1

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+base_model: google/byt5-small
+tags:
+- generated_from_trainer
+model-index:
+- name: byt5_re_1k
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# byt5_re_1k
+
+This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 1.4231
+- eval_runtime: 10.6751
+- eval_samples_per_second: 936.758
+- eval_steps_per_second: 1.218
+- epoch: 192.0
+- step: 384
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 800
+- eval_batch_size: 800
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 200
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,127 @@
+{
+  "<extra_id_0>": 259,
+  "<extra_id_100>": 359,
+  "<extra_id_101>": 360,
+  "<extra_id_102>": 361,
+  "<extra_id_103>": 362,
+  "<extra_id_104>": 363,
+  "<extra_id_105>": 364,
+  "<extra_id_106>": 365,
+  "<extra_id_107>": 366,
+  "<extra_id_108>": 367,
+  "<extra_id_109>": 368,
+  "<extra_id_10>": 269,
+  "<extra_id_110>": 369,
+  "<extra_id_111>": 370,
+  "<extra_id_112>": 371,
+  "<extra_id_113>": 372,
+  "<extra_id_114>": 373,
+  "<extra_id_115>": 374,
+  "<extra_id_116>": 375,
+  "<extra_id_117>": 376,
+  "<extra_id_118>": 377,
+  "<extra_id_119>": 378,
+  "<extra_id_11>": 270,
+  "<extra_id_120>": 379,
+  "<extra_id_121>": 380,
+  "<extra_id_122>": 381,
+  "<extra_id_123>": 382,
+  "<extra_id_124>": 383,
+  "<extra_id_12>": 271,
+  "<extra_id_13>": 272,
+  "<extra_id_14>": 273,
+  "<extra_id_15>": 274,
+  "<extra_id_16>": 275,
+  "<extra_id_17>": 276,
+  "<extra_id_18>": 277,
+  "<extra_id_19>": 278,
+  "<extra_id_1>": 260,
+  "<extra_id_20>": 279,
+  "<extra_id_21>": 280,
+  "<extra_id_22>": 281,
+  "<extra_id_23>": 282,
+  "<extra_id_24>": 283,
+  "<extra_id_25>": 284,
+  "<extra_id_26>": 285,
+  "<extra_id_27>": 286,
+  "<extra_id_28>": 287,
+  "<extra_id_29>": 288,
+  "<extra_id_2>": 261,
+  "<extra_id_30>": 289,
+  "<extra_id_31>": 290,
+  "<extra_id_32>": 291,
+  "<extra_id_33>": 292,
+  "<extra_id_34>": 293,
+  "<extra_id_35>": 294,
+  "<extra_id_36>": 295,
+  "<extra_id_37>": 296,
+  "<extra_id_38>": 297,
+  "<extra_id_39>": 298,
+  "<extra_id_3>": 262,
+  "<extra_id_40>": 299,
+  "<extra_id_41>": 300,
+  "<extra_id_42>": 301,
+  "<extra_id_43>": 302,
+  "<extra_id_44>": 303,
+  "<extra_id_45>": 304,
+  "<extra_id_46>": 305,
+  "<extra_id_47>": 306,
+  "<extra_id_48>": 307,
+  "<extra_id_49>": 308,
+  "<extra_id_4>": 263,
+  "<extra_id_50>": 309,
+  "<extra_id_51>": 310,
+  "<extra_id_52>": 311,
+  "<extra_id_53>": 312,
+  "<extra_id_54>": 313,
+  "<extra_id_55>": 314,
+  "<extra_id_56>": 315,
+  "<extra_id_57>": 316,
+  "<extra_id_58>": 317,
+  "<extra_id_59>": 318,
+  "<extra_id_5>": 264,
+  "<extra_id_60>": 319,
+  "<extra_id_61>": 320,
+  "<extra_id_62>": 321,
+  "<extra_id_63>": 322,
+  "<extra_id_64>": 323,
+  "<extra_id_65>": 324,
+  "<extra_id_66>": 325,
+  "<extra_id_67>": 326,
+  "<extra_id_68>": 327,
+  "<extra_id_69>": 328,
+  "<extra_id_6>": 265,
+  "<extra_id_70>": 329,
+  "<extra_id_71>": 330,
+  "<extra_id_72>": 331,
+  "<extra_id_73>": 332,
+  "<extra_id_74>": 333,
+  "<extra_id_75>": 334,
+  "<extra_id_76>": 335,
+  "<extra_id_77>": 336,
+  "<extra_id_78>": 337,
+  "<extra_id_79>": 338,
+  "<extra_id_7>": 266,
+  "<extra_id_80>": 339,
+  "<extra_id_81>": 340,
+  "<extra_id_82>": 341,
+  "<extra_id_83>": 342,
+  "<extra_id_84>": 343,
+  "<extra_id_85>": 344,
+  "<extra_id_86>": 345,
+  "<extra_id_87>": 346,
+  "<extra_id_88>": 347,
+  "<extra_id_89>": 348,
+  "<extra_id_8>": 267,
+  "<extra_id_90>": 349,
+  "<extra_id_91>": 350,
+  "<extra_id_92>": 351,
+  "<extra_id_93>": 352,
+  "<extra_id_94>": 353,
+  "<extra_id_95>": 354,
+  "<extra_id_96>": 355,
+  "<extra_id_97>": 356,
+  "<extra_id_98>": 357,
+  "<extra_id_99>": 358,
+  "<extra_id_9>": 268
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/byt5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 3584,
+  "d_kv": 64,
+  "d_model": 1472,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 4,
+  "num_heads": 6,
+  "num_layers": 12,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "ByT5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 384
+}

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": "4.35.2"
+}

logs/events.out.tfevents.1713685284.ip-10-25-205-144.20025.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81fc49606027e44d37d37d48dcdb72a8b06bc4903fdd4e172ddf1bff67fc4bd9
+size 4184

logs/events.out.tfevents.1713685311.ip-10-25-205-144.35483.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff30cce4f9e2a6d79e32bc4d18bc4336dc2548e22305b628c2dbc533fc80874a
+size 56257

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:381a2b7816651bce720169845bddc66377a00495415cb28b3a14772a8fc1cec8
+size 1198571496

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df72105d2df2ce7240c656b6f70b3d339b2d168ae4b283b30fdbe24751c1077d
+size 2397245434

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb3bc9427b9603cd821ab227a00b7085ebf5502db2c94065150b802bf9b753a
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3c91e6a11603780a9f34c5b82893b90d2b511fdaddd63582eb62e3d7a20cd25
+size 1064

special_tokens_map.json

@@ -0,0 +1,150 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>",
+    "<extra_id_100>",
+    "<extra_id_101>",
+    "<extra_id_102>",
+    "<extra_id_103>",
+    "<extra_id_104>",
+    "<extra_id_105>",
+    "<extra_id_106>",
+    "<extra_id_107>",
+    "<extra_id_108>",
+    "<extra_id_109>",
+    "<extra_id_110>",
+    "<extra_id_111>",
+    "<extra_id_112>",
+    "<extra_id_113>",
+    "<extra_id_114>",
+    "<extra_id_115>",
+    "<extra_id_116>",
+    "<extra_id_117>",
+    "<extra_id_118>",
+    "<extra_id_119>",
+    "<extra_id_120>",
+    "<extra_id_121>",
+    "<extra_id_122>",
+    "<extra_id_123>",
