Upload 13 files

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "facebook/bart-large-cnn",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "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,
+  "force_bos_token_to_be_generated": true,
+  "forced_bos_token_id": 0,
+  "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
+  },
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "max_position_embeddings": 1024,
+  "min_length": 56,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e3750677140c4f3f559f956327969501d58096c84a7fb367a8b054d5f3e0b1
+size 3250623963

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7480d096c6ce4caa865180e6bc6b8fd0bc97847f6c125999a56e1456583f424
+size 1625537293

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5af76b41e20d211a2584a1a2f80184de8f82f273de6d649ee84894b7ec544a6a
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f655f559386263d0563b0cabb405d87db61f0bacbec331e3dac6e78944084e
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d1ae5b8fd20a37f22de64369788a21010fc135d8a4efe8d8c6e435cbf51ac1a
+size 627

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-large-cnn", "tokenizer_class": "BartTokenizer"}

trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.527415143603133,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 94.0526,
+      "eval_loss": 0.7492660284042358,
+      "eval_rouge-1": 53.4952,
+      "eval_rouge-2": 36.0108,
+      "eval_rouge-l": 50.182,
+      "eval_runtime": 234.7689,
+      "eval_samples_per_second": 0.405,
+      "eval_steps_per_second": 0.204,
+      "step": 383
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.6292428198433423e-05,
+      "loss": 0.678,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 84.5579,
+      "eval_loss": 0.7632046341896057,
+      "eval_rouge-1": 55.1066,
+      "eval_rouge-2": 37.3528,
+      "eval_rouge-l": 51.2075,
+      "eval_runtime": 126.1849,
+      "eval_samples_per_second": 0.753,
+      "eval_steps_per_second": 0.38,
+      "step": 766
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 1.256247668780306e-05,
+      "loss": 0.3715,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 91.2632,
+      "eval_loss": 0.8486695885658264,
+      "eval_rouge-1": 54.3003,
+      "eval_rouge-2": 36.1799,
+      "eval_rouge-l": 50.6709,
+      "eval_runtime": 132.7271,
+      "eval_samples_per_second": 0.716,
+      "eval_steps_per_second": 0.362,
+      "step": 1149
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 8.839985080193958e-06,
+      "loss": 0.217,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 89.6211,
+      "eval_loss": 0.9863687753677368,
+      "eval_rouge-1": 54.1436,
+      "eval_rouge-2": 35.8237,
+      "eval_rouge-l": 50.1118,
+      "eval_runtime": 132.6394,
+      "eval_samples_per_second": 0.716,
+      "eval_steps_per_second": 0.362,
+      "step": 1532
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 85.8947,
+      "eval_loss": 1.104886770248413,
+      "eval_rouge-1": 55.0895,
+      "eval_rouge-2": 36.1364,
+      "eval_rouge-l": 51.2227,
+      "eval_runtime": 127.3071,
+      "eval_samples_per_second": 0.746,
+      "eval_steps_per_second": 0.377,
+      "step": 1915
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 5.110033569563596e-06,
+      "loss": 0.1121,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_gen_len": 84.5474,
+      "eval_loss": 1.2047064304351807,
+      "eval_rouge-1": 54.1134,
+      "eval_rouge-2": 35.4271,
+      "eval_rouge-l": 50.1432,
+      "eval_runtime": 128.8352,
+      "eval_samples_per_second": 0.737,
+      "eval_steps_per_second": 0.373,
+      "step": 2298
+    },
+    {
+      "epoch": 6.53,
+      "learning_rate": 1.3800820589332339e-06,
+      "loss": 0.0628,
+      "step": 2500
+    }
+  ],
+  "max_steps": 2681,
+  "num_train_epochs": 7,
+  "total_flos": 5084996667949056.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f2d19613717697f4fc879b6137a1abc84bec2274ae2b6d568168af530bbe387
+size 3323