Upload folder using huggingface_hub

config.json

@@ -0,0 +1,73 @@
+{
+  "_name_or_path": "BART_Legal/checkpoint-7040",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "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": null,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": null,
+  "normalize_before": false,
+  "num_beams": null,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "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": "4.48.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.48.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dfde0bfae01a6117c1b6b3aaa59afb0ef3404c41e2aed1c86a07bcee7e88670
+size 1625426996

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbfd422d77c6349810ca3522bd2f51d0d6cd78da38afe304b71ef6e807242f9d
+size 3250759951

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f49dfebd633bd7113eef7a30651d41f25af7eeee2348cd39216d9d55e5b077f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef0633ffba0098dc88c3a96a72c3bbfb90875db8f84c44d160f9169e4482098
+size 1064

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,314 @@
+{
+  "best_metric": 2.20927357673645,
+  "best_model_checkpoint": "./BART_Legal_Simplified/checkpoint-5655",
+  "epoch": 15.0,
+  "eval_steps": 500,
+  "global_step": 5655,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.4774136543273926,
+      "eval_rouge1": 14.0166,
+      "eval_rouge2": 4.1514,
+      "eval_rougeL": 12.0262,
+      "eval_rougeLsum": 12.9552,
+      "eval_runtime": 67.2594,
+      "eval_samples_per_second": 14.868,
+      "eval_steps_per_second": 0.937,
+      "step": 377
+    },
+    {
+      "epoch": 1.3262599469496021,
+      "grad_norm": 3.8841850757598877,
+      "learning_rate": 2.9679536474022893e-06,
+      "loss": 2.7911,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.4116153717041016,
+      "eval_rouge1": 15.4198,
+      "eval_rouge2": 4.9082,
+      "eval_rougeL": 13.0752,
+      "eval_rougeLsum": 14.0963,
+      "eval_runtime": 67.0343,
+      "eval_samples_per_second": 14.918,
+      "eval_steps_per_second": 0.94,
+      "step": 754
+    },
+    {
+      "epoch": 2.6525198938992043,
+      "grad_norm": 3.047675609588623,
+      "learning_rate": 2.8726803935335058e-06,
+      "loss": 2.6079,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.361037015914917,
+      "eval_rouge1": 14.4451,
+      "eval_rouge2": 4.1966,
+      "eval_rougeL": 12.4145,
+      "eval_rougeLsum": 13.3276,
+      "eval_runtime": 67.3927,
+      "eval_samples_per_second": 14.838,
+      "eval_steps_per_second": 0.935,
+      "step": 1131
+    },
+    {
+      "epoch": 3.9787798408488064,
+      "grad_norm": 3.2164223194122314,
+      "learning_rate": 2.7179185904101013e-06,
+      "loss": 2.5257,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.3306336402893066,
+      "eval_rouge1": 15.3416,
+      "eval_rouge2": 4.9854,
+      "eval_rougeL": 12.9566,
+      "eval_rougeLsum": 14.1013,
+      "eval_runtime": 67.2572,
+      "eval_samples_per_second": 14.868,
+      "eval_steps_per_second": 0.937,
+      "step": 1508
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.3049843311309814,
+      "eval_rouge1": 14.3986,
+      "eval_rouge2": 4.4147,
+      "eval_rougeL": 12.4714,
+      "eval_rougeLsum": 13.246,
+      "eval_runtime": 67.0817,
+      "eval_samples_per_second": 14.907,
+      "eval_steps_per_second": 0.939,
+      "step": 1885
+    },
+    {
+      "epoch": 5.305039787798409,
+      "grad_norm": 2.956613540649414,
+      "learning_rate": 2.510489126644959e-06,
+      "loss": 2.4671,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.2791953086853027,
+      "eval_rouge1": 14.4795,
+      "eval_rouge2": 4.3774,
+      "eval_rougeL": 12.3508,
+      "eval_rougeLsum": 13.5492,
+      "eval_runtime": 67.3975,
+      "eval_samples_per_second": 14.837,
+      "eval_steps_per_second": 0.935,
+      "step": 2262
+    },
+    {
+      "epoch": 6.63129973474801,
+      "grad_norm": 6.920361518859863,
+      "learning_rate": 2.259362080115781e-06,
+      "loss": 2.4141,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.265429973602295,
+      "eval_rouge1": 14.8242,
+      "eval_rouge2": 4.491,
+      "eval_rougeL": 12.5708,
+      "eval_rougeLsum": 13.6373,
+      "eval_runtime": 67.3074,
+      "eval_samples_per_second": 14.857,
+      "eval_steps_per_second": 0.936,
