Upload folder using huggingface_hub

training_checkpoints/checkpoint-20552/config.json

@@ -0,0 +1,99 @@
+{
+  "_name_or_path": "facebook/bart-large",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "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
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

training_checkpoints/checkpoint-20552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50adaf043e2e2d3ab51c38fed9733c58d82086b0aa1af109ebb387456717ebf6
+size 1629486164

training_checkpoints/checkpoint-20552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10fe2c0d62164c1b9114e776b93522b18968e94510baebc2b657f547a2b7525b
+size 3259283099

training_checkpoints/checkpoint-20552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d0bab989f8c8caafe22258b4fc03aaf03b26eccf35352a86b31d929830cf256
+size 14244

training_checkpoints/checkpoint-20552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000e9cfd32239dfc443cd3403054554767a064760585feefa087620671a465d4
+size 1064

training_checkpoints/checkpoint-20552/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

training_checkpoints/checkpoint-20552/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_checkpoints/checkpoint-20552/trainer_state.json

@@ -0,0 +1,441 @@
+{
+  "best_metric": 0.6979809418287721,
+  "best_model_checkpoint": "bart-large/checkpoint-20552",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 20552,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.967886337096146e-05,
+      "loss": 2.0273,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.9354482937589206e-05,
+      "loss": 1.4983,
+      "step": 1000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.903140002595043e-05,
+      "loss": 1.4727,
+      "step": 1500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.870701959257818e-05,
+      "loss": 1.3945,
+      "step": 2000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.8383287920072665e-05,
+      "loss": 1.1685,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6847405112316034,
+      "eval_f1_macro": 0.4296023125768376,
+      "eval_f1_micro": 0.6847405112316034,
+      "eval_f1_weighted": 0.6471198955620663,
+      "eval_loss": 1.258675456047058,
+      "eval_macro_fpr": 0.03310536835500512,
+      "eval_macro_sensitivity": 0.47197476920519743,
+      "eval_macro_specificity": 0.9759825618150952,
+      "eval_precision": 0.6359796796355663,
+      "eval_precision_macro": 0.4175869918662546,
+      "eval_recall": 0.6847405112316034,
+      "eval_recall_macro": 0.47197476920519743,
+      "eval_runtime": 166.2079,
+      "eval_samples_per_second": 7.767,
+      "eval_steps_per_second": 3.887,
+      "eval_weighted_fpr": 0.03183916138621607,
+      "eval_weighted_sensitivity": 0.6847405112316034,
+      "eval_weighted_specificity": 0.9549979159948256,
+      "step": 2569
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 4.80589074867004e-05,
+      "loss": 1.2814,
+      "step": 3000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.7734527053328146e-05,
+      "loss": 1.2579,
+      "step": 3500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.741079538082263e-05,
+      "loss": 1.246,
+      "step": 4000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 4.708641494745037e-05,
+      "loss": 1.0685,
+      "step": 4500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 4.676203451407811e-05,
+      "loss": 1.1965,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6638264910921766,
+      "eval_f1_macro": 0.3954707529203812,
+      "eval_f1_micro": 0.6638264910921766,
+      "eval_f1_weighted": 0.6467821848395333,
+      "eval_loss": 1.1623183488845825,
+      "eval_macro_fpr": 0.03422706134984445,
+      "eval_macro_sensitivity": 0.4261017849773373,
+      "eval_macro_specificity": 0.9752839802406176,
+      "eval_precision": 0.6943370263824146,
+      "eval_precision_macro": 0.45636498568634104,
+      "eval_recall": 0.6638264910921766,
+      "eval_recall_macro": 0.4261017849773373,
+      "eval_runtime": 320.2013,
+      "eval_samples_per_second": 4.032,
+      "eval_steps_per_second": 2.017,
+      "eval_weighted_fpr": 0.03490990990990991,
+      "eval_weighted_sensitivity": 0.6638264910921766,
+      "eval_weighted_specificity": 0.9654332125170877,
+      "step": 5138
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.643765408070585e-05,
+      "loss": 1.0697,
+      "step": 5500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 4.611327364733359e-05,
+      "loss": 1.1042,
+      "step": 6000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 4.578954197482808e-05,
