Add trained sentiment model and tokenizer

.gitignore

@@ -0,0 +1,7 @@
+venv310/
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+*.log
+*.DS_Store

config.json

@@ -0,0 +1,25 @@
+{
+  "_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,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c229880bd9d0f94d9c0fdb08e9750f71cf475f96fba14155833c41994389bf2a
+size 267832560

results/checkpoint-250/config.json

@@ -0,0 +1,25 @@
+{
+  "_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,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "vocab_size": 30522
+}

results/checkpoint-250/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ae47ca212efc45aaa3075ba0ad22ad1f1eccaf4b7e65c8d8995aa6d49b1224
+size 267832560

results/checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8661a7472efda2437d17a7971250b621ff19b9b75e0d19f610c1e8af6aafd1d0
+size 535724875

results/checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a06415bb43c924d2a25f8b3c831e8f97886f4e932a4b3fcbbea178458ccd14d
+size 14455

results/checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6fca1d0d5cc6c340c241d864da3a023dc41548ff1130eb59cb86627cad2626c
+size 1465

results/checkpoint-250/special_tokens_map.json

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

results/checkpoint-250/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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]"
+}

results/checkpoint-250/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.609426498413086,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.6223,
+      "step": 50
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 8.905411720275879,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.4075,
+      "step": 100
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 11.050198554992676,
+      "learning_rate": 4e-05,
+      "loss": 0.4125,
+      "step": 150
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.73728084564209,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.4522,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.976237297058105,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.3458,
+      "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.3327711224555969,
+      "eval_runtime": 29.3806,
+      "eval_samples_per_second": 17.018,
+      "eval_steps_per_second": 2.144,
+      "step": 250
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 132467398656000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bbea30fa528a706a75824b0dc6a7c088554c90e711ee73c1b8e434dd2b4f6d4
+size 5329

results/checkpoint-500/config.json

@@ -0,0 +1,25 @@
+{
+  "_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,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "vocab_size": 30522
+}

results/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73e2aacd21969ddb68e2d652faa616d76b49e909f652d9d8d4426e39e6d719de
+size 267832560

results/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b9d16d976ac212e14b2466e44873705f1807a2d6aeb9b7d9257a7b48025f60
+size 535724875

results/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e21af60e88f2ecaa42642ddcb3f6d94b5832e377b29cf61b9183dbde2e91fe26
+size 14455

results/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0bf09babf9ab3b0323bd8c33087573f0c0c2f6fd6af50cb8d498cd6f1363fb
+size 1465

results/checkpoint-500/special_tokens_map.json

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

results/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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]"
+}

results/checkpoint-500/trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.609426498413086,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.6223,
+      "step": 50
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 8.905411720275879,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.4075,
+      "step": 100
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 11.050198554992676,
+      "learning_rate": 4e-05,
+      "loss": 0.4125,
+      "step": 150
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.73728084564209,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.4522,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.976237297058105,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.3458,
+      "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.3327711224555969,
+      "eval_runtime": 29.3806,
+      "eval_samples_per_second": 17.018,
+      "eval_steps_per_second": 2.144,
+      "step": 250
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 11.21533489227295,
+      "learning_rate": 3e-05,
+      "loss": 0.2181,
+      "step": 300
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 6.712032318115234,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.3282,
+      "step": 350
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.10278991609811783,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.1943,
+      "step": 400
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.1258127689361572,
+      "learning_rate": 2e-05,
+      "loss": 0.1923,
+      "step": 450
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 17.39550018310547,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.2048,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.48086223006248474,
+      "eval_runtime": 31.6622,
+      "eval_samples_per_second": 15.792,
+      "eval_steps_per_second": 1.99,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 264934797312000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bbea30fa528a706a75824b0dc6a7c088554c90e711ee73c1b8e434dd2b4f6d4
+size 5329

results/checkpoint-750/config.json

@@ -0,0 +1,25 @@
+{
+  "_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,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "vocab_size": 30522
+}

results/checkpoint-750/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c229880bd9d0f94d9c0fdb08e9750f71cf475f96fba14155833c41994389bf2a
+size 267832560

