diff --git a/.gitattributes b/.gitattributes
index c7d9f3332a950355d5a77d85000f05e6f45435ea..e3d4fcf7e2a8735ae3efc903926a68b8238225ec 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -32,3 +32,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+mt5-new-summarize-final/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+mt5-new-summarize-final/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+mt5-new-summarize-final/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+mt5-new-summarize-final/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+mt5-new-summarize-final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/mt5-new-summarize-final/checkpoint-1000/config.json b/mt5-new-summarize-final/checkpoint-1000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..139799c6bf6129096048bf33ed41a9cb2f2eb678
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1000/config.json
@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.6,
+  "max_length": 128,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}
diff --git a/mt5-new-summarize-final/checkpoint-1000/generation_config.json b/mt5-new-summarize-final/checkpoint-1000/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a5a5137b6c89be4407a330b5240bbd35976c1380
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1000/generation_config.json
@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "length_penalty": 0.6,
+  "max_length": 128,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.0"
+}
diff --git a/mt5-new-summarize-final/checkpoint-1000/optimizer.pt b/mt5-new-summarize-final/checkpoint-1000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6db4f1a04bf68f6422abfd45288acba50e5ee31f
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf3baa2f0acf6564b212a6bede34f1f382b1d244d1399dc6e36525e87f19aff8
+size 2879429
diff --git a/mt5-new-summarize-final/checkpoint-1000/rng_state.pth b/mt5-new-summarize-final/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..22e1e214635672bc69cc743c4cd0330ce6a01e43
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93b72fbffc25dd7aa7d70e3be24dbad99632d4072a14d2ccf2e19ebfaa6ee482
+size 14575
diff --git a/mt5-new-summarize-final/checkpoint-1000/scheduler.pt b/mt5-new-summarize-final/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8894c2d75e257e78914f0d2fb27723f6bb92fc04
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb7cf2c3437ec60e3b841c26e0417054892b0d02ce922430502dd61a0091fd1
+size 627
diff --git a/mt5-new-summarize-final/checkpoint-1000/special_tokens_map.json b/mt5-new-summarize-final/checkpoint-1000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..79ae7ea5bf033de69d0055820c57885e3d377bbb
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1000/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
diff --git a/mt5-new-summarize-final/checkpoint-1000/spiece.model b/mt5-new-summarize-final/checkpoint-1000/spiece.model
new file mode 100644
index 0000000000000000000000000000000000000000..e417801865fd66bd40f9d45d46b6d0d0c2aa36b6
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1000/spiece.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802
diff --git a/mt5-new-summarize-final/checkpoint-1000/tokenizer.json b/mt5-new-summarize-final/checkpoint-1000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..db5a8773175d9750d86374dc47b64f6d55615279
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
+size 16330369
diff --git a/mt5-new-summarize-final/checkpoint-1000/tokenizer_config.json b/mt5-new-summarize-final/checkpoint-1000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4b9f3a5b62b2d1a57a16a8ae5ef280ed093e45bf
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1000/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "google/mt5-small",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--google--mt5-small/snapshots/38f23af8ec210eb6c376d40e9c56bd25a80f195d/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/mt5-new-summarize-final/checkpoint-1000/trainer_state.json b/mt5-new-summarize-final/checkpoint-1000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..bec000f86a766db87e473a313593e35a36ea4acf
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1000/trainer_state.json
@@ -0,0 +1,628 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.426928516156576,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.555555555555555e-05,
+      "loss": 20.8315,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001111111111111111,
+      "loss": 16.4875,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 10.6503,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002222222222222222,
+      "loss": 6.6236,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 5.2548,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 4.6801,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003888888888888889,
+      "loss": 4.3374,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0004444444444444444,
+      "loss": 3.9614,
+      "step": 80
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0005,
+      "loss": 3.9704,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0004977797513321492,
+      "loss": 3.8112,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0004955595026642984,
+      "loss": 3.6272,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0004933392539964477,
+      "loss": 3.5572,
+      "step": 120
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004911190053285969,
+      "loss": 3.3966,
+      "step": 130
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000488898756660746,
+      "loss": 3.4632,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004866785079928952,
+      "loss": 3.4591,
+      "step": 150
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0004844582593250444,
+      "loss": 3.2218,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0004822380106571936,
+      "loss": 3.4101,
+      "step": 170
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00048001776198934283,
+      "loss": 3.2787,
+      "step": 180
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000477797513321492,
+      "loss": 3.1043,
+      "step": 190
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0004755772646536412,
+      "loss": 3.2435,
+      "step": 200
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00047335701598579037,
+      "loss": 3.2286,
+      "step": 210
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00047113676731793964,
+      "loss": 3.1484,
+      "step": 220
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00046891651865008885,
+      "loss": 3.1817,
+      "step": 230
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000466696269982238,
+      "loss": 3.1608,
+      "step": 240
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00046447602131438723,
+      "loss": 3.1457,
+      "step": 250
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0004622557726465364,
+      "loss": 3.1212,
+      "step": 260
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00046003552397868566,
+      "loss": 2.9937,
+      "step": 270
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0004578152753108348,
+      "loss": 3.2031,
+      "step": 280
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00045559502664298403,
+      "loss": 3.0713,
+      "step": 290
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0004533747779751332,
+      "loss": 3.0352,
+      "step": 300
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0004511545293072824,
+      "loss": 3.0872,
+      "step": 310
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0004489342806394316,
+      "loss": 3.0049,
+      "step": 320
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00044671403197158084,
+      "loss": 3.0659,
+      "step": 330
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00044449378330373,
+      "loss": 3.0852,
+      "step": 340
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0004422735346358792,
+      "loss": 2.9506,
+      "step": 350
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00044005328596802843,
+      "loss": 3.027,
+      "step": 360
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00043783303730017764,
+      "loss": 2.8812,
+      "step": 370
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00043561278863232686,
+      "loss": 2.9738,
+      "step": 380
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000433392539964476,
+      "loss": 3.0504,
+      "step": 390
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00043117229129662523,
+      "loss": 3.0195,
+      "step": 400
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0004289520426287744,
+      "loss": 2.968,
+      "step": 410
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00042673179396092366,
+      "loss": 3.0864,
+      "step": 420
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0004245115452930728,
+      "loss": 2.8735,
+      "step": 430
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00042229129662522204,
+      "loss": 3.0391,
+      "step": 440
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004200710479573712,
+      "loss": 2.8288,
+      "step": 450
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0004178507992895204,
+      "loss": 3.0182,
+      "step": 460
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0004156305506216697,
+      "loss": 3.0606,
+      "step": 470
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00041341030195381884,
+      "loss": 2.9467,
+      "step": 480
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00041119005328596806,
+      "loss": 2.7842,
+      "step": 490
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0004089698046181172,
+      "loss": 2.8472,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00040674955595026643,
+      "loss": 2.7883,
+      "step": 510
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00040452930728241565,
+      "loss": 2.8592,
+      "step": 520
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00040230905861456486,
