feature: Faz upload de arquivos do modelo

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[BOS]": 29794
+}

all_results.json

@@ -0,0 +1,66 @@
+{
+    "EOP_f1": 0.7691492742875305,
+    "EOP_number": 4774,
+    "EOP_precision": 0.7781350482315113,
+    "EOP_recall": 0.7603686635944701,
+    "accuracy": 0.9456432259834859,
+    "epoch": 5.0,
+    "eval_EOP_f1": 0.7546452702702704,
+    "eval_EOP_number": 2446,
+    "eval_EOP_precision": 0.780349344978166,
+    "eval_EOP_recall": 0.7305805396565822,
+    "eval_da_EOP_f1": 0.7679782903663502,
+    "eval_da_EOP_number": 2704,
+    "eval_da_EOP_precision": 0.8069246435845214,
+    "eval_da_EOP_recall": 0.7326183431952663,
+    "eval_da_overall_accuracy": 0.9443618109138235,
+    "eval_da_overall_f1": 0.7679782903663502,
+    "eval_da_overall_precision": 0.8069246435845214,
+    "eval_da_overall_recall": 0.7326183431952663,
+    "eval_loss": NaN,
+    "eval_overall_accuracy": 0.9436660687448489,
+    "eval_overall_f1": 0.7546452702702704,
+    "eval_overall_precision": 0.780349344978166,
+    "eval_overall_recall": 0.7305805396565822,
+    "eval_runtime": 115.155,
+    "eval_samples": 1523,
+    "eval_samples_per_second": 13.226,
+    "eval_steps_per_second": 3.309,
+    "overall_accuracy": 0.9456432259834859,
+    "overall_f1": 0.7691492742875305,
+    "overall_precision": 0.7781350482315113,
+    "overall_recall": 0.7603686635944701,
+    "predict_EOP_f1": 0.7691492742875305,
+    "predict_EOP_number": 4774,
+    "predict_EOP_precision": 0.7781350482315113,
+    "predict_EOP_recall": 0.7603686635944701,
+    "predict_da_EOP_f1": 0.7890958478851378,
+    "predict_da_EOP_number": 5339,
+    "predict_da_EOP_precision": 0.8184745421614007,
+    "predict_da_EOP_recall": 0.7617531372916276,
+    "predict_da_overall_accuracy": 0.9483659509785294,
+    "predict_da_overall_f1": 0.7890958478851378,
+    "predict_da_overall_precision": 0.8184745421614007,
+    "predict_da_overall_recall": 0.7617531372916276,
+    "predict_examples": 718,
+    "predict_loss": NaN,
+    "predict_overall_accuracy": 0.9456432259834859,
+    "predict_overall_f1": 0.7691492742875305,
+    "predict_overall_precision": 0.7781350482315113,
+    "predict_overall_recall": 0.7603686635944701,
+    "predict_runtime": 220.4272,
+    "predict_samples_per_second": 13.238,
+    "predict_steps_per_second": 3.312,
+    "threshold_0.5_example_level_1-pk": 0.8284,
+    "threshold_0.5_example_level_1-wd": 0.8055,
+    "threshold_0.5_example_level_f1": 0.7691,
+    "threshold_0.5_example_level_pk": 0.17159999999999997,
+    "threshold_0.5_example_level_precision": 0.7781,
+    "threshold_0.5_example_level_recall": 0.7604,
+    "threshold_0.5_example_level_wd": 0.1945,
+    "train_loss": 0.545391144610428,
+    "train_runtime": 12631.9735,
+    "train_samples": 10739,
+    "train_samples_per_second": 4.251,
+    "train_steps_per_second": 1.063
+}

