Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,98 @@
+---
+license: mit
+base_model: roberta-base
+tags:
+  - genre
+  - books
+  - multi-label
+  - dataset tools
+metrics:
+  - f1
+widget:
+  - text: >-
+      Meet Gertrude, a penguin detective who can't stand the cold. When a shrimp
+      cocktail goes missing from the Iceberg Lounge, it's up to her to solve the
+      mystery, wearing her collection of custom-made tropical turtlenecks.
+    example_title: Tropical Turtlenecks
+  - text: >-
+      Professor Wobblebottom, a notorious forgetful scientist, invents a time
+      machine but forgets how to use it. Now he is randomly popping into
+      significant historical events, ruining everything. The future of the past
+      is in the balance.
+    example_title: When I Forgot The Time
+  - text: >-
+      In a world where hugs are currency and your social credit score is
+      determined by your knack for dad jokes, John, a man who is allergic to
+      laughter, has to navigate his way without becoming broke—or
+      broken-hearted.
+    example_title: Laugh Now, Pay Later
+  - text: >-
+      Emily, a vegan vampire, is faced with an ethical dilemma when she falls
+      head over heels for a human butcher named Bob. Will she bite the forbidden
+      fruit or stick to her plant-based blood substitutes?
+    example_title: Love at First Bite... Or Not
+  - text: >-
+      Steve, a sentient self-driving car, wants to be a Broadway star. His dream
+      seems unreachable until he meets Sally, a GPS system with the voice of an
+      angel and ambitions of her own.
+    example_title: Broadway or Bust
+  - text: >-
+      Dr. Fredrick Tensor, a socially awkward computer scientist, is on a quest
+      to perfect AI companionship. However, his models keep outputting
+      cringe-worthy, melodramatic waifus that scare away even the most die-hard
+      fans of AI romance. Frustrated and lonely, Fredrick must debug his love
+      life and algorithms before it's too late.
+    example_title: Love.exe Has Stopped Working
+language:
+  - en
+pipeline_tag: text-classification
+---
+
+<!-- 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. -->
+
+# BEE-spoke-data/roberta-base-description2genre
+
+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
+
+This classifies one or more **genre** labels in a **multi-label** setting for a given book **description**.
+
+## 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

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_f1": 0.6717231571462432,
+    "eval_loss": 0.21304987370967865,
+    "eval_runtime": 3.3638,
+    "eval_samples": 989,
+    "eval_samples_per_second": 294.016,
+    "eval_steps_per_second": 4.757,
+    "train_loss": 0.2572957956662742,
+    "train_runtime": 515.2049,
+    "train_samples": 7914,
+    "train_samples_per_second": 92.165,
+    "train_steps_per_second": 0.722
+}

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
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_f1": 0.6717231571462432,
+    "eval_loss": 0.21304987370967865,
+    "eval_runtime": 3.3638,
+    "eval_samples": 989,
+    "eval_samples_per_second": 294.016,
+    "eval_steps_per_second": 4.757
+}

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>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.2572957956662742,
+    "train_runtime": 515.2049,
+    "train_samples": 7914,
+    "train_samples_per_second": 92.165,
+    "train_steps_per_second": 0.722
+}

