Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: rss9051/autotrein-BERT-iiLEX-dgs-0003
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 1.5718337297439575
+
+f1_macro: 0.5764297665936106
+
+f1_micro: 0.6607142857142857
+
+f1_weighted: 0.6685474450942381
+
+precision_macro: 0.5781369792997699
+
+precision_micro: 0.6607142857142857
+
+precision_weighted: 0.6808154556545336
+
+recall_macro: 0.5778714544420972
+
+recall_micro: 0.6607142857142857
+
+recall_weighted: 0.6607142857142857
+
+accuracy: 0.6607142857142857

checkpoint-112/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "rss9051/autotrein-BERT-iiLEX-dgs-0003",
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "1 - INTIMA\u00c7\u00c3O INICIAL",
+    "1": "2 - INTIMA\u00c7\u00c3O INSTRU\u00c7\u00c3O",
+    "2": "3 - INTIMA\u00c7\u00c3O RECURSAL",
+    "3": "4 - INTIMA\u00c7\u00c3O CUMPRIMENTO DE SENTEN\u00c7A",
+    "4": "5 - INTIMA\u00c7\u00c3O TR\u00c2NSITO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "1 - INTIMA\u00c7\u00c3O INICIAL": 0,
+    "2 - INTIMA\u00c7\u00c3O INSTRU\u00c7\u00c3O": 1,
+    "3 - INTIMA\u00c7\u00c3O RECURSAL": 2,
+    "4 - INTIMA\u00c7\u00c3O CUMPRIMENTO DE SENTEN\u00c7A": 3,
+    "5 - INTIMA\u00c7\u00c3O TR\u00c2NSITO": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "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": 29794
+}

checkpoint-112/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e862230639b434d621415800f8f78f8357102efe8d1f6c75d4f0e442b4d432ba
+size 435731452

checkpoint-112/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a5351bcb40dd62c95fde697f7843d7cd45698ad2f8b327562c7ee2bc13d4d6
+size 871578362

checkpoint-112/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b456c81202d31e710b49d15ba22807b951015bcd98801e116a131e7ece372405
+size 13990

checkpoint-112/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab0cb6f06ff9e8ddeb90c4504035e1188707df9046a29fb9907dfbf1bbac175
+size 1064

checkpoint-112/trainer_state.json

@@ -0,0 +1,214 @@
+{
+  "best_metric": 1.5718337297439575,
+  "best_model_checkpoint": "autotrein-BERT-iiLEX-dgs-0004/checkpoint-112",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.044642857142857144,
+      "grad_norm": 2.0444529056549072,
+      "learning_rate": 7.3529411764705884e-06,
+      "loss": 0.266,
+      "step": 5
+    },
+    {
+      "epoch": 0.08928571428571429,
+      "grad_norm": 17.472654342651367,
+      "learning_rate": 1.4705882352941177e-05,
+      "loss": 0.1248,
+      "step": 10
+    },
+    {
+      "epoch": 0.13392857142857142,
+      "grad_norm": 6.122802257537842,
+      "learning_rate": 2.2058823529411766e-05,
+      "loss": 0.1436,
+      "step": 15
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 12.507484436035156,
+      "learning_rate": 2.9411764705882354e-05,
+      "loss": 0.1236,
+      "step": 20
+    },
+    {
+      "epoch": 0.22321428571428573,
+      "grad_norm": 1.480406403541565,
+      "learning_rate": 3.6764705882352945e-05,
+      "loss": 0.0626,
+      "step": 25
+    },
+    {
+      "epoch": 0.26785714285714285,
+      "grad_norm": 0.38904812932014465,
+      "learning_rate": 4.411764705882353e-05,
+      "loss": 0.0915,
+      "step": 30
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.2865840792655945,
+      "learning_rate": 4.983443708609272e-05,
+      "loss": 0.0897,
+      "step": 35
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 25.76744842529297,
+      "learning_rate": 4.900662251655629e-05,
+      "loss": 0.0871,
+      "step": 40
+    },
+    {
+      "epoch": 0.4017857142857143,
+      "grad_norm": 0.760350227355957,
+      "learning_rate": 4.8178807947019873e-05,
+      "loss": 0.0056,
+      "step": 45
+    },
+    {
+      "epoch": 0.44642857142857145,
+      "grad_norm": 11.40116024017334,
+      "learning_rate": 4.735099337748345e-05,
+      "loss": 0.0448,
+      "step": 50
+    },
+    {
+      "epoch": 0.49107142857142855,
+      "grad_norm": 0.7093308568000793,
+      "learning_rate": 4.652317880794702e-05,
+      "loss": 0.005,
+      "step": 55
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 13.429608345031738,
+      "learning_rate": 4.56953642384106e-05,
+      "loss": 0.1927,
+      "step": 60
+    },
+    {
+      "epoch": 0.5803571428571429,
+      "grad_norm": 18.583410263061523,
+      "learning_rate": 4.4867549668874174e-05,
+      "loss": 0.3076,
+      "step": 65
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.15568283200263977,
+      "learning_rate": 4.403973509933775e-05,
+      "loss": 0.227,
+      "step": 70
+    },
+    {
+      "epoch": 0.6696428571428571,
+      "grad_norm": 21.115196228027344,
+      "learning_rate": 4.321192052980133e-05,
+      "loss": 0.1072,
+      "step": 75
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.23123915493488312,
+      "learning_rate": 4.23841059602649e-05,
+      "loss": 0.2157,
+      "step": 80
+    },
+    {
+      "epoch": 0.7589285714285714,
+      "grad_norm": 1.810465931892395,
+      "learning_rate": 4.155629139072848e-05,
+      "loss": 0.0198,
+      "step": 85
+    },
+    {
+      "epoch": 0.8035714285714286,
+      "grad_norm": 7.193124771118164,
+      "learning_rate": 4.0728476821192055e-05,
+      "loss": 0.2872,
+      "step": 90
+    },
+    {
+      "epoch": 0.8482142857142857,
+      "grad_norm": 0.040846243500709534,
+      "learning_rate": 3.990066225165563e-05,
+      "loss": 0.1349,
+      "step": 95
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 1.4968816041946411,
+      "learning_rate": 3.907284768211921e-05,
+      "loss": 0.0838,
+      "step": 100
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.02432333491742611,
+      "learning_rate": 3.824503311258278e-05,
+      "loss": 0.0513,
+      "step": 105
+    },
+    {
+      "epoch": 0.9821428571428571,
+      "grad_norm": 11.377039909362793,
+      "learning_rate": 3.741721854304636e-05,
+      "loss": 0.6275,
+      "step": 110
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6607142857142857,
+      "eval_f1_macro": 0.5764297665936106,
+      "eval_f1_micro": 0.6607142857142857,
+      "eval_f1_weighted": 0.6685474450942381,
+      "eval_loss": 1.5718337297439575,
+      "eval_precision_macro": 0.5781369792997699,
+      "eval_precision_micro": 0.6607142857142857,
+      "eval_precision_weighted": 0.6808154556545336,
+      "eval_recall_macro": 0.5778714544420972,
+      "eval_recall_micro": 0.6607142857142857,
+      "eval_recall_weighted": 0.6607142857142857,
+      "eval_runtime": 266.3448,
+      "eval_samples_per_second": 0.841,
+      "eval_steps_per_second": 0.053,
+      "step": 112
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 336,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 235753855647744.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-112/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f994341241ba90be91228ec7a602f6de5e0556ebd324acdcc374266428f117a
+size 5304