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "architectures": [
+    "BertWithDAForSentenceLabelingTopicSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "cache_dir": null,
+  "cl_anchor_level": "eop_list",
+  "cl_loss_weight": 0.5,
+  "cl_negative_k": 3,
+  "cl_positive_k": 1,
+  "cl_temp": 0.1,
+  "classifier_dropout": null,
+  "config_name": null,
+  "directionality": "bidi",
+  "do_cssl": true,
+  "do_da_ts": true,
+  "do_tssp": true,
+  "finetuning_task": "topic_segment",
+  "focal_loss_gamma": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-EOP",
+    "1": "O"
+  },
+  "ignore_mismatched_sizes": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-EOP": 0,
+    "O": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "model_revision": "main",
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_gpu": 1,
+  "num_hidden_layers": 12,
+  "num_topic_labels": 0,
+  "num_tssp_labels": 3,
+  "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",
+  "sentence_pooler_type": null,
+  "tokenizer_name": null,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "ts_loss_weight": 1.0,
+  "ts_score_predictor": "lt",
+  "ts_score_predictor_cos_temp": 1,
+  "tssp_ablation": "none",
+  "tssp_loss_weight": 1.0,
+  "type_vocab_size": 2,
+  "use_auth_token": false,
+  "use_cache": true,
+  "vocab_size": 29795,
+  "weight_label_zero": 0.5
+}

eval_results.json

@@ -0,0 +1,24 @@
+{
+    "epoch": 5.0,
+    "eval_EOP_f1": 0.7546452702702704,
+    "eval_EOP_number": 2446,
+    "eval_EOP_precision": 0.780349344978166,
+    "eval_EOP_recall": 0.7305805396565822,
+    "eval_da_EOP_f1": 0.7679782903663502,
+    "eval_da_EOP_number": 2704,
+    "eval_da_EOP_precision": 0.8069246435845214,
+    "eval_da_EOP_recall": 0.7326183431952663,
+    "eval_da_overall_accuracy": 0.9443618109138235,
+    "eval_da_overall_f1": 0.7679782903663502,
+    "eval_da_overall_precision": 0.8069246435845214,
+    "eval_da_overall_recall": 0.7326183431952663,
+    "eval_loss": NaN,
+    "eval_overall_accuracy": 0.9436660687448489,
+    "eval_overall_f1": 0.7546452702702704,
+    "eval_overall_precision": 0.780349344978166,
+    "eval_overall_recall": 0.7305805396565822,
+    "eval_runtime": 115.155,
+    "eval_samples": 1523,
+    "eval_samples_per_second": 13.226,
+    "eval_steps_per_second": 3.309
+}

example_level_predict_wiki_section_disease_max_seq512_ts_score_lt_results.json

@@ -0,0 +1,19 @@
+{
+    "EOP_f1": 0.7691492742875305,
+    "EOP_number": 4774,
+    "EOP_precision": 0.7781350482315113,
+    "EOP_recall": 0.7603686635944701,
+    "accuracy": 0.9456432259834859,
+    "overall_accuracy": 0.9456432259834859,
+    "overall_f1": 0.7691492742875305,
+    "overall_precision": 0.7781350482315113,
+    "overall_recall": 0.7603686635944701,
+    "predict_examples": 718,
+    "threshold_0.5_example_level_1-pk": 0.8284,
+    "threshold_0.5_example_level_1-wd": 0.8055,
+    "threshold_0.5_example_level_f1": 0.7691,
+    "threshold_0.5_example_level_pk": 0.17159999999999997,
+    "threshold_0.5_example_level_precision": 0.7781,
+    "threshold_0.5_example_level_recall": 0.7604,
+    "threshold_0.5_example_level_wd": 0.1945
+}

example_level_predict_wiki_section_disease_max_seq512_ts_score_lt_results_str_metric.txt

@@ -0,0 +1,4 @@
+p / r / f / pk / wd
+threshold_0.5_example_level_metric
+77.81 / 76.04 / 76.91 / 17.16 / 19.45
+

