Upload folder using huggingface_hub

training_checkpoints/checkpoint-4501/config.json

@@ -0,0 +1,78 @@
+{
+  "_name_or_path": "xlnet/xlnet-base-cased",
+  "architectures": [
+    "XLNetForSequenceClassification"
+  ],
+  "attn_type": "bi",
+  "bi_data": false,
+  "bos_token_id": 1,
+  "clamp_len": -1,
+  "d_head": 64,
+  "d_inner": 3072,
+  "d_model": 768,
+  "dropout": 0.1,
+  "end_n_top": 5,
+  "eos_token_id": 2,
+  "ff_activation": "gelu",
+  "id2label": {
+    "0": "Issue",
+    "1": "Court Discourse",
+    "2": "Conclusion",
+    "3": "Precedent Analysis",
+    "4": "Section Analysis",
+    "5": "Argument by Petitioner",
+    "6": "Fact",
+    "7": "Argument by Respondent",
+    "8": "Ratio",
+    "9": "Appellant",
+    "10": "Respondent",
+    "11": "Argument by Appellant",
+    "12": "Petitioner",
+    "13": "Judge",
+    "14": "Argument by Defendant"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Appellant": 9,
+    "Argument by Appellant": 11,
+    "Argument by Defendant": 14,
+    "Argument by Petitioner": 5,
+    "Argument by Respondent": 7,
+    "Conclusion": 2,
+    "Court Discourse": 1,
+    "Fact": 6,
+    "Issue": 0,
+    "Judge": 13,
+    "Petitioner": 12,
+    "Precedent Analysis": 3,
+    "Ratio": 8,
+    "Respondent": 10,
+    "Section Analysis": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "mem_len": null,
+  "model_type": "xlnet",
+  "n_head": 12,
+  "n_layer": 12,
+  "pad_token_id": 5,
+  "problem_type": "single_label_classification",
+  "reuse_len": null,
+  "same_length": false,
+  "start_n_top": 5,
+  "summary_activation": "tanh",
+  "summary_last_dropout": 0.1,
+  "summary_type": "last",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 250
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
+}

training_checkpoints/checkpoint-4501/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd2226f2b8234a49b9205a17fedad8a144ee64af9d8c79e7b3a4dbc2bad9490
+size 469304588

training_checkpoints/checkpoint-4501/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1103438a567d1545c3d420d060a23a7d27fc2aa96743ed1159f2405d0f8bc3b2
+size 938733178

training_checkpoints/checkpoint-4501/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09618f6d1e998ad862ffbb6a0347cf2690661da10da98fb9312c6197f4d1df20
+size 14244

training_checkpoints/checkpoint-4501/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e991f1bac27bcba60bce2f4b3d141a477e7c85eec8f3e0c54ae0eab698714594
+size 1064

training_checkpoints/checkpoint-4501/special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

training_checkpoints/checkpoint-4501/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
+size 798011

training_checkpoints/checkpoint-4501/tokenizer_config.json

@@ -0,0 +1,94 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "keep_accents": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "<sep>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLNetTokenizer",
+  "unk_token": "<unk>"
+}

