Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- autotrain-57208-4mv8z/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.4916948974132538
+
+f1: 0.8059701492537313
+
+precision: 0.782608695652174
+
+recall: 0.8307692307692308
+
+auc: 0.8416783216783217
+
+accuracy: 0.7833333333333333

checkpoint-60/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "h-e-l-l-o/email-spam-classification-merged",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-60/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1773f58c250a228c90a7d970a29c322df7cbfbc9d75123bfe7ec4fe503eee4d1
+size 437958648

checkpoint-60/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a53dc85f6b437bc5653d111d97c65f400a899764dba72e370e66aa7c6ebdb38
+size 876038394

checkpoint-60/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caac0ee40fc2d655eee6b30e0d0641edde0b3b6003f52d95d8796ae61b1e0a86
+size 14244

checkpoint-60/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd84329c3ea3cbfc8eec6d05cafbf7d38ee7ea3882f0597f5a8665f554621cbb
+size 1064

checkpoint-60/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_metric": 0.4916948974132538,
+  "best_model_checkpoint": "autotrain-57208-4mv8z/checkpoint-60",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 0.9702,
+      "step": 3
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 25.49532699584961,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 0.7682,
+      "step": 6
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 36.088096618652344,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 1.1279,
+      "step": 9
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 42.65789031982422,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 1.2649,
+      "step": 12
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 13.15088176727295,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.7979,
+      "step": 15
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 26.759204864501953,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.6888,
+      "step": 18
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 23.444761276245117,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.7643,
+      "step": 21
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 46.247528076171875,
+      "learning_rate": 4.938271604938271e-05,
+      "loss": 0.6103,
+      "step": 24
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 18.17511749267578,
+      "learning_rate": 4.845679012345679e-05,
+      "loss": 1.2048,
+      "step": 27
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 12.499485969543457,
+      "learning_rate": 4.7530864197530866e-05,
+      "loss": 0.5038,
+      "step": 30
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 14.672439575195312,
+      "learning_rate": 4.6604938271604945e-05,
+      "loss": 0.7822,
+      "step": 33
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 13.163423538208008,
+      "learning_rate": 4.567901234567901e-05,
+      "loss": 0.5031,
+      "step": 36
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 21.604719161987305,
+      "learning_rate": 4.4753086419753084e-05,
+      "loss": 0.5332,
+      "step": 39
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 26.531099319458008,
+      "learning_rate": 4.3827160493827164e-05,
+      "loss": 0.5944,
+      "step": 42
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 7.5323615074157715,
+      "learning_rate": 4.290123456790124e-05,
+      "loss": 0.6344,
+      "step": 45
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 7.045075416564941,
+      "learning_rate": 4.197530864197531e-05,
+      "loss": 0.5561,
+      "step": 48
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 19.56390953063965,
+      "learning_rate": 4.104938271604938e-05,
+      "loss": 0.7812,
+      "step": 51
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 9.734304428100586,
+      "learning_rate": 4.012345679012346e-05,
+      "loss": 0.7483,
+      "step": 54
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 13.189071655273438,
+      "learning_rate": 3.9197530864197535e-05,
+      "loss": 0.6367,
+      "step": 57
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.375649929046631,
+      "learning_rate": 3.82716049382716e-05,
+      "loss": 0.5642,
+      "step": 60
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7833333333333333,
+      "eval_auc": 0.8416783216783217,
+      "eval_f1": 0.8059701492537313,
+      "eval_loss": 0.4916948974132538,
+      "eval_precision": 0.782608695652174,
+      "eval_recall": 0.8307692307692308,
+      "eval_runtime": 0.2902,
+      "eval_samples_per_second": 413.471,
+      "eval_steps_per_second": 27.565,
+      "step": 60
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 31310215587840.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-60/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0289f43907026be4e37502d57e5f6d28ee1acf5abed09db983916d2a4278a98
+size 4920

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "h-e-l-l-o/email-spam-classification-merged",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1773f58c250a228c90a7d970a29c322df7cbfbc9d75123bfe7ec4fe503eee4d1
+size 437958648

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "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]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0289f43907026be4e37502d57e5f6d28ee1acf5abed09db983916d2a4278a98
+size 4920

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-57208-4mv8z/autotrain-data",
+    "model": "h-e-l-l-o/email-spam-classification-merged",
+    "lr": 5e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": -1,
+    "project_name": "autotrain-57208-4mv8z",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "push_to_hub": true,
+    "repo_id": "rizdel/autotrain-57208-4mv8z",
+    "evaluation_strategy": "epoch",
+    "username": "rizdel",
+    "log": "none"
+}