Upload folder using huggingface_hub

config.json

@@ -0,0 +1,73 @@
+{
+  "_name_or_path": "facebook/bart-large",
+  "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:c21bd2f1036ac3c4d095c2c53de88bcbc4690c8d21672043b988009fae4f0f96
+size 1625426996

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e7eb93de0d99a06b14bb3145ae0e45bad47a24901b41f3c8dce33cc2809dbc
+size 3250759951

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef38a381c233dfd7247e140491cd69aeb93c8a2309d1306f07186e8390b93ee
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83fccd2e15fb44571417b63818e1c4a2b3b29462944a8061f12af40a039dbeb
+size 1064

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>"
+}

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 +1,400 @@
+{
+  "best_metric": 1.161091685295105,
+  "best_model_checkpoint": "./BART_Legal/checkpoint-5984",
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 7040,
+  "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": 1.371184229850769,
+      "eval_rouge1": 16.2547,
+      "eval_rouge2": 9.6949,
+      "eval_rougeL": 14.0623,
+      "eval_rougeLsum": 15.5626,
+      "eval_runtime": 96.7786,
+      "eval_samples_per_second": 14.528,
+      "eval_steps_per_second": 0.909,
+      "step": 352
+    },
+    {
+      "epoch": 1.4204545454545454,
+      "grad_norm": 4.283212184906006,
+      "learning_rate": 1.975604259192243e-06,
+      "loss": 1.6871,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.296962857246399,
+      "eval_rouge1": 15.9413,
+      "eval_rouge2": 9.6091,
+      "eval_rougeL": 13.8601,
+      "eval_rougeLsum": 15.3188,
+      "eval_runtime": 96.896,
+      "eval_samples_per_second": 14.51,
+      "eval_steps_per_second": 0.908,
+      "step": 704
+    },
+    {
+      "epoch": 2.840909090909091,
+      "grad_norm": 3.6476199626922607,
+      "learning_rate": 1.9028412780702233e-06,
+      "loss": 1.4446,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.260762095451355,
+      "eval_rouge1": 16.5266,
+      "eval_rouge2": 10.0679,
+      "eval_rougeL": 14.3339,
+      "eval_rougeLsum": 15.8563,
+      "eval_runtime": 96.5071,
+      "eval_samples_per_second": 14.569,
+      "eval_steps_per_second": 0.912,
+      "step": 1056
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.2416234016418457,
+      "eval_rouge1": 16.6338,
+      "eval_rouge2": 10.1766,
+      "eval_rougeL": 14.5447,
+      "eval_rougeLsum": 15.9669,
+      "eval_runtime": 96.5225,
+      "eval_samples_per_second": 14.567,
+      "eval_steps_per_second": 0.912,
+      "step": 1408
+    },
+    {
+      "epoch": 4.261363636363637,
+      "grad_norm": 4.507070064544678,
+      "learning_rate": 1.7853169308807447e-06,
+      "loss": 1.3688,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.232724905014038,
+      "eval_rouge1": 16.7571,
+      "eval_rouge2": 10.1866,
+      "eval_rougeL": 14.6125,
+      "eval_rougeLsum": 16.0794,
+      "eval_runtime": 96.7579,
+      "eval_samples_per_second": 14.531,
+      "eval_steps_per_second": 0.909,
+      "step": 1760
+    },
+    {
+      "epoch": 5.681818181818182,
+      "grad_norm": 7.366779327392578,
+      "learning_rate": 1.6292047838965046e-06,
+      "loss": 1.3173,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.2103159427642822,
+      "eval_rouge1": 16.5799,
+      "eval_rouge2": 10.1068,
+      "eval_rougeL": 14.4487,
+      "eval_rougeLsum": 15.9372,
+      "eval_runtime": 96.3022,
+      "eval_samples_per_second": 14.6,
+      "eval_steps_per_second": 0.914,
+      "step": 2112
+    },
+    {