+      "loss": 2.9186,
+      "step": 530
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000400088809946714,
+      "loss": 2.911,
+      "step": 540
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00039786856127886324,
+      "loss": 2.8355,
+      "step": 550
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003956483126110124,
+      "loss": 2.9385,
+      "step": 560
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039342806394316167,
+      "loss": 2.8465,
+      "step": 570
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003912078152753108,
+      "loss": 2.8408,
+      "step": 580
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00038898756660746004,
+      "loss": 2.767,
+      "step": 590
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00038676731793960926,
+      "loss": 2.9691,
+      "step": 600
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003845470692717584,
+      "loss": 2.7348,
+      "step": 610
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003823268206039077,
+      "loss": 2.7477,
+      "step": 620
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00038010657193605685,
+      "loss": 2.8142,
+      "step": 630
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00037788632326820606,
+      "loss": 2.7522,
+      "step": 640
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003756660746003552,
+      "loss": 2.9403,
+      "step": 650
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00037344582593250444,
+      "loss": 2.8956,
+      "step": 660
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00037122557726465365,
+      "loss": 2.7331,
+      "step": 670
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00036900532859680287,
+      "loss": 2.8265,
+      "step": 680
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.000366785079928952,
+      "loss": 2.8919,
+      "step": 690
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00036456483126110124,
+      "loss": 2.8362,
+      "step": 700
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003623445825932504,
+      "loss": 2.7282,
+      "step": 710
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00036012433392539967,
+      "loss": 2.7628,
+      "step": 720
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003579040852575489,
+      "loss": 2.8508,
+      "step": 730
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00035568383658969805,
+      "loss": 2.8603,
+      "step": 740
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00035346358792184726,
+      "loss": 2.6765,
+      "step": 750
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003512433392539964,
+      "loss": 2.8767,
+      "step": 760
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003490230905861457,
+      "loss": 2.8446,
+      "step": 770
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034680284191829485,
+      "loss": 2.8524,
+      "step": 780
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00034458259325044407,
+      "loss": 2.778,
+      "step": 790
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003423623445825932,
+      "loss": 2.7359,
+      "step": 800
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00034014209591474244,
+      "loss": 2.7803,
+      "step": 810
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033792184724689166,
+      "loss": 2.7631,
+      "step": 820
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033570159857904087,
+      "loss": 2.7818,
+      "step": 830
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033348134991119003,
+      "loss": 2.6591,
+      "step": 840
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033126110124333925,
+      "loss": 2.6843,
+      "step": 850
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00032904085257548846,
+      "loss": 2.7299,
+      "step": 860
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003268206039076377,
+      "loss": 2.6928,
+      "step": 870
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003246003552397869,
+      "loss": 2.8512,
+      "step": 880
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00032238010657193605,
+      "loss": 2.7944,
+      "step": 890
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00032015985790408526,
+      "loss": 2.7365,
+      "step": 900
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003179396092362344,
+      "loss": 2.6992,
+      "step": 910
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003157193605683837,
+      "loss": 2.743,
+      "step": 920
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00031349911190053285,
+      "loss": 2.8022,
+      "step": 930
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00031127886323268207,
+      "loss": 2.6603,
+      "step": 940
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00030905861456483123,
+      "loss": 2.6277,
+      "step": 950
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00030683836589698044,
+      "loss": 2.7652,
+      "step": 960
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003046181172291297,
+      "loss": 2.7063,
+      "step": 970
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003023978685612789,
+      "loss": 2.6602,
+      "step": 980
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003001776198934281,
+      "loss": 2.7592,
+      "step": 990
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00029795737122557725,
+      "loss": 2.6628,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.51519775390625,
+      "eval_rouge1": 0.8067071482496617,
+      "eval_rouge2": 0.7472387953801375,
+      "eval_rougeL": 0.7071393649432568,
+      "eval_rougeLsum": 0.8209607917685595,
+      "eval_runtime": 1807.8081,
+      "eval_samples_per_second": 0.553,
+      "eval_steps_per_second": 0.553,
+      "step": 1000
+    }
+  ],
+  "max_steps": 2342,
+  "num_train_epochs": 1,
+  "total_flos": 2.369574390079488e+16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mt5-new-summarize-final/checkpoint-1000/training_args.bin b/mt5-new-summarize-final/checkpoint-1000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bc9d3b4d1721cf653ac83f80538b07e6a0b8161a
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233a568dcedd606fd72b432d2c6cc678ea8c5e086885a5642ed616a886f52eb9
+size 3643
diff --git a/mt5-new-summarize-final/checkpoint-1500/config.json b/mt5-new-summarize-final/checkpoint-1500/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..139799c6bf6129096048bf33ed41a9cb2f2eb678
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1500/config.json
@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.6,
+  "max_length": 128,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}
diff --git a/mt5-new-summarize-final/checkpoint-1500/generation_config.json b/mt5-new-summarize-final/checkpoint-1500/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a5a5137b6c89be4407a330b5240bbd35976c1380
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1500/generation_config.json
@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "length_penalty": 0.6,
+  "max_length": 128,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.0"
+}
diff --git a/mt5-new-summarize-final/checkpoint-1500/optimizer.pt b/mt5-new-summarize-final/checkpoint-1500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..435d9aad1390f8cb2ff5b4b744a33b147a7eaeac
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e68e0cee8d46a585d3814147b91f8b4bc012059656c68afb9a2a293be699d9
+size 2879429
diff --git a/mt5-new-summarize-final/checkpoint-1500/rng_state.pth b/mt5-new-summarize-final/checkpoint-1500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..48d7f2f54f3223d26a7b9af30829af0da83f869c
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e8b74df13be81372e8f28a3be8d00e9fa6155ca3f835bba73863ea1acbfd61
+size 14575
diff --git a/mt5-new-summarize-final/checkpoint-1500/scheduler.pt b/mt5-new-summarize-final/checkpoint-1500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6a40c7f8d5a9a53437c392dc271964e5c67a22ac
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07335cb72d3786e62311ca2b940c12fc5ac51a973658311a4a7d90cbf94853af
+size 627
diff --git a/mt5-new-summarize-final/checkpoint-1500/special_tokens_map.json b/mt5-new-summarize-final/checkpoint-1500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..79ae7ea5bf033de69d0055820c57885e3d377bbb
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1500/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
diff --git a/mt5-new-summarize-final/checkpoint-1500/spiece.model b/mt5-new-summarize-final/checkpoint-1500/spiece.model
new file mode 100644
index 0000000000000000000000000000000000000000..e417801865fd66bd40f9d45d46b6d0d0c2aa36b6
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1500/spiece.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802
diff --git a/mt5-new-summarize-final/checkpoint-1500/tokenizer.json b/mt5-new-summarize-final/checkpoint-1500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..db5a8773175d9750d86374dc47b64f6d55615279
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
+size 16330369
diff --git a/mt5-new-summarize-final/checkpoint-1500/tokenizer_config.json b/mt5-new-summarize-final/checkpoint-1500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4b9f3a5b62b2d1a57a16a8ae5ef280ed093e45bf
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1500/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "google/mt5-small",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--google--mt5-small/snapshots/38f23af8ec210eb6c376d40e9c56bd25a80f195d/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/mt5-new-summarize-final/checkpoint-1500/trainer_state.json b/mt5-new-summarize-final/checkpoint-1500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..853aff88b558394624d3278898a56be6c2ffec32
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1500/trainer_state.json