predict_wiki_section_disease_max_seq512_ts_score_lt_results.json

@@ -0,0 +1,22 @@
+{
+    "predict_EOP_f1": 0.7691492742875305,
+    "predict_EOP_number": 4774,
+    "predict_EOP_precision": 0.7781350482315113,
+    "predict_EOP_recall": 0.7603686635944701,
+    "predict_da_EOP_f1": 0.7890958478851378,
+    "predict_da_EOP_number": 5339,
+    "predict_da_EOP_precision": 0.8184745421614007,
+    "predict_da_EOP_recall": 0.7617531372916276,
+    "predict_da_overall_accuracy": 0.9483659509785294,
+    "predict_da_overall_f1": 0.7890958478851378,
+    "predict_da_overall_precision": 0.8184745421614007,
+    "predict_da_overall_recall": 0.7617531372916276,
+    "predict_loss": NaN,
+    "predict_overall_accuracy": 0.9456432259834859,
+    "predict_overall_f1": 0.7691492742875305,
+    "predict_overall_precision": 0.7781350482315113,
+    "predict_overall_recall": 0.7603686635944701,
+    "predict_runtime": 220.4272,
+    "predict_samples_per_second": 13.238,
+    "predict_steps_per_second": 3.312
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567df42ee1adc5e4ede487db9d98b4c4f359c7e6e8506667892385c303303ff6
+size 435782697