+    "<extra_id_124>"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,1162 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "259": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "260": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "261": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "262": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "263": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "264": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "265": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "266": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "267": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "268": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "269": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "270": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "271": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "272": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "273": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "274": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "275": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "276": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "277": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "278": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "279": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "280": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "281": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "282": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "283": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "284": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "285": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "286": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "287": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "288": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "289": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "290": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "291": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "292": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "293": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "294": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "295": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "296": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "297": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "298": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "299": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "300": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "301": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "302": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "303": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "304": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "305": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "306": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "307": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "308": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "309": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "310": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "311": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "312": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "313": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "314": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "315": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "316": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "317": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "318": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "319": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "320": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "321": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "322": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "323": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "324": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "325": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "326": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "327": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "328": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "329": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "330": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "331": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "332": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "333": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "334": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "335": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "336": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "337": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "338": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "339": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "340": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "341": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "342": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "343": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "344": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "345": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "346": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "347": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "348": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "349": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "350": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "351": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "352": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "353": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "354": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "355": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "356": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "357": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "358": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "359": {
+      "content": "<extra_id_100>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "360": {
+      "content": "<extra_id_101>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "361": {
+      "content": "<extra_id_102>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "362": {
+      "content": "<extra_id_103>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "363": {
+      "content": "<extra_id_104>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "364": {
+      "content": "<extra_id_105>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "365": {
+      "content": "<extra_id_106>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "366": {
+      "content": "<extra_id_107>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "367": {
+      "content": "<extra_id_108>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "368": {
+      "content": "<extra_id_109>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "369": {
+      "content": "<extra_id_110>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "370": {
+      "content": "<extra_id_111>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "371": {
+      "content": "<extra_id_112>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "372": {
+      "content": "<extra_id_113>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "373": {
+      "content": "<extra_id_114>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "374": {
+      "content": "<extra_id_115>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "375": {