@@ -0,0 +1,928 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6403927742348641,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.555555555555555e-05,
+      "loss": 20.8315,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001111111111111111,
+      "loss": 16.4875,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 10.6503,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002222222222222222,
+      "loss": 6.6236,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 5.2548,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 4.6801,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003888888888888889,
+      "loss": 4.3374,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0004444444444444444,
+      "loss": 3.9614,
+      "step": 80
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0005,
+      "loss": 3.9704,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0004977797513321492,
+      "loss": 3.8112,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0004955595026642984,
+      "loss": 3.6272,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0004933392539964477,
+      "loss": 3.5572,
+      "step": 120
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004911190053285969,
+      "loss": 3.3966,
+      "step": 130
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000488898756660746,
+      "loss": 3.4632,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004866785079928952,
+      "loss": 3.4591,
+      "step": 150
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0004844582593250444,
+      "loss": 3.2218,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0004822380106571936,
+      "loss": 3.4101,
+      "step": 170
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00048001776198934283,
+      "loss": 3.2787,
+      "step": 180
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000477797513321492,
+      "loss": 3.1043,
+      "step": 190
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0004755772646536412,
+      "loss": 3.2435,
+      "step": 200
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00047335701598579037,
+      "loss": 3.2286,
+      "step": 210
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00047113676731793964,
+      "loss": 3.1484,
+      "step": 220
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00046891651865008885,
+      "loss": 3.1817,
+      "step": 230
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000466696269982238,
+      "loss": 3.1608,
+      "step": 240
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00046447602131438723,
+      "loss": 3.1457,
+      "step": 250
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0004622557726465364,
+      "loss": 3.1212,
+      "step": 260
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00046003552397868566,
+      "loss": 2.9937,
+      "step": 270
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0004578152753108348,
+      "loss": 3.2031,
+      "step": 280
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00045559502664298403,
+      "loss": 3.0713,
+      "step": 290
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0004533747779751332,
+      "loss": 3.0352,
+      "step": 300
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0004511545293072824,
+      "loss": 3.0872,
+      "step": 310
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0004489342806394316,
+      "loss": 3.0049,
+      "step": 320
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00044671403197158084,
+      "loss": 3.0659,
+      "step": 330
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00044449378330373,
+      "loss": 3.0852,
+      "step": 340
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0004422735346358792,
+      "loss": 2.9506,
+      "step": 350
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00044005328596802843,
+      "loss": 3.027,
+      "step": 360
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00043783303730017764,
+      "loss": 2.8812,
+      "step": 370
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00043561278863232686,
+      "loss": 2.9738,
+      "step": 380
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000433392539964476,
+      "loss": 3.0504,
+      "step": 390
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00043117229129662523,
+      "loss": 3.0195,
+      "step": 400
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0004289520426287744,
+      "loss": 2.968,
+      "step": 410
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00042673179396092366,
+      "loss": 3.0864,
+      "step": 420
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0004245115452930728,
+      "loss": 2.8735,
+      "step": 430
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00042229129662522204,
+      "loss": 3.0391,
+      "step": 440
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004200710479573712,
+      "loss": 2.8288,
+      "step": 450
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0004178507992895204,
+      "loss": 3.0182,
+      "step": 460
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0004156305506216697,
+      "loss": 3.0606,
+      "step": 470
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00041341030195381884,
+      "loss": 2.9467,
+      "step": 480
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00041119005328596806,
+      "loss": 2.7842,
+      "step": 490
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0004089698046181172,
+      "loss": 2.8472,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00040674955595026643,
+      "loss": 2.7883,
+      "step": 510
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00040452930728241565,
+      "loss": 2.8592,
+      "step": 520
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00040230905861456486,
+      "loss": 2.9186,
+      "step": 530
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000400088809946714,
+      "loss": 2.911,
+      "step": 540
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00039786856127886324,
+      "loss": 2.8355,
+      "step": 550
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003956483126110124,
+      "loss": 2.9385,
+      "step": 560
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039342806394316167,
+      "loss": 2.8465,
+      "step": 570
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003912078152753108,
+      "loss": 2.8408,
+      "step": 580
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00038898756660746004,
+      "loss": 2.767,
+      "step": 590
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00038676731793960926,
+      "loss": 2.9691,
+      "step": 600
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003845470692717584,
+      "loss": 2.7348,
+      "step": 610
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003823268206039077,
+      "loss": 2.7477,
+      "step": 620
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00038010657193605685,
+      "loss": 2.8142,
+      "step": 630
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00037788632326820606,
+      "loss": 2.7522,
+      "step": 640
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003756660746003552,
+      "loss": 2.9403,
+      "step": 650
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00037344582593250444,
+      "loss": 2.8956,
+      "step": 660
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00037122557726465365,
+      "loss": 2.7331,
+      "step": 670
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00036900532859680287,
+      "loss": 2.8265,
+      "step": 680
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.000366785079928952,
+      "loss": 2.8919,
+      "step": 690
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00036456483126110124,
+      "loss": 2.8362,
+      "step": 700
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003623445825932504,
+      "loss": 2.7282,
+      "step": 710
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00036012433392539967,
+      "loss": 2.7628,
+      "step": 720
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003579040852575489,
+      "loss": 2.8508,
+      "step": 730
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00035568383658969805,
+      "loss": 2.8603,
+      "step": 740
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00035346358792184726,
+      "loss": 2.6765,
+      "step": 750
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003512433392539964,
+      "loss": 2.8767,
+      "step": 760
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003490230905861457,
+      "loss": 2.8446,
+      "step": 770
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034680284191829485,
+      "loss": 2.8524,
+      "step": 780
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00034458259325044407,
+      "loss": 2.778,
+      "step": 790
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003423623445825932,
+      "loss": 2.7359,
+      "step": 800
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00034014209591474244,
+      "loss": 2.7803,
+      "step": 810
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033792184724689166,
+      "loss": 2.7631,
+      "step": 820
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033570159857904087,
+      "loss": 2.7818,
+      "step": 830
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033348134991119003,
+      "loss": 2.6591,
+      "step": 840
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033126110124333925,
+      "loss": 2.6843,
+      "step": 850
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00032904085257548846,
+      "loss": 2.7299,
+      "step": 860
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003268206039076377,
+      "loss": 2.6928,
+      "step": 870
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003246003552397869,
+      "loss": 2.8512,
+      "step": 880
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00032238010657193605,
+      "loss": 2.7944,
+      "step": 890
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00032015985790408526,
