model update

epoch_8/added_tokens.json

@@ -0,0 +1 @@
+{"<hl>": 32100}

epoch_8/config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "lmqg_output/optimized_no_passage/t5_small_squad/model_mzgdpa/epoch_2",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "transformers_version": "4.8.2",
+  "use_cache": true,
+  "vocab_size": 32101
+}

epoch_8/eval/metric.first.answer.json

@@ -0,0 +1 @@
+{"dev": {"Bleu_1": 0.5092676033339868, "Bleu_2": 0.3570276685723709, "Bleu_3": 0.27250640243572005, "Bleu_4": 0.21488091476242271, "METEOR": 0.24218272971380284, "ROUGE_L": 0.48970024299282416}, "test": {"Bleu_1": 0.4768294508443798, "Bleu_2": 0.32340368850694357, "Bleu_3": 0.24016015950781064, "Bleu_4": 0.18453466860975226, "METEOR": 0.22615973164974987, "ROUGE_L": 0.4624701735447314}}

epoch_8/eval/metric.first.sentence.json

@@ -0,0 +1 @@
+{"dev": {"Bleu_1": 0.5620847843127104, "Bleu_2": 0.40370357025580644, "Bleu_3": 0.3132746126031115, "Bleu_4": 0.25021035877332515, "METEOR": 0.260551191576624, "ROUGE_L": 0.5195087561449607}, "test": {"Bleu_1": 0.5511942555458558, "Bleu_2": 0.3883022566450035, "Bleu_3": 0.29440247284979587, "Bleu_4": 0.22989418952012325, "METEOR": 0.24803004691027772, "ROUGE_L": 0.5000614574486049}}

epoch_8/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b06c68cc5aef2ec0f61f16bf804ce05fdaa563c72f60de38e67d5ac4c9221b
+size 242030331

epoch_8/special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<hl>"]}

epoch_8/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

epoch_8/tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "name_or_path": "lmqg_output/optimized_no_passage/t5_small_squad/model_mzgdpa/epoch_2", "special_tokens_map_file": "lmqg_output/optimized_no_passage/t5_small_squad/model_mzgdpa/epoch_2/special_tokens_map.json", "tokenizer_class": "T5Tokenizer"}

trainer_config.additional_training.json

@@ -0,0 +1 @@
+{"dataset": "squad", "language": ["en"], "task_type": ["qg_no_passage"], "model": "t5-small", "max_length": 128, "max_length_output": 32, "epoch": 9, "batch": 64, "lr": 0.0001, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 1, "label_smoothing": 0.15}

trainer_config.json

@@ -0,0 +1 @@
+{"dataset": "squad", "language": ["en"], "task_type": ["qg_no_passage"], "model": "t5-small", "max_length": 128, "max_length_output": 32, "epoch": 8, "batch": 64, "lr": 0.0001, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 1, "label_smoothing": 0.15}