trainer_state.json

@@ -0,0 +1,304 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 372,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.6871,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.943977591036415e-05,
+      "loss": 0.506,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.8319327731092444e-05,
+      "loss": 0.386,
+      "step": 30
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.719887955182073e-05,
+      "loss": 0.3467,
+      "step": 40
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.6078431372549025e-05,
+      "loss": 0.3235,
+      "step": 50
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.495798319327731e-05,
+      "loss": 0.3118,
+      "step": 60
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.336166194523135,
+      "eval_loss": 0.2885044813156128,
+      "eval_runtime": 3.3771,
+      "eval_samples_per_second": 292.857,
+      "eval_steps_per_second": 4.738,
+      "step": 62
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.383753501400561e-05,
+      "loss": 0.3046,
+      "step": 70
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.2717086834733894e-05,
+      "loss": 0.2906,
+      "step": 80
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.159663865546219e-05,
+      "loss": 0.2896,
+      "step": 90
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 3.047619047619048e-05,
+      "loss": 0.2826,
+      "step": 100
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 2.935574229691877e-05,
+      "loss": 0.2749,
+      "step": 110
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 2.8235294117647063e-05,
+      "loss": 0.2676,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.4882154882154882,
+      "eval_loss": 0.25112977623939514,
+      "eval_runtime": 3.3888,
+      "eval_samples_per_second": 291.842,
+      "eval_steps_per_second": 4.721,
+      "step": 124
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 2.7114845938375354e-05,
+      "loss": 0.2534,
+      "step": 130
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 2.5994397759103644e-05,
+      "loss": 0.2491,
+      "step": 140
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 2.4873949579831935e-05,
+      "loss": 0.2452,
+      "step": 150
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 2.3753501400560226e-05,
+      "loss": 0.2373,
+      "step": 160
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 2.2633053221288516e-05,
+      "loss": 0.2355,
+      "step": 170
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 2.1512605042016807e-05,
+      "loss": 0.2325,
+      "step": 180
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.6093467596178673,
+      "eval_loss": 0.22724518179893494,
+      "eval_runtime": 3.3851,
+      "eval_samples_per_second": 292.16,
+      "eval_steps_per_second": 4.727,
+      "step": 186
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 2.0392156862745097e-05,
+      "loss": 0.231,
+      "step": 190
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 1.927170868347339e-05,
+      "loss": 0.2195,
+      "step": 200
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 1.8151260504201682e-05,
+      "loss": 0.2156,
+      "step": 210
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 1.7030812324929973e-05,
+      "loss": 0.2184,
+      "step": 220
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 1.5910364145658263e-05,
+      "loss": 0.2109,
+      "step": 230
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 1.4789915966386557e-05,
+      "loss": 0.2127,
+      "step": 240
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.6591346153846154,
+      "eval_loss": 0.21806256473064423,
+      "eval_runtime": 3.3784,
+      "eval_samples_per_second": 292.738,
+      "eval_steps_per_second": 4.736,
+      "step": 248
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 1.3669467787114848e-05,
+      "loss": 0.2067,
+      "step": 250
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 1.2549019607843138e-05,
+      "loss": 0.1984,
+      "step": 260
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.1957,
+      "step": 270
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 1.030812324929972e-05,
+      "loss": 0.1967,
+      "step": 280
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 9.187675070028012e-06,
+      "loss": 0.1975,
+      "step": 290
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 8.067226890756303e-06,
+      "loss": 0.194,
+      "step": 300
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 6.946778711484594e-06,
+      "loss": 0.1978,
+      "step": 310
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.6685687113647171,
+      "eval_loss": 0.2140355408191681,
+      "eval_runtime": 3.3785,
+      "eval_samples_per_second": 292.736,
+      "eval_steps_per_second": 4.736,
+      "step": 310
+    },
+    {
+      "epoch": 5.16,
+      "learning_rate": 5.826330532212886e-06,
+      "loss": 0.1877,
+      "step": 320
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 0.1877,
+      "step": 330
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 3.585434173669468e-06,
+      "loss": 0.1803,
+      "step": 340
+    },
+    {
+      "epoch": 5.65,
+      "learning_rate": 2.4649859943977594e-06,
+      "loss": 0.1874,
+      "step": 350
+    },
+    {
+      "epoch": 5.81,
+      "learning_rate": 1.3445378151260504e-06,
+      "loss": 0.1911,
+      "step": 360
+    },
+    {
+      "epoch": 5.97,
+      "learning_rate": 2.2408963585434175e-07,
+      "loss": 0.1817,
+      "step": 370
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1": 0.6717231571462432,
+      "eval_loss": 0.21304987370967865,
+      "eval_runtime": 3.3805,
+      "eval_samples_per_second": 292.556,
+      "eval_steps_per_second": 4.733,
+      "step": 372
+    },
+    {
+      "epoch": 6.0,
+      "step": 372,
+      "total_flos": 1.2495360147628032e+16,
+      "train_loss": 0.2572957956662742,
+      "train_runtime": 515.2049,
+      "train_samples_per_second": 92.165,
+      "train_steps_per_second": 0.722
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 372,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 1.2495360147628032e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffcdde489b8cb6656f86cad05fc0b45b1a8c7061c8dc94ef0ae77c80b51974bd
+size 4600