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 +1,82 @@
+---
+license: apache-2.0
+base_model: deepmind/language-perceiver
+tags:
+- book
+- genre
+- book title
+metrics:
+- f1
+widget:
+- text: The Quantum Chip
+  example_title: Science Fiction & Fantasy
+- text: One Dollar's Journey
+  example_title: Business & Finance
+- text: Timmy The Talking Tree
+  example_title: idk fiction
+- text: The Cursed Canvas
+  example_title: Arts & Design
+- text: Hoops and Hegel
+  example_title: Philosophy & Religion
+- text: Overview of Streams in North Dakota
+  example_title: Nature
+- text: Advanced Topology
+  example_title: Non-fiction/Math
+- text: Cooking Up Love
+  example_title: Food & Cooking
+- text: Dr. Doolittle's Extraplanatary Commute
+  example_title: Science & Technology
+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. -->
+
+# language-perceiver for title-genre classification
+
+This model is a fine-tuned version of [deepmind/language-perceiver](https://huggingface.co/deepmind/language-perceiver) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2832
+- F1: 0.5108
+
+## Model description
+
+This classifies one or more **genre** labels in a **multi-label** setting for a given book **title**.
+
+The 'standard' way of interpreting the predictions is that the predicted labels for a given example are **only the ones with a greater than 50% probability.**
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.3059        | 1.0   | 62   | 0.2893          | 0.3263 |
+| 0.2879        | 2.0   | 124  | 0.2795          | 0.4290 |
+| 0.2729        | 3.0   | 186  | 0.2730          | 0.4356 |
+| 0.2606        | 4.0   | 248  | 0.2722          | 0.4590 |
+| 0.2433        | 5.0   | 310  | 0.2747          | 0.4775 |
+| 0.227         | 6.0   | 372  | 0.2777          | 0.4976 |
+| 0.207         | 7.0   | 434  | 0.2814          | 0.5088 |
+| 0.1969        | 8.0   | 496  | 0.2832          | 0.5108 |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.2.0.dev20231001+cu121
+- Datasets 2.14.5
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 8.0,
+    "eval_f1": 0.5107802874743327,
+    "eval_loss": 0.283179372549057,
+    "eval_runtime": 3.5813,
+    "eval_samples": 989,
+    "eval_samples_per_second": 276.158,
+    "eval_steps_per_second": 8.656,
+    "train_loss": 0.2570930659290283,
+    "train_runtime": 822.741,
+    "train_samples": 7914,
+    "train_samples_per_second": 76.953,
+    "train_steps_per_second": 0.603
+}

config.json

@@ -0,0 +1,86 @@
+{
+  "_label_trainable_num_channels": 1024,
+  "_name_or_path": "deepmind/language-perceiver",
+  "architectures": [
+    "PerceiverForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "audio_samples_per_frame": 1920,
+  "cross_attention_shape_for_attention": "kv",
+  "cross_attention_widening_factor": 1,
+  "d_latents": 1280,
+  "d_model": 768,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "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"
+  },
+  "image_size": 56,
+  "initializer_range": 0.02,
+  "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-12,
+  "max_position_embeddings": 2048,
+  "model_type": "perceiver",
+  "num_blocks": 1,
+  "num_cross_attention_heads": 8,
+  "num_frames": 16,
+  "num_latents": 256,
+  "num_self_attends_per_block": 26,
+  "num_self_attention_heads": 8,
+  "output_num_channels": 512,
+  "output_shape": [
+    1,
+    16,
+    224,
+    224
+  ],
+  "problem_type": "multi_label_classification",
+  "qk_channels": 256,
+  "samples_per_patch": 16,
+  "self_attention_widening_factor": 1,
+  "torch_dtype": "float32",
+  "train_size": [
+    368,
+    496
+  ],
+  "transformers_version": "4.33.3",
+  "use_query_residual": true,
+  "v_channels": 1280,
+  "vocab_size": 262
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_f1": 0.5107802874743327,
+    "eval_loss": 0.283179372549057,
+    "eval_runtime": 3.5813,
+    "eval_samples": 989,
+    "eval_samples_per_second": 276.158,
+    "eval_steps_per_second": 8.656
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9312728a4bb10a39a19e2e83c6166b9dc3ec22deee8d403c62ad974aaa094294
+size 824536032