+      "epoch": 7.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.2007499933242798,
+      "eval_rouge1": 16.5958,
+      "eval_rouge2": 10.1498,
+      "eval_rougeL": 14.4406,
+      "eval_rougeLsum": 15.945,
+      "eval_runtime": 96.3959,
+      "eval_samples_per_second": 14.586,
+      "eval_steps_per_second": 0.913,
+      "step": 2464
+    },
+    {
+      "epoch": 7.1022727272727275,
+      "grad_norm": 3.5551233291625977,
+      "learning_rate": 1.4416215204103047e-06,
+      "loss": 1.2818,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.193101167678833,
+      "eval_rouge1": 16.6412,
+      "eval_rouge2": 10.1469,
+      "eval_rougeL": 14.4385,
+      "eval_rougeLsum": 15.9981,
+      "eval_runtime": 96.0432,
+      "eval_samples_per_second": 14.639,
+      "eval_steps_per_second": 0.916,
+      "step": 2816
+    },
+    {
+      "epoch": 8.522727272727273,
+      "grad_norm": 3.9627692699432373,
+      "learning_rate": 1.2321433978624924e-06,
+      "loss": 1.2533,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.1837595701217651,
+      "eval_rouge1": 16.6114,
+      "eval_rouge2": 10.1789,
+      "eval_rougeL": 14.4309,
+      "eval_rougeLsum": 15.9703,
+      "eval_runtime": 95.5751,
+      "eval_samples_per_second": 14.711,
+      "eval_steps_per_second": 0.921,
+      "step": 3168
+    },
+    {
+      "epoch": 9.943181818181818,
+      "grad_norm": 3.2599680423736572,
+      "learning_rate": 1.0111559924935877e-06,
+      "loss": 1.2269,
+      "step": 3500
+    },
+    {
+      "epoch": 10.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.1798343658447266,
+      "eval_rouge1": 16.6425,
+      "eval_rouge2": 10.1569,
+      "eval_rougeL": 14.5234,
+      "eval_rougeLsum": 15.9968,
+      "eval_runtime": 96.0029,
+      "eval_samples_per_second": 14.645,
+      "eval_steps_per_second": 0.917,
+      "step": 3520
+    },
+    {
+      "epoch": 11.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.1735297441482544,
+      "eval_rouge1": 16.7312,
+      "eval_rouge2": 10.2697,
+      "eval_rougeL": 14.6245,
+      "eval_rougeLsum": 16.0927,
+      "eval_runtime": 439.0443,
+      "eval_samples_per_second": 3.202,
+      "eval_steps_per_second": 0.2,
+      "step": 3872
+    },
+    {
+      "epoch": 11.363636363636363,
+      "grad_norm": 3.0771420001983643,
+      "learning_rate": 7.896154916072532e-07,
+      "loss": 1.2102,
+      "step": 4000
+    },
+    {
+      "epoch": 12.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.1649082899093628,
+      "eval_rouge1": 16.5778,
+      "eval_rouge2": 10.126,
+      "eval_rougeL": 14.4729,
+      "eval_rougeLsum": 15.948,
+      "eval_runtime": 428.9181,
+      "eval_samples_per_second": 3.278,
+      "eval_steps_per_second": 0.205,
+      "step": 4224
+    },
+    {
+      "epoch": 12.784090909090908,
+      "grad_norm": 3.9918179512023926,
+      "learning_rate": 5.785055040612244e-07,
+      "loss": 1.2001,
+      "step": 4500
+    },
+    {
+      "epoch": 13.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.1660524606704712,
+      "eval_rouge1": 16.6632,
+      "eval_rouge2": 10.1667,
+      "eval_rougeL": 14.5389,
+      "eval_rougeLsum": 16.0237,
+      "eval_runtime": 433.402,
+      "eval_samples_per_second": 3.244,
+      "eval_steps_per_second": 0.203,
+      "step": 4576
+    },
+    {
+      "epoch": 14.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.1648682355880737,
+      "eval_rouge1": 16.7154,
+      "eval_rouge2": 10.2296,
+      "eval_rougeL": 14.5912,
+      "eval_rougeLsum": 16.0608,