+      "content": "<extra_id_116>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "376": {
+      "content": "<extra_id_117>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "377": {
+      "content": "<extra_id_118>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "378": {
+      "content": "<extra_id_119>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "379": {
+      "content": "<extra_id_120>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "380": {
+      "content": "<extra_id_121>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "381": {
+      "content": "<extra_id_122>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "382": {
+      "content": "<extra_id_123>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "383": {
+      "content": "<extra_id_124>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>",
+    "<extra_id_100>",
+    "<extra_id_101>",
+    "<extra_id_102>",
+    "<extra_id_103>",
+    "<extra_id_104>",
+    "<extra_id_105>",
+    "<extra_id_106>",
+    "<extra_id_107>",
+    "<extra_id_108>",
+    "<extra_id_109>",
+    "<extra_id_110>",
+    "<extra_id_111>",
+    "<extra_id_112>",
+    "<extra_id_113>",
+    "<extra_id_114>",
+    "<extra_id_115>",
+    "<extra_id_116>",
+    "<extra_id_117>",
+    "<extra_id_118>",
+    "<extra_id_119>",
+    "<extra_id_120>",
+    "<extra_id_121>",
+    "<extra_id_122>",
+    "<extra_id_123>",
+    "<extra_id_124>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "ByT5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,1467 @@
+{
+  "best_metric": 1.4208089113235474,
+  "best_model_checkpoint": "AlexWang99/byt5_re_1k/checkpoint-362",
+  "epoch": 181.0,
+  "eval_steps": 500,
+  "global_step": 362,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 7.775562286376953,
+      "eval_runtime": 10.6848,
+      "eval_samples_per_second": 935.909,
+      "eval_steps_per_second": 1.217,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.888936519622803,
+      "eval_runtime": 10.8293,
+      "eval_samples_per_second": 923.42,
+      "eval_steps_per_second": 1.2,
+      "step": 4
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.1838483810424805,
+      "eval_runtime": 10.6887,
+      "eval_samples_per_second": 935.569,
+      "eval_steps_per_second": 1.216,
+      "step": 6
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.626400947570801,
+      "eval_runtime": 10.9681,
+      "eval_samples_per_second": 911.734,
+      "eval_steps_per_second": 1.185,
+      "step": 8
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 5.153331279754639,
+      "eval_runtime": 10.7369,
+      "eval_samples_per_second": 931.367,
+      "eval_steps_per_second": 1.211,
+      "step": 10
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 4.734142780303955,
+      "eval_runtime": 11.004,
+      "eval_samples_per_second": 908.762,
+      "eval_steps_per_second": 1.181,
+      "step": 12
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 4.333576679229736,
+      "eval_runtime": 10.7676,
+      "eval_samples_per_second": 928.708,
+      "eval_steps_per_second": 1.207,
+      "step": 14
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 3.938502788543701,
+      "eval_runtime": 10.782,
+      "eval_samples_per_second": 927.476,
+      "eval_steps_per_second": 1.206,
+      "step": 16
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 3.557016134262085,
+      "eval_runtime": 11.022,
+      "eval_samples_per_second": 907.278,
+      "eval_steps_per_second": 1.179,
+      "step": 18
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 3.2168831825256348,
+      "eval_runtime": 10.7843,
+      "eval_samples_per_second": 927.273,
+      "eval_steps_per_second": 1.205,
+      "step": 20
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 2.9309566020965576,
+      "eval_runtime": 10.8755,
+      "eval_samples_per_second": 919.501,
+      "eval_steps_per_second": 1.195,
+      "step": 22
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 2.7042219638824463,
+      "eval_runtime": 10.7967,
+      "eval_samples_per_second": 926.21,
+      "eval_steps_per_second": 1.204,
+      "step": 24
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 2.5138416290283203,
+      "eval_runtime": 10.8666,
+      "eval_samples_per_second": 920.248,
+      "eval_steps_per_second": 1.196,
+      "step": 26
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 2.3652985095977783,
+      "eval_runtime": 10.7919,
+      "eval_samples_per_second": 926.619,
+      "eval_steps_per_second": 1.205,
+      "step": 28
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 2.248030185699463,
+      "eval_runtime": 10.8705,
+      "eval_samples_per_second": 919.923,
+      "eval_steps_per_second": 1.196,
+      "step": 30
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 2.13440203666687,
+      "eval_runtime": 10.7977,
+      "eval_samples_per_second": 926.12,
+      "eval_steps_per_second": 1.204,
+      "step": 32
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 2.0899171829223633,
+      "eval_runtime": 10.7912,
+      "eval_samples_per_second": 926.685,
+      "eval_steps_per_second": 1.205,
+      "step": 34
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 2.100477457046509,
+      "eval_runtime": 10.8653,
+      "eval_samples_per_second": 920.357,
+      "eval_steps_per_second": 1.196,
+      "step": 36
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 2.047548532485962,
+      "eval_runtime": 10.7885,
+      "eval_samples_per_second": 926.915,
+      "eval_steps_per_second": 1.205,
+      "step": 38
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 1.996556043624878,
+      "eval_runtime": 11.0201,
+      "eval_samples_per_second": 907.429,
+      "eval_steps_per_second": 1.18,
+      "step": 40
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.9695481061935425,
+      "eval_runtime": 10.783,
+      "eval_samples_per_second": 927.385,
+      "eval_steps_per_second": 1.206,
+      "step": 42
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 1.9760867357254028,
+      "eval_runtime": 10.8889,
+      "eval_samples_per_second": 918.37,
+      "eval_steps_per_second": 1.194,
+      "step": 44
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.9658013582229614,
+      "eval_runtime": 10.7879,
+      "eval_samples_per_second": 926.962,
+      "eval_steps_per_second": 1.205,
+      "step": 46
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.9119044542312622,
+      "eval_runtime": 10.8618,
+      "eval_samples_per_second": 920.659,
+      "eval_steps_per_second": 1.197,
+      "step": 48
