Upload folder using huggingface_hub

training_checkpoints/checkpoint-1568/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 30522
+}

training_checkpoints/checkpoint-1568/config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "nlpaueb/legal-bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_ids": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "positive",
+    "1": "negative",
+    "2": "neutral",
+    "3": "rel_by_party"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 1,
+    "neutral": 2,
+    "positive": 0,
+    "rel_by_party": 3
+  },
+  "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": 30522,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30523
+}

training_checkpoints/checkpoint-1568/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1d82e67d25f01efb4eae38a075e41ec235d88ff4eaafd0a3f27d836cb32a7c
+size 437967872

training_checkpoints/checkpoint-1568/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56133d3fa86da7e2da6af8ae719ab74a13a19b826a489ed04896b2602cf3eb97
+size 876056826

training_checkpoints/checkpoint-1568/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8335c8b9680f9a1351ace33a028e811c2c0313c567cb65c91afc62b6165a4657
+size 14244

training_checkpoints/checkpoint-1568/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed585f8ee302e7c62531631104fe45916e53f9b76025901bb9cd160936008b1
+size 1064

training_checkpoints/checkpoint-1568/special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

training_checkpoints/checkpoint-1568/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "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
+    },
+    "30522": {
+      "content": "<pad>",
+      "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": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_checkpoints/checkpoint-1568/trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": 0.6741993002516824,
+  "best_model_checkpoint": "case-analysis-legal-bert-base-uncased/checkpoint-1568",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1568,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6570155902004454,
+      "eval_f1_macro": 0.4081263564022185,
+      "eval_f1_micro": 0.6570155902004454,
+      "eval_f1_weighted": 0.6166399839312825,
+      "eval_loss": 1.0114229917526245,
+      "eval_macro_fpr": 0.19475132363363487,
+      "eval_macro_sensitivity": 0.40746667217255456,
+      "eval_macro_specificity": 0.8324392236563901,
+      "eval_precision": 0.6178816225558943,
+      "eval_precision_macro": 0.4664000256488353,
+      "eval_recall": 0.6570155902004454,
+      "eval_recall_macro": 0.40746667217255456,
+      "eval_runtime": 7.3199,
+      "eval_samples_per_second": 61.34,
+      "eval_steps_per_second": 7.787,
+      "eval_weighted_fpr": 0.1482194417709336,
+      "eval_weighted_sensitivity": 0.6570155902004454,
+      "eval_weighted_specificity": 0.6727413044251147,
+      "step": 224
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7750556792873051,
+      "eval_f1_macro": 0.5658663855845003,
+      "eval_f1_micro": 0.775055679287305,
+      "eval_f1_weighted": 0.7564492543508543,
+      "eval_loss": 0.764952540397644,
+      "eval_macro_fpr": 0.10943701020063132,
+      "eval_macro_sensitivity": 0.5805958747135218,
+      "eval_macro_specificity": 0.9039084791647444,
+      "eval_precision": 0.7425093237919278,
+      "eval_precision_macro": 0.5566158325717437,
+      "eval_recall": 0.7750556792873051,
+      "eval_recall_macro": 0.5805958747135218,
+      "eval_runtime": 30.7218,
+      "eval_samples_per_second": 14.615,
+      "eval_steps_per_second": 1.855,
+      "eval_weighted_fpr": 0.08820960698689956,
+      "eval_weighted_sensitivity": 0.7750556792873051,
+      "eval_weighted_specificity": 0.8405782373716723,
+      "step": 448
+    },
+    {
+      "epoch": 2.232142857142857,
+      "grad_norm": 9.53757095336914,
+      "learning_rate": 4.631696428571429e-05,
+      "loss": 0.7677,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7817371937639198,
+      "eval_f1_macro": 0.5707248076329534,
+      "eval_f1_micro": 0.7817371937639198,
+      "eval_f1_weighted": 0.7678448816993292,
+      "eval_loss": 0.7341566681861877,
+      "eval_macro_fpr": 0.10409605667370833,
+      "eval_macro_sensitivity": 0.5967117805353099,
+      "eval_macro_specificity": 0.9083046086144851,
+      "eval_precision": 0.7694906286035585,
+      "eval_precision_macro": 0.5673619923602318,
+      "eval_recall": 0.7817371937639198,
