Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+
+---
+library_name: transformers
+tags:
+- autotrain
+- text-classification
+base_model: google-bert/bert-base-uncased
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.3812274634838104
+
+f1: 0.8502415458937198
+
+precision: 0.822429906542056
+
+recall: 0.88
+
+auc: 0.9464999999999999
+
+accuracy: 0.845

checkpoint-300/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "google-bert/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": "4.48.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a01d60f273c8576f366915c15f17ca5ba70e8bd0590fb3a84987ccb926eceb
+size 437958648

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725954b4e5fe493b40624ca019e42e68a21be7e5f8e42aad398e61bcebff55ee
+size 876032762

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:355ff693dd1878a9e3df58f8e819caad2f7a93cdd5e2940b69c6f69d588cb920
+size 13990

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cabdd96162ecddbb53d954d7eb1984d5ac789bd18a1ad68743eeb1f283f45df1
+size 1064

checkpoint-300/trainer_state.json

@@ -0,0 +1,501 @@
+{
+  "best_metric": 0.3812274634838104,
+  "best_model_checkpoint": "autotrain-q1a8e-lkjvk/checkpoint-300",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 5.388425350189209,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.7766,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.8578948974609375,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6896,
+      "step": 10
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 5.80257511138916,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7209,
+      "step": 15
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 8.230175018310547,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6836,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.696407318115234,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.7048,
+      "step": 25
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.938593864440918,
+      "learning_rate": 5e-05,
+      "loss": 0.6372,
+      "step": 30
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 4.806497097015381,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.6904,
+      "step": 35
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 11.051752090454102,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.559,
+      "step": 40
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 7.299765586853027,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.5984,
+      "step": 45
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.504423141479492,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 0.5253,
+      "step": 50
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 5.611149787902832,
+      "learning_rate": 4.5370370370370374e-05,
+      "loss": 0.6248,
+      "step": 55
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 8.887447357177734,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.5015,
+      "step": 60
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 5.124234676361084,
+      "learning_rate": 4.351851851851852e-05,
+      "loss": 0.3478,
+      "step": 65
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.9970197677612305,
+      "learning_rate": 4.259259259259259e-05,
+      "loss": 0.4066,
+      "step": 70
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 5.6670050621032715,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.3821,
+      "step": 75
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 8.8970365524292,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.6293,
+      "step": 80
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 3.2790770530700684,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.3839,
+      "step": 85
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 10.91942310333252,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.4401,
+      "step": 90
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.8900542259216309,
+      "learning_rate": 3.7962962962962964e-05,
+      "loss": 0.3463,
+      "step": 95
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.880194187164307,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.2759,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.845,
+      "eval_auc": 0.9094000000000001,
+      "eval_f1": 0.8530805687203792,
+      "eval_loss": 0.4790796637535095,
+      "eval_precision": 0.8108108108108109,
+      "eval_recall": 0.9,
+      "eval_runtime": 16.6896,
+      "eval_samples_per_second": 11.984,
+      "eval_steps_per_second": 0.779,
+      "step": 100
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 2.454345703125,
+      "learning_rate": 3.611111111111111e-05,
+      "loss": 0.4381,
+      "step": 105
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 10.043645858764648,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.5042,
+      "step": 110
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 5.180539131164551,
+      "learning_rate": 3.425925925925926e-05,
+      "loss": 0.4578,
+      "step": 115
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 12.207428932189941,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.3022,
+      "step": 120
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 4.682361602783203,
+      "learning_rate": 3.240740740740741e-05,
+      "loss": 0.392,
+      "step": 125
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 8.122267723083496,
+      "learning_rate": 3.148148148148148e-05,
+      "loss": 0.523,
+      "step": 130
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 5.794045448303223,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.3841,
+      "step": 135
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 11.040246963500977,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 0.5252,
+      "step": 140
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 5.601756572723389,
+      "learning_rate": 2.8703703703703706e-05,
+      "loss": 0.3077,
+      "step": 145
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 5.826776027679443,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.5758,
+      "step": 150
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 4.407803535461426,
+      "learning_rate": 2.6851851851851855e-05,
+      "loss": 0.3963,
+      "step": 155
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 3.584040880203247,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.4942,
+      "step": 160
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 5.058577537536621,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3166,
+      "step": 165
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 4.095223426818848,
+      "learning_rate": 2.4074074074074074e-05,
+      "loss": 0.357,
+      "step": 170
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 5.765600681304932,
+      "learning_rate": 2.314814814814815e-05,
+      "loss": 0.3702,
+      "step": 175
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 6.91631555557251,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.5198,
+      "step": 180
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 5.872054100036621,
+      "learning_rate": 2.1296296296296296e-05,
+      "loss": 0.2841,
+      "step": 185
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 5.530134677886963,
+      "learning_rate": 2.037037037037037e-05,
+      "loss": 0.268,
+      "step": 190
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 15.666342735290527,
+      "learning_rate": 1.9444444444444445e-05,
+      "loss": 0.4452,
+      "step": 195
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 30.758365631103516,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.4575,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.83,
+      "eval_auc": 0.9433999999999999,
+      "eval_f1": 0.8454545454545455,
+      "eval_loss": 0.43705540895462036,
+      "eval_precision": 0.775,
+      "eval_recall": 0.93,
+      "eval_runtime": 16.2132,
+      "eval_samples_per_second": 12.336,
+      "eval_steps_per_second": 0.802,
+      "step": 200
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 4.886333465576172,
+      "learning_rate": 1.7592592592592595e-05,
+      "loss": 0.3694,
+      "step": 205
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 2.4083738327026367,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.044,
+      "step": 210
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 5.403554439544678,
+      "learning_rate": 1.574074074074074e-05,
+      "loss": 0.3129,
+      "step": 215
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 2.1031603813171387,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.3065,
+      "step": 220
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 11.965121269226074,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 0.3365,
+      "step": 225
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 4.058045864105225,
+      "learning_rate": 1.2962962962962962e-05,
+      "loss": 0.7497,
+      "step": 230
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 1.9264256954193115,
+      "learning_rate": 1.2037037037037037e-05,
+      "loss": 0.0322,
+      "step": 235
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 12.697930335998535,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.258,
+      "step": 240
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.867317259311676,
+      "learning_rate": 1.0185185185185185e-05,
+      "loss": 0.1621,
+      "step": 245
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 9.345597267150879,
+      "learning_rate": 9.259259259259259e-06,
+      "loss": 0.3019,
+      "step": 250
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 3.1092865467071533,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.402,
+      "step": 255
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 4.402215480804443,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.3476,
+      "step": 260
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 8.964146614074707,
+      "learning_rate": 6.481481481481481e-06,
+      "loss": 0.1856,
+      "step": 265
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 6.020453929901123,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 0.4585,
+      "step": 270
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 7.299376964569092,
+      "learning_rate": 4.6296296296296296e-06,
+      "loss": 0.3123,
+      "step": 275
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 7.876248359680176,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.2968,
+      "step": 280
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 7.705789566040039,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 0.2672,
+      "step": 285
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 11.458267211914062,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 0.242,
+      "step": 290
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 8.3551607131958,
+      "learning_rate": 9.259259259259259e-07,
+      "loss": 0.2979,
+      "step": 295
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.3359227180480957,
+      "learning_rate": 0.0,
+      "loss": 0.3926,
+      "step": 300
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.845,
+      "eval_auc": 0.9464999999999999,
+      "eval_f1": 0.8502415458937198,
+      "eval_loss": 0.3812274634838104,
+      "eval_precision": 0.822429906542056,
+      "eval_recall": 0.88,
+      "eval_runtime": 16.8077,
+      "eval_samples_per_second": 11.899,
+      "eval_steps_per_second": 0.773,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 300,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 157866633216000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c1969a1d079c3076e5353475e77ce40b390edfd550e8c9316fa2349d7254f0e
+size 5368

