Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+
+---
+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: 0.7645955681800842
+
+f1_macro: 0.27586206896551724
+
+f1_micro: 0.7058823529411765
+
+f1_weighted: 0.5841784989858012
+
+precision_macro: 0.23529411764705885
+
+precision_micro: 0.7058823529411765
+
+precision_weighted: 0.49826989619377166
+
+recall_macro: 0.3333333333333333
+
+recall_micro: 0.7058823529411765
+
+recall_weighted: 0.7058823529411765
+
+accuracy: 0.7058823529411765

checkpoint-27/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 3,
+  "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": "inne",
+    "1": "komunikat prasowy",
+    "2": "zaproszenie"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "inne": 0,
+    "komunikat prasowy": 1,
+    "zaproszenie": 2
+  },
+  "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-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee4292d019774fddcc52c3a802d32a1aa76798ad6c126b91f891c2944f2ea89
+size 437961724

checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:338e2aecf6d135d367488e1f3ff881dad89a100d8b983a1a471108d1bd34b176
+size 876038906

checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993e0b09a5873cb3bb45ef2e52af603f4fd9416cbc15185b6c33b659c296306c
+size 13990

checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b7770298a17e6017d76ce8c062723991fd462ec0e649435f72764ded329a407
+size 1064

checkpoint-27/trainer_state.json

@@ -0,0 +1,285 @@
+{
+  "best_metric": 0.7645955681800842,
+  "best_model_checkpoint": "email-classifier/checkpoint-27",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 12.661477088928223,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.0907,
+      "step": 1
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 9.262643814086914,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.1452,
+      "step": 2
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 4.253861427307129,
+      "learning_rate": 5e-05,
+      "loss": 1.0398,
+      "step": 3
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 5.083256721496582,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 1.0236,
+      "step": 4
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 6.380894184112549,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 0.8063,
+      "step": 5
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 7.080038070678711,
+      "learning_rate": 4.375e-05,
+      "loss": 0.8933,
+      "step": 6
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 5.052453994750977,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.5092,
+      "step": 7
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 4.828819751739502,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 0.9788,
+      "step": 8
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.715775012969971,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.7505,
+      "step": 9
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_f1_macro": 0.27586206896551724,
+      "eval_f1_micro": 0.7058823529411765,
+      "eval_f1_weighted": 0.5841784989858012,
+      "eval_loss": 0.8175652027130127,
+      "eval_precision_macro": 0.23529411764705885,
+      "eval_precision_micro": 0.7058823529411765,
+      "eval_precision_weighted": 0.49826989619377166,
+      "eval_recall_macro": 0.3333333333333333,
+      "eval_recall_micro": 0.7058823529411765,
+      "eval_recall_weighted": 0.7058823529411765,
+      "eval_runtime": 4.292,
+      "eval_samples_per_second": 3.961,
+      "eval_steps_per_second": 0.466,
+      "step": 9
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 5.281602382659912,
+      "learning_rate": 3.541666666666667e-05,
+      "loss": 1.0502,
+      "step": 10
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 4.289942741394043,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.7533,
+      "step": 11
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 4.913335800170898,
+      "learning_rate": 3.125e-05,
+      "loss": 1.0854,
+      "step": 12
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 4.09973669052124,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 0.4934,
+      "step": 13
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 6.382025718688965,
+      "learning_rate": 2.7083333333333332e-05,
+      "loss": 0.8873,
+      "step": 14
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.496077299118042,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7701,
+      "step": 15
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 3.6502137184143066,
+      "learning_rate": 2.2916666666666667e-05,
+      "loss": 0.653,
+      "step": 16
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 3.0348548889160156,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 0.8641,
+      "step": 17
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.570982456207275,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.835,
+      "step": 18
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_f1_macro": 0.27586206896551724,
+      "eval_f1_micro": 0.7058823529411765,
+      "eval_f1_weighted": 0.5841784989858012,
+      "eval_loss": 0.7890189290046692,
+      "eval_precision_macro": 0.23529411764705885,
+      "eval_precision_micro": 0.7058823529411765,
+      "eval_precision_weighted": 0.49826989619377166,
+      "eval_recall_macro": 0.3333333333333333,
+      "eval_recall_micro": 0.7058823529411765,
+      "eval_recall_weighted": 0.7058823529411765,
+      "eval_runtime": 4.8269,
+      "eval_samples_per_second": 3.522,
+      "eval_steps_per_second": 0.414,
+      "step": 18
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 2.422776699066162,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.875,
+      "step": 19
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 6.083028316497803,
+      "learning_rate": 1.4583333333333335e-05,
+      "loss": 0.5999,
+      "step": 20
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 4.942434310913086,
+      "learning_rate": 1.25e-05,
+      "loss": 0.9778,
+      "step": 21
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 5.678409099578857,
+      "learning_rate": 1.0416666666666668e-05,
+      "loss": 0.5364,
+      "step": 22
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 5.16926383972168,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.7531,
+      "step": 23
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 4.587949275970459,
+      "learning_rate": 6.25e-06,
+      "loss": 0.7907,
+      "step": 24
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 5.132978916168213,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.7656,
+      "step": 25
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 2.9670441150665283,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 0.8906,
+      "step": 26
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 10.066261291503906,
+      "learning_rate": 0.0,
+      "loss": 0.3755,
+      "step": 27
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_f1_macro": 0.27586206896551724,
+      "eval_f1_micro": 0.7058823529411765,
+      "eval_f1_weighted": 0.5841784989858012,
+      "eval_loss": 0.7645955681800842,
+      "eval_precision_macro": 0.23529411764705885,
+      "eval_precision_micro": 0.7058823529411765,
+      "eval_precision_weighted": 0.49826989619377166,
+      "eval_recall_macro": 0.3333333333333333,
+      "eval_recall_micro": 0.7058823529411765,
+      "eval_recall_weighted": 0.7058823529411765,
+      "eval_runtime": 4.2687,
+      "eval_samples_per_second": 3.982,
+      "eval_steps_per_second": 0.469,
+      "step": 27
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 27,
+  "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": 13418784304128.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-27/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386d50d48b9e9ac48b9d1ab7652d3a4a16710b21585eb4b6944eb9de6cd370b4
+size 5368

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 3,
+  "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": "inne",
+    "1": "komunikat prasowy",
+    "2": "zaproszenie"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "inne": 0,
+    "komunikat prasowy": 1,
+    "zaproszenie": 2
+  },
+  "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 sha256:7ee4292d019774fddcc52c3a802d32a1aa76798ad6c126b91f891c2944f2ea89
+size 437961724

runs/May17_16-37-09_r-igiag-document-classification-sknn8sdt-9892e-fqjem/events.out.tfevents.1747499832.r-igiag-document-classification-sknn8sdt-9892e-fqjem.106.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce9dd053e4355a0fb20947ad1c3405906f60b028a0cf3fe31b2e254930e3156d
-size 5277
+oid sha256:4c46db794f3cca7fb8f0eba77a45f11169b82cbcf948f701418d6d8ccb21d210
+size 13668

runs/May17_16-37-09_r-igiag-document-classification-sknn8sdt-9892e-fqjem/events.out.tfevents.1747500048.r-igiag-document-classification-sknn8sdt-9892e-fqjem.106.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a8e21da2ab0247b0a7c2efed2c366d64bb695726275fe82d4fc7f8545a0c09
+size 906

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 sha256:386d50d48b9e9ac48b9d1ab7652d3a4a16710b21585eb4b6944eb9de6cd370b4
+size 5368

training_params.json

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