Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+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: 0.03319514915347099
+
+f1: 1.0
+
+precision: 1.0
+
+recall: 1.0
+
+auc: 1.0
+
+accuracy: 1.0

checkpoint-33/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": "bad",
+    "1": "good"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bad": 0,
+    "good": 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": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-33/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c788798205d3d53d6b443880010736a675707ccfff41bee6c274ae7443392d6
+size 437958648

checkpoint-33/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eeecebdf9beb45fbffecbc97765dae401a17c4db19470ca8128238bfe16b10c
+size 876032762

checkpoint-33/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348fb8fcc20a54e94bcc1e929a18a2b2866c705ca130e8ae75d703f77c5e05fd
+size 13990

checkpoint-33/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c83ada173bd68ec90f0f92b7e1947554b1d5c514bcf319907210588decb5cc3
+size 1064

checkpoint-33/trainer_state.json

@@ -0,0 +1,312 @@
+{
+  "best_metric": 0.03319514915347099,
+  "best_model_checkpoint": "autotrain-4usrt-85kzb/checkpoint-33",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 33,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 11.761338233947754,
+      "learning_rate": 1.25e-05,
+      "loss": 0.8704,
+      "step": 1
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 7.499186038970947,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5885,
+      "step": 2
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 5.171218395233154,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.615,
+      "step": 3
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 10.380544662475586,
+      "learning_rate": 5e-05,
+      "loss": 0.6992,
+      "step": 4
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 5.8920512199401855,
+      "learning_rate": 4.827586206896552e-05,
+      "loss": 0.5152,
+      "step": 5
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 6.648828506469727,
+      "learning_rate": 4.655172413793104e-05,
+      "loss": 0.4446,
+      "step": 6
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 12.528966903686523,
+      "learning_rate": 4.482758620689655e-05,
+      "loss": 0.4955,
+      "step": 7
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 7.694393157958984,
+      "learning_rate": 4.3103448275862066e-05,
+      "loss": 0.5072,
+      "step": 8
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 7.016471862792969,
+      "learning_rate": 4.1379310344827587e-05,
+      "loss": 0.2834,
+      "step": 9
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 7.048137664794922,
+      "learning_rate": 3.965517241379311e-05,
+      "loss": 0.2472,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.261392116546631,
+      "learning_rate": 3.793103448275862e-05,
+      "loss": 0.2076,
+      "step": 11
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9523809523809523,
+      "eval_auc": 1.0,
+      "eval_f1": 0.9473684210526315,
+      "eval_loss": 0.1770750731229782,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9,
+      "eval_runtime": 4.8171,
+      "eval_samples_per_second": 4.359,
+      "eval_steps_per_second": 0.415,
+      "step": 11
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 6.019667625427246,
+      "learning_rate": 3.620689655172414e-05,
+      "loss": 0.1873,
+      "step": 12
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 4.4459710121154785,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 0.119,
+      "step": 13
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 2.7395246028900146,
+      "learning_rate": 3.275862068965517e-05,
+      "loss": 0.0936,
+      "step": 14
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 2.9547948837280273,
+      "learning_rate": 3.103448275862069e-05,
+      "loss": 0.0986,
+      "step": 15
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 7.345340251922607,
+      "learning_rate": 2.9310344827586206e-05,
+      "loss": 0.0939,
+      "step": 16
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 2.4599573612213135,
+      "learning_rate": 2.7586206896551727e-05,
+      "loss": 0.0789,
+      "step": 17
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 3.887648582458496,
+      "learning_rate": 2.5862068965517244e-05,
+      "loss": 0.0814,
+      "step": 18
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 2.253195285797119,
+      "learning_rate": 2.413793103448276e-05,
+      "loss": 0.0746,
+      "step": 19
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 2.3239686489105225,
+      "learning_rate": 2.2413793103448276e-05,
+      "loss": 0.0713,
+      "step": 20
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 2.0128979682922363,
+      "learning_rate": 2.0689655172413793e-05,
+      "loss": 0.0609,
+      "step": 21
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.9712774753570557,
+      "learning_rate": 1.896551724137931e-05,
+      "loss": 0.0998,
+      "step": 22
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 1.0,
+      "eval_auc": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.054505739361047745,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 4.8545,
+      "eval_samples_per_second": 4.326,
+      "eval_steps_per_second": 0.412,
+      "step": 22
+    },
+    {
+      "epoch": 2.090909090909091,
+      "grad_norm": 1.6843291521072388,
+      "learning_rate": 1.7241379310344828e-05,
+      "loss": 0.0552,
+      "step": 23
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 1.4115827083587646,
+      "learning_rate": 1.5517241379310346e-05,
+      "loss": 0.0461,
+      "step": 24
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 1.6311649084091187,
+      "learning_rate": 1.3793103448275863e-05,
+      "loss": 0.0515,
+      "step": 25
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 1.2126336097717285,
+      "learning_rate": 1.206896551724138e-05,
+      "loss": 0.0385,
+      "step": 26
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 1.5105429887771606,
+      "learning_rate": 1.0344827586206897e-05,
+      "loss": 0.0463,
+      "step": 27
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 1.3499268293380737,
+      "learning_rate": 8.620689655172414e-06,
+      "loss": 0.0418,
+      "step": 28
+    },
+    {
+      "epoch": 2.6363636363636362,
+      "grad_norm": 1.2205418348312378,
+      "learning_rate": 6.896551724137932e-06,
+      "loss": 0.0381,
+      "step": 29
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 1.1028234958648682,
+      "learning_rate": 5.172413793103448e-06,
+      "loss": 0.0346,
+      "step": 30
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 1.0579960346221924,
+      "learning_rate": 3.448275862068966e-06,
+      "loss": 0.0336,
+      "step": 31
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 1.2498091459274292,
+      "learning_rate": 1.724137931034483e-06,
+      "loss": 0.0392,
+      "step": 32
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.5818809270858765,
+      "learning_rate": 0.0,
+      "loss": 0.0462,
+      "step": 33
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 1.0,
+      "eval_auc": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.03319514915347099,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 4.8139,
+      "eval_samples_per_second": 4.362,
+      "eval_steps_per_second": 0.415,
+      "step": 33
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 33,
+  "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": 15983996613120.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-33/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c30ecce45839480cd8052abce5a4e9800aefe1b7e7694bbc951deee261f72a40
+size 5176

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": "bad",
+    "1": "good"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bad": 0,
+    "good": 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": "4.41.2",
+  "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 sha256:7c788798205d3d53d6b443880010736a675707ccfff41bee6c274ae7443392d6
+size 437958648

runs/Jun22_14-03-07_r-amre-autotrain-foerderfibel-x0kr21pd-8e24b-22osc/events.out.tfevents.1719064988.r-amre-autotrain-foerderfibel-x0kr21pd-8e24b-22osc.209.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1034f73db1ac9bc1c31beffb1b8cd4231854ac3d034ec5f00dd12a58189a69f5
-size 4981
+oid sha256:ec1df2089d6dc6f16a5f0e03bd9928994c86fd2a1bed05e48f51ffac5e9b6493
+size 13687

runs/Jun22_14-03-07_r-amre-autotrain-foerderfibel-x0kr21pd-8e24b-22osc/events.out.tfevents.1719065201.r-amre-autotrain-foerderfibel-x0kr21pd-8e24b-22osc.209.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa5fa713a79d6ad98a21b15710f38fa81907ba3ada37f904ac890813ef4167b
+size 597

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:c30ecce45839480cd8052abce5a4e9800aefe1b7e7694bbc951deee261f72a40
+size 5176

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-4usrt-85kzb/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-4usrt-85kzb",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "amre",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}