Upload 32 files

13b9/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "base_model_name_or_path": "sharpbai/Llama-2-13b-hf",
+  "bias": "none",
+  "enable_lora": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "merge_weights": false,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

13b9/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29c63d6be77bdc2d95f5a1b4d74a93c2ae25e4763f5d675146ffa31d950f130f
+size 26329549

13b9/checkpoint-2600/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

13b9/checkpoint-2600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94bb58913b92c8671fbbd9ee73283a60ef74c2d4628a0bd77482b4b60ebb8882
+size 52696837

13b9/checkpoint-2600/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17840b7431a706df62461129525793bfe3ffd72883f5c4de2944bdcf94aa634d
+size 26329549

13b9/checkpoint-2600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50815c933eb83036c609fcc7328a6e2afde72ff387dcab3a0d56425bb4bcf17a
+size 14575

13b9/checkpoint-2600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b218950567fa75e02e22cfd165b28e0a68faf346c918756b9603fa3771152e46
+size 627

13b9/checkpoint-2600/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

13b9/checkpoint-2600/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

13b9/checkpoint-2600/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

13b9/checkpoint-2600/trainer_state.json

@@ -0,0 +1,1576 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 30.952380952380953,
+  "global_step": 2600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.3126,
+      "step": 10
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.3439,
+      "step": 20
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.3104,
+      "step": 30
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.2288,
+      "step": 40
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00015,
+      "loss": 1.1731,
+      "step": 50
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.1577,
+      "step": 60
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.1174,
+      "step": 70
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.0971,
+      "step": 80
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00027,
+      "loss": 1.0506,
+      "step": 90
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0003,
+      "loss": 1.0976,
+      "step": 100
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002996385542168674,
+      "loss": 1.125,
+      "step": 110
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00029927710843373495,
+      "loss": 1.0538,
+      "step": 120
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0002989156626506024,
+      "loss": 1.1258,
+      "step": 130
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00029855421686746987,
+      "loss": 1.0822,
+      "step": 140
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00029819277108433735,
+      "loss": 1.1109,
+      "step": 150
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.0002978313253012048,
+      "loss": 1.0948,
+      "step": 160
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.00029746987951807227,
+      "loss": 1.0414,
+      "step": 170
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.00029710843373493976,
+      "loss": 1.0601,
+      "step": 180
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.0002967469879518072,
+      "loss": 1.0577,
+      "step": 190
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 0.0002963855421686747,
+      "loss": 1.0807,
+      "step": 200
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.00029602409638554216,
+      "loss": 1.1074,
+      "step": 210
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 0.0002956626506024096,
+      "loss": 1.069,
+      "step": 220
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 0.0002953012048192771,
+      "loss": 1.0588,
+      "step": 230
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 0.00029493975903614457,
+      "loss": 1.1084,
+      "step": 240
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.000294578313253012,
+      "loss": 1.0767,
+      "step": 250
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 0.0002942168674698795,
+      "loss": 1.0462,
+      "step": 260
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 0.000293855421686747,
+      "loss": 1.0666,
+      "step": 270
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.0002934939759036144,
+      "loss": 1.0284,
+      "step": 280
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 0.0002931325301204819,
+      "loss": 1.0777,
+      "step": 290
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 0.0002927710843373494,
+      "loss": 1.0611,
+      "step": 300
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 0.00029240963855421687,
+      "loss": 1.0645,
+      "step": 310
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 0.0002920481927710843,
+      "loss": 1.0233,
+      "step": 320
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 0.0002916867469879518,
+      "loss": 1.0475,
+      "step": 330
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 0.00029132530120481927,
+      "loss": 1.0703,
+      "step": 340
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 0.0002909638554216867,
+      "loss": 1.0487,
+      "step": 350
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.0002906024096385542,
+      "loss": 1.0293,
+      "step": 360