+      "loss": 2.7365,
+      "step": 900
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003179396092362344,
+      "loss": 2.6992,
+      "step": 910
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003157193605683837,
+      "loss": 2.743,
+      "step": 920
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00031349911190053285,
+      "loss": 2.8022,
+      "step": 930
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00031127886323268207,
+      "loss": 2.6603,
+      "step": 940
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00030905861456483123,
+      "loss": 2.6277,
+      "step": 950
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00030683836589698044,
+      "loss": 2.7652,
+      "step": 960
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003046181172291297,
+      "loss": 2.7063,
+      "step": 970
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003023978685612789,
+      "loss": 2.6602,
+      "step": 980
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003001776198934281,
+      "loss": 2.7592,
+      "step": 990
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00029795737122557725,
+      "loss": 2.6628,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.51519775390625,
+      "eval_rouge1": 0.8067071482496617,
+      "eval_rouge2": 0.7472387953801375,
+      "eval_rougeL": 0.7071393649432568,
+      "eval_rougeLsum": 0.8209607917685595,
+      "eval_runtime": 1807.8081,
+      "eval_samples_per_second": 0.553,
+      "eval_steps_per_second": 0.553,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00029573712255772646,
+      "loss": 2.6164,
+      "step": 1010
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002935168738898757,
+      "loss": 2.6947,
+      "step": 1020
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002912966252220249,
+      "loss": 2.4547,
+      "step": 1030
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00028907637655417405,
+      "loss": 2.7347,
+      "step": 1040
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00028685612788632327,
+      "loss": 2.6491,
+      "step": 1050
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00028463587921847243,
+      "loss": 2.6778,
+      "step": 1060
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002824156305506217,
+      "loss": 2.7157,
+      "step": 1070
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00028019538188277086,
+      "loss": 2.6445,
+      "step": 1080
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002779751332149201,
+      "loss": 2.7732,
+      "step": 1090
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002757548845470693,
+      "loss": 2.6777,
+      "step": 1100
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00027353463587921845,
+      "loss": 2.6231,
+      "step": 1110
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002713143872113677,
+      "loss": 2.6003,
+      "step": 1120
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002690941385435169,
+      "loss": 2.7226,
+      "step": 1130
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0002668738898756661,
+      "loss": 2.8623,
+      "step": 1140
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00026465364120781525,
+      "loss": 2.7391,
+      "step": 1150
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00026243339253996447,
+      "loss": 2.6836,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002602131438721137,
+      "loss": 2.6357,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002579928952042629,
+      "loss": 2.5891,
+      "step": 1180
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00025577264653641206,
+      "loss": 2.7383,
+      "step": 1190
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00025355239786856127,
+      "loss": 2.738,
+      "step": 1200
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00025133214920071043,
+      "loss": 2.62,
+      "step": 1210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002491119005328597,
+      "loss": 2.5796,
+      "step": 1220
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002468916518650089,
+      "loss": 2.5744,
+      "step": 1230
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002446714031971581,
+      "loss": 2.5047,
+      "step": 1240
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002424511545293073,
+      "loss": 2.5233,
+      "step": 1250
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00024023090586145648,
+      "loss": 2.5248,
+      "step": 1260
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00023801065719360567,
+      "loss": 2.6073,
+      "step": 1270
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002357904085257549,
+      "loss": 2.596,
+      "step": 1280
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002335701598579041,
+      "loss": 2.6899,
+      "step": 1290
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002313499111900533,
+      "loss": 2.6293,
+      "step": 1300
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002291296625222025,
+      "loss": 2.639,
+      "step": 1310
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002269094138543517,
+      "loss": 2.7105,
+      "step": 1320
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002246891651865009,
+      "loss": 2.723,
+      "step": 1330
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002224689165186501,
+      "loss": 2.5697,
+      "step": 1340
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002202486678507993,
+      "loss": 2.715,
+      "step": 1350
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002180284191829485,
+      "loss": 2.6387,
+      "step": 1360
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00021580817051509768,
+      "loss": 2.5276,
+      "step": 1370
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002135879218472469,
+      "loss": 2.627,
+      "step": 1380
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00021136767317939608,
+      "loss": 2.5249,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002091474245115453,
+      "loss": 2.629,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002069271758436945,
+      "loss": 2.703,
+      "step": 1410
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002047069271758437,
+      "loss": 2.544,
+      "step": 1420
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002024866785079929,
+      "loss": 2.5992,
+      "step": 1430
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002002664298401421,
+      "loss": 2.6988,
+      "step": 1440
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00019804618117229132,
+      "loss": 2.6195,
+      "step": 1450
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0001958259325044405,
+      "loss": 2.6247,
+      "step": 1460
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0001936056838365897,
+      "loss": 2.5853,
+      "step": 1470
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0001913854351687389,
+      "loss": 2.6298,
+      "step": 1480
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001891651865008881,
+      "loss": 2.6378,
+      "step": 1490
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001869449378330373,
+      "loss": 2.5682,
+      "step": 1500
+    }
+  ],
+  "max_steps": 2342,
+  "num_train_epochs": 1,
+  "total_flos": 3.54937584731136e+16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mt5-new-summarize-final/checkpoint-1500/training_args.bin b/mt5-new-summarize-final/checkpoint-1500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bc9d3b4d1721cf653ac83f80538b07e6a0b8161a
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-1500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233a568dcedd606fd72b432d2c6cc678ea8c5e086885a5642ed616a886f52eb9
+size 3643
diff --git a/mt5-new-summarize-final/checkpoint-2000/config.json b/mt5-new-summarize-final/checkpoint-2000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..139799c6bf6129096048bf33ed41a9cb2f2eb678
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-2000/config.json
@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.6,
+  "max_length": 128,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}
diff --git a/mt5-new-summarize-final/checkpoint-2000/generation_config.json b/mt5-new-summarize-final/checkpoint-2000/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a5a5137b6c89be4407a330b5240bbd35976c1380
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-2000/generation_config.json
@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "length_penalty": 0.6,
+  "max_length": 128,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.0"
+}
diff --git a/mt5-new-summarize-final/checkpoint-2000/optimizer.pt b/mt5-new-summarize-final/checkpoint-2000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7b36bfbb297095155019d36ebd59246fc29feb2e
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-2000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8398a38588a1d29c290e233a3aa7d80a655280542c57444f7f1ef146e8131d2e
+size 2879429
diff --git a/mt5-new-summarize-final/checkpoint-2000/rng_state.pth b/mt5-new-summarize-final/checkpoint-2000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e3c351a5d46d6084409302c69db147eba2efe479
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-2000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f116c931fa378a37a851637fc90de078ddb5e1fd5892542c59de11eeac2cd8f3
+size 14575
diff --git a/mt5-new-summarize-final/checkpoint-2000/scheduler.pt b/mt5-new-summarize-final/checkpoint-2000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ce6972ea0d2cd0b7126e1b9e9187ef6247ca6988
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-2000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed71672921938371fe751b4cf233d20e73dc5785b84b089e803a193211e35ae
+size 627
diff --git a/mt5-new-summarize-final/checkpoint-2000/special_tokens_map.json b/mt5-new-summarize-final/checkpoint-2000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..79ae7ea5bf033de69d0055820c57885e3d377bbb
