models

models/distil_bert_tuned_2/README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+- recall
+- precision
+model-index:
+- name: distil_bert_tuned_2
+  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. -->
+
+# distil_bert_tuned_2
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5698
+- F1: 0.8253
+- Accuracy: 0.7816
+- Recall: 0.7088
+- Precision: 0.2347
+
+## 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: 5e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Accuracy | Recall | Precision |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|:------:|:---------:|
+| 0.5698        | 1.0   | 605  | 0.5390          | 0.8419 | 0.8063   | 0.6549 | 0.2502    |
+| 0.5006        | 2.0   | 1210 | 0.5075          | 0.8052 | 0.7527   | 0.7599 | 0.2192    |
+| 0.4526        | 3.0   | 1815 | 0.5698          | 0.8253 | 0.7816   | 0.7088 | 0.2347    |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.0.1+cpu
+- Datasets 2.14.5
+- Tokenizers 0.13.3

models/distil_bert_tuned_2/checkpoint-1210/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "vocab_size": 30522
+}

models/distil_bert_tuned_2/checkpoint-1210/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:469f5e5f81c7ba7724f2a7a23f839fdfad196e69dcb530772819fcbab858e62f
+size 535723973

models/distil_bert_tuned_2/checkpoint-1210/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e084ed0b1171a5647cf64ab223f391cb2a29ea8de5dd9e9c389ec2cf09062772
+size 267854125

models/distil_bert_tuned_2/checkpoint-1210/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d93ec19bfefc75807fea042ecf5a692d9b1f6039fa6be20381e65f1747d4904
+size 13553

models/distil_bert_tuned_2/checkpoint-1210/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60b4ab99044e755b98e9953c7ab25276cd31ee58d9b7fdc78887a78488ad4f0
+size 627

models/distil_bert_tuned_2/checkpoint-1210/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

models/distil_bert_tuned_2/checkpoint-1210/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

models/distil_bert_tuned_2/checkpoint-1210/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": 0.841893952974485,
+  "best_model_checkpoint": "models/distil_bert_tuned_2\\checkpoint-605",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.622589531680441e-05,
+      "loss": 0.5698,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.806346525096525,
+      "eval_f1": 0.841893952974485,
+      "eval_loss": 0.5389575958251953,
+      "eval_precision": 0.2502059873661082,
+      "eval_recall": 0.6549245147375988,
+      "eval_runtime": 507.9128,
+      "eval_samples_per_second": 32.636,
+      "eval_steps_per_second": 0.51,
+      "step": 605
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.2451790633608817e-05,
+      "loss": 0.5006,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7526544401544402,
+      "eval_f1": 0.805202705989081,
+      "eval_loss": 0.5074611306190491,
+      "eval_precision": 0.21915820029027577,
+      "eval_recall": 0.7598849748382459,
+      "eval_runtime": 533.6219,
+      "eval_samples_per_second": 31.063,
+      "eval_steps_per_second": 0.485,
+      "step": 1210
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1815,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "total_flos": 860578077524136.0,
+  "trial_name": null,
+  "trial_params": null
+}

models/distil_bert_tuned_2/checkpoint-1210/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36827b6b0b8811db5f8b63dc4e35b8867da164725b097e20e4aab14ff8b4f86b
+size 4091

models/distil_bert_tuned_2/checkpoint-1815/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "vocab_size": 30522
+}

models/distil_bert_tuned_2/checkpoint-1815/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab724ba09be1f6d003f7866eb0c45aa62ed0067f9bf95190ae891c91fb76543
+size 535723973

models/distil_bert_tuned_2/checkpoint-1815/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc6afb3c986581c1b3df417078daa2bfeb58023c778e3625f5d80bdb7ce9f60b
+size 267854125

models/distil_bert_tuned_2/checkpoint-1815/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68081e4ce389dbed91c182289d82c311db47321a8404b7870812f8d1c833aa5
+size 13553

models/distil_bert_tuned_2/checkpoint-1815/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6355a3fc8f63bf39ff6116518446dd4931ed92fd60aa715c6676ad2bd54c4cb1
+size 627

models/distil_bert_tuned_2/checkpoint-1815/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

models/distil_bert_tuned_2/checkpoint-1815/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

