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: 0.05558604374527931
+
+f1: 0.9881956155143339
+
+precision: 0.9881956155143339
+
+recall: 0.9881956155143339
+
+auc: 0.9994592560589801
+
+accuracy: 0.988313856427379

checkpoint-450/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": "opposed",
+    "1": "supportive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "opposed": 0,
+    "supportive": 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": "4.46.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-450/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b407f3c7934da163dc6b7d6ad38adacc3c4dd3d70cedd9a073eeb20cba196251
+size 437958648

checkpoint-450/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c85240b059415b620842bd5d4e2c2705510ace8f91e8a3f7afd867557d9a961b
+size 876038394

checkpoint-450/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f5115f09977e692a14dda8bcf59e0d966e88359214c0c40355daa73364cb335
+size 15024

checkpoint-450/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036dab5184f539d698044441c1bc9aab6a4a6b3ea257283fe0f9a0fe633d99a1
+size 15024

checkpoint-450/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:435311c5d899ab724fbfe86e455893ac4ad8f348bd91d92f2d9b346a7890fdb8
+size 15024

checkpoint-450/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf692dc84925732e598b71ef3c07ea6cad7b4ae59c199dd9811abf6a684e0c1
+size 15024

checkpoint-450/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f929bd687b5c6b08b1462d393761cd513de93e4f67531c943d93ead016b99428
+size 1064

checkpoint-450/trainer_state.json

@@ -0,0 +1,207 @@
+{
+  "best_metric": 0.052102286368608475,
+  "best_model_checkpoint": "autotrain-pbt7y-rt1dv/checkpoint-450",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 4.162468433380127,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.6911,
+      "step": 25
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 14.043020248413086,
+      "learning_rate": 4.950617283950618e-05,
+      "loss": 0.5826,
+      "step": 50
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 12.165104866027832,
+      "learning_rate": 4.654320987654321e-05,
+      "loss": 0.421,
+      "step": 75
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.5717558264732361,
+      "learning_rate": 4.345679012345679e-05,
+      "loss": 0.2736,
+      "step": 100
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.27614304423332214,
+      "learning_rate": 4.0370370370370374e-05,
+      "loss": 0.4425,
+      "step": 125
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 10.753256797790527,
+      "learning_rate": 3.7283950617283955e-05,
+      "loss": 0.232,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9607679465776294,
+      "eval_auc": 0.9811715189608797,
+      "eval_f1": 0.9595872742906277,
+      "eval_loss": 0.15245321393013,
+      "eval_precision": 0.9789473684210527,
+      "eval_recall": 0.9409780775716695,
+      "eval_runtime": 0.5784,
+      "eval_samples_per_second": 2071.084,
+      "eval_steps_per_second": 32.847,
+      "step": 150
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.11041617393493652,
+      "learning_rate": 3.419753086419753e-05,
+      "loss": 0.2218,
+      "step": 175
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.048719145357608795,
+      "learning_rate": 3.123456790123457e-05,
+      "loss": 0.1994,
+      "step": 200
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.0485817976295948,
+      "learning_rate": 2.814814814814815e-05,
+      "loss": 0.1059,
+      "step": 225
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 17.67010498046875,
+      "learning_rate": 2.5061728395061727e-05,
+      "loss": 0.1323,
+      "step": 250
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.08793912082910538,
+      "learning_rate": 2.1975308641975308e-05,
+      "loss": 0.0836,
+      "step": 275
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 57.188568115234375,
+      "learning_rate": 1.901234567901235e-05,
+      "loss": 0.1419,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9841402337228714,
+      "eval_auc": 0.9959527824620573,
+      "eval_f1": 0.9840201850294366,
+      "eval_loss": 0.08388863503932953,
+      "eval_precision": 0.9815436241610739,
+      "eval_recall": 0.9865092748735245,
+      "eval_runtime": 0.5767,
+      "eval_samples_per_second": 2077.214,
+      "eval_steps_per_second": 32.944,
+      "step": 300
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.05389270931482315,
+      "learning_rate": 1.5925925925925926e-05,
+      "loss": 0.0871,
+      "step": 325
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.06370247155427933,
+      "learning_rate": 1.2839506172839508e-05,
+      "loss": 0.1008,
+      "step": 350
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.0631629005074501,
+      "learning_rate": 9.753086419753086e-06,
+      "loss": 0.1163,
+      "step": 375
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.053911201655864716,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0639,
+      "step": 400
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 4.950315952301025,
+      "learning_rate": 3.580246913580247e-06,
+      "loss": 0.0894,
+      "step": 425
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.06562542915344238,
+      "learning_rate": 4.938271604938272e-07,
+      "loss": 0.0789,
+      "step": 450
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.988313856427379,
+      "eval_auc": 0.9985157415020973,
+      "eval_f1": 0.9881756756756757,
+      "eval_loss": 0.052102286368608475,
+      "eval_precision": 0.9898477157360406,
+      "eval_recall": 0.9865092748735245,
+      "eval_runtime": 0.5865,
+      "eval_samples_per_second": 2042.526,
+      "eval_steps_per_second": 32.394,
+      "step": 450
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 450,
+  "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": 947199814926336.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-450/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf345290dae9dd1d22ff03e99f9e6a7a9387176a11de0799f6ca34b3bd7f67f
+size 5304

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": "opposed",
+    "1": "supportive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "opposed": 0,
+    "supportive": 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": "4.46.2",
+  "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:b407f3c7934da163dc6b7d6ad38adacc3c4dd3d70cedd9a073eeb20cba196251
+size 437958648

runs/Dec02_15-17-32_r-cbpuschmann-sfautotrain-sc85mtwn-91fb6-5441j/events.out.tfevents.1733152653.r-cbpuschmann-sfautotrain-sc85mtwn-91fb6-5441j.216.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2ec98a99d2c4315b542b4eac4a88e5313164edec535fffe7ded9b144cae455b
-size 5234
+oid sha256:1695ed72002846c98606c9fb7a15bbc3cd00b6993c9d38143e698293793f82e6
+size 10923

runs/Dec02_15-17-32_r-cbpuschmann-sfautotrain-sc85mtwn-91fb6-5441j/events.out.tfevents.1733152686.r-cbpuschmann-sfautotrain-sc85mtwn-91fb6-5441j.216.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1dee74cacb9a8b16475ee02b7bffef4fc31f39fcad99d2ca07085ca515ea6ee
+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": false,
+  "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:bbf345290dae9dd1d22ff03e99f9e6a7a9387176a11de0799f6ca34b3bd7f67f
+size 5304

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-pbt7y-rt1dv/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-pbt7y-rt1dv",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "cbpuschmann",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}