training_checkpoints/checkpoint-4501/trainer_state.json

@@ -0,0 +1,227 @@
+{
+  "best_metric": 0.7667275846579111,
+  "best_model_checkpoint": "xlnet-base-cased/checkpoint-4501",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 4501,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.871695178849145e-05,
+      "loss": 1.2613,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7676219984508134,
+      "eval_f1_macro": 0.4818756771742453,
+      "eval_f1_micro": 0.7676219984508135,
+      "eval_f1_weighted": 0.7524385212708887,
+      "eval_loss": 0.775787353515625,
+      "eval_macro_fpr": 0.022019799606126652,
+      "eval_macro_sensitivity": 0.5128622254580788,
+      "eval_macro_specificity": 0.9823717840367622,
+      "eval_precision": 0.7672637518290021,
+      "eval_precision_macro": 0.5269420024270713,
+      "eval_recall": 0.7676219984508134,
+      "eval_recall_macro": 0.5128622254580788,
+      "eval_runtime": 65.0712,
+      "eval_samples_per_second": 19.84,
+      "eval_steps_per_second": 2.49,
+      "eval_weighted_fpr": 0.021165514321998025,
+      "eval_weighted_sensitivity": 0.7676219984508134,
+      "eval_weighted_specificity": 0.9679547621006213,
+      "step": 643
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.7420943494038366e-05,
+      "loss": 0.7364,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8071262587141751,
+      "eval_f1_macro": 0.701878478303997,
+      "eval_f1_micro": 0.8071262587141751,
+      "eval_f1_weighted": 0.8012788916547595,
+      "eval_loss": 0.6754755973815918,
+      "eval_macro_fpr": 0.01739858713969909,
+      "eval_macro_sensitivity": 0.6971761972643127,
+      "eval_macro_specificity": 0.9854830758512745,
+      "eval_precision": 0.8087721671110009,
+      "eval_precision_macro": 0.7425135911700289,
+      "eval_recall": 0.8071262587141751,
+      "eval_recall_macro": 0.6971761972643127,
+      "eval_runtime": 86.774,
+      "eval_samples_per_second": 14.878,
+      "eval_steps_per_second": 1.867,
+      "eval_weighted_fpr": 0.016782368403316036,
+      "eval_weighted_sensitivity": 0.8071262587141751,
+      "eval_weighted_specificity": 0.9751198790549438,
+      "step": 1286
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 4.612493519958528e-05,
+      "loss": 0.6021,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8063516653756778,
+      "eval_f1_macro": 0.722931923188587,
+      "eval_f1_micro": 0.8063516653756778,
+      "eval_f1_weighted": 0.8013697737227732,
+      "eval_loss": 0.8442708253860474,
+      "eval_macro_fpr": 0.01757802934678216,
+      "eval_macro_sensitivity": 0.7262014539622089,
+      "eval_macro_specificity": 0.9852110484486459,
+      "eval_precision": 0.8016312862866737,
+      "eval_precision_macro": 0.7269969408457856,
+      "eval_recall": 0.8063516653756778,
+      "eval_recall_macro": 0.7262014539622089,
+      "eval_runtime": 89.8454,
+      "eval_samples_per_second": 14.369,
+      "eval_steps_per_second": 1.803,
+      "eval_weighted_fpr": 0.01686454398273071,
+      "eval_weighted_sensitivity": 0.8063516653756778,
+      "eval_weighted_specificity": 0.9718140613540133,
+      "step": 1929
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 4.4828926905132196e-05,
+      "loss": 0.5435,
+      "step": 2000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 4.353551062726802e-05,
+      "loss": 0.4361,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8001549186676995,
+      "eval_f1_macro": 0.7051095861561788,
+      "eval_f1_micro": 0.8001549186676995,
+      "eval_f1_weighted": 0.7970808578587494,
+      "eval_loss": 0.8849796056747437,
+      "eval_macro_fpr": 0.017973543700983616,
+      "eval_macro_sensitivity": 0.704754303632947,
+      "eval_macro_specificity": 0.984883284344937,
+      "eval_precision": 0.8001040615771999,
+      "eval_precision_macro": 0.716655759638538,
+      "eval_recall": 0.8001549186676995,
+      "eval_recall_macro": 0.704754303632947,
+      "eval_runtime": 88.029,
+      "eval_samples_per_second": 14.666,
+      "eval_steps_per_second": 1.84,
+      "eval_weighted_fpr": 0.017527173913043478,
+      "eval_weighted_sensitivity": 0.8001549186676995,
+      "eval_weighted_specificity": 0.9730943465063553,
+      "step": 2572
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 4.223950233281493e-05,
+      "loss": 0.3359,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.801704105344694,
+      "eval_f1_macro": 0.6458763793901992,
+      "eval_f1_micro": 0.801704105344694,
+      "eval_f1_weighted": 0.7961730342415405,
+      "eval_loss": 1.126444935798645,
+      "eval_macro_fpr": 0.01805997413754306,
+      "eval_macro_sensitivity": 0.6681366041180199,
+      "eval_macro_specificity": 0.9849908327913178,
+      "eval_precision": 0.7981459541145973,
+      "eval_precision_macro": 0.6531140613829887,
+      "eval_recall": 0.801704105344694,
+      "eval_recall_macro": 0.6681366041180199,
+      "eval_runtime": 90.8127,
+      "eval_samples_per_second": 14.216,
+      "eval_steps_per_second": 1.784,
+      "eval_weighted_fpr": 0.0173606401736064,
+      "eval_weighted_sensitivity": 0.801704105344694,
+      "eval_weighted_specificity": 0.973158386525071,
+      "step": 3215
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 4.0943494038361847e-05,
+      "loss": 0.2827,
+      "step": 3500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7993803253292022,
+      "eval_f1_macro": 0.7042383323872946,
+      "eval_f1_micro": 0.7993803253292022,
+      "eval_f1_weighted": 0.7951558065494785,
+      "eval_loss": 1.1471006870269775,
+      "eval_macro_fpr": 0.01833120632003448,
+      "eval_macro_sensitivity": 0.692160115457962,
+      "eval_macro_specificity": 0.9845339432297603,
+      "eval_precision": 0.8091520232110664,
+      "eval_precision_macro": 0.7389074945114087,
+      "eval_recall": 0.7993803253292022,
+      "eval_recall_macro": 0.692160115457962,
+      "eval_runtime": 89.506,
+      "eval_samples_per_second": 14.424,
+      "eval_steps_per_second": 1.81,
+      "eval_weighted_fpr": 0.017610661589719183,
+      "eval_weighted_sensitivity": 0.7993803253292022,
+      "eval_weighted_specificity": 0.9686288231172028,
+      "step": 3858
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 3.964748574390876e-05,
+      "loss": 0.2626,
+      "step": 4000
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.835147744945568e-05,
+      "loss": 0.1945,
+      "step": 4500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.814872192099148,
+      "eval_f1_macro": 0.7667275846579111,
+      "eval_f1_micro": 0.814872192099148,
+      "eval_f1_weighted": 0.812156980007075,
+      "eval_loss": 1.1841164827346802,
+      "eval_macro_fpr": 0.016569799909363286,
+      "eval_macro_sensitivity": 0.7598143558862378,
+      "eval_macro_specificity": 0.9859673331635007,
+      "eval_precision": 0.8128843369221012,
+      "eval_precision_macro": 0.7850186311075981,
+      "eval_recall": 0.814872192099148,
+      "eval_recall_macro": 0.7598143558862378,
+      "eval_runtime": 89.1729,
+      "eval_samples_per_second": 14.477,
+      "eval_steps_per_second": 1.817,
+      "eval_weighted_fpr": 0.015968463954032203,
+      "eval_weighted_sensitivity": 0.814872192099148,
+      "eval_weighted_specificity": 0.974637805353365,
+      "step": 4501
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 19290,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 1.0247108678424576e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-4501/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec20e9f8adfcfee3337ee75e60d11aa0228a2bd24494baa212e8cd20722381d4
+size 4600