+      "loss": 1.124,
+      "step": 6500
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.546516154145582e-05,
+      "loss": 1.1449,
+      "step": 7000
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 4.514078110808356e-05,
+      "loss": 1.189,
+      "step": 7500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7234701781564679,
+      "eval_f1_macro": 0.5196282925085354,
+      "eval_f1_micro": 0.7234701781564679,
+      "eval_f1_weighted": 0.7031290239201134,
+      "eval_loss": 1.357356309890747,
+      "eval_macro_fpr": 0.027073020005110214,
+      "eval_macro_sensitivity": 0.5527845991176076,
+      "eval_macro_specificity": 0.9790845865453512,
+      "eval_precision": 0.7219921821470505,
+      "eval_precision_macro": 0.5413306235947684,
+      "eval_recall": 0.7234701781564679,
+      "eval_recall_macro": 0.5527845991176076,
+      "eval_runtime": 290.3268,
+      "eval_samples_per_second": 4.447,
+      "eval_steps_per_second": 2.225,
+      "eval_weighted_fpr": 0.026576341844710787,
+      "eval_weighted_sensitivity": 0.7234701781564679,
+      "eval_weighted_specificity": 0.9627986200238022,
+      "step": 7707
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 4.481704943557805e-05,
+      "loss": 0.9829,
+      "step": 8000
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 4.4492669002205786e-05,
+      "loss": 0.9172,
+      "step": 8500
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 4.416828856883353e-05,
+      "loss": 0.9911,
+      "step": 9000
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 4.384390813546127e-05,
+      "loss": 0.9934,
+      "step": 9500
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 4.351952770208901e-05,
+      "loss": 1.0127,
+      "step": 10000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7668474051123161,
+      "eval_f1_macro": 0.6233324855492023,
+      "eval_f1_micro": 0.7668474051123161,
+      "eval_f1_weighted": 0.7569127961671379,
+      "eval_loss": 1.4684507846832275,
+      "eval_macro_fpr": 0.022371017412255348,
+      "eval_macro_sensitivity": 0.6201844239757082,
+      "eval_macro_specificity": 0.9821444214871504,
+      "eval_precision": 0.7584494799967734,
+      "eval_precision_macro": 0.6670503035550461,
+      "eval_recall": 0.7668474051123161,
+      "eval_recall_macro": 0.6201844239757082,
+      "eval_runtime": 296.0277,
+      "eval_samples_per_second": 4.361,
+      "eval_steps_per_second": 2.182,
+      "eval_weighted_fpr": 0.021255561047948592,
+      "eval_weighted_sensitivity": 0.7668474051123161,
+      "eval_weighted_specificity": 0.9653189171949409,
+      "step": 10276
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 4.3196444790450244e-05,
+      "loss": 0.9926,
+      "step": 10500
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 4.287206435707798e-05,
+      "loss": 1.1046,
+      "step": 11000
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 4.2547683923705725e-05,
+      "loss": 0.8572,
+      "step": 11500
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 4.222330349033346e-05,
+      "loss": 0.8623,
+      "step": 12000
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 4.1898923056961206e-05,
+      "loss": 1.0205,
+      "step": 12500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7668474051123161,
+      "eval_f1_macro": 0.6732447131282889,
+      "eval_f1_micro": 0.7668474051123161,
+      "eval_f1_weighted": 0.7643097206437405,
+      "eval_loss": 1.4232454299926758,
+      "eval_macro_fpr": 0.021536303183803004,
+      "eval_macro_sensitivity": 0.6871530786461169,
+      "eval_macro_specificity": 0.9827017397959152,
+      "eval_precision": 0.7710604143740172,
+      "eval_precision_macro": 0.6764905863857386,
+      "eval_recall": 0.7668474051123161,
+      "eval_recall_macro": 0.6871530786461169,
+      "eval_runtime": 288.8657,
+      "eval_samples_per_second": 4.469,
+      "eval_steps_per_second": 2.236,
+      "eval_weighted_fpr": 0.021255561047948592,
+      "eval_weighted_sensitivity": 0.7668474051123161,
+      "eval_weighted_specificity": 0.9736786918264111,
+      "step": 12845
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 4.1574542623588944e-05,
+      "loss": 0.888,
+      "step": 13000
+    },
+    {
+      "epoch": 5.25,
+      "learning_rate": 4.125016219021669e-05,
+      "loss": 0.7739,
+      "step": 13500
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 4.0925781756844425e-05,
+      "loss": 0.9572,
+      "step": 14000
+    },
+    {