+      "step": 2639
+    },
+    {
+      "epoch": 7.957559681697613,
+      "grad_norm": 3.1763737201690674,
+      "learning_rate": 1.9753971865788855e-06,
+      "loss": 2.3762,
+      "step": 3000
+    },
+    {
+      "epoch": 8.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.2510550022125244,
+      "eval_rouge1": 14.0375,
+      "eval_rouge2": 4.2281,
+      "eval_rougeL": 11.8873,
+      "eval_rougeLsum": 13.0706,
+      "eval_runtime": 67.322,
+      "eval_samples_per_second": 14.854,
+      "eval_steps_per_second": 0.936,
+      "step": 3016
+    },
+    {
+      "epoch": 9.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.243184804916382,
+      "eval_rouge1": 14.361,
+      "eval_rouge2": 4.2973,
+      "eval_rougeL": 12.2662,
+      "eval_rougeLsum": 13.3223,
+      "eval_runtime": 67.3884,
+      "eval_samples_per_second": 14.839,
+      "eval_steps_per_second": 0.935,
+      "step": 3393
+    },
+    {
+      "epoch": 9.283819628647215,
+      "grad_norm": 3.3851265907287598,
+      "learning_rate": 1.670874221353189e-06,
+      "loss": 2.3448,
+      "step": 3500
+    },
+    {
+      "epoch": 10.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.233320713043213,
+      "eval_rouge1": 14.5529,
+      "eval_rouge2": 4.473,
+      "eval_rougeL": 12.3184,
+      "eval_rougeLsum": 13.5086,
+      "eval_runtime": 67.1925,
+      "eval_samples_per_second": 14.883,
+      "eval_steps_per_second": 0.938,
+      "step": 3770
+    },
+    {
+      "epoch": 10.610079575596817,
+      "grad_norm": 3.073219060897827,
+      "learning_rate": 1.3589619728260362e-06,
+      "loss": 2.3218,
+      "step": 4000
+    },
+    {
+      "epoch": 11.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.2254180908203125,
+      "eval_rouge1": 15.2796,
+      "eval_rouge2": 4.9093,
+      "eval_rougeL": 12.8965,
+      "eval_rougeLsum": 14.0065,
+      "eval_runtime": 67.4321,
+      "eval_samples_per_second": 14.83,
+      "eval_steps_per_second": 0.934,
+      "step": 4147
+    },
+    {
+      "epoch": 11.936339522546419,
+      "grad_norm": 2.9745752811431885,
+      "learning_rate": 1.0537454192171958e-06,
+      "loss": 2.3051,
+      "step": 4500
+    },
+    {
+      "epoch": 12.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.218329906463623,
+      "eval_rouge1": 14.4976,
+      "eval_rouge2": 4.4548,
+      "eval_rougeL": 12.4437,
+      "eval_rougeLsum": 13.4006,
+      "eval_runtime": 67.3343,
+      "eval_samples_per_second": 14.851,
+      "eval_steps_per_second": 0.936,
+      "step": 4524
+    },
+    {
+      "epoch": 13.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.2131404876708984,
+      "eval_rouge1": 13.7356,
+      "eval_rouge2": 3.9722,
+      "eval_rougeL": 11.9368,
+      "eval_rougeLsum": 12.6061,
+      "eval_runtime": 67.1588,
+      "eval_samples_per_second": 14.89,
+      "eval_steps_per_second": 0.938,
+      "step": 4901
+    },
+    {
+      "epoch": 13.26259946949602,
+      "grad_norm": 3.053661346435547,
+      "learning_rate": 7.672044660199723e-07,
+      "loss": 2.2886,
+      "step": 5000
+    },
+    {
+      "epoch": 14.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.21189284324646,
+      "eval_rouge1": 13.9471,
+      "eval_rouge2": 4.0646,
+      "eval_rougeL": 11.8361,
+      "eval_rougeLsum": 13.0378,
+      "eval_runtime": 67.2619,
+      "eval_samples_per_second": 14.867,
+      "eval_steps_per_second": 0.937,
+      "step": 5278
+    },
+    {
+      "epoch": 14.588859416445624,
+      "grad_norm": 3.23205304145813,
+      "learning_rate": 5.128229913064035e-07,
+      "loss": 2.2759,
+      "step": 5500
+    },
+    {
+      "epoch": 15.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 2.20927357673645,
+      "eval_rouge1": 14.412,
+      "eval_rouge2": 4.296,
+      "eval_rougeL": 12.3594,
+      "eval_rougeLsum": 13.3282,
+      "eval_runtime": 67.5821,
+      "eval_samples_per_second": 14.797,
+      "eval_steps_per_second": 0.932,
+      "step": 5655
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7540,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 4,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9575455870877696e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f66a62e4ac0d599ab8227b731512d36efd2140848cd98e79899d1b060fb3f064
+size 5496