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "[BOS]",
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/home/ext_maiara_frodrigues2000_gmail_/.cache/huggingface/hub/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.545391144610428,
+    "train_runtime": 12631.9735,
+    "train_samples": 10739,
+    "train_samples_per_second": 4.251,
+    "train_steps_per_second": 1.063
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.7546452702702704,
+  "best_model_checkpoint": "./output/neuralmind/bert-base-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-03_16:56:29/checkpoint-13420",
+  "epoch": 5.0,
+  "global_step": 13425,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.000372439478585e-05,
+      "loss": 0.9152,
+      "step": 2684
+    },
+    {
+      "epoch": 1.0,
+      "eval_EOP_f1": 0.7217790669567319,
+      "eval_EOP_number": 2446,
+      "eval_EOP_precision": 0.882909520993495,
+      "eval_EOP_recall": 0.6103843008994276,
+      "eval_da_EOP_f1": 0.7340590979782271,
+      "eval_da_EOP_number": 2704,
+      "eval_da_EOP_precision": 0.9193099610461881,
+      "eval_da_EOP_recall": 0.6109467455621301,
+      "eval_da_overall_accuracy": 0.9443618109138235,
+      "eval_da_overall_f1": 0.7340590979782271,
+      "eval_da_overall_precision": 0.9193099610461881,
+      "eval_da_overall_recall": 0.6109467455621301,
+      "eval_loss": NaN,
+      "eval_overall_accuracy": 0.9441993503660251,
+      "eval_overall_f1": 0.7217790669567319,
+      "eval_overall_precision": 0.882909520993495,
+      "eval_overall_recall": 0.6103843008994276,
+      "eval_runtime": 115.3406,
+      "eval_samples_per_second": 13.204,
+      "eval_steps_per_second": 3.303,
+      "step": 2684
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.0007448789571697e-05,
+      "loss": 0.6588,
+      "step": 5368
+    },
+    {
+      "epoch": 2.0,
+      "eval_EOP_f1": 0.7412026726057906,
+      "eval_EOP_number": 2446,
+      "eval_EOP_precision": 0.8140900195694716,
+      "eval_EOP_recall": 0.6802943581357318,
+      "eval_da_EOP_f1": 0.7685429790692948,
+      "eval_da_EOP_number": 2704,
+      "eval_da_EOP_precision": 0.8529544429409112,
+      "eval_da_EOP_recall": 0.6993343195266272,
+      "eval_da_overall_accuracy": 0.94705772985033,
+      "eval_da_overall_f1": 0.7685429790692948,
+      "eval_da_overall_precision": 0.8529544429409112,
+      "eval_da_overall_recall": 0.6993343195266272,
+      "eval_loss": NaN,
+      "eval_overall_accuracy": 0.9436660687448489,
+      "eval_overall_f1": 0.7412026726057906,
+      "eval_overall_precision": 0.8140900195694716,
+      "eval_overall_recall": 0.6802943581357318,
+      "eval_runtime": 115.0795,
+      "eval_samples_per_second": 13.234,
+      "eval_steps_per_second": 3.311,
+      "step": 5368
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.0011173184357543e-05,
+      "loss": 0.4949,
+      "step": 8052
+    },
+    {
+      "epoch": 3.0,
+      "eval_EOP_f1": 0.7511530858774434,
+      "eval_EOP_number": 2446,
+      "eval_EOP_precision": 0.8115804461319411,
+      "eval_EOP_recall": 0.6991005723630417,
+      "eval_da_EOP_f1": 0.7725617159044921,
+      "eval_da_EOP_number": 2704,
+      "eval_da_EOP_precision": 0.8529937444146559,
+      "eval_da_EOP_recall": 0.705991124260355,
+      "eval_da_overall_accuracy": 0.9477549502649437,
+      "eval_da_overall_f1": 0.7725617159044921,
+      "eval_da_overall_precision": 0.8529937444146559,
+      "eval_da_overall_recall": 0.705991124260355,
+      "eval_loss": NaN,
+      "eval_overall_accuracy": 0.9450719930188588,
+      "eval_overall_f1": 0.7511530858774434,
+      "eval_overall_precision": 0.8115804461319411,
+      "eval_overall_recall": 0.6991005723630417,
+      "eval_runtime": 114.897,
+      "eval_samples_per_second": 13.255,
+      "eval_steps_per_second": 3.316,
+      "step": 8052
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.001489757914339e-05,
+      "loss": 0.3741,
+      "step": 10736
+    },
+    {
+      "epoch": 4.0,
+      "eval_EOP_f1": 0.752757949383517,
+      "eval_EOP_number": 2446,
+      "eval_EOP_precision": 0.799265043638034,
+      "eval_EOP_recall": 0.7113654946852003,
+      "eval_da_EOP_f1": 0.7717067355454003,
+      "eval_da_EOP_number": 2704,
+      "eval_da_EOP_precision": 0.8338342636324603,
+      "eval_da_EOP_recall": 0.7181952662721893,
+      "eval_da_overall_accuracy": 0.9465929162405875,
+      "eval_da_overall_f1": 0.7717067355454003,
+      "eval_da_overall_precision": 0.8338342636324603,
+      "eval_da_overall_recall": 0.7181952662721893,
+      "eval_loss": NaN,
+      "eval_overall_accuracy": 0.9445871915450623,
+      "eval_overall_f1": 0.752757949383517,
+      "eval_overall_precision": 0.799265043638034,
+      "eval_overall_recall": 0.7113654946852003,
+      "eval_runtime": 114.8732,
+      "eval_samples_per_second": 13.258,
+      "eval_steps_per_second": 3.317,
+      "step": 10736
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.86219739292365e-08,
+      "loss": 0.2844,
+      "step": 13420
+    },
+    {
+      "epoch": 5.0,
+      "eval_EOP_f1": 0.7546452702702704,
+      "eval_EOP_number": 2446,
+      "eval_EOP_precision": 0.780349344978166,
+      "eval_EOP_recall": 0.7305805396565822,
+      "eval_da_EOP_f1": 0.7679782903663502,
+      "eval_da_EOP_number": 2704,
+      "eval_da_EOP_precision": 0.8069246435845214,
+      "eval_da_EOP_recall": 0.7326183431952663,
+      "eval_da_overall_accuracy": 0.9443618109138235,
+      "eval_da_overall_f1": 0.7679782903663502,
+      "eval_da_overall_precision": 0.8069246435845214,
+      "eval_da_overall_recall": 0.7326183431952663,
+      "eval_loss": NaN,
+      "eval_overall_accuracy": 0.9436660687448489,
+      "eval_overall_f1": 0.7546452702702704,
+      "eval_overall_precision": 0.780349344978166,
+      "eval_overall_recall": 0.7305805396565822,
+      "eval_runtime": 114.7975,
+      "eval_samples_per_second": 13.267,
+      "eval_steps_per_second": 3.319,
+      "step": 13420
+    },
+    {
+      "epoch": 5.0,
+      "step": 13425,
+      "total_flos": 2.825625731920896e+16,
+      "train_loss": 0.545391144610428,
+      "train_runtime": 12631.9735,
+      "train_samples_per_second": 4.251,
+      "train_steps_per_second": 1.063
+    }
+  ],
+  "max_steps": 13425,
+  "num_train_epochs": 5,
+  "total_flos": 2.825625731920896e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3194332b372ea2b036e0fccb377db061e11a589363b40609c5b08e15e729e4f7
+size 3759