Training in progress, step 500

config.json

@@ -1,25 +1,23 @@
 {
-  "_name_or_path": "csebuetnlp/mT5_m2o_arabic_crossSum",
+  "_name_or_path": "VietAI/vit5-base-vietnews-summarization",
   "architectures": [
-    "MT5ForConditionalGeneration"
+    "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 3072,
   "d_kv": 64,
   "d_model": 768,
-  "decoder_start_token_id": 250021,
-  "dense_act_fn": "gelu_new",
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
+  "feed_forward_proj": "relu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": true,
+  "is_gated_act": false,
   "layer_norm_epsilon": 1e-06,
-  "length_penalty": 0.6,
-  "max_length": 84,
-  "model_type": "mt5",
-  "num_beams": 4,
+  "model_type": "t5",
+  "n_positions": 512,
   "num_decoder_layers": 12,
   "num_heads": 12,
   "num_layers": 12,
@@ -27,194 +25,8 @@
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
-  "task_specific_params": {
-    "langid_map": {
-      "amharic": [
-        35,
-        "\u2581<extra_id_64>"
-      ],
-      "arabic": [
-        4,
-        "\u2581<extra_id_95>"
-      ],
-      "azerbaijani": [
-        7,
-        "\u2581<extra_id_92>"
-      ],
-      "bengali": [
-        42,
-        "\u2581<extra_id_57>"
-      ],
-      "burmese": [
-        33,
-        "\u2581<extra_id_66>"
-      ],
-      "chinese_simplified": [
-        40,
-        "\u2581<extra_id_59>"
-      ],
-      "chinese_traditional": [
-        44,
-        "\u2581<extra_id_55>"
-      ],
-      "english": [
-        30,
-        "\u2581<extra_id_69>"
-      ],
-      "french": [
-        10,
-        "\u2581<extra_id_89>"
-      ],
-      "gujarati": [
-        27,
-        "\u2581<extra_id_72>"
-      ],
-      "hausa": [
-        43,
-        "\u2581<extra_id_56>"
-      ],
-      "hindi": [
-        21,
-        "\u2581<extra_id_78>"
-      ],
-      "igbo": [
-        9,
-        "\u2581<extra_id_90>"
-      ],
-      "indonesian": [
-        1,
-        "\u2581<extra_id_98>"
-      ],
-      "japanese": [
-        37,
-        "\u2581<extra_id_62>"
-      ],
-      "kirundi": [
-        0,
-        "\u2581<extra_id_99>"
-      ],
-      "korean": [
-        29,
-        "\u2581<extra_id_70>"
-      ],
-      "kyrgyz": [
-        5,
-        "\u2581<extra_id_94>"
-      ],
-      "marathi": [
-        13,
-        "\u2581<extra_id_86>"
-      ],
-      "nepali": [
-        20,
-        "\u2581<extra_id_79>"
-      ],
-      "oromo": [
-        41,
-        "\u2581<extra_id_58>"
-      ],
-      "pashto": [
-        34,
-        "\u2581<extra_id_65>"
-      ],
-      "persian": [
-        23,
-        "\u2581<extra_id_76>"
-      ],
-      "pidgin": [
-        14,
-        "\u2581<extra_id_85>"
-      ],
-      "portuguese": [
-        39,
-        "\u2581<extra_id_60>"
-      ],
-      "punjabi": [
-        17,
-        "\u2581<extra_id_82>"
-      ],
-      "russian": [
-        36,
-        "\u2581<extra_id_63>"
-      ],
-      "scottish_gaelic": [
-        24,
-        "\u2581<extra_id_75>"
-      ],
-      "serbian_cyrillic": [
-        28,
-        "\u2581<extra_id_71>"
-      ],
-      "serbian_latin": [
-        11,
-        "\u2581<extra_id_88>"
-      ],
-      "sinhala": [
-        31,
-        "\u2581<extra_id_68>"
-      ],
-      "somali": [
-        19,
-        "\u2581<extra_id_80>"
-      ],
-      "spanish": [
-        3,
-        "\u2581<extra_id_96>"
-      ],
-      "swahili": [
-        18,
-        "\u2581<extra_id_81>"
-      ],
-      "tamil": [
-        32,
-        "\u2581<extra_id_67>"
-      ],
-      "telugu": [
-        22,
-        "\u2581<extra_id_77>"
-      ],
-      "thai": [
-        6,
-        "\u2581<extra_id_93>"
-      ],
-      "tigrinya": [
-        16,
-        "\u2581<extra_id_83>"
-      ],
-      "turkish": [
-        15,
-        "\u2581<extra_id_84>"
-      ],
-      "ukrainian": [
-        2,
-        "\u2581<extra_id_97>"
-      ],
-      "urdu": [
-        38,
-        "\u2581<extra_id_61>"
-      ],
-      "uzbek": [
-        8,
-        "\u2581<extra_id_91>"
-      ],
-      "vietnamese": [
-        12,
-        "\u2581<extra_id_87>"
-      ],
-      "welsh": [
-        26,
-        "\u2581<extra_id_73>"
-      ],
-      "yoruba": [
-        25,
-        "\u2581<extra_id_74>"
-      ]
-    }
-  },
-  "tie_word_embeddings": false,
-  "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.32.0",
   "use_cache": true,
-  "vocab_size": 250112
+  "vocab_size": 36096
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cdb96a74bf67fdf9baaadd25a6aed4e568a0f610ab3759785abe2ee5c726b85
-size 2329702581
+oid sha256:8fb5070cd9e483b48e23d11bd08c3c74e57181f58fee392990c098bd12d0ef04
+size 903892625