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-2000/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
diff --git a/mt5-new-summarize-final/checkpoint-2000/spiece.model b/mt5-new-summarize-final/checkpoint-2000/spiece.model
new file mode 100644
index 0000000000000000000000000000000000000000..e417801865fd66bd40f9d45d46b6d0d0c2aa36b6
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-2000/spiece.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802
diff --git a/mt5-new-summarize-final/checkpoint-2000/tokenizer.json b/mt5-new-summarize-final/checkpoint-2000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..db5a8773175d9750d86374dc47b64f6d55615279
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-2000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
+size 16330369
diff --git a/mt5-new-summarize-final/checkpoint-2000/tokenizer_config.json b/mt5-new-summarize-final/checkpoint-2000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4b9f3a5b62b2d1a57a16a8ae5ef280ed093e45bf
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-2000/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "google/mt5-small",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--google--mt5-small/snapshots/38f23af8ec210eb6c376d40e9c56bd25a80f195d/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/mt5-new-summarize-final/checkpoint-2000/trainer_state.json b/mt5-new-summarize-final/checkpoint-2000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..41618abef1a59368ad2449208c94082408b79e92
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-2000/trainer_state.json
@@ -0,0 +1,1240 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.853857032313152,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.555555555555555e-05,
+      "loss": 20.8315,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001111111111111111,
+      "loss": 16.4875,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 10.6503,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002222222222222222,
+      "loss": 6.6236,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 5.2548,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 4.6801,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003888888888888889,
+      "loss": 4.3374,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0004444444444444444,
+      "loss": 3.9614,
+      "step": 80
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0005,
+      "loss": 3.9704,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0004977797513321492,
+      "loss": 3.8112,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0004955595026642984,
+      "loss": 3.6272,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0004933392539964477,
+      "loss": 3.5572,
+      "step": 120
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004911190053285969,
+      "loss": 3.3966,
+      "step": 130
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000488898756660746,
+      "loss": 3.4632,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004866785079928952,
+      "loss": 3.4591,
+      "step": 150
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0004844582593250444,
+      "loss": 3.2218,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0004822380106571936,
+      "loss": 3.4101,
+      "step": 170
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00048001776198934283,
+      "loss": 3.2787,
+      "step": 180
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000477797513321492,
+      "loss": 3.1043,
+      "step": 190
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0004755772646536412,
+      "loss": 3.2435,
+      "step": 200
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00047335701598579037,
+      "loss": 3.2286,
+      "step": 210
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00047113676731793964,
+      "loss": 3.1484,
+      "step": 220
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00046891651865008885,
+      "loss": 3.1817,
+      "step": 230
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000466696269982238,
+      "loss": 3.1608,
+      "step": 240
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00046447602131438723,
+      "loss": 3.1457,
+      "step": 250
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0004622557726465364,
+      "loss": 3.1212,
+      "step": 260
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00046003552397868566,
+      "loss": 2.9937,
+      "step": 270
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0004578152753108348,
+      "loss": 3.2031,
+      "step": 280
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00045559502664298403,
+      "loss": 3.0713,
+      "step": 290
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0004533747779751332,
+      "loss": 3.0352,
+      "step": 300
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0004511545293072824,
+      "loss": 3.0872,
+      "step": 310
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0004489342806394316,
+      "loss": 3.0049,
+      "step": 320
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00044671403197158084,
+      "loss": 3.0659,
+      "step": 330
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00044449378330373,
+      "loss": 3.0852,
+      "step": 340
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0004422735346358792,
+      "loss": 2.9506,
+      "step": 350
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00044005328596802843,
+      "loss": 3.027,
+      "step": 360
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00043783303730017764,
+      "loss": 2.8812,
+      "step": 370
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00043561278863232686,
+      "loss": 2.9738,
+      "step": 380
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000433392539964476,
+      "loss": 3.0504,
+      "step": 390
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00043117229129662523,
+      "loss": 3.0195,
+      "step": 400
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0004289520426287744,
+      "loss": 2.968,
+      "step": 410
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00042673179396092366,
+      "loss": 3.0864,
+      "step": 420
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0004245115452930728,
+      "loss": 2.8735,
+      "step": 430
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00042229129662522204,
+      "loss": 3.0391,
+      "step": 440
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004200710479573712,
+      "loss": 2.8288,
+      "step": 450
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0004178507992895204,
+      "loss": 3.0182,
+      "step": 460
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0004156305506216697,
+      "loss": 3.0606,
+      "step": 470
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00041341030195381884,
+      "loss": 2.9467,
+      "step": 480
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00041119005328596806,
+      "loss": 2.7842,
+      "step": 490
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0004089698046181172,
+      "loss": 2.8472,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00040674955595026643,
+      "loss": 2.7883,
+      "step": 510
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00040452930728241565,
+      "loss": 2.8592,
+      "step": 520
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00040230905861456486,
+      "loss": 2.9186,
+      "step": 530
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000400088809946714,
+      "loss": 2.911,
+      "step": 540
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00039786856127886324,
+      "loss": 2.8355,
+      "step": 550
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003956483126110124,
+      "loss": 2.9385,
+      "step": 560
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00039342806394316167,
+      "loss": 2.8465,
+      "step": 570
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003912078152753108,
+      "loss": 2.8408,
+      "step": 580
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00038898756660746004,
+      "loss": 2.767,
+      "step": 590
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00038676731793960926,
+      "loss": 2.9691,
+      "step": 600
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003845470692717584,
+      "loss": 2.7348,
+      "step": 610
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003823268206039077,
+      "loss": 2.7477,
+      "step": 620
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00038010657193605685,
+      "loss": 2.8142,
+      "step": 630
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00037788632326820606,
+      "loss": 2.7522,
+      "step": 640
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003756660746003552,
+      "loss": 2.9403,
+      "step": 650
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00037344582593250444,
+      "loss": 2.8956,
+      "step": 660
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00037122557726465365,
+      "loss": 2.7331,
+      "step": 670
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00036900532859680287,
+      "loss": 2.8265,
+      "step": 680
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.000366785079928952,
+      "loss": 2.8919,
+      "step": 690
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00036456483126110124,
+      "loss": 2.8362,
+      "step": 700
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003623445825932504,
+      "loss": 2.7282,
+      "step": 710
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00036012433392539967,
+      "loss": 2.7628,
+      "step": 720
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003579040852575489,
+      "loss": 2.8508,
+      "step": 730
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00035568383658969805,
+      "loss": 2.8603,
+      "step": 740