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 1.89186429977417,
+      "eval_runtime": 10.7933,
+      "eval_samples_per_second": 926.503,
+      "eval_steps_per_second": 1.204,
+      "step": 50
+    },
+    {
+      "epoch": 26.0,
+      "eval_loss": 1.8932195901870728,
+      "eval_runtime": 10.873,
+      "eval_samples_per_second": 919.709,
+      "eval_steps_per_second": 1.196,
+      "step": 52
+    },
+    {
+      "epoch": 27.0,
+      "eval_loss": 1.9076615571975708,
+      "eval_runtime": 10.7917,
+      "eval_samples_per_second": 926.637,
+      "eval_steps_per_second": 1.205,
+      "step": 54
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 1.8671808242797852,
+      "eval_runtime": 10.7945,
+      "eval_samples_per_second": 926.402,
+      "eval_steps_per_second": 1.204,
+      "step": 56
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 1.8664835691452026,
+      "eval_runtime": 10.8739,
+      "eval_samples_per_second": 919.632,
+      "eval_steps_per_second": 1.196,
+      "step": 58
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 1.8679856061935425,
+      "eval_runtime": 10.7966,
+      "eval_samples_per_second": 926.219,
+      "eval_steps_per_second": 1.204,
+      "step": 60
+    },
+    {
+      "epoch": 31.0,
+      "eval_loss": 1.858332633972168,
+      "eval_runtime": 10.8742,
+      "eval_samples_per_second": 919.609,
+      "eval_steps_per_second": 1.195,
+      "step": 62
+    },
+    {
+      "epoch": 32.0,
+      "eval_loss": 1.8586550951004028,
+      "eval_runtime": 10.7775,
+      "eval_samples_per_second": 927.859,
+      "eval_steps_per_second": 1.206,
+      "step": 64
+    },
+    {
+      "epoch": 33.0,
+      "eval_loss": 1.836769700050354,
+      "eval_runtime": 10.8615,
+      "eval_samples_per_second": 920.686,
+      "eval_steps_per_second": 1.197,
+      "step": 66
+    },
+    {
+      "epoch": 34.0,
+      "eval_loss": 1.8279472589492798,
+      "eval_runtime": 10.7787,
+      "eval_samples_per_second": 927.754,
+      "eval_steps_per_second": 1.206,
+      "step": 68
+    },
+    {
+      "epoch": 35.0,
+      "eval_loss": 1.817927360534668,
+      "eval_runtime": 10.7813,
+      "eval_samples_per_second": 927.534,
+      "eval_steps_per_second": 1.206,
+      "step": 70
+    },
+    {
+      "epoch": 36.0,
+      "eval_loss": 1.7950810194015503,
+      "eval_runtime": 11.0203,
+      "eval_samples_per_second": 907.419,
+      "eval_steps_per_second": 1.18,
+      "step": 72
+    },
+    {
+      "epoch": 37.0,
+      "eval_loss": 1.7667052745819092,
+      "eval_runtime": 10.7915,
+      "eval_samples_per_second": 926.655,
+      "eval_steps_per_second": 1.205,
+      "step": 74
+    },
+    {
+      "epoch": 38.0,
+      "eval_loss": 1.7852015495300293,
+      "eval_runtime": 10.8703,
+      "eval_samples_per_second": 919.941,
+      "eval_steps_per_second": 1.196,
+      "step": 76
+    },
+    {
+      "epoch": 39.0,
+      "eval_loss": 1.7741429805755615,
+      "eval_runtime": 10.7837,
+      "eval_samples_per_second": 927.326,
+      "eval_steps_per_second": 1.206,
+      "step": 78
+    },
+    {
+      "epoch": 40.0,
+      "eval_loss": 1.718443512916565,
+      "eval_runtime": 10.8729,
+      "eval_samples_per_second": 919.72,
+      "eval_steps_per_second": 1.196,
+      "step": 80
+    },
+    {
+      "epoch": 41.0,
+      "eval_loss": 1.6899281740188599,
+      "eval_runtime": 10.789,
+      "eval_samples_per_second": 926.869,
+      "eval_steps_per_second": 1.205,
+      "step": 82
+    },
+    {
+      "epoch": 42.0,
+      "eval_loss": 1.6984148025512695,
+      "eval_runtime": 10.8669,
+      "eval_samples_per_second": 920.229,
+      "eval_steps_per_second": 1.196,
+      "step": 84
+    },
+    {
+      "epoch": 43.0,
+      "eval_loss": 1.68986177444458,
+      "eval_runtime": 10.7878,
+      "eval_samples_per_second": 926.976,
+      "eval_steps_per_second": 1.205,
+      "step": 86
+    },
+    {
+      "epoch": 44.0,
+      "eval_loss": 1.643083930015564,
+      "eval_runtime": 10.7947,
+      "eval_samples_per_second": 926.384,
+      "eval_steps_per_second": 1.204,
+      "step": 88
+    },
+    {
+      "epoch": 45.0,
+      "eval_loss": 1.6373401880264282,
+      "eval_runtime": 10.8675,
+      "eval_samples_per_second": 920.171,
+      "eval_steps_per_second": 1.196,
+      "step": 90
+    },
+    {
+      "epoch": 46.0,
+      "eval_loss": 1.6289523839950562,
+      "eval_runtime": 10.7853,
+      "eval_samples_per_second": 927.192,
+      "eval_steps_per_second": 1.205,
+      "step": 92
+    },
+    {
+      "epoch": 47.0,
+      "eval_loss": 1.6165605783462524,
+      "eval_runtime": 11.0285,
+      "eval_samples_per_second": 906.741,
+      "eval_steps_per_second": 1.179,
+      "step": 94
+    },
+    {
+      "epoch": 48.0,
+      "eval_loss": 1.6076592206954956,
+      "eval_runtime": 10.7945,
+      "eval_samples_per_second": 926.401,
+      "eval_steps_per_second": 1.204,
+      "step": 96
+    },
+    {
+      "epoch": 49.0,
+      "eval_loss": 1.604373574256897,
+      "eval_runtime": 10.8717,
+      "eval_samples_per_second": 919.822,
+      "eval_steps_per_second": 1.196,
+      "step": 98
+    },
+    {
+      "epoch": 50.0,
+      "eval_loss": 1.616941213607788,
+      "eval_runtime": 10.793,
+      "eval_samples_per_second": 926.53,
+      "eval_steps_per_second": 1.204,
+      "step": 100
+    },
+    {
+      "epoch": 51.0,
+      "eval_loss": 1.6135770082473755,
+      "eval_runtime": 11.0422,
+      "eval_samples_per_second": 905.614,
+      "eval_steps_per_second": 1.177,
+      "step": 102
+    },
+    {
+      "epoch": 52.0,
+      "eval_loss": 1.584197759628296,
+      "eval_runtime": 10.7862,
+      "eval_samples_per_second": 927.109,
+      "eval_steps_per_second": 1.205,
+      "step": 104
+    },
+    {
+      "epoch": 53.0,
+      "eval_loss": 1.5821086168289185,
+      "eval_runtime": 11.0219,
+      "eval_samples_per_second": 907.286,
+      "eval_steps_per_second": 1.179,
+      "step": 106
+    },
+    {
+      "epoch": 54.0,
+      "eval_loss": 1.592121958732605,
+      "eval_runtime": 10.7783,
+      "eval_samples_per_second": 927.787,
+      "eval_steps_per_second": 1.206,
+      "step": 108
+    },
+    {
+      "epoch": 55.0,
+      "eval_loss": 1.598443865776062,
+      "eval_runtime": 11.0215,
+      "eval_samples_per_second": 907.318,
+      "eval_steps_per_second": 1.18,
+      "step": 110
+    },
+    {
+      "epoch": 56.0,
+      "eval_loss": 1.562904715538025,
+      "eval_runtime": 10.8689,
+      "eval_samples_per_second": 920.053,
+      "eval_steps_per_second": 1.196,
