First version (word index representation)

added_tokens.json

@@ -0,0 +1 @@
+{"<abs>": 50267, "<edit_pad>": 50268, "<EV>": 50265, "<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,
+  "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": 16,
+  "model_type": "led",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": false,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "use_cache": false,
+  "vocab_size": 50269
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54fcbe2f7fe52ff2c0cb99f9cfddd06793de8e1860f6cb06786a8114418c8bd
+size 3678812077

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2add04ef7ade45672f29bb02c6edbec2062e73d84d603eeddfed3cf8f5fea2
+size 1839658423

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83bbd0a3ee4574e48ff11ba9849926f3358ad32fc9d67a30e35ee7a07d0e1ae8
+size 14657

runs/Apr11_08-32-09_d3089/1649680331.8728905/events.out.tfevents.1649680331.d3089.10784.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6221be6c8c954d39e81b913dcb518377ac27e7cca256f5b7d3da3ce7234b36b9
+size 5266

runs/Apr11_08-32-09_d3089/events.out.tfevents.1649680331.d3089.10784.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f2d7407966d10fa2486b70459855ca658492a88de7cac2d8360fae103e828e
+size 11676

runs/Apr11_08-32-09_d3089/events.out.tfevents.1649773806.d3089.10784.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b71ea1ac3f772276a057a8ba39630a80a7cdd014bd6a6711e4ae02fdea1f4fc1
+size 487

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c074160d85f03387fb2660f088ce1b178e8fd5e71ff272246664ecb9334576b
+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>", "<edit_pad>"]}

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"}, "trim_offsets": true, "model_max_length": 16384, "additional_special_tokens": ["<EV>", "<t>", "<abs>", "<edit_pad>"], "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 +1,231 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8761073308512004,
+  "global_step": 5600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 3.641,
+      "step": 240
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 1.9178,
+      "step": 480
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.7533,
+      "step": 720
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 1.9066718816757202,
+      "eval_rouge2_fmeasure": 0.1762,
+      "eval_rouge2_precision": 0.1696,
+      "eval_rouge2_recall": 0.2103,
+      "eval_runtime": 1724.6841,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.252,
+      "step": 800
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 1.6872,
+      "step": 960
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.6179,
+      "step": 1200
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 1.6207,
+      "step": 1440
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 1.9220949411392212,
+      "eval_rouge2_fmeasure": 0.1758,
+      "eval_rouge2_precision": 0.1798,
+      "eval_rouge2_recall": 0.1946,
+      "eval_runtime": 1498.1119,
+      "eval_samples_per_second": 0.29,
+      "eval_steps_per_second": 0.29,
+      "step": 1600
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.917069799585349e-05,
+      "loss": 1.6178,
+      "step": 1680
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.806496199032481e-05,
+      "loss": 1.5584,
+      "step": 1920
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.695922598479613e-05,
+      "loss": 1.335,
+      "step": 2160
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.585348997926745e-05,
+      "loss": 1.3719,
+      "step": 2400
+    },
+    {
+      "epoch": 1.23,
+      "eval_loss": 1.7529886960983276,
+      "eval_rouge2_fmeasure": 0.2175,
+      "eval_rouge2_precision": 0.2233,
+      "eval_rouge2_recall": 0.2326,
+      "eval_runtime": 1473.4895,
+      "eval_samples_per_second": 0.295,
+      "eval_steps_per_second": 0.295,
+      "step": 2400
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.4747753973738772e-05,
+      "loss": 1.3211,
+      "step": 2640
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.3642017968210091e-05,
+      "loss": 1.3276,
+      "step": 2880
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.2536281962681412e-05,
+      "loss": 1.2702,
+      "step": 3120
+    },
+    {
+      "epoch": 1.64,
+      "eval_loss": 1.668319821357727,
+      "eval_rouge2_fmeasure": 0.2329,
+      "eval_rouge2_precision": 0.2476,
+      "eval_rouge2_recall": 0.2394,
+      "eval_runtime": 1458.0732,
+      "eval_samples_per_second": 0.298,
+      "eval_steps_per_second": 0.298,
+      "step": 3200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.143054595715273e-05,
+      "loss": 1.2236,
+      "step": 3360
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.0324809951624052e-05,
+      "loss": 1.2533,
+      "step": 3600
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 9.21907394609537e-06,
+      "loss": 1.2119,
+      "step": 3840
+    },
+    {
+      "epoch": 2.05,
+      "eval_loss": 1.6909013986587524,
+      "eval_rouge2_fmeasure": 0.2427,
+      "eval_rouge2_precision": 0.2552,
+      "eval_rouge2_recall": 0.2507,
+      "eval_runtime": 1496.8818,
+      "eval_samples_per_second": 0.29,
+      "eval_steps_per_second": 0.29,
+      "step": 4000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 8.11333794056669e-06,
+      "loss": 1.0075,
+      "step": 4080
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 7.00760193503801e-06,
+      "loss": 0.9473,
+      "step": 4320
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 5.901865929509331e-06,
+      "loss": 0.9265,
+      "step": 4560
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 4.796129923980651e-06,
+      "loss": 0.9583,
+      "step": 4800
+    },
+    {
+      "epoch": 2.47,
+      "eval_loss": 1.6477222442626953,
+      "eval_rouge2_fmeasure": 0.253,
+      "eval_rouge2_precision": 0.2591,
+      "eval_rouge2_recall": 0.2655,
+      "eval_runtime": 1466.7648,
+      "eval_samples_per_second": 0.296,
+      "eval_steps_per_second": 0.296,
+      "step": 4800
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 3.69039391845197e-06,
+      "loss": 0.8958,
+      "step": 5040
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.5846579129232894e-06,
+      "loss": 0.9714,
+      "step": 5280
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.4789219073946095e-06,
+      "loss": 0.8989,
+      "step": 5520
+    },
+    {
+      "epoch": 2.88,
+      "eval_loss": 1.6045594215393066,
+      "eval_rouge2_fmeasure": 0.264,
+      "eval_rouge2_precision": 0.2695,
+      "eval_rouge2_recall": 0.2781,
+      "eval_runtime": 1496.2313,
+      "eval_samples_per_second": 0.29,
+      "eval_steps_per_second": 0.29,
+      "step": 5600
+    }
+  ],
+  "max_steps": 5841,
+  "num_train_epochs": 3,
+  "total_flos": 5.3748207477325824e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da289e1dbcc6aac22884fe9de9bbd05e3fec6203479e03d934e624f70f9c0146
+size 3311