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "google-bert/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": "4.48.0",
+  "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 sha256:08a01d60f273c8576f366915c15f17ca5ba70e8bd0590fb3a84987ccb926eceb
+size 437958648

runs/Nov30_11-14-35_r-mralexgov-autotrain-advanced-0rxyi0n4-2b521-dnngt/events.out.tfevents.1764501277.r-mralexgov-autotrain-advanced-0rxyi0n4-2b521-dnngt.74.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cfbe221e7a3bbbd6b85b35ba82ac21465b70b384705a3d4b73446e5246bdb17
-size 14786
+oid sha256:525cdfd665b5e3a8d800479691d49d23a0db493e9ea7f67867e875d3221ecb50
+size 19668

runs/Nov30_11-14-35_r-mralexgov-autotrain-advanced-0rxyi0n4-2b521-dnngt/events.out.tfevents.1764502165.r-mralexgov-autotrain-advanced-0rxyi0n4-2b521-dnngt.74.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37ea56c733c1b1f273dfb6a63d2413ec3d5e85cffe027b2275e5130f11b2139
+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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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 sha256:0c1969a1d079c3076e5353475e77ce40b390edfd550e8c9316fa2349d7254f0e
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-q1a8e-lkjvk/autotrain-data",
+    "model": "google-bert/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": "autotrain-q1a8e-lkjvk",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "MrAlexGov",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}