Upload folder using huggingface_hub

training_checkpoints/checkpoint-5787/config.json

@@ -0,0 +1,100 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "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": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "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,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "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-5787/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0c4d137e99553e2ae8cdf8fa3df1dbb06b697f03afdae2bd83d3ee70f9cae5
+size 560120380

training_checkpoints/checkpoint-5787/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0bbde65d4158503d712316e58990ad45444ff7253e550410c524895195f1e2
+size 1120400122

training_checkpoints/checkpoint-5787/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40104848c2f02696d8de3e5372709e62f15f19b335656c494f93a8dedce4aae
+size 14244

training_checkpoints/checkpoint-5787/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c482de6e518d3aef89601342ba0160b5cab73328e4f83a5965d0d2873c671212
+size 1064

training_checkpoints/checkpoint-5787/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-5787/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-5787/trainer_state.json

@@ -0,0 +1,283 @@
+{
+  "best_metric": 0.7736489492761546,
+  "best_model_checkpoint": "bart-base/checkpoint-4501",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 5787,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.871176775531364e-05,
+      "loss": 1.2028,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7598760650658405,
+      "eval_f1_macro": 0.6063644681337579,
+      "eval_f1_micro": 0.7598760650658405,
+      "eval_f1_weighted": 0.7489266744747745,
+      "eval_loss": 0.8429557681083679,
+      "eval_macro_fpr": 0.023226157303183535,
+      "eval_macro_sensitivity": 0.6366904609623596,
+      "eval_macro_specificity": 0.981694425945952,
+      "eval_precision": 0.7600880594489849,
+      "eval_precision_macro": 0.6003620126022547,
+      "eval_recall": 0.7598760650658405,
+      "eval_recall_macro": 0.6366904609623596,
+      "eval_runtime": 43.5934,
+      "eval_samples_per_second": 29.615,
+      "eval_steps_per_second": 3.716,
+      "eval_weighted_fpr": 0.02207348333808032,
+      "eval_weighted_sensitivity": 0.7598760650658405,
+      "eval_weighted_specificity": 0.9655403241234398,
+      "step": 643
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.741575946086055e-05,
+      "loss": 0.715,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7931835786212239,
+      "eval_f1_macro": 0.7213629796675549,
+      "eval_f1_micro": 0.793183578621224,
+      "eval_f1_weighted": 0.7853477061503886,
+      "eval_loss": 0.7331996560096741,
+      "eval_macro_fpr": 0.018982515099395962,
+      "eval_macro_sensitivity": 0.7320748785168393,
+      "eval_macro_specificity": 0.9845140063777027,
+      "eval_precision": 0.8019650926098448,
+      "eval_precision_macro": 0.7386000214414028,
+      "eval_recall": 0.7931835786212239,
+      "eval_recall_macro": 0.7320748785168393,
+      "eval_runtime": 77.2393,
+      "eval_samples_per_second": 16.714,
+      "eval_steps_per_second": 2.097,
+      "eval_weighted_fpr": 0.018283914264192288,
+      "eval_weighted_sensitivity": 0.7931835786212239,
+      "eval_weighted_specificity": 0.9745265170443169,
+      "step": 1286
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 4.611975116640747e-05,
+      "loss": 0.578,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7939581719597212,
+      "eval_f1_macro": 0.6998313050068915,
+      "eval_f1_micro": 0.7939581719597211,
+      "eval_f1_weighted": 0.79006368267302,
+      "eval_loss": 0.8045273423194885,
+      "eval_macro_fpr": 0.018545878882531782,
+      "eval_macro_sensitivity": 0.7068834234702027,
+      "eval_macro_specificity": 0.9847671550097226,
+      "eval_precision": 0.8075005963568469,
+      "eval_precision_macro": 0.7230632440844518,
+      "eval_recall": 0.7939581719597212,
+      "eval_recall_macro": 0.7068834234702027,
+      "eval_runtime": 86.4099,
+      "eval_samples_per_second": 14.94,
+      "eval_steps_per_second": 1.875,
+      "eval_weighted_fpr": 0.018199233716475097,
+      "eval_weighted_sensitivity": 0.7939581719597212,
+      "eval_weighted_specificity": 0.977549153186118,
+      "step": 1929
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 4.482633488854329e-05,
+      "loss": 0.481,
+      "step": 2000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 4.3530326594090203e-05,
+      "loss": 0.3938,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8156467854376452,
+      "eval_f1_macro": 0.7369315728111729,
+      "eval_f1_micro": 0.8156467854376452,
+      "eval_f1_weighted": 0.8105168035589256,
+      "eval_loss": 0.8291025161743164,
+      "eval_macro_fpr": 0.016938074954137138,
+      "eval_macro_sensitivity": 0.7217605983180461,
+      "eval_macro_specificity": 0.9857842035419169,
+      "eval_precision": 0.8171220006778526,
+      "eval_precision_macro": 0.7937034642937142,
+      "eval_recall": 0.8156467854376452,
+      "eval_recall_macro": 0.7217605983180461,
+      "eval_runtime": 84.4366,
+      "eval_samples_per_second": 15.29,
+      "eval_steps_per_second": 1.919,
+      "eval_weighted_fpr": 0.01588785046728972,
+      "eval_weighted_sensitivity": 0.8156467854376452,
+      "eval_weighted_specificity": 0.9711162676911109,