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 0.0002902409638554217,
+      "loss": 1.037,
+      "step": 370
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 0.0002898795180722891,
+      "loss": 1.0678,
+      "step": 380
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 0.0002895180722891566,
+      "loss": 1.0603,
+      "step": 390
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 0.0002891566265060241,
+      "loss": 1.0428,
+      "step": 400
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 0.0002887951807228915,
+      "loss": 1.035,
+      "step": 410
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.000288433734939759,
+      "loss": 1.0401,
+      "step": 420
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 0.0002880722891566265,
+      "loss": 1.0475,
+      "step": 430
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 0.0002877108433734939,
+      "loss": 1.0064,
+      "step": 440
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 0.0002873493975903614,
+      "loss": 1.0432,
+      "step": 450
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 0.0002869879518072289,
+      "loss": 1.0251,
+      "step": 460
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 0.0002866265060240963,
+      "loss": 1.0731,
+      "step": 470
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.0002862650602409638,
+      "loss": 1.0108,
+      "step": 480
+    },
+    {
+      "epoch": 5.83,
+      "learning_rate": 0.0002859036144578313,
+      "loss": 1.0032,
+      "step": 490
+    },
+    {
+      "epoch": 5.95,
+      "learning_rate": 0.00028554216867469873,
+      "loss": 1.0084,
+      "step": 500
+    },
+    {
+      "epoch": 6.07,
+      "learning_rate": 0.00028518072289156627,
+      "loss": 1.011,
+      "step": 510
+    },
+    {
+      "epoch": 6.19,
+      "learning_rate": 0.0002848192771084337,
+      "loss": 1.0214,
+      "step": 520
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 0.0002844578313253012,
+      "loss": 1.0117,
+      "step": 530
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 0.0002840963855421687,
+      "loss": 1.0065,
+      "step": 540
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 0.0002837349397590361,
+      "loss": 1.0052,
+      "step": 550
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 0.0002833734939759036,
+      "loss": 1.0286,
+      "step": 560
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 0.0002830120481927711,
+      "loss": 0.9932,
+      "step": 570
+    },
+    {
+      "epoch": 6.9,
+      "learning_rate": 0.0002826506024096385,
+      "loss": 1.0117,
+      "step": 580
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 0.000282289156626506,
+      "loss": 0.9999,
+      "step": 590
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 0.0002819277108433735,
+      "loss": 0.992,
+      "step": 600
+    },
+    {
+      "epoch": 7.26,
+      "learning_rate": 0.0002815662650602409,
+      "loss": 1.0053,
+      "step": 610
+    },
+    {
+      "epoch": 7.38,
+      "learning_rate": 0.0002812048192771084,
+      "loss": 0.9967,
+      "step": 620
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 0.0002808433734939759,
+      "loss": 0.9603,
+      "step": 630
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 0.0002804819277108433,
+      "loss": 0.9778,
+      "step": 640
+    },
+    {
+      "epoch": 7.74,
+      "learning_rate": 0.0002801204819277108,
+      "loss": 1.0112,
+      "step": 650
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 0.0002797590361445783,
+      "loss": 0.9785,
+      "step": 660
+    },
+    {
+      "epoch": 7.98,
+      "learning_rate": 0.00027939759036144573,
+      "loss": 0.9976,
+      "step": 670
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 0.0002790361445783132,
+      "loss": 0.9728,
+      "step": 680
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 0.0002786746987951807,
+      "loss": 0.9541,
+      "step": 690
+    },
+    {
+      "epoch": 8.33,
+      "learning_rate": 0.0002783132530120482,
+      "loss": 0.9576,
+      "step": 700
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 0.0002779518072289156,
+      "loss": 0.9821,
+      "step": 710
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 0.0002775903614457831,
+      "loss": 0.9833,
+      "step": 720
+    },
+    {
+      "epoch": 8.69,
+      "learning_rate": 0.0002772289156626506,
+      "loss": 0.9733,
+      "step": 730
+    },
+    {
+      "epoch": 8.81,
+      "learning_rate": 0.00027686746987951803,
+      "loss": 0.9662,
+      "step": 740
+    },
+    {
+      "epoch": 8.93,
+      "learning_rate": 0.0002765060240963855,
+      "loss": 0.9954,
+      "step": 750
+    },
+    {
+      "epoch": 9.05,
+      "learning_rate": 0.000276144578313253,
+      "loss": 0.9656,
+      "step": 760
+    },
+    {
+      "epoch": 9.17,
+      "learning_rate": 0.00027578313253012044,
+      "loss": 0.9462,
+      "step": 770
+    },
+    {
+      "epoch": 9.29,
+      "learning_rate": 0.0002754216867469879,
+      "loss": 0.8893,
+      "step": 780
+    },
+    {
+      "epoch": 9.4,
+      "learning_rate": 0.0002750602409638554,
+      "loss": 0.967,
+      "step": 790
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 0.00027469879518072284,
+      "loss": 0.8942,
+      "step": 800
+    },
+    {
+      "epoch": 9.64,
+      "learning_rate": 0.00027433734939759033,
