pegasus XSUM model fine-tuned with 11500 iterations on gigaword to produce short coherant summaries

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "google/pegasus-xsum",
+  "activation_dropout": 0.1,
+  "activation_function": "relu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "PegasusForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "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": 16,
+  "decoder_start_token_id": 0,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 16,
+  "eos_token_id": 1,
+  "extra_pos_embeddings": 0,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 1,
+  "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": 0.6,
+  "max_length": 64,
+  "max_position_embeddings": 512,
+  "model_type": "pegasus",
+  "normalize_before": true,
+  "normalize_embedding": false,
+  "num_beams": 8,
+  "num_hidden_layers": 16,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.5.0.dev0",
+  "use_cache": true,
+  "vocab_size": 96103
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88135d49b8ac110ef03fd97a28c56186e8f409db9a6916e62a1010cf18cc2976
+size 4550012928

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f66dd28963cd6410fb63156defa5fe65cd4e02aa3f4f411d5b854a0bea8eff74
+size 2279640522

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72400869c8937c8330eb8067dbc7fd5c38bc80e224dc9d40bc460162381213e
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask_2>", "additional_special_tokens": ["<mask_1>", "<unk_2>", "<unk_3>", "<unk_4>", "<unk_5>", "<unk_6>", "<unk_7>", "<unk_8>", "<unk_9>", "<unk_10>", "<unk_11>", "<unk_12>", "<unk_13>", "<unk_14>", "<unk_15>", "<unk_16>", "<unk_17>", "<unk_18>", "<unk_19>", "<unk_20>", "<unk_21>", "<unk_22>", "<unk_23>", "<unk_24>", "<unk_25>", "<unk_26>", "<unk_27>", "<unk_28>", "<unk_29>", "<unk_30>", "<unk_31>", "<unk_32>", "<unk_33>", "<unk_34>", "<unk_35>", "<unk_36>", "<unk_37>", "<unk_38>", "<unk_39>", "<unk_40>", "<unk_41>", "<unk_42>", "<unk_43>", "<unk_44>", "<unk_45>", "<unk_46>", "<unk_47>", "<unk_48>", "<unk_49>", "<unk_50>", "<unk_51>", "<unk_52>", "<unk_53>", "<unk_54>", "<unk_55>", "<unk_56>", "<unk_57>", "<unk_58>", "<unk_59>", "<unk_60>", "<unk_61>", "<unk_62>", "<unk_63>", "<unk_64>", "<unk_65>", "<unk_66>", "<unk_67>", "<unk_68>", "<unk_69>", "<unk_70>", "<unk_71>", "<unk_72>", "<unk_73>", "<unk_74>", "<unk_75>", "<unk_76>", "<unk_77>", "<unk_78>", "<unk_79>", "<unk_80>", "<unk_81>", "<unk_82>", "<unk_83>", "<unk_84>", "<unk_85>", "<unk_86>", "<unk_87>", "<unk_88>", "<unk_89>", "<unk_90>", "<unk_91>", "<unk_92>", "<unk_93>", "<unk_94>", "<unk_95>", "<unk_96>", "<unk_97>", "<unk_98>", "<unk_99>", "<unk_100>", "<unk_101>", "<unk_102>"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0015189ef36359283fec8b93cf6d9ce51bca37eb1101defc68a53b394913b96c
+size 1912529