+      "eval_recall_macro": 0.5967117805353099,
+      "eval_runtime": 32.9882,
+      "eval_samples_per_second": 13.611,
+      "eval_steps_per_second": 1.728,
+      "eval_weighted_fpr": 0.08514335360556038,
+      "eval_weighted_sensitivity": 0.7817371937639198,
+      "eval_weighted_specificity": 0.8514812406940205,
+      "step": 672
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8173719376391982,
+      "eval_f1_macro": 0.5903876477694423,
+      "eval_f1_micro": 0.8173719376391981,
+      "eval_f1_weighted": 0.7920921547144288,
+      "eval_loss": 0.7967568635940552,
+      "eval_macro_fpr": 0.09654289346260755,
+      "eval_macro_sensitivity": 0.5892796922208687,
+      "eval_macro_specificity": 0.9135512326349768,
+      "eval_precision": 0.776630887817645,
+      "eval_precision_macro": 0.6035747039094435,
+      "eval_recall": 0.8173719376391982,
+      "eval_recall_macro": 0.5892796922208687,
+      "eval_runtime": 31.5737,
+      "eval_samples_per_second": 14.221,
+      "eval_steps_per_second": 1.805,
+      "eval_weighted_fpr": 0.06931530008453085,
+      "eval_weighted_sensitivity": 0.8173719376391982,
+      "eval_weighted_specificity": 0.836832992900709,
+      "step": 896
+    },
+    {
+      "epoch": 4.464285714285714,
+      "grad_norm": 0.4865407943725586,
+      "learning_rate": 4.260416666666667e-05,
+      "loss": 0.482,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8084632516703786,
+      "eval_f1_macro": 0.6140549414742963,
+      "eval_f1_micro": 0.8084632516703786,
+      "eval_f1_weighted": 0.7940411816552344,
+      "eval_loss": 0.8170605301856995,
+      "eval_macro_fpr": 0.09903328320796416,
+      "eval_macro_sensitivity": 0.6038384641325818,
+      "eval_macro_specificity": 0.9107621964110777,
+      "eval_precision": 0.7852994506060567,
+      "eval_precision_macro": 0.6365555789178582,
+      "eval_recall": 0.8084632516703786,
+      "eval_recall_macro": 0.6038384641325818,
+      "eval_runtime": 33.691,
+      "eval_samples_per_second": 13.327,
+      "eval_steps_per_second": 1.692,
+      "eval_weighted_fpr": 0.07319148936170213,
+      "eval_weighted_sensitivity": 0.8084632516703786,
+      "eval_weighted_specificity": 0.8345855339739323,
+      "step": 1120
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8240534521158129,
+      "eval_f1_macro": 0.6314846316884821,
+      "eval_f1_micro": 0.8240534521158129,
+      "eval_f1_weighted": 0.8083544635272152,
+      "eval_loss": 0.8909738659858704,
+      "eval_macro_fpr": 0.087529695086195,
+      "eval_macro_sensitivity": 0.6358500402618049,
+      "eval_macro_specificity": 0.9211652121242622,
+      "eval_precision": 0.8028335761470152,
+      "eval_precision_macro": 0.6659870176540079,
+      "eval_recall": 0.8240534521158129,
+      "eval_recall_macro": 0.6358500402618049,
+      "eval_runtime": 32.5936,
+      "eval_samples_per_second": 13.776,
+      "eval_steps_per_second": 1.749,
+      "eval_weighted_fpr": 0.06644238856181665,
+      "eval_weighted_sensitivity": 0.8240534521158129,
+      "eval_weighted_specificity": 0.8606073963812356,
+      "step": 1344
+    },
+    {
+      "epoch": 6.696428571428571,
+      "grad_norm": 24.31475257873535,
+      "learning_rate": 3.888392857142857e-05,
+      "loss": 0.2993,
+      "step": 1500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8040089086859689,
+      "eval_f1_macro": 0.6741993002516824,
+      "eval_f1_micro": 0.8040089086859689,
+      "eval_f1_weighted": 0.8067155865282774,
+      "eval_loss": 1.0094465017318726,
+      "eval_macro_fpr": 0.08913550870826559,
+      "eval_macro_sensitivity": 0.6773721773721774,
+      "eval_macro_specificity": 0.9217242184731483,
+      "eval_precision": 0.8108961670502116,
+      "eval_precision_macro": 0.6741723864688478,
+      "eval_recall": 0.8040089086859689,
+      "eval_recall_macro": 0.6773721773721774,
+      "eval_runtime": 33.2368,
+      "eval_samples_per_second": 13.509,
+      "eval_steps_per_second": 1.715,
+      "eval_weighted_fpr": 0.07514944491887275,
+      "eval_weighted_sensitivity": 0.8040089086859689,
+      "eval_weighted_specificity": 0.8828879652066246,
+      "step": 1568
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 3300524345524224.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-1568/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8124b12bb2d716832b587bea11323810e8fd3f54cf265a6935c0b9d891cdd1f6
+size 5048