models/distil_bert_tuned_2/checkpoint-1815/trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": 0.841893952974485,
+  "best_model_checkpoint": "models/distil_bert_tuned_2\\checkpoint-605",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1815,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.622589531680441e-05,
+      "loss": 0.5698,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.806346525096525,
+      "eval_f1": 0.841893952974485,
+      "eval_loss": 0.5389575958251953,
+      "eval_precision": 0.2502059873661082,
+      "eval_recall": 0.6549245147375988,
+      "eval_runtime": 507.9128,
+      "eval_samples_per_second": 32.636,
+      "eval_steps_per_second": 0.51,
+      "step": 605
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.2451790633608817e-05,
+      "loss": 0.5006,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7526544401544402,
+      "eval_f1": 0.805202705989081,
+      "eval_loss": 0.5074611306190491,
+      "eval_precision": 0.21915820029027577,
+      "eval_recall": 0.7598849748382459,
+      "eval_runtime": 533.6219,
+      "eval_samples_per_second": 31.063,
+      "eval_steps_per_second": 0.485,
+      "step": 1210
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 8.677685950413224e-06,
+      "loss": 0.4526,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.781551640926641,
+      "eval_f1": 0.8253061022873112,
+      "eval_loss": 0.5698077082633972,
+      "eval_precision": 0.23465016658733936,
+      "eval_recall": 0.7088425593098491,
+      "eval_runtime": 574.0732,
+      "eval_samples_per_second": 28.874,
+      "eval_steps_per_second": 0.451,
+      "step": 1815
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1815,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "total_flos": 1290867116286204.0,
+  "trial_name": null,
+  "trial_params": null
+}

models/distil_bert_tuned_2/checkpoint-1815/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36827b6b0b8811db5f8b63dc4e35b8867da164725b097e20e4aab14ff8b4f86b
+size 4091

models/distil_bert_tuned_2/checkpoint-605/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "vocab_size": 30522
+}

models/distil_bert_tuned_2/checkpoint-605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5fa8ef4ce35c8aeae4e11faf0d99e369b60536c3922fc55e31b67100df74d1
+size 535723973

models/distil_bert_tuned_2/checkpoint-605/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b0e50f4c1f2b6e2612f685f7a27da72b5966489a491179f5a6bd5c99893297
+size 267854125

models/distil_bert_tuned_2/checkpoint-605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9fc100675a4e3959bcb7c063d8a12d5996ec5d6c88cb72a9b5f81b575028a4
+size 13553

models/distil_bert_tuned_2/checkpoint-605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4092aeef05d2c0bc091a8ac9f9d6dd5c78a3dac56d3158f0ae9f3e309e9cd3f9
+size 627

models/distil_bert_tuned_2/checkpoint-605/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

models/distil_bert_tuned_2/checkpoint-605/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

models/distil_bert_tuned_2/checkpoint-605/trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": 0.841893952974485,
+  "best_model_checkpoint": "models/distil_bert_tuned_2\\checkpoint-605",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 605,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.622589531680441e-05,
+      "loss": 0.5698,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.806346525096525,
+      "eval_f1": 0.841893952974485,
+      "eval_loss": 0.5389575958251953,
+      "eval_precision": 0.2502059873661082,
+      "eval_recall": 0.6549245147375988,
+      "eval_runtime": 507.9128,
+      "eval_samples_per_second": 32.636,
+      "eval_steps_per_second": 0.51,
+      "step": 605
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1815,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "total_flos": 430289038762068.0,
+  "trial_name": null,
+  "trial_params": null
+}

models/distil_bert_tuned_2/checkpoint-605/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36827b6b0b8811db5f8b63dc4e35b8867da164725b097e20e4aab14ff8b4f86b
+size 4091

models/distil_bert_tuned_2/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "vocab_size": 30522
+}

models/distil_bert_tuned_2/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b0e50f4c1f2b6e2612f685f7a27da72b5966489a491179f5a6bd5c99893297
+size 267854125

models/distil_bert_tuned_2/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

models/distil_bert_tuned_2/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

models/distil_bert_tuned_2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36827b6b0b8811db5f8b63dc4e35b8867da164725b097e20e4aab14ff8b4f86b
+size 4091

models/lgbm_model_1/lgbm_model_1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b223948be14cf0fe3893b82df997351e4ff0eccc0a00eca1976bf8b9d8532a
+size 547093

models/lgbm_model_1/vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f954e48684d60a3bc71202ce07afaa19289454d54b9eacfaecc18a2941b480
+size 649886

models/lgbm_model_2/lgbm_model_2.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737a35c7b3118c9a321e18ea9d4de4bf56e1c8636f730160f3d203679b42a543
+size 676035

models/lgbm_model_3/lgbm_model_3.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd98c2ef3ca293fe831926c8768edd3264e5fea03c4e72963f72884b453a0769
+size 968908

models/xgb_tuned_2/vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07851147c3fd56da5d20bcec56f11b1e72ecaf81e74d468680c66acf0adebd8d
+size 666162

models/xgb_tuned_2/xgb_model_tuned_2.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e633e8a4606b5a7711c2e607944f569aa31f6fd2d162593e7614d000f7d454e3
+size 1124108