Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- neil-code/autotrain-data-autotrain-text-classific-imdb
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.32178911566734314
+
+f1: 0.8431746031746032
+
+precision: 0.8952808988764045
+
+recall: 0.7968
+
+auc: 0.94403024
+
+accuracy: 0.8518

checkpoint-2500/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "_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": "4.36.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18878d55f2de213b25cb68a5e77407f8cda1e5f47aaf97e58a4282540c3ba61a
+size 437958648

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d876d3e35e1d41e1c088852e6e7508cb08d9785298c0bef980896b2902b514
+size 876038394

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f5c67fc632c232978db075f1eab5671d9ef41a383e9dba613051b69c687679
+size 14244

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edd7412e2baed9b1857d36e4c263cd6c6b209eae628fa501c58f9c39591ce65
+size 1064

checkpoint-2500/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": 0.32178911566734314,
+  "best_model_checkpoint": "/tmp/model/checkpoint-2500",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.266666666666667e-06,
+      "loss": 0.6965,
+      "step": 125
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.6533333333333333e-05,
+      "loss": 0.5176,
+      "step": 250
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.486666666666667e-05,
+      "loss": 0.4482,
+      "step": 375
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.313333333333333e-05,
+      "loss": 0.4278,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.146666666666667e-05,
+      "loss": 0.4267,
+      "step": 625
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.973333333333334e-05,
+      "loss": 0.4106,
+      "step": 750
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.910370370370371e-05,
+      "loss": 0.4548,
+      "step": 875
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.817777777777778e-05,
+      "loss": 0.3838,
+      "step": 1000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.725185185185185e-05,
+      "loss": 0.3781,
+      "step": 1125
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.6325925925925926e-05,
+      "loss": 0.4206,
+      "step": 1250
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.5400000000000006e-05,
+      "loss": 0.3933,
+      "step": 1375
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.447407407407407e-05,
+      "loss": 0.4357,
+      "step": 1500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.354814814814815e-05,
+      "loss": 0.3704,
+      "step": 1625
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.2622222222222224e-05,
+      "loss": 0.3859,
+      "step": 1750
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.16962962962963e-05,
+      "loss": 0.3682,
+      "step": 1875
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.077037037037037e-05,
+      "loss": 0.3852,
+      "step": 2000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.984444444444444e-05,
+      "loss": 0.3641,
+      "step": 2125
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.891851851851852e-05,
+      "loss": 0.3814,
+      "step": 2250
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.7992592592592596e-05,
+      "loss": 0.3471,
+      "step": 2375
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.706666666666667e-05,
+      "loss": 0.3565,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8518,
+      "eval_auc": 0.94403024,
+      "eval_f1": 0.8431746031746032,
+      "eval_loss": 0.32178911566734314,
+      "eval_precision": 0.8952808988764045,
+      "eval_recall": 0.7968,
+      "eval_runtime": 10.5615,
+      "eval_samples_per_second": 473.418,
+      "eval_steps_per_second": 29.636,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 125,
+  "max_steps": 7500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1315555276800000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a3e8fe360ed01949c463b74a76e432d4de9b4d4db45cd2a14e2b54ba47cebf
+size 4728

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "_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": "4.36.1",
+  "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 sha256:18878d55f2de213b25cb68a5e77407f8cda1e5f47aaf97e58a4282540c3ba61a
+size 437958648

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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a3e8fe360ed01949c463b74a76e432d4de9b4d4db45cd2a14e2b54ba47cebf
+size 4728

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "neil-code/autotrain-data-autotrain-text-classific-imdb",
+    "model": "bert-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": "/tmp/model",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "push_to_hub": true,
+    "repo_id": "neil-code/autotrain-text-classific-imdb",
+    "evaluation_strategy": "epoch",
+    "username": "neil-code",
+    "log": "none"
+}