+      "epoch": 5.64,
+      "learning_rate": 4.060140132347217e-05,
+      "loss": 0.8296,
+      "step": 14500
+    },
+    {
+      "epoch": 5.84,
+      "learning_rate": 4.0277020890099906e-05,
+      "loss": 0.7927,
+      "step": 15000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7428350116189001,
+      "eval_f1_macro": 0.6107557579512543,
+      "eval_f1_micro": 0.7428350116189001,
+      "eval_f1_weighted": 0.729163687728552,
+      "eval_loss": 1.5677722692489624,
+      "eval_macro_fpr": 0.024790721920250693,
+      "eval_macro_sensitivity": 0.6332883060366477,
+      "eval_macro_specificity": 0.9807865890062467,
+      "eval_precision": 0.7451349692354797,
+      "eval_precision_macro": 0.6488747447950202,
+      "eval_recall": 0.7428350116189001,
+      "eval_recall_macro": 0.6332883060366477,
+      "eval_runtime": 291.455,
+      "eval_samples_per_second": 4.429,
+      "eval_steps_per_second": 2.216,
+      "eval_weighted_fpr": 0.024131414449774676,
+      "eval_weighted_sensitivity": 0.7428350116189001,
+      "eval_weighted_specificity": 0.9689638234747989,
+      "step": 15414
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 3.995264045672765e-05,
+      "loss": 0.8196,
+      "step": 15500
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 3.9628260023355394e-05,
+      "loss": 0.6989,
+      "step": 16000
+    },
+    {
+      "epoch": 6.42,
+      "learning_rate": 3.930387958998313e-05,
+      "loss": 0.7149,
+      "step": 16500
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 3.8979499156610875e-05,
+      "loss": 0.7459,
+      "step": 17000
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 3.865511872323861e-05,
+      "loss": 0.7701,
+      "step": 17500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7467079783113865,
+      "eval_f1_macro": 0.6583574261846535,
+      "eval_f1_micro": 0.7467079783113864,
+      "eval_f1_weighted": 0.7399270546375634,
+      "eval_loss": 1.7336597442626953,
+      "eval_macro_fpr": 0.023989153033760927,
+      "eval_macro_sensitivity": 0.6536163621805403,
+      "eval_macro_specificity": 0.9809809544706846,
+      "eval_precision": 0.759972067375925,
+      "eval_precision_macro": 0.6862877418910309,
+      "eval_recall": 0.7467079783113865,
+      "eval_recall_macro": 0.6536163621805403,
+      "eval_runtime": 289.659,
+      "eval_samples_per_second": 4.457,
+      "eval_steps_per_second": 2.23,
+      "eval_weighted_fpr": 0.023656225132026334,
+      "eval_weighted_sensitivity": 0.7467079783113865,
+      "eval_weighted_specificity": 0.9680063387488825,
+      "step": 17983
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 3.83313870507331e-05,
+      "loss": 0.826,
+      "step": 18000
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 3.800765537822758e-05,
+      "loss": 0.6803,
+      "step": 18500
+    },
+    {
+      "epoch": 7.4,
+      "learning_rate": 3.7683274944855327e-05,
+      "loss": 0.6779,
+      "step": 19000
+    },
+    {
+      "epoch": 7.59,
+      "learning_rate": 3.7358894511483064e-05,
+      "loss": 0.616,
+      "step": 19500
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 3.703451407811081e-05,
+      "loss": 0.608,
+      "step": 20000
+    },
+    {
+      "epoch": 7.98,
+      "learning_rate": 3.671013364473855e-05,
+      "loss": 0.584,
+      "step": 20500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7691711851278079,
+      "eval_f1_macro": 0.6979809418287721,
+      "eval_f1_micro": 0.7691711851278079,
+      "eval_f1_weighted": 0.7682883483181749,
+      "eval_loss": 1.6188185214996338,
+      "eval_macro_fpr": 0.021432185448306138,
+      "eval_macro_sensitivity": 0.7065204224528159,
+      "eval_macro_specificity": 0.9826542042505794,
+      "eval_precision": 0.7766202006674988,
+      "eval_precision_macro": 0.6979437669181305,
+      "eval_recall": 0.7691711851278079,
+      "eval_recall_macro": 0.7065204224528159,
+      "eval_runtime": 303.6709,
+      "eval_samples_per_second": 4.251,
+      "eval_steps_per_second": 2.127,
+      "eval_weighted_fpr": 0.020985915492957745,
+      "eval_weighted_sensitivity": 0.7691711851278079,
+      "eval_weighted_specificity": 0.9706418786308822,
+      "step": 20552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 77070,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 4.467280976053862e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-20552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e37f60a60daa651d8e7f2ff3947107bcf8c19f622a0416af7b872e6562bd538
+size 4600