Upload folder using huggingface_hub

training_checkpoints/checkpoint-5138/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-5138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d15fd9e16fd8eb584ca63cfb5259c9afddc1f033f1adf25cf8fee0456a88fed
+size 1629486164

training_checkpoints/checkpoint-5138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123dacb138656f6ba164ce5fcdcfa92f5927afd02a0cf77c3b0797a09bc3ab4a
+size 3259283099

training_checkpoints/checkpoint-5138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a9261b6d820a584af48739dde76e4aebf0f24dfcedba8ff2af2c0a2db12267
+size 14244

training_checkpoints/checkpoint-5138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c8a072f4bbb7b951604099f15e8fa5688a966c548868fe30352d4822df0811
+size 1064

training_checkpoints/checkpoint-5138/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-5138/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-5138/trainer_state.json

@@ -0,0 +1,123 @@
+{
+  "best_metric": 0.4296023125768376,
+  "best_model_checkpoint": "bart-large/checkpoint-2569",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 5138,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 77070,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 1.1168202440134656e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-5138/training_args.bin

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