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00035346358792184726,
+      "loss": 2.6765,
+      "step": 750
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003512433392539964,
+      "loss": 2.8767,
+      "step": 760
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003490230905861457,
+      "loss": 2.8446,
+      "step": 770
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034680284191829485,
+      "loss": 2.8524,
+      "step": 780
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00034458259325044407,
+      "loss": 2.778,
+      "step": 790
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003423623445825932,
+      "loss": 2.7359,
+      "step": 800
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00034014209591474244,
+      "loss": 2.7803,
+      "step": 810
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033792184724689166,
+      "loss": 2.7631,
+      "step": 820
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033570159857904087,
+      "loss": 2.7818,
+      "step": 830
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033348134991119003,
+      "loss": 2.6591,
+      "step": 840
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033126110124333925,
+      "loss": 2.6843,
+      "step": 850
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00032904085257548846,
+      "loss": 2.7299,
+      "step": 860
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003268206039076377,
+      "loss": 2.6928,
+      "step": 870
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003246003552397869,
+      "loss": 2.8512,
+      "step": 880
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00032238010657193605,
+      "loss": 2.7944,
+      "step": 890
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00032015985790408526,
+      "loss": 2.7365,
+      "step": 900
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003179396092362344,
+      "loss": 2.6992,
+      "step": 910
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003157193605683837,
+      "loss": 2.743,
+      "step": 920
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00031349911190053285,
+      "loss": 2.8022,
+      "step": 930
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00031127886323268207,
+      "loss": 2.6603,
+      "step": 940
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00030905861456483123,
+      "loss": 2.6277,
+      "step": 950
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00030683836589698044,
+      "loss": 2.7652,
+      "step": 960
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003046181172291297,
+      "loss": 2.7063,
+      "step": 970
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003023978685612789,
+      "loss": 2.6602,
+      "step": 980
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003001776198934281,
+      "loss": 2.7592,
+      "step": 990
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00029795737122557725,
+      "loss": 2.6628,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.51519775390625,
+      "eval_rouge1": 0.8067071482496617,
+      "eval_rouge2": 0.7472387953801375,
+      "eval_rougeL": 0.7071393649432568,
+      "eval_rougeLsum": 0.8209607917685595,
+      "eval_runtime": 1807.8081,
+      "eval_samples_per_second": 0.553,
+      "eval_steps_per_second": 0.553,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00029573712255772646,
+      "loss": 2.6164,
+      "step": 1010
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002935168738898757,
+      "loss": 2.6947,
+      "step": 1020
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002912966252220249,
+      "loss": 2.4547,
+      "step": 1030
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00028907637655417405,
+      "loss": 2.7347,
+      "step": 1040
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00028685612788632327,
+      "loss": 2.6491,
+      "step": 1050
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00028463587921847243,
+      "loss": 2.6778,
+      "step": 1060
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002824156305506217,
+      "loss": 2.7157,
+      "step": 1070
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00028019538188277086,
+      "loss": 2.6445,
+      "step": 1080
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002779751332149201,
+      "loss": 2.7732,
+      "step": 1090
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002757548845470693,
+      "loss": 2.6777,
+      "step": 1100
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00027353463587921845,
+      "loss": 2.6231,
+      "step": 1110
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002713143872113677,
+      "loss": 2.6003,
+      "step": 1120
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002690941385435169,
+      "loss": 2.7226,
+      "step": 1130
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0002668738898756661,
+      "loss": 2.8623,
+      "step": 1140
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00026465364120781525,
+      "loss": 2.7391,
+      "step": 1150
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00026243339253996447,
+      "loss": 2.6836,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002602131438721137,
+      "loss": 2.6357,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002579928952042629,
+      "loss": 2.5891,
+      "step": 1180
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00025577264653641206,
+      "loss": 2.7383,
+      "step": 1190
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00025355239786856127,
+      "loss": 2.738,
+      "step": 1200
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00025133214920071043,
+      "loss": 2.62,
+      "step": 1210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002491119005328597,
+      "loss": 2.5796,
+      "step": 1220
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002468916518650089,
+      "loss": 2.5744,
+      "step": 1230
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002446714031971581,
+      "loss": 2.5047,
+      "step": 1240
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002424511545293073,
+      "loss": 2.5233,
+      "step": 1250
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00024023090586145648,
+      "loss": 2.5248,
+      "step": 1260
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00023801065719360567,
+      "loss": 2.6073,
+      "step": 1270
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002357904085257549,
+      "loss": 2.596,
+      "step": 1280
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002335701598579041,
+      "loss": 2.6899,
+      "step": 1290
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002313499111900533,
+      "loss": 2.6293,
+      "step": 1300
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002291296625222025,
+      "loss": 2.639,
+      "step": 1310
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002269094138543517,
+      "loss": 2.7105,
+      "step": 1320
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002246891651865009,
+      "loss": 2.723,
+      "step": 1330
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002224689165186501,
+      "loss": 2.5697,
+      "step": 1340
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002202486678507993,
+      "loss": 2.715,
+      "step": 1350
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002180284191829485,
+      "loss": 2.6387,
+      "step": 1360
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00021580817051509768,
+      "loss": 2.5276,
+      "step": 1370
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002135879218472469,
+      "loss": 2.627,
+      "step": 1380
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00021136767317939608,
+      "loss": 2.5249,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002091474245115453,
+      "loss": 2.629,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002069271758436945,
+      "loss": 2.703,
+      "step": 1410
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002047069271758437,
+      "loss": 2.544,
+      "step": 1420
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002024866785079929,
+      "loss": 2.5992,
+      "step": 1430
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002002664298401421,
+      "loss": 2.6988,
+      "step": 1440
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00019804618117229132,
+      "loss": 2.6195,
+      "step": 1450
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0001958259325044405,
+      "loss": 2.6247,
+      "step": 1460
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0001936056838365897,
+      "loss": 2.5853,
+      "step": 1470
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0001913854351687389,
+      "loss": 2.6298,
+      "step": 1480
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001891651865008881,
+      "loss": 2.6378,
+      "step": 1490
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001869449378330373,
+      "loss": 2.5682,
+      "step": 1500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001847246891651865,
+      "loss": 2.4707,
+      "step": 1510
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00018250444049733568,
+      "loss": 2.6558,
+      "step": 1520
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00018028419182948492,
+      "loss": 2.5891,
+      "step": 1530
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001780639431616341,
+      "loss": 2.6053,
+      "step": 1540
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00017584369449378333,
+      "loss": 2.7265,
+      "step": 1550
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00017362344582593251,
+      "loss": 2.604,
+      "step": 1560
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0001714031971580817,
+      "loss": 2.5988,
+      "step": 1570
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00016918294849023092,
+      "loss": 2.5128,
+      "step": 1580