+      "step": 112
+    },
+    {
+      "epoch": 57.0,
+      "eval_loss": 1.556736707687378,
+      "eval_runtime": 10.7877,
+      "eval_samples_per_second": 926.98,
+      "eval_steps_per_second": 1.205,
+      "step": 114
+    },
+    {
+      "epoch": 58.0,
+      "eval_loss": 1.554081916809082,
+      "eval_runtime": 10.8724,
+      "eval_samples_per_second": 919.757,
+      "eval_steps_per_second": 1.196,
+      "step": 116
+    },
+    {
+      "epoch": 59.0,
+      "eval_loss": 1.5780812501907349,
+      "eval_runtime": 10.7882,
+      "eval_samples_per_second": 926.94,
+      "eval_steps_per_second": 1.205,
+      "step": 118
+    },
+    {
+      "epoch": 60.0,
+      "eval_loss": 1.5569387674331665,
+      "eval_runtime": 10.878,
+      "eval_samples_per_second": 919.289,
+      "eval_steps_per_second": 1.195,
+      "step": 120
+    },
+    {
+      "epoch": 61.0,
+      "eval_loss": 1.5472592115402222,
+      "eval_runtime": 10.797,
+      "eval_samples_per_second": 926.18,
+      "eval_steps_per_second": 1.204,
+      "step": 122
+    },
+    {
+      "epoch": 62.0,
+      "eval_loss": 1.5447337627410889,
+      "eval_runtime": 10.7871,
+      "eval_samples_per_second": 927.031,
+      "eval_steps_per_second": 1.205,
+      "step": 124
+    },
+    {
+      "epoch": 63.0,
+      "eval_loss": 1.5714285373687744,
+      "eval_runtime": 11.0266,
+      "eval_samples_per_second": 906.896,
+      "eval_steps_per_second": 1.179,
+      "step": 126
+    },
+    {
+      "epoch": 64.0,
+      "eval_loss": 1.572940468788147,
+      "eval_runtime": 10.7931,
+      "eval_samples_per_second": 926.518,
+      "eval_steps_per_second": 1.204,
+      "step": 128
+    },
+    {
+      "epoch": 65.0,
+      "eval_loss": 1.5434839725494385,
+      "eval_runtime": 10.8657,
+      "eval_samples_per_second": 920.328,
+      "eval_steps_per_second": 1.196,
+      "step": 130
+    },
+    {
+      "epoch": 66.0,
+      "eval_loss": 1.5406599044799805,
+      "eval_runtime": 10.7896,
+      "eval_samples_per_second": 926.816,
+      "eval_steps_per_second": 1.205,
+      "step": 132
+    },
+    {
+      "epoch": 67.0,
+      "eval_loss": 1.5430865287780762,
+      "eval_runtime": 10.868,
+      "eval_samples_per_second": 920.137,
+      "eval_steps_per_second": 1.196,
+      "step": 134
+    },
+    {
+      "epoch": 68.0,
+      "eval_loss": 1.5774503946304321,
+      "eval_runtime": 10.7888,
+      "eval_samples_per_second": 926.889,
+      "eval_steps_per_second": 1.205,
+      "step": 136
+    },
+    {
+      "epoch": 69.0,
+      "eval_loss": 1.5680021047592163,
+      "eval_runtime": 10.8677,
+      "eval_samples_per_second": 920.161,
+      "eval_steps_per_second": 1.196,
+      "step": 138
+    },
+    {
+      "epoch": 70.0,
+      "eval_loss": 1.5386120080947876,
+      "eval_runtime": 10.7802,
+      "eval_samples_per_second": 927.629,
+      "eval_steps_per_second": 1.206,
+      "step": 140
+    },
+    {
+      "epoch": 71.0,
+      "eval_loss": 1.537217378616333,
+      "eval_runtime": 10.7876,
+      "eval_samples_per_second": 926.994,
+      "eval_steps_per_second": 1.205,
+      "step": 142
+    },
+    {
+      "epoch": 72.0,
+      "eval_loss": 1.5415935516357422,
+      "eval_runtime": 10.8784,
+      "eval_samples_per_second": 919.255,
+      "eval_steps_per_second": 1.195,
+      "step": 144
+    },
+    {
+      "epoch": 73.0,
+      "eval_loss": 1.5851819515228271,
+      "eval_runtime": 10.7879,
+      "eval_samples_per_second": 926.962,
+      "eval_steps_per_second": 1.205,
+      "step": 146
+    },
+    {
+      "epoch": 74.0,
+      "eval_loss": 1.5615135431289673,
+      "eval_runtime": 11.0229,
+      "eval_samples_per_second": 907.205,
+      "eval_steps_per_second": 1.179,
+      "step": 148
+    },
+    {
+      "epoch": 75.0,
+      "eval_loss": 1.5356107950210571,
+      "eval_runtime": 10.7892,
+      "eval_samples_per_second": 926.852,
+      "eval_steps_per_second": 1.205,
+      "step": 150
+    },
+    {
+      "epoch": 76.0,
+      "eval_loss": 1.5345250368118286,
+      "eval_runtime": 10.8628,
+      "eval_samples_per_second": 920.574,
+      "eval_steps_per_second": 1.197,
+      "step": 152
+    },
+    {
+      "epoch": 77.0,
+      "eval_loss": 1.5348494052886963,
+      "eval_runtime": 10.7982,
+      "eval_samples_per_second": 926.08,
+      "eval_steps_per_second": 1.204,
+      "step": 154
+    },
+    {
+      "epoch": 78.0,
+      "eval_loss": 1.5350173711776733,
+      "eval_runtime": 11.0234,
+      "eval_samples_per_second": 907.165,
+      "eval_steps_per_second": 1.179,
+      "step": 156
+    },
+    {
+      "epoch": 79.0,
+      "eval_loss": 1.5344058275222778,
+      "eval_runtime": 10.7938,
+      "eval_samples_per_second": 926.459,
+      "eval_steps_per_second": 1.204,
+      "step": 158
+    },
+    {
+      "epoch": 80.0,
+      "eval_loss": 1.5319613218307495,
+      "eval_runtime": 11.0103,
+      "eval_samples_per_second": 908.24,
+      "eval_steps_per_second": 1.181,
+      "step": 160
+    },
+    {
+      "epoch": 81.0,
+      "eval_loss": 1.5311990976333618,
+      "eval_runtime": 10.7993,
+      "eval_samples_per_second": 925.99,
+      "eval_steps_per_second": 1.204,
+      "step": 162
+    },
+    {
+      "epoch": 82.0,
+      "eval_loss": 1.5308246612548828,
+      "eval_runtime": 11.0279,
+      "eval_samples_per_second": 906.787,
+      "eval_steps_per_second": 1.179,
+      "step": 164
+    },
+    {
+      "epoch": 83.0,
+      "eval_loss": 1.530852198600769,
+      "eval_runtime": 10.8812,
+      "eval_samples_per_second": 919.019,
+      "eval_steps_per_second": 1.195,
+      "step": 166
+    },
+    {
+      "epoch": 84.0,
+      "eval_loss": 1.528510332107544,
+      "eval_runtime": 10.7908,
+      "eval_samples_per_second": 926.72,
+      "eval_steps_per_second": 1.205,
+      "step": 168
+    },
+    {
+      "epoch": 85.0,
+      "eval_loss": 1.5265289545059204,
+      "eval_runtime": 10.8831,
+      "eval_samples_per_second": 918.858,
+      "eval_steps_per_second": 1.195,
+      "step": 170
+    },
+    {
+      "epoch": 86.0,
+      "eval_loss": 1.525810956954956,
+      "eval_runtime": 10.7922,
+      "eval_samples_per_second": 926.595,
+      "eval_steps_per_second": 1.205,
+      "step": 172
+    },
+    {
+      "epoch": 87.0,
+      "eval_loss": 1.5260074138641357,
+      "eval_runtime": 10.8658,
+      "eval_samples_per_second": 920.317,
+      "eval_steps_per_second": 1.196,
+      "step": 174
+    },
+    {
+      "epoch": 88.0,
+      "eval_loss": 1.523621678352356,
+      "eval_runtime": 10.8062,
+      "eval_samples_per_second": 925.398,
