 2,
+    "Nature & Environment": 10,
+    "Non-Fiction": 6,
+    "Other": 9,
+    "Philosophy & Religion": 13,
+    "Romance": 12,
+    "Science & Technology": 15,
+    "Science Fiction & Fantasy": 7,
+    "Self-Help & Wellness": 4,
+    "Sports & Recreation": 5
+  },
+  "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": "4.33.3",
+  "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:e4c520c7abd073c82df56cea22a01dc256096be731a5bda3998f9f2a214a9049
+size 498662040

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "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:ffcdde489b8cb6656f86cad05fc0b45b1a8c7061c8dc94ef0ae77c80b51974bd
+size 4600