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0001669626998223801,
+      "loss": 2.7477,
+      "step": 1590
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00016474245115452932,
+      "loss": 2.5823,
+      "step": 1600
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0001625222024866785,
+      "loss": 2.6041,
+      "step": 1610
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0001603019538188277,
+      "loss": 2.6499,
+      "step": 1620
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0001580817051509769,
+      "loss": 2.5358,
+      "step": 1630
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0001558614564831261,
+      "loss": 2.636,
+      "step": 1640
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0001536412078152753,
+      "loss": 2.6257,
+      "step": 1650
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00015142095914742453,
+      "loss": 2.6454,
+      "step": 1660
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00014920071047957371,
+      "loss": 2.563,
+      "step": 1670
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00014698046181172293,
+      "loss": 2.6789,
+      "step": 1680
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00014476021314387212,
+      "loss": 2.5691,
+      "step": 1690
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00014253996447602133,
+      "loss": 2.4895,
+      "step": 1700
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00014031971580817052,
+      "loss": 2.5423,
+      "step": 1710
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0001380994671403197,
+      "loss": 2.6112,
+      "step": 1720
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00013587921847246892,
+      "loss": 2.5571,
+      "step": 1730
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0001336589698046181,
+      "loss": 2.5789,
+      "step": 1740
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00013143872113676732,
+      "loss": 2.6101,
+      "step": 1750
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0001292184724689165,
+      "loss": 2.591,
+      "step": 1760
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0001269982238010657,
+      "loss": 2.6079,
+      "step": 1770
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00012477797513321494,
+      "loss": 2.6617,
+      "step": 1780
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00012255772646536413,
+      "loss": 2.579,
+      "step": 1790
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00012033747779751332,
+      "loss": 2.594,
+      "step": 1800
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00011811722912966252,
+      "loss": 2.6464,
+      "step": 1810
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00011589698046181173,
+      "loss": 2.6125,
+      "step": 1820
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00011367673179396093,
+      "loss": 2.6031,
+      "step": 1830
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00011145648312611012,
+      "loss": 2.5603,
+      "step": 1840
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00010923623445825932,
+      "loss": 2.5277,
+      "step": 1850
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00010701598579040852,
+      "loss": 2.6054,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00010479573712255772,
+      "loss": 2.4357,
+      "step": 1870
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00010257548845470694,
+      "loss": 2.5417,
+      "step": 1880
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00010035523978685614,
+      "loss": 2.5977,
+      "step": 1890
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.813499111900533e-05,
+      "loss": 2.5966,
+      "step": 1900
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 9.591474245115453e-05,
+      "loss": 2.5847,
+      "step": 1910
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 9.369449378330373e-05,
+      "loss": 2.5082,
+      "step": 1920
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 9.147424511545293e-05,
+      "loss": 2.6329,
+      "step": 1930
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.925399644760215e-05,
+      "loss": 2.5748,
+      "step": 1940
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.703374777975133e-05,
+      "loss": 2.7223,
+      "step": 1950
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.481349911190053e-05,
+      "loss": 2.6406,
+      "step": 1960
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.259325044404974e-05,
+      "loss": 2.5924,
+      "step": 1970
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.037300177619894e-05,
+      "loss": 2.7957,
+      "step": 1980
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.815275310834814e-05,
+      "loss": 2.5123,
+      "step": 1990
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.593250444049734e-05,
+      "loss": 2.579,
+      "step": 2000
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 0.48173585534095764,
+      "eval_rouge1": 0.8206909390534098,
+      "eval_rouge2": 0.7623428554475744,
+      "eval_rougeL": 0.7177491451029034,
+      "eval_rougeLsum": 0.8341139788232226,
+      "eval_runtime": 1978.7356,
+      "eval_samples_per_second": 0.505,
+      "eval_steps_per_second": 0.505,
+      "step": 2000
+    }
+  ],
+  "max_steps": 2342,
+  "num_train_epochs": 1,
+  "total_flos": 4.738034481494016e+16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mt5-new-summarize-final/checkpoint-2000/training_args.bin b/mt5-new-summarize-final/checkpoint-2000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bc9d3b4d1721cf653ac83f80538b07e6a0b8161a
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-2000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233a568dcedd606fd72b432d2c6cc678ea8c5e086885a5642ed616a886f52eb9
+size 3643
diff --git a/mt5-new-summarize-final/checkpoint-500/config.json b/mt5-new-summarize-final/checkpoint-500/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..139799c6bf6129096048bf33ed41a9cb2f2eb678
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-500/config.json
@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.6,
+  "max_length": 128,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}
diff --git a/mt5-new-summarize-final/checkpoint-500/generation_config.json b/mt5-new-summarize-final/checkpoint-500/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5767cc0cacebfd06884eb27ae1c796d3ca829fd2
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-500/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.0"
+}
diff --git a/mt5-new-summarize-final/checkpoint-500/optimizer.pt b/mt5-new-summarize-final/checkpoint-500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..70ead67666b71695b1f05c6d6c902ea1e59a3037
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:862e91e1511f48c42446f90fddd26797161ae5d0f9789080e8f3ed1aac89b679
+size 2879429
diff --git a/mt5-new-summarize-final/checkpoint-500/rng_state.pth b/mt5-new-summarize-final/checkpoint-500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3381a05a740b1a2b7ccf9b9ff292fdd72d797468
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e7569591bd924cae7a6b055850f4f744dea0b196b0796846f38580fc3438db6
+size 14575
diff --git a/mt5-new-summarize-final/checkpoint-500/scheduler.pt b/mt5-new-summarize-final/checkpoint-500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..365730c48b2cf37eeee01f23e46d4349fd167a79
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e52e8159d86a2671fd8a649cd3c2e0d18aace8a5ba6181d11c8e8237ec341dcf
+size 627
diff --git a/mt5-new-summarize-final/checkpoint-500/special_tokens_map.json b/mt5-new-summarize-final/checkpoint-500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..79ae7ea5bf033de69d0055820c57885e3d377bbb
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-500/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
diff --git a/mt5-new-summarize-final/checkpoint-500/spiece.model b/mt5-new-summarize-final/checkpoint-500/spiece.model
new file mode 100644
index 0000000000000000000000000000000000000000..e417801865fd66bd40f9d45d46b6d0d0c2aa36b6
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-500/spiece.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802
diff --git a/mt5-new-summarize-final/checkpoint-500/tokenizer.json b/mt5-new-summarize-final/checkpoint-500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..db5a8773175d9750d86374dc47b64f6d55615279
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
+size 16330369
diff --git a/mt5-new-summarize-final/checkpoint-500/tokenizer_config.json b/mt5-new-summarize-final/checkpoint-500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4b9f3a5b62b2d1a57a16a8ae5ef280ed093e45bf
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-500/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "google/mt5-small",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--google--mt5-small/snapshots/38f23af8ec210eb6c376d40e9c56bd25a80f195d/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/mt5-new-summarize-final/checkpoint-500/trainer_state.json b/mt5-new-summarize-final/checkpoint-500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..443fb85c6e5fccf2e397f9adde37318949c8660d
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-500/trainer_state.json
@@ -0,0 +1,316 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.213464258078288,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.555555555555555e-05,
+      "loss": 20.8315,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001111111111111111,
+      "loss": 16.4875,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 10.6503,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002222222222222222,
+      "loss": 6.6236,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 5.2548,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 4.6801,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003888888888888889,
+      "loss": 4.3374,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0004444444444444444,