tokenizer_config.json

@@ -0,0 +1 @@
+{"pad_token": "<pad>", "eos_token": "</s>", "unk_token": "<unk>", "mask_token": "<mask_2>", "mask_token_sent": "<mask_1>", "additional_special_tokens": ["<mask_1>", "<unk_2>", "<unk_3>", "<unk_4>", "<unk_5>", "<unk_6>", "<unk_7>", "<unk_8>", "<unk_9>", "<unk_10>", "<unk_11>", "<unk_12>", "<unk_13>", "<unk_14>", "<unk_15>", "<unk_16>", "<unk_17>", "<unk_18>", "<unk_19>", "<unk_20>", "<unk_21>", "<unk_22>", "<unk_23>", "<unk_24>", "<unk_25>", "<unk_26>", "<unk_27>", "<unk_28>", "<unk_29>", "<unk_30>", "<unk_31>", "<unk_32>", "<unk_33>", "<unk_34>", "<unk_35>", "<unk_36>", "<unk_37>", "<unk_38>", "<unk_39>", "<unk_40>", "<unk_41>", "<unk_42>", "<unk_43>", "<unk_44>", "<unk_45>", "<unk_46>", "<unk_47>", "<unk_48>", "<unk_49>", "<unk_50>", "<unk_51>", "<unk_52>", "<unk_53>", "<unk_54>", "<unk_55>", "<unk_56>", "<unk_57>", "<unk_58>", "<unk_59>", "<unk_60>", "<unk_61>", "<unk_62>", "<unk_63>", "<unk_64>", "<unk_65>", "<unk_66>", "<unk_67>", "<unk_68>", "<unk_69>", "<unk_70>", "<unk_71>", "<unk_72>", "<unk_73>", "<unk_74>", "<unk_75>", "<unk_76>", "<unk_77>", "<unk_78>", "<unk_79>", "<unk_80>", "<unk_81>", "<unk_82>", "<unk_83>", "<unk_84>", "<unk_85>", "<unk_86>", "<unk_87>", "<unk_88>", "<unk_89>", "<unk_90>", "<unk_91>", "<unk_92>", "<unk_93>", "<unk_94>", "<unk_95>", "<unk_96>", "<unk_97>", "<unk_98>", "<unk_99>", "<unk_100>", "<unk_101>", "<unk_102>"], "model_max_length": 512, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "google/pegasus-xsum"}

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.012092661331875204,
+  "global_step": 11500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9991237201933425e-05,
+      "loss": 3.5502,
+      "step": 500
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9982474403866854e-05,
+      "loss": 3.0742,
+      "step": 1000
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.997371160580027e-05,
+      "loss": 2.9389,
+      "step": 1500
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.99649488077337e-05,
+      "loss": 2.8079,
+      "step": 2000
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.995618600966712e-05,
+      "loss": 2.7687,
+      "step": 2500
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9947423211600545e-05,
+      "loss": 2.7448,
+      "step": 3000
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.993866041353397e-05,
+      "loss": 2.6388,
+      "step": 3500
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.992989761546739e-05,
+      "loss": 2.6045,
+      "step": 4000
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.992113481740082e-05,
+      "loss": 2.5276,
+      "step": 4500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.991237201933424e-05,
+      "loss": 2.5322,
+      "step": 5000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9903609221267665e-05,
+      "loss": 2.4583,
+      "step": 5500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.989484642320109e-05,
+      "loss": 2.5075,
+      "step": 6000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.988608362513451e-05,
+      "loss": 2.4178,
+      "step": 6500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.987732082706794e-05,
+      "loss": 2.3881,
+      "step": 7000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.986855802900136e-05,
+      "loss": 2.3897,
+      "step": 7500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.985979523093478e-05,
+      "loss": 2.3356,
+      "step": 8000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.985103243286821e-05,
+      "loss": 2.3406,
+      "step": 8500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.984226963480163e-05,
+      "loss": 2.3413,
+      "step": 9000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.983350683673505e-05,
+      "loss": 2.3287,
+      "step": 9500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9824744038668475e-05,
+      "loss": 2.3343,
+      "step": 10000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.98159812406019e-05,
+      "loss": 2.3305,
+      "step": 10500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.980721844253533e-05,
+      "loss": 2.3109,
+      "step": 11000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.979845564446875e-05,
+      "loss": 2.3059,
+      "step": 11500
+    }
+  ],
+  "max_steps": 2852970,
+  "num_train_epochs": 3,
+  "total_flos": 1.082983380369408e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b7caca996f4f96a3374083fc58a9d7cd924e57bdb8855c3795d439c63eaee1
+size 2351