+      "eval_steps_per_second": 1.203,
+      "step": 176
+    },
+    {
+      "epoch": 89.0,
+      "eval_loss": 1.522126317024231,
+      "eval_runtime": 10.7844,
+      "eval_samples_per_second": 927.263,
+      "eval_steps_per_second": 1.205,
+      "step": 178
+    },
+    {
+      "epoch": 90.0,
+      "eval_loss": 1.5219790935516357,
+      "eval_runtime": 10.8694,
+      "eval_samples_per_second": 920.018,
+      "eval_steps_per_second": 1.196,
+      "step": 180
+    },
+    {
+      "epoch": 91.0,
+      "eval_loss": 1.5207847356796265,
+      "eval_runtime": 10.7979,
+      "eval_samples_per_second": 926.103,
+      "eval_steps_per_second": 1.204,
+      "step": 182
+    },
+    {
+      "epoch": 92.0,
+      "eval_loss": 1.517883062362671,
+      "eval_runtime": 10.8783,
+      "eval_samples_per_second": 919.261,
+      "eval_steps_per_second": 1.195,
+      "step": 184
+    },
+    {
+      "epoch": 93.0,
+      "eval_loss": 1.515496015548706,
+      "eval_runtime": 10.783,
+      "eval_samples_per_second": 927.387,
+      "eval_steps_per_second": 1.206,
+      "step": 186
+    },
+    {
+      "epoch": 94.0,
+      "eval_loss": 1.5140419006347656,
+      "eval_runtime": 11.0298,
+      "eval_samples_per_second": 906.635,
+      "eval_steps_per_second": 1.179,
+      "step": 188
+    },
+    {
+      "epoch": 95.0,
+      "eval_loss": 1.5137407779693604,
+      "eval_runtime": 10.8014,
+      "eval_samples_per_second": 925.809,
+      "eval_steps_per_second": 1.204,
+      "step": 190
+    },
+    {
+      "epoch": 96.0,
+      "eval_loss": 1.5128830671310425,
+      "eval_runtime": 10.8766,
+      "eval_samples_per_second": 919.402,
+      "eval_steps_per_second": 1.195,
+      "step": 192
+    },
+    {
+      "epoch": 97.0,
+      "eval_loss": 1.5099443197250366,
+      "eval_runtime": 10.809,
+      "eval_samples_per_second": 925.158,
+      "eval_steps_per_second": 1.203,
+      "step": 194
+    },
+    {
+      "epoch": 98.0,
+      "eval_loss": 1.506999135017395,
+      "eval_runtime": 10.9785,
+      "eval_samples_per_second": 910.872,
+      "eval_steps_per_second": 1.184,
+      "step": 196
+    },
+    {
+      "epoch": 99.0,
+      "eval_loss": 1.5044018030166626,
+      "eval_runtime": 10.883,
+      "eval_samples_per_second": 918.868,
+      "eval_steps_per_second": 1.195,
+      "step": 198
+    },
+    {
+      "epoch": 100.0,
+      "eval_loss": 1.5024514198303223,
+      "eval_runtime": 10.7906,
+      "eval_samples_per_second": 926.73,
+      "eval_steps_per_second": 1.205,
+      "step": 200
+    },
+    {
+      "epoch": 101.0,
+      "eval_loss": 1.501634120941162,
+      "eval_runtime": 10.7793,
+      "eval_samples_per_second": 927.703,
+      "eval_steps_per_second": 1.206,
+      "step": 202
+    },
+    {
+      "epoch": 102.0,
+      "eval_loss": 1.5009431838989258,
+      "eval_runtime": 10.7085,
+      "eval_samples_per_second": 933.839,
+      "eval_steps_per_second": 1.214,
+      "step": 204
+    },
+    {
+      "epoch": 103.0,
+      "eval_loss": 1.499057650566101,
+      "eval_runtime": 10.6874,
+      "eval_samples_per_second": 935.68,
+      "eval_steps_per_second": 1.216,
+      "step": 206
+    },
+    {
+      "epoch": 104.0,
+      "eval_loss": 1.4963877201080322,
+      "eval_runtime": 10.6752,
+      "eval_samples_per_second": 936.753,
+      "eval_steps_per_second": 1.218,
+      "step": 208
+    },
+    {
+      "epoch": 105.0,
+      "eval_loss": 1.4944827556610107,
+      "eval_runtime": 10.6755,
+      "eval_samples_per_second": 936.725,
+      "eval_steps_per_second": 1.218,
+      "step": 210
+    },
+    {
+      "epoch": 106.0,
+      "eval_loss": 1.4929250478744507,
+      "eval_runtime": 10.682,
+      "eval_samples_per_second": 936.158,
+      "eval_steps_per_second": 1.217,
+      "step": 212
+    },
+    {
+      "epoch": 107.0,
+      "eval_loss": 1.4915369749069214,
+      "eval_runtime": 10.6838,
+      "eval_samples_per_second": 935.995,
+      "eval_steps_per_second": 1.217,
+      "step": 214
+    },
+    {
+      "epoch": 108.0,
+      "eval_loss": 1.49076509475708,
+      "eval_runtime": 10.6769,
+      "eval_samples_per_second": 936.603,
+      "eval_steps_per_second": 1.218,
+      "step": 216
+    },
+    {
+      "epoch": 109.0,
+      "eval_loss": 1.4891281127929688,
+      "eval_runtime": 10.6778,
+      "eval_samples_per_second": 936.521,
+      "eval_steps_per_second": 1.217,
+      "step": 218
+    },
+    {
+      "epoch": 110.0,
+      "eval_loss": 1.486264944076538,
+      "eval_runtime": 10.67,
+      "eval_samples_per_second": 937.205,
+      "eval_steps_per_second": 1.218,
+      "step": 220
+    },
+    {
+      "epoch": 111.0,
+      "eval_loss": 1.481858730316162,
+      "eval_runtime": 10.6684,
+      "eval_samples_per_second": 937.351,
+      "eval_steps_per_second": 1.219,
+      "step": 222
+    },
+    {
+      "epoch": 112.0,
+      "eval_loss": 1.4790288209915161,
+      "eval_runtime": 10.6764,
+      "eval_samples_per_second": 936.646,
+      "eval_steps_per_second": 1.218,
+      "step": 224
+    },
+    {
+      "epoch": 113.0,
+      "eval_loss": 1.477858066558838,
+      "eval_runtime": 10.672,
+      "eval_samples_per_second": 937.028,
+      "eval_steps_per_second": 1.218,
+      "step": 226
+    },
+    {
+      "epoch": 114.0,
+      "eval_loss": 1.477932095527649,
+      "eval_runtime": 10.6779,
+      "eval_samples_per_second": 936.51,
+      "eval_steps_per_second": 1.217,
+      "step": 228
+    },
+    {
+      "epoch": 115.0,
+      "eval_loss": 1.4761333465576172,
+      "eval_runtime": 10.6829,
+      "eval_samples_per_second": 936.078,
+      "eval_steps_per_second": 1.217,
+      "step": 230
+    },
+    {
+      "epoch": 116.0,
+      "eval_loss": 1.472651481628418,
+      "eval_runtime": 10.6687,
+      "eval_samples_per_second": 937.324,
+      "eval_steps_per_second": 1.219,
+      "step": 232
+    },
+    {
+      "epoch": 117.0,
+      "eval_loss": 1.4697270393371582,
+      "eval_runtime": 10.6649,
+      "eval_samples_per_second": 937.657,
+      "eval_steps_per_second": 1.219,
+      "step": 234
+    },
+    {
+      "epoch": 118.0,
+      "eval_loss": 1.4677116870880127,
+      "eval_runtime": 10.6723,
+      "eval_samples_per_second": 937.001,
+      "eval_steps_per_second": 1.218,
+      "step": 236
+    },
+    {
+      "epoch": 119.0,
+      "eval_loss": 1.4658899307250977,
+      "eval_runtime": 10.6745,
+      "eval_samples_per_second": 936.811,
+      "eval_steps_per_second": 1.218,
+      "step": 238
+    },
+    {
+      "epoch": 120.0,