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "bos_token": {
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[EOS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "[EOS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "PerceiverTokenizer"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "train_loss": 0.2570930659290283,
+    "train_runtime": 822.741,
+    "train_samples": 7914,
+    "train_samples_per_second": 76.953,
+    "train_steps_per_second": 0.603
+}

trainer_state.json

@@ -0,0 +1,394 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 496,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9596774193548388e-05,
+      "loss": 0.4886,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9193548387096777e-05,
+      "loss": 0.3236,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8790322580645163e-05,
+      "loss": 0.3137,
+      "step": 30
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.838709677419355e-05,
+      "loss": 0.3073,
+      "step": 40
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7983870967741936e-05,
+      "loss": 0.3068,
+      "step": 50
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.7580645161290325e-05,
+      "loss": 0.3059,
+      "step": 60
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.32627646326276466,
+      "eval_loss": 0.2893124222755432,
+      "eval_runtime": 3.6709,
+      "eval_samples_per_second": 269.418,
+      "eval_steps_per_second": 8.445,
+      "step": 62
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.717741935483871e-05,
+      "loss": 0.3038,
+      "step": 70
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.6774193548387098e-05,
+      "loss": 0.2959,
+      "step": 80
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.6370967741935487e-05,
+      "loss": 0.2953,
+      "step": 90
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.596774193548387e-05,
+      "loss": 0.2908,
+      "step": 100
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.556451612903226e-05,
+      "loss": 0.2902,
+      "step": 110
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.5161290322580646e-05,
+      "loss": 0.2879,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.429018492176387,
+      "eval_loss": 0.2794504165649414,
+      "eval_runtime": 3.6769,
+      "eval_samples_per_second": 268.977,
+      "eval_steps_per_second": 8.431,
+      "step": 124
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.4758064516129033e-05,
+      "loss": 0.2774,
+      "step": 130
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.4354838709677421e-05,
+      "loss": 0.2762,
+      "step": 140
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.3951612903225809e-05,
+      "loss": 0.2811,
+      "step": 150
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.3548387096774194e-05,
+      "loss": 0.2734,
+      "step": 160
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 1.3145161290322581e-05,
+      "loss": 0.279,
+      "step": 170
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.274193548387097e-05,
+      "loss": 0.2729,
+      "step": 180
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.4356266057664859,
+      "eval_loss": 0.27300506830215454,
+      "eval_runtime": 3.6734,
+      "eval_samples_per_second": 269.233,
+      "eval_steps_per_second": 8.439,
+      "step": 186
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 1.2338709677419355e-05,
+      "loss": 0.2722,
+      "step": 190
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 1.1935483870967743e-05,
+      "loss": 0.2605,
+      "step": 200
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 1.1532258064516131e-05,
+      "loss": 0.2564,
+      "step": 210
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 1.1129032258064516e-05,
+      "loss": 0.264,
+      "step": 220
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 1.0725806451612903e-05,
+      "loss": 0.2627,
+      "step": 230
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 1.0322580645161291e-05,
+      "loss": 0.2606,
+      "step": 240
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.458980044345898,
+      "eval_loss": 0.272247850894928,
+      "eval_runtime": 3.6724,
+      "eval_samples_per_second": 269.307,
+      "eval_steps_per_second": 8.441,
+      "step": 248
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 9.919354838709679e-06,
