jamesbaskerville/classify-article-titles

README.md

@@ -0,0 +1,76 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: albert/albert-base-v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: classify-articles
+  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. -->
+
+# classify-articles
+
+This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3819
+- Accuracy: 0.9070
+- F1: 0.9061
+- Precision: 0.9126
+- Recall: 0.9070
+- Accuracy Label Economy: 0.9429
+- Accuracy Label Politics: 0.9574
+- Accuracy Label Science: 0.9362
+- Accuracy Label Sports: 0.96
+- Accuracy Label Technology: 0.6944
+
+## 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: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall | Accuracy Label Economy | Accuracy Label Politics | Accuracy Label Science | Accuracy Label Sports | Accuracy Label Technology |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:----------------------:|:-----------------------:|:----------------------:|:---------------------:|:-------------------------:|
+| 1.3703        | 1.3072 | 100  | 1.3775          | 0.4930   | 0.4238 | 0.6100    | 0.4930 | 0.8                    | 0.0213                  | 0.7021                 | 0.72                  | 0.2222                    |
+| 0.4329        | 2.6144 | 200  | 0.4495          | 0.8977   | 0.9004 | 0.9134    | 0.8977 | 0.9429                 | 0.8936                  | 0.9149                 | 0.96                  | 0.75                      |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "albert/albert-base-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,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "economy",
+    "1": "politics",
+    "2": "science",
+    "3": "sports",
+    "4": "technology"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "economy": 0,
+    "politics": 1,
+    "science": 2,
+    "sports": 3,
+    "technology": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf37bf834442ed64e7594dc101754a1a27db9fc60e46c578dae2c6a95326d59
+size 46753140

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

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,247 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.980392156862745,
+  "eval_steps": 100,
+  "global_step": 228,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13071895424836602,
+      "grad_norm": 17.214561462402344,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.6592,
+      "step": 10
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 12.780923843383789,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.6322,
+      "step": 20
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 30.824169158935547,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.5926,
+      "step": 30
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 17.90578842163086,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.5943,
+      "step": 40
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 17.254802703857422,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.5476,
+      "step": 50
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 23.29121971130371,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.5345,
+      "step": 60
+    },
+    {
+      "epoch": 0.9150326797385621,
+      "grad_norm": 21.84389305114746,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.5421,
+      "step": 70
+    },
+    {
+      "epoch": 1.0457516339869282,
+      "grad_norm": 24.690324783325195,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 1.4884,
+      "step": 80
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 25.043909072875977,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 1.4151,
+      "step": 90
+    },
+    {
+      "epoch": 1.3071895424836601,
+      "grad_norm": 25.61355209350586,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.3703,
+      "step": 100
+    },
+    {
+      "epoch": 1.3071895424836601,
+      "eval_accuracy": 0.4930232558139535,
+      "eval_accuracy_label_economy": 0.8,
+      "eval_accuracy_label_politics": 0.02127659574468085,
+      "eval_accuracy_label_science": 0.7021276595744681,
+      "eval_accuracy_label_sports": 0.72,
+      "eval_accuracy_label_technology": 0.2222222222222222,
+      "eval_f1": 0.42383332698769244,
+      "eval_loss": 1.377465844154358,
+      "eval_precision": 0.6099528142905292,
+      "eval_recall": 0.4930232558139535,
+      "eval_runtime": 0.9308,
+      "eval_samples_per_second": 230.989,
+      "eval_steps_per_second": 15.041,
+      "step": 100
+    },
+    {
+      "epoch": 1.4379084967320261,
+      "grad_norm": 25.733768463134766,
+      "learning_rate": 4.4e-06,
+      "loss": 1.3219,
+      "step": 110
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 19.24130630493164,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.2374,
+      "step": 120
+    },
+    {
+      "epoch": 1.6993464052287581,
+      "grad_norm": 20.945722579956055,
+      "learning_rate": 5.2e-06,
+      "loss": 1.1398,
+      "step": 130
+    },
+    {
+      "epoch": 1.8300653594771243,
+      "grad_norm": 18.362749099731445,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 1.049,
+      "step": 140
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 21.393177032470703,
+      "learning_rate": 6e-06,
+      "loss": 0.9089,
+      "step": 150
+    },
+    {
+      "epoch": 2.0915032679738563,
+      "grad_norm": 20.148643493652344,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.7627,
+      "step": 160
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 37.801212310791016,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 0.5946,
+      "step": 170
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 22.492183685302734,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.6173,
+      "step": 180
+    },
+    {
+      "epoch": 2.4836601307189543,
+      "grad_norm": 58.739967346191406,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 0.4892,
+      "step": 190
+    },
+    {
+      "epoch": 2.6143790849673203,
+      "grad_norm": 31.867156982421875,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4329,
+      "step": 200
+    },
+    {
+      "epoch": 2.6143790849673203,
+      "eval_accuracy": 0.8976744186046511,
+      "eval_accuracy_label_economy": 0.9428571428571428,
+      "eval_accuracy_label_politics": 0.8936170212765957,
+      "eval_accuracy_label_science": 0.9148936170212766,
+      "eval_accuracy_label_sports": 0.96,
+      "eval_accuracy_label_technology": 0.75,
+      "eval_f1": 0.9004308622967181,
+      "eval_loss": 0.4494597017765045,
+      "eval_precision": 0.9133808113740947,
+      "eval_recall": 0.8976744186046511,
+      "eval_runtime": 0.5691,
+      "eval_samples_per_second": 377.764,
+      "eval_steps_per_second": 24.599,
+      "step": 200
+    },
+    {
+      "epoch": 2.7450980392156863,
+      "grad_norm": 16.43819808959961,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 0.3908,
+      "step": 210
+    },
+    {
+      "epoch": 2.8758169934640523,
+      "grad_norm": 8.563356399536133,
+      "learning_rate": 8.8e-06,
+      "loss": 0.3735,
+      "step": 220
+    },
+    {
+      "epoch": 2.980392156862745,
+      "step": 228,
+      "total_flos": 9501472156644.0,
+      "train_loss": 1.0989631905890347,
+      "train_runtime": 56.2949,
+      "train_samples_per_second": 129.71,
+      "train_steps_per_second": 4.05
+    },
+    {
+      "epoch": 2.980392156862745,
+      "eval_accuracy": 0.9069767441860465,
+      "eval_accuracy_label_economy": 0.9428571428571428,
+      "eval_accuracy_label_politics": 0.9574468085106383,
+      "eval_accuracy_label_science": 0.9361702127659575,
+      "eval_accuracy_label_sports": 0.96,
+      "eval_accuracy_label_technology": 0.6944444444444444,
+      "eval_f1": 0.9060619059788495,
+      "eval_loss": 0.38190317153930664,
+      "eval_precision": 0.9125925762408804,
+      "eval_recall": 0.9069767441860465,
+      "eval_runtime": 0.626,
+      "eval_samples_per_second": 343.446,
+      "eval_steps_per_second": 22.364,
+      "step": 228
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 228,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9501472156644.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b7addff3ab260590f7c38e75fee14524a056b7ecc31ded451903532746931f8
+size 5176