End of full fine-tuning with BART

checkpoint-2000/config.json

@@ -0,0 +1,73 @@
+{
+  "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": 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": null,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "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,
+  "normalize_embedding": true,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "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": "4.55.4",
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-2000/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": "4.55.4"
+}

checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f6d55b29b959a791b8b3de2c5e99ae2ecc22e59ef7928ed4e89778e2e80064e
+size 557912620

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fabed8ed6f4d4642f9a830a503d7768ef44dd77886cf1ccdefdd5d908202b1f
+size 1115579898

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2719dd9a301fee3d9b84ead22711c97603b9d1d8830a1081f7cbe2d12c2cafbf
+size 14244

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f23693cd48dc1c8f860f826b13e2b2a67e0d16f339a792eac1d10aa86ac535
+size 1064

checkpoint-2000/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>"
+}

checkpoint-2000/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": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,235 @@
+{
+  "best_global_step": 500,
+  "best_metric": 0.23719677329063416,
+  "best_model_checkpoint": "bart-pristine-finetune/checkpoint-500",
+  "epoch": 0.6955312119631368,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03477656059815684,
+      "grad_norm": 18.65494728088379,
+      "learning_rate": 9.900000000000002e-06,
+      "loss": 6.5893,
+      "step": 100
+    },
+    {
+      "epoch": 0.06955312119631368,
+      "grad_norm": 15.10452938079834,
+      "learning_rate": 1.9900000000000003e-05,
+      "loss": 1.9811,
+      "step": 200
+    },
+    {
+      "epoch": 0.10432968179447052,
+      "grad_norm": 1.449442744255066,
+      "learning_rate": 2.9900000000000002e-05,
+      "loss": 0.3884,
+      "step": 300
+    },
+    {
+      "epoch": 0.13910624239262737,
+      "grad_norm": 0.8391104340553284,
+      "learning_rate": 3.99e-05,
+      "loss": 0.1479,
+      "step": 400
+    },
+    {
+      "epoch": 0.1738828029907842,
+      "grad_norm": 0.8194042444229126,
+      "learning_rate": 4.99e-05,
+      "loss": 0.1068,
+      "step": 500
+    },
+    {
+      "epoch": 0.1738828029907842,
+      "eval_gen_len": 20.974,
+      "eval_loss": 0.23719677329063416,
+      "eval_rouge1": 0.4651,
+      "eval_rouge2": 0.3753,
+      "eval_rougeL": 0.4611,
+      "eval_rougeLsum": 0.4615,
+      "eval_runtime": 131.8304,
+      "eval_samples_per_second": 36.737,
+      "eval_steps_per_second": 2.298,
+      "step": 500
+    },
+    {
+      "epoch": 0.20865936358894105,
+      "grad_norm": 1.0611430406570435,
+      "learning_rate": 4.998169963441797e-05,
+      "loss": 0.0866,
+      "step": 600
+    },
+    {
+      "epoch": 0.2434359241870979,
+      "grad_norm": 0.7572854161262512,
+      "learning_rate": 4.99260846907095e-05,
+      "loss": 0.0751,
+      "step": 700
+    },
+    {
+      "epoch": 0.27821248478525473,
+      "grad_norm": 0.7568580508232117,
+      "learning_rate": 4.9833236376345854e-05,
+      "loss": 0.0673,
+      "step": 800
+    },
+    {
+      "epoch": 0.3129890453834116,
+      "grad_norm": 0.7505958676338196,
+      "learning_rate": 4.970329338361449e-05,
+      "loss": 0.0568,
+      "step": 900
+    },
+    {
+      "epoch": 0.3477656059815684,
+      "grad_norm": 0.47339868545532227,
+      "learning_rate": 4.9536449815025784e-05,
+      "loss": 0.0549,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3477656059815684,
+      "eval_gen_len": 20.9787,
+      "eval_loss": 0.25489160418510437,
+      "eval_rouge1": 0.4699,
+      "eval_rouge2": 0.3828,
+      "eval_rougeL": 0.4652,
+      "eval_rougeLsum": 0.4655,
+      "eval_runtime": 132.5745,
+      "eval_samples_per_second": 36.53,
+      "eval_steps_per_second": 2.286,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3825421665797253,
+      "grad_norm": 0.6434345245361328,
+      "learning_rate": 4.9332954893372166e-05,
+      "loss": 0.0509,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4173187271778821,
+      "grad_norm": 0.6275453567504883,
+      "learning_rate": 4.909311258945123e-05,
+      "loss": 0.0498,
+      "step": 1200
+    },
+    {
+      "epoch": 0.45209528777603897,
+      "grad_norm": 0.4585914611816406,
+      "learning_rate": 4.881728116800898e-05,
+      "loss": 0.0462,
+      "step": 1300
+    },
+    {
+      "epoch": 0.4868718483741958,
+      "grad_norm": 0.5186077356338501,
+      "learning_rate": 4.8505872652581405e-05,
+      "loss": 0.0401,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5216484089723527,
+      "grad_norm": 0.6465528011322021,
+      "learning_rate": 4.815935221003384e-05,
+      "loss": 0.0419,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5216484089723527,
+      "eval_gen_len": 20.976,
+      "eval_loss": 0.25857001543045044,
+      "eval_rouge1": 0.4613,
+      "eval_rouge2": 0.3799,
+      "eval_rougeL": 0.457,
+      "eval_rougeLsum": 0.4573,
+      "eval_runtime": 132.433,
+      "eval_samples_per_second": 36.569,
+      "eval_steps_per_second": 2.288,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5564249695705095,
+      "grad_norm": 0.5534175634384155,
+      "learning_rate": 4.77782374557173e-05,
+      "loss": 0.0362,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5912015301686663,
+      "grad_norm": 0.6548935770988464,
+      "learning_rate": 4.7363097680279955e-05,
+      "loss": 0.0376,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6259780907668232,
+      "grad_norm": 0.5545147657394409,
+      "learning_rate": 4.691455299928845e-05,
+      "loss": 0.0353,
+      "step": 1800
+    },
+    {
+      "epoch": 0.66075465136498,
+      "grad_norm": 0.5930569767951965,
+      "learning_rate": 4.6433273426929536e-05,
+      "loss": 0.0344,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6955312119631368,
+      "grad_norm": 0.38679584860801697,
+      "learning_rate": 4.59199778751755e-05,
+      "loss": 0.03,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6955312119631368,
+      "eval_gen_len": 20.9845,
+      "eval_loss": 0.25054243206977844,
+      "eval_rouge1": 0.4638,
+      "eval_rouge2": 0.3831,
+      "eval_rougeL": 0.4593,
+      "eval_rougeLsum": 0.4596,
+      "eval_runtime": 132.3868,
+      "eval_samples_per_second": 36.582,
+      "eval_steps_per_second": 2.289,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 8628,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "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": 2438945832960000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef6f177ab8f24fe6cda28b2200956a214e9fa0aa595b10b332843b91ffc8677
+size 5496