+      "eval_loss": 1.4640589952468872,
+      "eval_runtime": 10.6687,
+      "eval_samples_per_second": 937.323,
+      "eval_steps_per_second": 1.219,
+      "step": 240
+    },
+    {
+      "epoch": 121.0,
+      "eval_loss": 1.4623686075210571,
+      "eval_runtime": 10.6735,
+      "eval_samples_per_second": 936.896,
+      "eval_steps_per_second": 1.218,
+      "step": 242
+    },
+    {
+      "epoch": 122.0,
+      "eval_loss": 1.4619512557983398,
+      "eval_runtime": 10.6694,
+      "eval_samples_per_second": 937.256,
+      "eval_steps_per_second": 1.218,
+      "step": 244
+    },
+    {
+      "epoch": 123.0,
+      "eval_loss": 1.4633115530014038,
+      "eval_runtime": 10.6685,
+      "eval_samples_per_second": 937.343,
+      "eval_steps_per_second": 1.219,
+      "step": 246
+    },
+    {
+      "epoch": 124.0,
+      "eval_loss": 1.464633584022522,
+      "eval_runtime": 10.6778,
+      "eval_samples_per_second": 936.522,
+      "eval_steps_per_second": 1.217,
+      "step": 248
+    },
+    {
+      "epoch": 125.0,
+      "eval_loss": 1.464717984199524,
+      "eval_runtime": 10.7082,
+      "eval_samples_per_second": 933.861,
+      "eval_steps_per_second": 1.214,
+      "step": 250
+    },
+    {
+      "epoch": 126.0,
+      "eval_loss": 1.4619494676589966,
+      "eval_runtime": 10.6743,
+      "eval_samples_per_second": 936.83,
+      "eval_steps_per_second": 1.218,
+      "step": 252
+    },
+    {
+      "epoch": 127.0,
+      "eval_loss": 1.4600682258605957,
+      "eval_runtime": 10.6839,
+      "eval_samples_per_second": 935.989,
+      "eval_steps_per_second": 1.217,
+      "step": 254
+    },
+    {
+      "epoch": 128.0,
+      "eval_loss": 1.460466980934143,
+      "eval_runtime": 10.6674,
+      "eval_samples_per_second": 937.434,
+      "eval_steps_per_second": 1.219,
+      "step": 256
+    },
+    {
+      "epoch": 129.0,
+      "eval_loss": 1.4635497331619263,
+      "eval_runtime": 10.685,
+      "eval_samples_per_second": 935.888,
+      "eval_steps_per_second": 1.217,
+      "step": 258
+    },
+    {
+      "epoch": 130.0,
+      "eval_loss": 1.4629032611846924,
+      "eval_runtime": 10.6911,
+      "eval_samples_per_second": 935.356,
+      "eval_steps_per_second": 1.216,
+      "step": 260
+    },
+    {
+      "epoch": 131.0,
+      "eval_loss": 1.4596558809280396,
+      "eval_runtime": 10.6919,
+      "eval_samples_per_second": 935.291,
+      "eval_steps_per_second": 1.216,
+      "step": 262
+    },
+    {
+      "epoch": 132.0,
+      "eval_loss": 1.4560246467590332,
+      "eval_runtime": 10.6769,
+      "eval_samples_per_second": 936.603,
+      "eval_steps_per_second": 1.218,
+      "step": 264
+    },
+    {
+      "epoch": 133.0,
+      "eval_loss": 1.453616738319397,
+      "eval_runtime": 10.6767,
+      "eval_samples_per_second": 936.622,
+      "eval_steps_per_second": 1.218,
+      "step": 266
+    },
+    {
+      "epoch": 134.0,
+      "eval_loss": 1.4538458585739136,
+      "eval_runtime": 10.6773,
+      "eval_samples_per_second": 936.563,
+      "eval_steps_per_second": 1.218,
+      "step": 268
+    },
+    {
+      "epoch": 135.0,
+      "eval_loss": 1.4554544687271118,
+      "eval_runtime": 10.6749,
+      "eval_samples_per_second": 936.779,
+      "eval_steps_per_second": 1.218,
+      "step": 270
+    },
+    {
+      "epoch": 136.0,
+      "eval_loss": 1.458116054534912,
+      "eval_runtime": 10.6729,
+      "eval_samples_per_second": 936.95,
+      "eval_steps_per_second": 1.218,
+      "step": 272
+    },
+    {
+      "epoch": 137.0,
+      "eval_loss": 1.458404541015625,
+      "eval_runtime": 10.6614,
+      "eval_samples_per_second": 937.965,
+      "eval_steps_per_second": 1.219,
+      "step": 274
+    },
+    {
+      "epoch": 138.0,
+      "eval_loss": 1.4573506116867065,
+      "eval_runtime": 10.6734,
+      "eval_samples_per_second": 936.913,
+      "eval_steps_per_second": 1.218,
+      "step": 276
+    },
+    {
+      "epoch": 139.0,
+      "eval_loss": 1.4543631076812744,
+      "eval_runtime": 10.6672,
+      "eval_samples_per_second": 937.452,
+      "eval_steps_per_second": 1.219,
+      "step": 278
+    },
+    {
+      "epoch": 140.0,
+      "eval_loss": 1.4508144855499268,
+      "eval_runtime": 10.6794,
+      "eval_samples_per_second": 936.382,
+      "eval_steps_per_second": 1.217,
+      "step": 280
+    },
+    {
+      "epoch": 141.0,
+      "eval_loss": 1.447538137435913,
+      "eval_runtime": 10.6758,
+      "eval_samples_per_second": 936.702,
+      "eval_steps_per_second": 1.218,
+      "step": 282
+    },
+    {
+      "epoch": 142.0,
+      "eval_loss": 1.4447238445281982,
+      "eval_runtime": 10.6659,
+      "eval_samples_per_second": 937.568,
+      "eval_steps_per_second": 1.219,
+      "step": 284
+    },
+    {
+      "epoch": 143.0,
+      "eval_loss": 1.4447556734085083,
+      "eval_runtime": 10.6716,
+      "eval_samples_per_second": 937.067,
+      "eval_steps_per_second": 1.218,
+      "step": 286
+    },
+    {
+      "epoch": 144.0,
+      "eval_loss": 1.4442577362060547,
+      "eval_runtime": 10.676,
+      "eval_samples_per_second": 936.684,
+      "eval_steps_per_second": 1.218,
+      "step": 288
+    },
+    {
+      "epoch": 145.0,
+      "eval_loss": 1.4424697160720825,
+      "eval_runtime": 10.668,
+      "eval_samples_per_second": 937.381,
+      "eval_steps_per_second": 1.219,
+      "step": 290
+    },
+    {
+      "epoch": 146.0,
+      "eval_loss": 1.4408490657806396,
+      "eval_runtime": 10.6762,
+      "eval_samples_per_second": 936.664,
+      "eval_steps_per_second": 1.218,
+      "step": 292
+    },
+    {
+      "epoch": 147.0,
+      "eval_loss": 1.4410812854766846,
+      "eval_runtime": 10.6701,
+      "eval_samples_per_second": 937.198,
+      "eval_steps_per_second": 1.218,
+      "step": 294
+    },
+    {
+      "epoch": 148.0,
+      "eval_loss": 1.4422898292541504,
+      "eval_runtime": 10.7048,
+      "eval_samples_per_second": 934.163,
+      "eval_steps_per_second": 1.214,
+      "step": 296
+    },
+    {
+      "epoch": 149.0,
+      "eval_loss": 1.4430429935455322,
+      "eval_runtime": 10.7029,
+      "eval_samples_per_second": 934.33,
+      "eval_steps_per_second": 1.215,
+      "step": 298
+    },
+    {
+      "epoch": 150.0,
+      "eval_loss": 1.4431097507476807,
+      "eval_runtime": 10.701,
+      "eval_samples_per_second": 934.49,
+      "eval_steps_per_second": 1.215,
+      "step": 300
+    },
+    {
+      "epoch": 151.0,
+      "eval_loss": 1.4416182041168213,
+      "eval_runtime": 10.7066,
+      "eval_samples_per_second": 934.002,