special_tokens_map.json

@@ -1,50 +1,101 @@
 {
   "additional_special_tokens": [
-    "▁<extra_id_64>",
-    "▁<extra_id_95>",
-    "▁<extra_id_92>",
-    "▁<extra_id_57>",
-    "▁<extra_id_66>",
-    "▁<extra_id_59>",
-    "▁<extra_id_55>",
-    "▁<extra_id_69>",
-    "▁<extra_id_89>",
-    "▁<extra_id_72>",
-    "▁<extra_id_56>",
-    "▁<extra_id_78>",
-    "▁<extra_id_90>",
-    "▁<extra_id_98>",
-    "▁<extra_id_62>",
-    "▁<extra_id_99>",
-    "▁<extra_id_70>",
-    "▁<extra_id_94>",
-    "▁<extra_id_86>",
-    "▁<extra_id_79>",
-    "▁<extra_id_58>",
-    "▁<extra_id_65>",
-    "▁<extra_id_76>",
-    "▁<extra_id_85>",
-    "▁<extra_id_60>",
-    "▁<extra_id_82>",
-    "▁<extra_id_63>",
-    "▁<extra_id_75>",
-    "▁<extra_id_71>",
-    "▁<extra_id_88>",
-    "▁<extra_id_68>",
-    "▁<extra_id_80>",
-    "▁<extra_id_96>",
-    "▁<extra_id_81>",
-    "▁<extra_id_67>",
-    "▁<extra_id_77>",
-    "▁<extra_id_93>",
-    "▁<extra_id_83>",
-    "▁<extra_id_84>",
-    "▁<extra_id_97>",
-    "▁<extra_id_61>",
-    "▁<extra_id_91>",
-    "▁<extra_id_87>",
-    "▁<extra_id_73>",
-    "▁<extra_id_74>"
+    "<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>"
   ],
   "eos_token": "</s>",
   "pad_token": "<pad>",

spiece.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
-size 4309802
+oid sha256:59986b62f9f0b90edafb9b073ea7b93d21114a5841219a1ea2399ade73f729c6
+size 820370

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c87e0c0c4807ff408ebe1e3d8974b136b593183c5eed5f4c1aa80640b30cad3
-size 16339317
+oid sha256:7157ec8a33c7d8b9e27d123c9938bcdfcbc6f2e502a2bf25ef434d05a542ac12
+size 2418088

tokenizer_config.json

@@ -1,9 +1,105 @@
 {
-  "additional_special_tokens": null,
+  "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>"
+  ],
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
-  "extra_ids": 0,
-  "legacy": true,
+  "extra_ids": 96,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b0caaef3812808a33407ed82f01e1814853d66a933e10a3c392756bb8b41ab
+oid sha256:4aa92890800e4c27c897debaa35f8eb7e0b83fcfec55c552cf59ca8a21d5fa5b
 size 4219