checkpoint-500/config.json

@@ -0,0 +1,73 @@
+{
+  "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": 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": null,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "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,
+  "normalize_embedding": true,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "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": "4.55.4",
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-500/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": "4.55.4"
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:670669f5a92f77fe36348bd983e6405374a2b49457406b35a3b95cecf859d164
+size 557912620

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15643698d14012f6640bb268560e6cdadb79b18e92c911b852431610776a5c44
+size 1115579898

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9213ea170165519462409cd3afc6a3d6a5132d97e751b011c32515a1299630
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a40ecfa3f3fd838108dc1603326181f7cc7fa9cd66a24dab20698df0575be28
+size 1064

checkpoint-500/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>"
+}

checkpoint-500/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": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_global_step": 500,
+  "best_metric": 0.23719677329063416,
+  "best_model_checkpoint": "bart-pristine-finetune/checkpoint-500",
+  "epoch": 0.1738828029907842,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03477656059815684,
+      "grad_norm": 18.65494728088379,
+      "learning_rate": 9.900000000000002e-06,
+      "loss": 6.5893,
+      "step": 100
+    },
+    {
+      "epoch": 0.06955312119631368,
+      "grad_norm": 15.10452938079834,
+      "learning_rate": 1.9900000000000003e-05,
+      "loss": 1.9811,
+      "step": 200
+    },
+    {
+      "epoch": 0.10432968179447052,
+      "grad_norm": 1.449442744255066,
+      "learning_rate": 2.9900000000000002e-05,
+      "loss": 0.3884,
+      "step": 300
+    },
+    {
+      "epoch": 0.13910624239262737,
+      "grad_norm": 0.8391104340553284,
+      "learning_rate": 3.99e-05,
+      "loss": 0.1479,
+      "step": 400
+    },
+    {
+      "epoch": 0.1738828029907842,
+      "grad_norm": 0.8194042444229126,
+      "learning_rate": 4.99e-05,
+      "loss": 0.1068,
+      "step": 500
+    },
+    {
+      "epoch": 0.1738828029907842,
+      "eval_gen_len": 20.974,
+      "eval_loss": 0.23719677329063416,
+      "eval_rouge1": 0.4651,
+      "eval_rouge2": 0.3753,
+      "eval_rougeL": 0.4611,
+      "eval_rougeLsum": 0.4615,
+      "eval_runtime": 131.8304,
+      "eval_samples_per_second": 36.737,
+      "eval_steps_per_second": 2.298,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 8628,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "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": 609736458240000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef6f177ab8f24fe6cda28b2200956a214e9fa0aa595b10b332843b91ffc8677
+size 5496

config.json

@@ -0,0 +1,73 @@
+{
+  "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": 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": null,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "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,
+  "normalize_embedding": true,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "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": "4.55.4",
+  "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": "4.55.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:670669f5a92f77fe36348bd983e6405374a2b49457406b35a3b95cecf859d164
+size 557912620

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": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef6f177ab8f24fe6cda28b2200956a214e9fa0aa595b10b332843b91ffc8677
+size 5496