Upload folder using huggingface_hub

README.md

@@ -0,0 +1,25 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.012014556676149368
+
+f1: 0.9978768577494692
+
+precision: 0.9957627118644068
+
+recall: 1.0
+
+auc: 0.9996415974513596
+
+accuracy: 0.9969558599695586

checkpoint-329/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "_num_labels": 2,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "female",
+    "1": "male"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "female": 0,
+    "male": 1
+  },
+  "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": "4.41.0",
+  "vocab_size": 30522
+}

checkpoint-329/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874beb5217fb04ac90eb83cf40131232ee46acb4f1c920528d7abb10983a655e
+size 267832560

checkpoint-329/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36941336fe33680e6b59c80281f93d685cf36ac1c8b53e15c7e523897bb6c80
+size 535727290

checkpoint-329/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea445753622dc943616c16b795090b2fc7d3bef15cc5fcffd45efab648dcaf40
+size 14244

checkpoint-329/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21bf76b42ee3649264aee2f54fca7f17a5eb49ba05792595cee3af9177afca13
+size 1064

checkpoint-329/trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.012014556676149368,
+  "best_model_checkpoint": "autotrain-pmmxv-0342h/checkpoint-329",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 329,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0486322188449848,
+      "grad_norm": 1.4125925302505493,
+      "learning_rate": 8.080808080808082e-06,
+      "loss": 0.6751,
+      "step": 16
+    },
+    {
+      "epoch": 0.0972644376899696,
+      "grad_norm": 2.151017189025879,
+      "learning_rate": 1.6161616161616165e-05,
+      "loss": 0.5336,
+      "step": 32
+    },
+    {
+      "epoch": 0.1458966565349544,
+      "grad_norm": 2.7561874389648438,
+      "learning_rate": 2.4242424242424244e-05,
+      "loss": 0.4138,
+      "step": 48
+    },
+    {
+      "epoch": 0.1945288753799392,
+      "grad_norm": 6.935989856719971,
+      "learning_rate": 3.232323232323233e-05,
+      "loss": 0.1493,
+      "step": 64
+    },
+    {
+      "epoch": 0.24316109422492402,
+      "grad_norm": 5.60068416595459,
+      "learning_rate": 4.0404040404040405e-05,
+      "loss": 0.095,
+      "step": 80
+    },
+    {
+      "epoch": 0.2917933130699088,
+      "grad_norm": 1.5631191730499268,
+      "learning_rate": 4.848484848484849e-05,
+      "loss": 0.0697,
+      "step": 96
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.5951395630836487,
+      "learning_rate": 4.9324324324324325e-05,
+      "loss": 0.0401,
+      "step": 112
+    },
+    {
+      "epoch": 0.3890577507598784,
+      "grad_norm": 0.04545021429657936,
+      "learning_rate": 4.8479729729729735e-05,
+      "loss": 0.0506,
+      "step": 128
+    },
+    {
+      "epoch": 0.4376899696048632,
+      "grad_norm": 0.037650544196367264,
+      "learning_rate": 4.757882882882883e-05,
+      "loss": 0.0365,
+      "step": 144
+    },
+    {
+      "epoch": 0.48632218844984804,
+      "grad_norm": 0.023942653089761734,
+      "learning_rate": 4.667792792792793e-05,
+      "loss": 0.002,
+      "step": 160
+    },
+    {
+      "epoch": 0.5349544072948328,
+      "grad_norm": 0.024038679897785187,
+      "learning_rate": 4.577702702702703e-05,
+      "loss": 0.0364,
+      "step": 176
+    },
+    {
+      "epoch": 0.5835866261398176,
+      "grad_norm": 0.021927503868937492,
+      "learning_rate": 4.4876126126126126e-05,
+      "loss": 0.0031,
+      "step": 192
+    },
+    {
+      "epoch": 0.6322188449848024,
+      "grad_norm": 0.07690062373876572,
+      "learning_rate": 4.397522522522523e-05,
+      "loss": 0.001,
+      "step": 208
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.02904803678393364,
+      "learning_rate": 4.307432432432433e-05,
+      "loss": 0.042,
+      "step": 224
+    },
+    {
+      "epoch": 0.729483282674772,
+      "grad_norm": 0.017681801691651344,
+      "learning_rate": 4.222972972972973e-05,
+      "loss": 0.0739,
+      "step": 240
+    },
+    {
+      "epoch": 0.7781155015197568,
+      "grad_norm": 0.01349892932921648,
+      "learning_rate": 4.132882882882883e-05,
+      "loss": 0.0113,
+      "step": 256
+    },
+    {
+      "epoch": 0.8267477203647416,
+      "grad_norm": 0.0121884411200881,
+      "learning_rate": 4.042792792792793e-05,
+      "loss": 0.0009,
+      "step": 272
+    },
+    {
+      "epoch": 0.8753799392097265,
+      "grad_norm": 0.010667676106095314,
+      "learning_rate": 3.952702702702703e-05,
+      "loss": 0.037,
+      "step": 288
+    },
+    {
+      "epoch": 0.9240121580547113,
+      "grad_norm": 0.19501090049743652,
+      "learning_rate": 3.862612612612613e-05,
+      "loss": 0.0563,
+      "step": 304
+    },
+    {
+      "epoch": 0.9726443768996961,
+      "grad_norm": 0.009381966665387154,
+      "learning_rate": 3.7725225225225225e-05,
+      "loss": 0.0077,
+      "step": 320
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9969558599695586,
+      "eval_auc": 0.9996415974513596,
+      "eval_f1": 0.9978768577494692,
+      "eval_loss": 0.012014556676149368,
+      "eval_precision": 0.9957627118644068,
+      "eval_recall": 1.0,
+      "eval_runtime": 1.9672,
+      "eval_samples_per_second": 333.972,
+      "eval_steps_per_second": 21.35,
+      "step": 329
+    }
+  ],
+  "logging_steps": 16,
+  "max_steps": 987,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 87031080916992.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-329/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b0a41b4670524b257a763259424279661e003f6eadc3144551607b386d2da5
+size 5176

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "_num_labels": 2,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "female",
+    "1": "male"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "female": 0,
+    "male": 1
+  },
+  "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": "4.41.0",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874beb5217fb04ac90eb83cf40131232ee46acb4f1c920528d7abb10983a655e
+size 267832560

runs/May26_07-35-32_r-ben-yu-autotrain-advanced-htbsxre5-85eea-l22x4/events.out.tfevents.1716708933.r-ben-yu-autotrain-advanced-htbsxre5-85eea-l22x4.87.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfad7a6cb410f11c53936e0009f03cf080d9fe3be2caa9547007a21005c938fe
-size 4876
+oid sha256:dd093dd49b2b519a8154fec87ad4e874d4273ba8921ad848e70c78c9f7d66e80
+size 19630

runs/May26_07-35-32_r-ben-yu-autotrain-advanced-htbsxre5-85eea-l22x4/events.out.tfevents.1716709019.r-ben-yu-autotrain-advanced-htbsxre5-85eea-l22x4.87.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee33a7fc2362ed094994d7daae375a61ee39de6acabd86c5a75ad0500bcb36b3
+size 607

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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b0a41b4670524b257a763259424279661e003f6eadc3144551607b386d2da5
+size 5176

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-pmmxv-0342h/autotrain-data",
+    "model": "distilbert/distilbert-base-uncased",
+    "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-pmmxv-0342h",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "ben-yu",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}