First model version

added_tokens.json

@@ -0,0 +1 @@
+{"<EV>": 50265, "<abs>": 50267, "<t>": 50266}

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "allenai/led-large-16384",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "LEDForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_window": [
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024
+  ],
+  "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,
+  "gradient_checkpointing": true,
+  "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_decoder_position_embeddings": 1024,
+  "max_encoder_position_embeddings": 16384,
+  "max_length": 512,
+  "min_length": 128,
+  "model_type": "led",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": false,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "transformers_version": "4.8.2",
+  "use_cache": false,
+  "vocab_size": 50268
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ebafe071cf28b7540d463374bbbc141af0a197c466d2e84f20e92e3dc50b58
+size 3678803885

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc0c9ce2c2c3e0a95ffb4aec42247ae7b419bf53f1bfb5e98b2aacca7330c4c
+size 1839654263

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71fa475ba405c266f205bf1fdc4252fbe6de61775873c5e3a41554514a578fc2
+size 14593

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d02133ce8fe03e15b5bb47de95f55e7423f40925e163ff1b1d2523a1fc9d33c5
+size 623

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 16384, "additional_special_tokens": ["<EV>", "<t>", "<abs>"], "special_tokens_map_file": "/home/yun.hy/.cache/huggingface/transformers/2ad921573d53ebf0c0450d63a211e61d8e328324e84830c365abff01f2d115f1.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0", "name_or_path": "allenai/led-large-16384", "tokenizer_class": "LEDTokenizer"}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.710801393728223,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 2.4875,
+      "step": 250
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 2.2619,
+      "step": 500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.5e-05,
+      "loss": 2.2339,
+      "step": 750
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.2639,
+      "step": 1000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 2.1806,
+      "step": 1250
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 5e-05,
+      "loss": 2.012,
+      "step": 1500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.473240623683102e-05,
+      "loss": 1.9184,
+      "step": 1750
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 3.946481247366203e-05,
+      "loss": 1.925,
+      "step": 2000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 3.419721871049305e-05,
+      "loss": 1.8519,
+      "step": 2250
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 2.8929624947324065e-05,
+      "loss": 1.8232,
+      "step": 2500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 2.366203118415508e-05,
+      "loss": 1.5126,
+      "step": 2750
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.8394437420986094e-05,
+      "loss": 1.3707,
+      "step": 3000
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.3126843657817109e-05,
+      "loss": 1.311,
+      "step": 3250
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 7.859249894648125e-06,
+      "loss": 1.2866,
+      "step": 3500
+    }
+  ],
+  "max_steps": 3873,
+  "num_train_epochs": 3,
+  "total_flos": 3.956185882637107e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d07837650b7ad4bf370b0b43f78ffd044fececba27f1eb8fe76fbb7ea21152d4
+size 2735