+      "loss": 0.2523,
+      "step": 250
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 9.516129032258065e-06,
+      "loss": 0.2437,
+      "step": 260
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 9.112903225806451e-06,
+      "loss": 0.2451,
+      "step": 270
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 8.70967741935484e-06,
+      "loss": 0.2514,
+      "step": 280
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 8.306451612903227e-06,
+      "loss": 0.2439,
+      "step": 290
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 7.903225806451613e-06,
+      "loss": 0.2378,
+      "step": 300
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.2433,
+      "step": 310
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.4775401069518716,
+      "eval_loss": 0.2747083902359009,
+      "eval_runtime": 3.674,
+      "eval_samples_per_second": 269.186,
+      "eval_steps_per_second": 8.438,
+      "step": 310
+    },
+    {
+      "epoch": 5.16,
+      "learning_rate": 7.096774193548388e-06,
+      "loss": 0.2302,
+      "step": 320
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 6.693548387096774e-06,
+      "loss": 0.2292,
+      "step": 330
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 6.290322580645162e-06,
+      "loss": 0.223,
+      "step": 340
+    },
+    {
+      "epoch": 5.65,
+      "learning_rate": 5.887096774193549e-06,
+      "loss": 0.2281,
+      "step": 350
+    },
+    {
+      "epoch": 5.81,
+      "learning_rate": 5.483870967741935e-06,
+      "loss": 0.2301,
+      "step": 360
+    },
+    {
+      "epoch": 5.97,
+      "learning_rate": 5.080645161290323e-06,
+      "loss": 0.227,
+      "step": 370
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1": 0.49764027267960154,
+      "eval_loss": 0.2776886522769928,
+      "eval_runtime": 3.6732,
+      "eval_samples_per_second": 269.25,
+      "eval_steps_per_second": 8.44,
+      "step": 372
+    },
+    {
+      "epoch": 6.13,
+      "learning_rate": 4.67741935483871e-06,
+      "loss": 0.2188,
+      "step": 380
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 4.274193548387097e-06,
+      "loss": 0.2195,
+      "step": 390
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 3.870967741935484e-06,
+      "loss": 0.2123,
+      "step": 400
+    },
+    {
+      "epoch": 6.61,
+      "learning_rate": 3.4677419354838714e-06,
+      "loss": 0.2121,
+      "step": 410
+    },
+    {
+      "epoch": 6.77,
+      "learning_rate": 3.0645161290322584e-06,
+      "loss": 0.2136,
+      "step": 420
+    },
+    {
+      "epoch": 6.94,
+      "learning_rate": 2.6612903225806454e-06,
+      "loss": 0.207,
+      "step": 430
+    },
+    {
+      "epoch": 7.0,
+      "eval_f1": 0.5087719298245615,
+      "eval_loss": 0.28140273690223694,
+      "eval_runtime": 3.6742,
+      "eval_samples_per_second": 269.173,
+      "eval_steps_per_second": 8.437,
+      "step": 434
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 2.2580645161290324e-06,
+      "loss": 0.2085,
+      "step": 440
+    },
+    {
+      "epoch": 7.26,
+      "learning_rate": 1.8548387096774196e-06,
+      "loss": 0.2071,
+      "step": 450
+    },
+    {
+      "epoch": 7.42,
+      "learning_rate": 1.4516129032258066e-06,
+      "loss": 0.2027,
+      "step": 460
+    },
+    {
+      "epoch": 7.58,
+      "learning_rate": 1.0483870967741936e-06,
+      "loss": 0.2017,
+      "step": 470
+    },
+    {
+      "epoch": 7.74,
+      "learning_rate": 6.451612903225807e-07,
+      "loss": 0.2017,
+      "step": 480
+    },
+    {
+      "epoch": 7.9,
+      "learning_rate": 2.4193548387096775e-07,
+      "loss": 0.1969,
+      "step": 490
+    },
+    {
+      "epoch": 8.0,
+      "eval_f1": 0.5107802874743327,
+      "eval_loss": 0.283179372549057,
+      "eval_runtime": 3.6742,
+      "eval_samples_per_second": 269.174,
+      "eval_steps_per_second": 8.437,
+      "step": 496
+    },
+    {
+      "epoch": 8.0,
+      "step": 496,
+      "total_flos": 0.0,
+      "train_loss": 0.2570930659290283,
+      "train_runtime": 822.741,
+      "train_samples_per_second": 76.953,
+      "train_steps_per_second": 0.603
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 496,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05febb53989d3609718ff89cfe07adccc4fe13af016c2a02e54484aa6e188756
+size 4600