results/checkpoint-750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9249d4db419ad8ef15ab226780cbc1eb5de92b827d7142f2707b6eb732f5922
+size 535724875

results/checkpoint-750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dce7e9600f4d681c780b791cebbe3fb30752d4e14911ec457d8543b3c4e151f
+size 14455

results/checkpoint-750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a68ad7dcf06894d3c77081144d7e8163065b2ebe974de0b8563fb23664540f4f
+size 1465

results/checkpoint-750/special_tokens_map.json

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

results/checkpoint-750/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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]"
+}

results/checkpoint-750/trainer_state.json

@@ -0,0 +1,150 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.609426498413086,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.6223,
+      "step": 50
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 8.905411720275879,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.4075,
+      "step": 100
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 11.050198554992676,
+      "learning_rate": 4e-05,
+      "loss": 0.4125,
+      "step": 150
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.73728084564209,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.4522,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.976237297058105,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.3458,
+      "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.3327711224555969,
+      "eval_runtime": 29.3806,
+      "eval_samples_per_second": 17.018,
+      "eval_steps_per_second": 2.144,
+      "step": 250
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 11.21533489227295,
+      "learning_rate": 3e-05,
+      "loss": 0.2181,
+      "step": 300
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 6.712032318115234,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.3282,
+      "step": 350
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.10278991609811783,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.1943,
+      "step": 400
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.1258127689361572,
+      "learning_rate": 2e-05,
+      "loss": 0.1923,
+      "step": 450
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 17.39550018310547,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.2048,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.48086223006248474,
+      "eval_runtime": 31.6622,
+      "eval_samples_per_second": 15.792,
+      "eval_steps_per_second": 1.99,
+      "step": 500
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 69.4999008178711,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.128,
+      "step": 550
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.0629974976181984,
+      "learning_rate": 1e-05,
+      "loss": 0.1258,
+      "step": 600
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 3.221457004547119,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1061,
+      "step": 650
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.05550043657422066,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.1103,
+      "step": 700
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.24818731844425201,
+      "learning_rate": 0.0,
+      "loss": 0.0512,
+      "step": 750
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5193189978599548,
+      "eval_runtime": 29.0108,
+      "eval_samples_per_second": 17.235,
+      "eval_steps_per_second": 2.172,
+      "step": 750
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 397402195968000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bbea30fa528a706a75824b0dc6a7c088554c90e711ee73c1b8e434dd2b4f6d4
+size 5329

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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]"
+}

train_sentiment_model.py

@@ -0,0 +1,59 @@
+from datasets import load_dataset
+from transformers import (
+    AutoTokenizer,
+    AutoModelForSequenceClassification,
+    Trainer,
+    TrainingArguments,
+)
+import torch
+
+# STEP 1: Load IMDb Dataset
+dataset = load_dataset("imdb")
+
+# STEP 2: Tokenize the Data
+checkpoint = "distilbert-base-uncased"
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+
+def preprocess(example):
+    return tokenizer(example["text"], truncation=True, padding="max_length", max_length=256)
+
+tokenized = dataset.map(preprocess, batched=True)
+tokenized = tokenized.remove_columns(["text"])
+tokenized = tokenized.rename_column("label", "labels")
+tokenized.set_format("torch")
+
+# Use a smaller subset for quick training
+train_dataset = tokenized["train"].shuffle(seed=42).select(range(2000))
+val_dataset = tokenized["test"].shuffle(seed=42).select(range(500))
+
+# STEP 3: Load Model
+model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2)
+
+# STEP 4: Define Training Arguments
+training_args = TrainingArguments(
+    output_dir="./results",
+    evaluation_strategy="epoch",
+    save_strategy="epoch",
+    num_train_epochs=3,
+    per_device_train_batch_size=8,
+    per_device_eval_batch_size=8,
+    logging_dir="./logs",
+    logging_steps=50,
+    report_to="none"
+)
+
+# STEP 5: Train
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=train_dataset,
+    eval_dataset=val_dataset,
+    tokenizer=tokenizer,
+)
+
+trainer.train()
+
+# STEP 6: Save Locally to Repo Folder
+model.save_pretrained("./")
+tokenizer.save_pretrained("./")
+print("✅ Model and tokenizer saved locally!")