+      "eval_steps_per_second": 1.214,
+      "step": 302
+    },
+    {
+      "epoch": 152.0,
+      "eval_loss": 1.4399303197860718,
+      "eval_runtime": 10.6813,
+      "eval_samples_per_second": 936.212,
+      "eval_steps_per_second": 1.217,
+      "step": 304
+    },
+    {
+      "epoch": 153.0,
+      "eval_loss": 1.437761664390564,
+      "eval_runtime": 10.6766,
+      "eval_samples_per_second": 936.628,
+      "eval_steps_per_second": 1.218,
+      "step": 306
+    },
+    {
+      "epoch": 154.0,
+      "eval_loss": 1.436241865158081,
+      "eval_runtime": 10.6783,
+      "eval_samples_per_second": 936.479,
+      "eval_steps_per_second": 1.217,
+      "step": 308
+    },
+    {
+      "epoch": 155.0,
+      "eval_loss": 1.4360020160675049,
+      "eval_runtime": 10.7009,
+      "eval_samples_per_second": 934.499,
+      "eval_steps_per_second": 1.215,
+      "step": 310
+    },
+    {
+      "epoch": 156.0,
+      "eval_loss": 1.4338910579681396,
+      "eval_runtime": 10.6868,
+      "eval_samples_per_second": 935.733,
+      "eval_steps_per_second": 1.216,
+      "step": 312
+    },
+    {
+      "epoch": 157.0,
+      "eval_loss": 1.4325634241104126,
+      "eval_runtime": 10.6777,
+      "eval_samples_per_second": 936.527,
+      "eval_steps_per_second": 1.217,
+      "step": 314
+    },
+    {
+      "epoch": 158.0,
+      "eval_loss": 1.4329997301101685,
+      "eval_runtime": 10.6692,
+      "eval_samples_per_second": 937.275,
+      "eval_steps_per_second": 1.218,
+      "step": 316
+    },
+    {
+      "epoch": 159.0,
+      "eval_loss": 1.4324475526809692,
+      "eval_runtime": 10.6817,
+      "eval_samples_per_second": 936.178,
+      "eval_steps_per_second": 1.217,
+      "step": 318
+    },
+    {
+      "epoch": 160.0,
+      "eval_loss": 1.4320900440216064,
+      "eval_runtime": 10.6759,
+      "eval_samples_per_second": 936.685,
+      "eval_steps_per_second": 1.218,
+      "step": 320
+    },
+    {
+      "epoch": 161.0,
+      "eval_loss": 1.4325189590454102,
+      "eval_runtime": 10.6696,
+      "eval_samples_per_second": 937.244,
+      "eval_steps_per_second": 1.218,
+      "step": 322
+    },
+    {
+      "epoch": 162.0,
+      "eval_loss": 1.4319082498550415,
+      "eval_runtime": 10.6597,
+      "eval_samples_per_second": 938.116,
+      "eval_steps_per_second": 1.22,
+      "step": 324
+    },
+    {
+      "epoch": 163.0,
+      "eval_loss": 1.432405710220337,
+      "eval_runtime": 10.6632,
+      "eval_samples_per_second": 937.807,
+      "eval_steps_per_second": 1.219,
+      "step": 326
+    },
+    {
+      "epoch": 164.0,
+      "eval_loss": 1.4340990781784058,
+      "eval_runtime": 10.6793,
+      "eval_samples_per_second": 936.393,
+      "eval_steps_per_second": 1.217,
+      "step": 328
+    },
+    {
+      "epoch": 165.0,
+      "eval_loss": 1.4348700046539307,
+      "eval_runtime": 10.6745,
+      "eval_samples_per_second": 936.81,
+      "eval_steps_per_second": 1.218,
+      "step": 330
+    },
+    {
+      "epoch": 166.0,
+      "eval_loss": 1.4340572357177734,
+      "eval_runtime": 10.6758,
+      "eval_samples_per_second": 936.694,
+      "eval_steps_per_second": 1.218,
+      "step": 332
+    },
+    {
+      "epoch": 167.0,
+      "eval_loss": 1.432230830192566,
+      "eval_runtime": 10.6679,
+      "eval_samples_per_second": 937.39,
+      "eval_steps_per_second": 1.219,
+      "step": 334
+    },
+    {
+      "epoch": 168.0,
+      "eval_loss": 1.4290224313735962,
+      "eval_runtime": 10.6717,
+      "eval_samples_per_second": 937.056,
+      "eval_steps_per_second": 1.218,
+      "step": 336
+    },
+    {
+      "epoch": 169.0,
+      "eval_loss": 1.4260591268539429,
+      "eval_runtime": 10.6646,
+      "eval_samples_per_second": 937.683,
+      "eval_steps_per_second": 1.219,
+      "step": 338
+    },
+    {
+      "epoch": 170.0,
+      "eval_loss": 1.4241833686828613,
+      "eval_runtime": 10.6743,
+      "eval_samples_per_second": 936.827,
+      "eval_steps_per_second": 1.218,
+      "step": 340
+    },
+    {
+      "epoch": 171.0,
+      "eval_loss": 1.4232484102249146,
+      "eval_runtime": 10.6668,
+      "eval_samples_per_second": 937.489,
+      "eval_steps_per_second": 1.219,
+      "step": 342
+    },
+    {
+      "epoch": 172.0,
+      "eval_loss": 1.4233402013778687,
+      "eval_runtime": 10.674,
+      "eval_samples_per_second": 936.859,
+      "eval_steps_per_second": 1.218,
+      "step": 344
+    },
+    {
+      "epoch": 173.0,
+      "eval_loss": 1.4248952865600586,
+      "eval_runtime": 10.6819,
+      "eval_samples_per_second": 936.165,
+      "eval_steps_per_second": 1.217,
+      "step": 346
+    },
+    {
+      "epoch": 174.0,
+      "eval_loss": 1.4270906448364258,
+      "eval_runtime": 10.6759,
+      "eval_samples_per_second": 936.692,
+      "eval_steps_per_second": 1.218,
+      "step": 348
+    },
+    {
+      "epoch": 175.0,
+      "eval_loss": 1.4285681247711182,
+      "eval_runtime": 10.6797,
+      "eval_samples_per_second": 936.356,
+      "eval_steps_per_second": 1.217,
+      "step": 350
+    },
+    {
+      "epoch": 176.0,
+      "eval_loss": 1.4294575452804565,
+      "eval_runtime": 10.6749,
+      "eval_samples_per_second": 936.78,
+      "eval_steps_per_second": 1.218,
+      "step": 352
+    },
+    {
+      "epoch": 177.0,
+      "eval_loss": 1.428400993347168,
+      "eval_runtime": 10.6621,
+      "eval_samples_per_second": 937.902,
+      "eval_steps_per_second": 1.219,
+      "step": 354
+    },
+    {
+      "epoch": 178.0,
+      "eval_loss": 1.4263620376586914,
+      "eval_runtime": 10.6806,
+      "eval_samples_per_second": 936.281,
+      "eval_steps_per_second": 1.217,
+      "step": 356
+    },
+    {
+      "epoch": 179.0,
+      "eval_loss": 1.4240350723266602,
+      "eval_runtime": 10.669,
+      "eval_samples_per_second": 937.296,
+      "eval_steps_per_second": 1.218,
+      "step": 358
+    },
+    {
+      "epoch": 180.0,
+      "eval_loss": 1.4221690893173218,
+      "eval_runtime": 10.6788,
+      "eval_samples_per_second": 936.431,
+      "eval_steps_per_second": 1.217,
+      "step": 360
+    },
+    {
+      "epoch": 181.0,
+      "eval_loss": 1.4208089113235474,
+      "eval_runtime": 10.6801,
+      "eval_samples_per_second": 936.319,
+      "eval_steps_per_second": 1.217,
+      "step": 362
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 400,
+  "num_train_epochs": 200,
+  "save_steps": 500,
+  "total_flos": 5196677296128000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5db0db70c1ccde07ea78154a819196e3ef8880be96127bb8a8de50342e3ac2
+size 4792