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "rss9051/autotrein-BERT-iiLEX-dgs-0003",
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "1 - INTIMA\u00c7\u00c3O INICIAL",
+    "1": "2 - INTIMA\u00c7\u00c3O INSTRU\u00c7\u00c3O",
+    "2": "3 - INTIMA\u00c7\u00c3O RECURSAL",
+    "3": "4 - INTIMA\u00c7\u00c3O CUMPRIMENTO DE SENTEN\u00c7A",
+    "4": "5 - INTIMA\u00c7\u00c3O TR\u00c2NSITO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "1 - INTIMA\u00c7\u00c3O INICIAL": 0,
+    "2 - INTIMA\u00c7\u00c3O INSTRU\u00c7\u00c3O": 1,
+    "3 - INTIMA\u00c7\u00c3O RECURSAL": 2,
+    "4 - INTIMA\u00c7\u00c3O CUMPRIMENTO DE SENTEN\u00c7A": 3,
+    "5 - INTIMA\u00c7\u00c3O TR\u00c2NSITO": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "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": 29794
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e862230639b434d621415800f8f78f8357102efe8d1f6c75d4f0e442b4d432ba
+size 435731452

runs/Nov29_20-38-16_r-rss9051-helloword-ruz7g2f3-654e6-pbts8/events.out.tfevents.1732912699.r-rss9051-helloword-ruz7g2f3-654e6-pbts8.148.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cfa4296eb88439e7798bb40029fb7b62be8c76f9cbb27253e29d07999ba11d3
-size 20590
+oid sha256:9b7973f838b539144e48c7cc30e950cac2be763260dd93b744ba5e21fda05baa
+size 22832

runs/Nov29_20-38-16_r-rss9051-helloword-ruz7g2f3-654e6-pbts8/events.out.tfevents.1732924116.r-rss9051-helloword-ruz7g2f3-654e6-pbts8.148.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ca2e210f1ea2b2b4ed106668feb3dd99369adbc2fe748741bf9afa8b7370c2
+size 921

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f994341241ba90be91228ec7a602f6de5e0556ebd324acdcc374266428f117a
+size 5304

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrein-BERT-iiLEX-dgs-0004/autotrain-data",
+    "model": "rss9051/autotrein-BERT-iiLEX-dgs-0003",
+    "lr": 5e-05,
+    "epochs": 3,
+    "max_seq_length": 512,
+    "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": "autotrein-BERT-iiLEX-dgs-0004",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "rss9051",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}