+      "loss": 3.9614,
+      "step": 80
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0005,
+      "loss": 3.9704,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0004977797513321492,
+      "loss": 3.8112,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0004955595026642984,
+      "loss": 3.6272,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0004933392539964477,
+      "loss": 3.5572,
+      "step": 120
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004911190053285969,
+      "loss": 3.3966,
+      "step": 130
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000488898756660746,
+      "loss": 3.4632,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004866785079928952,
+      "loss": 3.4591,
+      "step": 150
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0004844582593250444,
+      "loss": 3.2218,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0004822380106571936,
+      "loss": 3.4101,
+      "step": 170
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00048001776198934283,
+      "loss": 3.2787,
+      "step": 180
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000477797513321492,
+      "loss": 3.1043,
+      "step": 190
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0004755772646536412,
+      "loss": 3.2435,
+      "step": 200
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00047335701598579037,
+      "loss": 3.2286,
+      "step": 210
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00047113676731793964,
+      "loss": 3.1484,
+      "step": 220
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00046891651865008885,
+      "loss": 3.1817,
+      "step": 230
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000466696269982238,
+      "loss": 3.1608,
+      "step": 240
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00046447602131438723,
+      "loss": 3.1457,
+      "step": 250
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0004622557726465364,
+      "loss": 3.1212,
+      "step": 260
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00046003552397868566,
+      "loss": 2.9937,
+      "step": 270
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0004578152753108348,
+      "loss": 3.2031,
+      "step": 280
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00045559502664298403,
+      "loss": 3.0713,
+      "step": 290
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0004533747779751332,
+      "loss": 3.0352,
+      "step": 300
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0004511545293072824,
+      "loss": 3.0872,
+      "step": 310
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0004489342806394316,
+      "loss": 3.0049,
+      "step": 320
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00044671403197158084,
+      "loss": 3.0659,
+      "step": 330
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00044449378330373,
+      "loss": 3.0852,
+      "step": 340
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0004422735346358792,
+      "loss": 2.9506,
+      "step": 350
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00044005328596802843,
+      "loss": 3.027,
+      "step": 360
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00043783303730017764,
+      "loss": 2.8812,
+      "step": 370
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00043561278863232686,
+      "loss": 2.9738,
+      "step": 380
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000433392539964476,
+      "loss": 3.0504,
+      "step": 390
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00043117229129662523,
+      "loss": 3.0195,
+      "step": 400
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0004289520426287744,
+      "loss": 2.968,
+      "step": 410
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00042673179396092366,
+      "loss": 3.0864,
+      "step": 420
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0004245115452930728,
+      "loss": 2.8735,
+      "step": 430
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00042229129662522204,
+      "loss": 3.0391,
+      "step": 440
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004200710479573712,
+      "loss": 2.8288,
+      "step": 450
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0004178507992895204,
+      "loss": 3.0182,
+      "step": 460
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0004156305506216697,
+      "loss": 3.0606,
+      "step": 470
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00041341030195381884,
+      "loss": 2.9467,
+      "step": 480
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00041119005328596806,
+      "loss": 2.7842,
+      "step": 490
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0004089698046181172,
+      "loss": 2.8472,
+      "step": 500
+    }
+  ],
+  "max_steps": 2342,
+  "num_train_epochs": 1,
+  "total_flos": 1.18055554516992e+16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mt5-new-summarize-final/checkpoint-500/training_args.bin b/mt5-new-summarize-final/checkpoint-500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bc9d3b4d1721cf653ac83f80538b07e6a0b8161a
--- /dev/null
+++ b/mt5-new-summarize-final/checkpoint-500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233a568dcedd606fd72b432d2c6cc678ea8c5e086885a5642ed616a886f52eb9
+size 3643
diff --git a/mt5-new-summarize-final/config.json b/mt5-new-summarize-final/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..139799c6bf6129096048bf33ed41a9cb2f2eb678
--- /dev/null
+++ b/mt5-new-summarize-final/config.json
@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.6,
+  "max_length": 128,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}
diff --git a/mt5-new-summarize-final/generation_config.json b/mt5-new-summarize-final/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a5a5137b6c89be4407a330b5240bbd35976c1380
--- /dev/null
+++ b/mt5-new-summarize-final/generation_config.json
@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "length_penalty": 0.6,
+  "max_length": 128,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.0"
+}
diff --git a/mt5-new-summarize-final/pytorch_model.bin b/mt5-new-summarize-final/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6a3743160db14ff57e76b06366f1679e8d58a72e
--- /dev/null
+++ b/mt5-new-summarize-final/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2902dce4d66552f797fdd41548dcbc0682bf2ab91938e503552557c0d0f7cb22
+size 1200772485
diff --git a/mt5-new-summarize-final/runs/Jan29_13-58-29_d0795309bd3b/1675000709.4761653/events.out.tfevents.1675000709.d0795309bd3b.4670.1 b/mt5-new-summarize-final/runs/Jan29_13-58-29_d0795309bd3b/1675000709.4761653/events.out.tfevents.1675000709.d0795309bd3b.4670.1
new file mode 100644
index 0000000000000000000000000000000000000000..791133eb3fd8ef804976527f140086a30e908bc7
--- /dev/null
+++ b/mt5-new-summarize-final/runs/Jan29_13-58-29_d0795309bd3b/1675000709.4761653/events.out.tfevents.1675000709.d0795309bd3b.4670.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad27ec134114b9f9f4fd9a2e390c618677f1ec53f9636eed716424805f0d91f
+size 5988
diff --git a/mt5-new-summarize-final/runs/Jan29_13-58-29_d0795309bd3b/events.out.tfevents.1675000709.d0795309bd3b.4670.0 b/mt5-new-summarize-final/runs/Jan29_13-58-29_d0795309bd3b/events.out.tfevents.1675000709.d0795309bd3b.4670.0
new file mode 100644
index 0000000000000000000000000000000000000000..9be6a18c50d9699b7a6c58f1506a8ac3b6794ccb
--- /dev/null
+++ b/mt5-new-summarize-final/runs/Jan29_13-58-29_d0795309bd3b/events.out.tfevents.1675000709.d0795309bd3b.4670.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ef820c793c89b6e6c4e554c2a7eb554edfb58be6f33776d7ad79c242fa8da8
+size 42224
diff --git a/mt5-new-summarize-final/runs/Jan29_13-58-29_d0795309bd3b/events.out.tfevents.1675016428.d0795309bd3b.4670.2 b/mt5-new-summarize-final/runs/Jan29_13-58-29_d0795309bd3b/events.out.tfevents.1675016428.d0795309bd3b.4670.2
new file mode 100644
index 0000000000000000000000000000000000000000..4da9a4dc1a532d27dcdb7565cf4c4fbc390a9599
--- /dev/null
+++ b/mt5-new-summarize-final/runs/Jan29_13-58-29_d0795309bd3b/events.out.tfevents.1675016428.d0795309bd3b.4670.2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539dd1948a8a60fbe98568cd0687fe881902c35784926e7915855bac1ddc7d21
+size 514
diff --git a/mt5-new-summarize-final/special_tokens_map.json b/mt5-new-summarize-final/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..79ae7ea5bf033de69d0055820c57885e3d377bbb
--- /dev/null
+++ b/mt5-new-summarize-final/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
diff --git a/mt5-new-summarize-final/spiece.model b/mt5-new-summarize-final/spiece.model
new file mode 100644
index 0000000000000000000000000000000000000000..e417801865fd66bd40f9d45d46b6d0d0c2aa36b6
--- /dev/null
+++ b/mt5-new-summarize-final/spiece.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802
diff --git a/mt5-new-summarize-final/tokenizer.json b/mt5-new-summarize-final/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..db5a8773175d9750d86374dc47b64f6d55615279
--- /dev/null
+++ b/mt5-new-summarize-final/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
+size 16330369
diff --git a/mt5-new-summarize-final/tokenizer_config.json b/mt5-new-summarize-final/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4b9f3a5b62b2d1a57a16a8ae5ef280ed093e45bf
--- /dev/null
+++ b/mt5-new-summarize-final/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "google/mt5-small",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--google--mt5-small/snapshots/38f23af8ec210eb6c376d40e9c56bd25a80f195d/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/mt5-new-summarize-final/training_args.bin b/mt5-new-summarize-final/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bc9d3b4d1721cf653ac83f80538b07e6a0b8161a
--- /dev/null
+++ b/mt5-new-summarize-final/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233a568dcedd606fd72b432d2c6cc678ea8c5e086885a5642ed616a886f52eb9
+size 3643