+      "eval_runtime": 438.5153,
+      "eval_samples_per_second": 3.206,
+      "eval_steps_per_second": 0.201,
+      "step": 4928
+    },
+    {
+      "epoch": 14.204545454545455,
+      "grad_norm": 3.055126667022705,
+      "learning_rate": 3.8864559256318376e-07,
+      "loss": 1.1922,
+      "step": 5000
+    },
+    {
+      "epoch": 15.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.1646767854690552,
+      "eval_rouge1": 16.6678,
+      "eval_rouge2": 10.1662,
+      "eval_rougeL": 14.5472,
+      "eval_rougeLsum": 16.0314,
+      "eval_runtime": 427.2745,
+      "eval_samples_per_second": 3.291,
+      "eval_steps_per_second": 0.206,
+      "step": 5280
+    },
+    {
+      "epoch": 15.625,
+      "grad_norm": 3.330857038497925,
+      "learning_rate": 2.2869089949783792e-07,
+      "loss": 1.1791,
+      "step": 5500
+    },
+    {
+      "epoch": 16.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.162706971168518,
+      "eval_rouge1": 16.6631,
+      "eval_rouge2": 10.2047,
+      "eval_rougeL": 14.5382,
+      "eval_rougeLsum": 16.031,
+      "eval_runtime": 437.8499,
+      "eval_samples_per_second": 3.211,
+      "eval_steps_per_second": 0.201,
+      "step": 5632
+    },
+    {
+      "epoch": 17.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.161091685295105,
+      "eval_rouge1": 16.6575,
+      "eval_rouge2": 10.1867,
+      "eval_rougeL": 14.5325,
+      "eval_rougeLsum": 16.0221,
+      "eval_runtime": 436.8448,
+      "eval_samples_per_second": 3.219,
+      "eval_steps_per_second": 0.201,
+      "step": 5984
+    },
+    {
+      "epoch": 17.045454545454547,
+      "grad_norm": 3.5640358924865723,
+      "learning_rate": 1.0697642632201121e-07,
+      "loss": 1.1809,
+      "step": 6000
+    },
+    {
+      "epoch": 18.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.1619925498962402,
+      "eval_rouge1": 16.6763,
+      "eval_rouge2": 10.2071,
+      "eval_rougeL": 14.5592,
+      "eval_rougeLsum": 16.0364,
+      "eval_runtime": 433.2267,
+      "eval_samples_per_second": 3.245,
+      "eval_steps_per_second": 0.203,
+      "step": 6336
+    },
+    {
+      "epoch": 18.46590909090909,
+      "grad_norm": 4.443442344665527,
+      "learning_rate": 2.953657379014829e-08,
+      "loss": 1.1743,
+      "step": 6500
+    },
+    {
+      "epoch": 19.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.1618391275405884,
+      "eval_rouge1": 16.6734,
+      "eval_rouge2": 10.1981,
+      "eval_rougeL": 14.5583,
+      "eval_rougeLsum": 16.032,
+      "eval_runtime": 435.6258,
+      "eval_samples_per_second": 3.228,
+      "eval_steps_per_second": 0.202,
+      "step": 6688
+    },
+    {
+      "epoch": 19.886363636363637,
+      "grad_norm": 3.133742094039917,
+      "learning_rate": 2.1068074461783049e-10,
+      "loss": 1.1759,
+      "step": 7000
+    },
+    {
+      "epoch": 20.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.1616698503494263,
+      "eval_rouge1": 16.6639,
+      "eval_rouge2": 10.1849,
+      "eval_rougeL": 14.5427,
+      "eval_rougeLsum": 16.0297,
+      "eval_runtime": 431.0391,
+      "eval_samples_per_second": 3.262,
+      "eval_steps_per_second": 0.204,
+      "step": 7040
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7040,
+  "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": 3
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.4375592564555776e+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 sha256:47e1e840c7d9017b9971388d4cb3755c69d174619a8f8c9df01c6824316bac26
+size 5432