+      "step": 2572
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 4.2236910316226025e-05,
+      "loss": 0.3238,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7939581719597212,
+      "eval_f1_macro": 0.7360579650857649,
+      "eval_f1_micro": 0.7939581719597211,
+      "eval_f1_weighted": 0.7995200606905476,
+      "eval_loss": 0.8888681530952454,
+      "eval_macro_fpr": 0.018767728188278533,
+      "eval_macro_sensitivity": 0.7515467286591376,
+      "eval_macro_specificity": 0.9846803211687324,
+      "eval_precision": 0.8146370555192632,
+      "eval_precision_macro": 0.7464262358644205,
+      "eval_recall": 0.7939581719597212,
+      "eval_recall_macro": 0.7515467286591376,
+      "eval_runtime": 82.179,
+      "eval_samples_per_second": 15.71,
+      "eval_steps_per_second": 1.971,
+      "eval_weighted_fpr": 0.018199233716475097,
+      "eval_weighted_sensitivity": 0.7939581719597212,
+      "eval_weighted_specificity": 0.9762466455712672,
+      "step": 3215
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 4.094090202177294e-05,
+      "loss": 0.246,
+      "step": 3500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7955073586367157,
+      "eval_f1_macro": 0.7362210043644567,
+      "eval_f1_micro": 0.7955073586367158,
+      "eval_f1_weighted": 0.7945977979999089,
+      "eval_loss": 1.1628626585006714,
+      "eval_macro_fpr": 0.01863187379355594,
+      "eval_macro_sensitivity": 0.7599986341032186,
+      "eval_macro_specificity": 0.9846932142915057,
+      "eval_precision": 0.8066758597712774,
+      "eval_precision_macro": 0.7483163388808308,
+      "eval_recall": 0.7955073586367157,
+      "eval_recall_macro": 0.7599986341032186,
+      "eval_runtime": 82.1621,
+      "eval_samples_per_second": 15.713,
+      "eval_steps_per_second": 1.972,
+      "eval_weighted_fpr": 0.018030323726266905,
+      "eval_weighted_sensitivity": 0.7955073586367157,
+      "eval_weighted_specificity": 0.9748908557358684,
+      "step": 3858
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 3.964489372731986e-05,
+      "loss": 0.228,
+      "step": 4000
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.834888543286677e-05,
+      "loss": 0.1791,
+      "step": 4500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8179705654531371,
+      "eval_f1_macro": 0.7736489492761546,
+      "eval_f1_micro": 0.817970565453137,
+      "eval_f1_weighted": 0.8146592022169725,
+      "eval_loss": 1.1354283094406128,
+      "eval_macro_fpr": 0.016454731140779742,
+      "eval_macro_sensitivity": 0.7696557438486226,
+      "eval_macro_specificity": 0.9861772746118799,
+      "eval_precision": 0.8150792023791334,
+      "eval_precision_macro": 0.7832166669456337,
+      "eval_recall": 0.8179705654531371,
+      "eval_recall_macro": 0.7696557438486226,
+      "eval_runtime": 85.4548,
+      "eval_samples_per_second": 15.107,
+      "eval_steps_per_second": 1.896,
+      "eval_weighted_fpr": 0.01564684732671949,
+      "eval_weighted_sensitivity": 0.8179705654531371,
+      "eval_weighted_specificity": 0.9746885537250626,
+      "step": 4501
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 3.705546915500259e-05,
+      "loss": 0.1305,
+      "step": 5000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8109992254066615,
+      "eval_f1_macro": 0.7368975448573482,
+      "eval_f1_micro": 0.8109992254066615,
+      "eval_f1_weighted": 0.808822910649843,
+      "eval_loss": 1.282464861869812,
+      "eval_macro_fpr": 0.016943107063520774,
+      "eval_macro_sensitivity": 0.7488577570944955,
+      "eval_macro_specificity": 0.9858309939135591,
+      "eval_precision": 0.8147632227505013,
+      "eval_precision_macro": 0.7422132710401315,
+      "eval_recall": 0.8109992254066615,
+      "eval_recall_macro": 0.7488577570944955,
+      "eval_runtime": 87.6049,
+      "eval_samples_per_second": 14.737,
+      "eval_steps_per_second": 1.849,
+      "eval_weighted_fpr": 0.016373641121997046,
+      "eval_weighted_sensitivity": 0.8109992254066615,
+      "eval_weighted_specificity": 0.9764656832967246,
+      "step": 5144
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 3.575946086054951e-05,
+      "loss": 0.0924,
+      "step": 5500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8040278853601859,
+      "eval_f1_macro": 0.7559721746710123,
+      "eval_f1_micro": 0.8040278853601859,
+      "eval_f1_weighted": 0.80145679310201,
+      "eval_loss": 1.421708583831787,
+      "eval_macro_fpr": 0.017802568540250287,
+      "eval_macro_sensitivity": 0.7809236600744539,
+      "eval_macro_specificity": 0.9853492039682624,
+      "eval_precision": 0.8113877598541575,
+      "eval_precision_macro": 0.7464644897074477,
+      "eval_recall": 0.8040278853601859,
+      "eval_recall_macro": 0.7809236600744539,
+      "eval_runtime": 89.5999,
+      "eval_samples_per_second": 14.408,
+      "eval_steps_per_second": 1.808,
+      "eval_weighted_fpr": 0.017111937774771727,
+      "eval_weighted_sensitivity": 0.8040278853601859,
+      "eval_weighted_specificity": 0.9762101741637506,
+      "step": 5787
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 19290,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 1.4183252057253888e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-5787/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0cdec3791602f3a208801abdf1b96f9559896ff555c412e7903eee9d6a2b88
+size 4600