update

added_tokens.json

@@ -1 +1 @@
-{"<sep>": 32100, "<hl>": 32101}
+{"<sep>": 250100, "<hl>": 250101}

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
@@ -8,11 +9,14 @@
   "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,
@@ -47,5 +51,7 @@
       "prefix": "translate English to Romanian: "
     }
   },
-  "vocab_size": 32102
+  "transformers_version": "4.8.2",
+  "use_cache": true,
+  "vocab_size": 250102
 }

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c43b7c142a2b36605844a75210db89957262dde8e0d7913c98037f1d1b833b4
-size 484032247
+oid sha256:a1d75f351dc4671507dc845cec0607f4dc72ddbe47d903a439766ad2f2cbcfe4
+size 352532601

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:642d4a629fd18a0ea346ea1fb464b34cd0099a368f3984bb93b4fb1f18b3efab
-size 242037587
+oid sha256:2ae091567a7a1df20b996379f0a769e156f82024bd31f2133508001070f8cef9
+size 688496379

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f6f297b3ce4962e17ee38f929c61739a072100dc27e55a9b5178680878042bb
+size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c0cd5d269c13ed044bcbbf5610dd0d4223da95bc96662ac0897be79d19fc849
+oid sha256:58b869f32634a9d5ba9caafd0266044120dc4b9c0090c5914938745c3d1b37bf
 size 623

special_tokens_map.json

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

spiece.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
-size 791656
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer_config.json

@@ -1 +1 @@
-{"model_max_length": 512}
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "sp_model_kwargs": {}, "special_tokens_map_file": "/home/long/.cache/huggingface/transformers/bde22e2f08347211bf47b72fb4730b4b9a2e3323a6a1254932cf0fb969eb18cd.b02fba13e4584f40329b20be0bad88c2ef97b5fda7d9f4f69b1cb3a620568a86", "tokenizer_file": null, "name_or_path": "NlpHUST/t5-vi-en-small", "tokenizer_class": "T5Tokenizer"}

trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.062402496099843996,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.987518721917125e-05,
+      "loss": 9.0489,
+      "step": 100
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.975037443834249e-05,
+      "loss": 5.8706,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.962556165751373e-05,
+      "loss": 5.4352,
+      "step": 300
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.950074887668498e-05,
+      "loss": 5.2032,
+      "step": 400
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.937593609585623e-05,
+      "loss": 5.0315,
+      "step": 500
+    }
+  ],
+  "max_steps": 80120,
+  "num_train_epochs": 10,
+  "total_flos": 3742609240031232.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a13276c8511fcaf3424e11a49f925c4fc984b37390e7b1766405e06e4c00951
-size 1327
+oid sha256:7cf91b4f4b11600f701c2793142e3dc2b495ffadface08af365fcb0cdb946085
+size 2607