Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: albert-xxlarge-v2
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: albert-xxlarge-v2-goodreads-bookgenres-Description_cls-5e
+  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. -->
+
+# albert-xxlarge-v2-goodreads-bookgenres-Description_cls-5e
+
+This model is a fine-tuned version of [albert-xxlarge-v2](https://huggingface.co/albert-xxlarge-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1905
+- F1: 0.7058
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.2903        | 0.99  | 123  | 0.2686          | 0.4011 |
+| 0.2171        | 2.0   | 247  | 0.2168          | 0.6493 |
+| 0.1879        | 3.0   | 371  | 0.1990          | 0.6612 |
+| 0.1476        | 4.0   | 495  | 0.1879          | 0.7060 |
+| 0.1279        | 4.97  | 615  | 0.1905          | 0.7058 |
+
+
+### 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": 5.0,
+    "eval_f1": 0.46636259977194994,
+    "eval_loss": 0.25748351216316223,
+    "eval_runtime": 1.8285,
+    "eval_samples": 989,
+    "eval_samples_per_second": 540.873,
+    "eval_steps_per_second": 8.75,
+    "train_loss": 0.3167446336438579,
+    "train_runtime": 225.8975,
+    "train_samples": 7914,
+    "train_samples_per_second": 175.168,
+    "train_steps_per_second": 1.372
+}

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "albert-xxlarge-v2",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "finetuning_task": "text-classification",
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 4096,
+  "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,
+  "inner_group_num": 1,
+  "intermediate_size": 16384,
+  "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,
+  "layers_to_keep": [],
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 64,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_f1": 0.46636259977194994,
+    "eval_loss": 0.25748351216316223,
+    "eval_runtime": 1.8285,
+    "eval_samples": 989,
+    "eval_samples_per_second": 540.873,
+    "eval_steps_per_second": 8.75
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4872acdc1be4953bdedd514e63fb9e8cc84c9a52f0ab86850986bfffa62f3d
+size 890687039

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.3167446336438579,
+    "train_runtime": 225.8975,
+    "train_samples": 7914,
+    "train_samples_per_second": 175.168,
+    "train_steps_per_second": 1.372
+}

trainer_state.json

@@ -0,0 +1,259 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 310,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.935483870967742e-05,
+      "loss": 0.6525,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.870967741935484e-05,
+      "loss": 0.5089,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.806451612903226e-05,
+      "loss": 0.422,
+      "step": 30
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.741935483870968e-05,
+      "loss": 0.3803,
+      "step": 40
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.6774193548387098e-05,
+      "loss": 0.3615,
+      "step": 50
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6129032258064517e-05,
+      "loss": 0.3453,
+      "step": 60
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.2621971457019582,
+      "eval_loss": 0.3179258704185486,
+      "eval_runtime": 1.9933,
+      "eval_samples_per_second": 496.167,
+      "eval_steps_per_second": 8.027,
+      "step": 62
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.5483870967741936e-05,
+      "loss": 0.3319,
+      "step": 70
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.4838709677419357e-05,
+      "loss": 0.3196,
+      "step": 80
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.4193548387096776e-05,
+      "loss": 0.3168,
+      "step": 90
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.3548387096774194e-05,
+      "loss": 0.3119,
+      "step": 100
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.2903225806451613e-05,
+      "loss": 0.3049,
+      "step": 110
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.2258064516129034e-05,
+      "loss": 0.3017,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.37271619975639464,
+      "eval_loss": 0.2839711308479309,
+      "eval_runtime": 1.8261,
+      "eval_samples_per_second": 541.593,
+      "eval_steps_per_second": 8.762,
+      "step": 124
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.1612903225806453e-05,
+      "loss": 0.2931,
+      "step": 130
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.096774193548387e-05,
+      "loss": 0.2924,
+      "step": 140
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.0322580645161291e-05,
+      "loss": 0.2911,
+      "step": 150
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 0.2857,
+      "step": 160
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 9.03225806451613e-06,
+      "loss": 0.2855,
+      "step": 170
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 8.387096774193549e-06,
+      "loss": 0.2828,
+      "step": 180
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.4075178997613365,
+      "eval_loss": 0.27112114429473877,
+      "eval_runtime": 1.8327,
+      "eval_samples_per_second": 539.642,
+      "eval_steps_per_second": 8.73,
+      "step": 186
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 7.741935483870968e-06,
+      "loss": 0.2874,
+      "step": 190
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 7.096774193548388e-06,
+      "loss": 0.2774,
+      "step": 200
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 0.2729,
+      "step": 210
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 5.806451612903226e-06,
+      "loss": 0.2784,
+      "step": 220
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 5.161290322580646e-06,
+      "loss": 0.2726,
+      "step": 230
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 4.516129032258065e-06,
+      "loss": 0.2723,
+      "step": 240
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.4506226469736461,
+      "eval_loss": 0.26035064458847046,
+      "eval_runtime": 1.8326,
+      "eval_samples_per_second": 539.658,
+      "eval_steps_per_second": 8.731,
+      "step": 248
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 3.870967741935484e-06,
+      "loss": 0.2688,
+      "step": 250
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 0.268,
+      "step": 260
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 2.580645161290323e-06,
+      "loss": 0.266,
+      "step": 270
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 1.935483870967742e-06,
+      "loss": 0.2657,
+      "step": 280
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 1.2903225806451614e-06,
+      "loss": 0.2687,
+      "step": 290
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 6.451612903225807e-07,
+      "loss": 0.2679,
+      "step": 300
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.2653,
+      "step": 310
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.46636259977194994,
+      "eval_loss": 0.25748351216316223,
+      "eval_runtime": 1.8325,
+      "eval_samples_per_second": 539.71,
+      "eval_steps_per_second": 8.731,
+      "step": 310
+    },
+    {
+      "epoch": 5.0,
+      "step": 310,
+      "total_flos": 5243230627246080.0,
+      "train_loss": 0.3167446336438579,
+      "train_runtime": 225.8975,
+      "train_samples_per_second": 175.168,
+      "train_steps_per_second": 1.372
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 310,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 5243230627246080.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6799f73d7789bea8ccf5a66eb0bed01d8621989e3edb84ce6232726b939c4fcb
+size 4536