+      "loss": 0.9385,
+      "step": 810
+    },
+    {
+      "epoch": 9.76,
+      "learning_rate": 0.0002739759036144578,
+      "loss": 0.9863,
+      "step": 820
+    },
+    {
+      "epoch": 9.88,
+      "learning_rate": 0.00027361445783132525,
+      "loss": 0.945,
+      "step": 830
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.00027325301204819273,
+      "loss": 0.9697,
+      "step": 840
+    },
+    {
+      "epoch": 10.12,
+      "learning_rate": 0.0002728915662650602,
+      "loss": 0.9053,
+      "step": 850
+    },
+    {
+      "epoch": 10.24,
+      "learning_rate": 0.00027253012048192765,
+      "loss": 0.916,
+      "step": 860
+    },
+    {
+      "epoch": 10.36,
+      "learning_rate": 0.00027216867469879514,
+      "loss": 0.9316,
+      "step": 870
+    },
+    {
+      "epoch": 10.48,
+      "learning_rate": 0.0002718072289156626,
+      "loss": 0.9116,
+      "step": 880
+    },
+    {
+      "epoch": 10.6,
+      "learning_rate": 0.00027144578313253006,
+      "loss": 0.8975,
+      "step": 890
+    },
+    {
+      "epoch": 10.71,
+      "learning_rate": 0.0002710843373493976,
+      "loss": 0.9206,
+      "step": 900
+    },
+    {
+      "epoch": 10.83,
+      "learning_rate": 0.00027072289156626503,
+      "loss": 0.9543,
+      "step": 910
+    },
+    {
+      "epoch": 10.95,
+      "learning_rate": 0.0002703614457831325,
+      "loss": 0.8909,
+      "step": 920
+    },
+    {
+      "epoch": 11.07,
+      "learning_rate": 0.00027,
+      "loss": 0.8982,
+      "step": 930
+    },
+    {
+      "epoch": 11.19,
+      "learning_rate": 0.00026963855421686744,
+      "loss": 0.9051,
+      "step": 940
+    },
+    {
+      "epoch": 11.31,
+      "learning_rate": 0.0002692771084337349,
+      "loss": 0.8927,
+      "step": 950
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 0.0002689156626506024,
+      "loss": 0.8364,
+      "step": 960
+    },
+    {
+      "epoch": 11.55,
+      "learning_rate": 0.00026855421686746984,
+      "loss": 0.9083,
+      "step": 970
+    },
+    {
+      "epoch": 11.67,
+      "learning_rate": 0.00026819277108433733,
+      "loss": 0.9085,
+      "step": 980
+    },
+    {
+      "epoch": 11.79,
+      "learning_rate": 0.0002678313253012048,
+      "loss": 0.8402,
+      "step": 990
+    },
+    {
+      "epoch": 11.9,
+      "learning_rate": 0.00026746987951807225,
+      "loss": 0.8964,
+      "step": 1000
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00026710843373493973,
+      "loss": 0.8608,
+      "step": 1010
+    },
+    {
+      "epoch": 12.14,
+      "learning_rate": 0.0002667469879518072,
+      "loss": 0.8442,
+      "step": 1020
+    },
+    {
+      "epoch": 12.26,
+      "learning_rate": 0.00026638554216867465,
+      "loss": 0.8686,
+      "step": 1030
+    },
+    {
+      "epoch": 12.38,
+      "learning_rate": 0.00026602409638554214,
+      "loss": 0.8222,
+      "step": 1040
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 0.0002656626506024096,
+      "loss": 0.8634,
+      "step": 1050
+    },
+    {
+      "epoch": 12.62,
+      "learning_rate": 0.00026530120481927706,
+      "loss": 0.8106,
+      "step": 1060
+    },
+    {
+      "epoch": 12.74,
+      "learning_rate": 0.00026493975903614454,
+      "loss": 0.8377,
+      "step": 1070
+    },
+    {
+      "epoch": 12.86,
+      "learning_rate": 0.00026457831325301203,
+      "loss": 0.8477,
+      "step": 1080
+    },
+    {
+      "epoch": 12.98,
+      "learning_rate": 0.00026421686746987946,
+      "loss": 0.8738,
+      "step": 1090
+    },
+    {
+      "epoch": 13.1,
+      "learning_rate": 0.00026385542168674695,
+      "loss": 0.8378,
+      "step": 1100
+    },
+    {
+      "epoch": 13.21,
+      "learning_rate": 0.00026349397590361444,
+      "loss": 0.7851,
+      "step": 1110
+    },
+    {
+      "epoch": 13.33,
+      "learning_rate": 0.0002631325301204819,
+      "loss": 0.8583,
+      "step": 1120
+    },
+    {
+      "epoch": 13.45,
+      "learning_rate": 0.00026277108433734936,
+      "loss": 0.7784,
+      "step": 1130
+    },
+    {
+      "epoch": 13.57,
+      "learning_rate": 0.00026240963855421684,
+      "loss": 0.8323,
+      "step": 1140
+    },
+    {
+      "epoch": 13.69,
+      "learning_rate": 0.00026204819277108433,
+      "loss": 0.7988,
+      "step": 1150
+    },
+    {
+      "epoch": 13.81,
+      "learning_rate": 0.0002616867469879518,
+      "loss": 0.7671,
+      "step": 1160
+    },
+    {
+      "epoch": 13.93,
+      "learning_rate": 0.00026132530120481925,
+      "loss": 0.8336,
+      "step": 1170
+    },
+    {
+      "epoch": 14.05,
+      "learning_rate": 0.00026096385542168673,
+      "loss": 0.7438,
+      "step": 1180
+    },
+    {
+      "epoch": 14.17,
+      "learning_rate": 0.0002606024096385542,
+      "loss": 0.7234,
+      "step": 1190
+    },
+    {
+      "epoch": 14.29,
+      "learning_rate": 0.00026024096385542165,
+      "loss": 0.7257,
+      "step": 1200
+    },
+    {
+      "epoch": 14.4,
+      "learning_rate": 0.00025987951807228914,
+      "loss": 0.7833,
+      "step": 1210
+    },
+    {
+      "epoch": 14.52,
+      "learning_rate": 0.0002595180722891566,
+      "loss": 0.77,
+      "step": 1220
+    },
+    {
+      "epoch": 14.64,
+      "learning_rate": 0.00025915662650602406,
+      "loss": 0.7756,
+      "step": 1230
+    },
+    {
+      "epoch": 14.76,
+      "learning_rate": 0.00025879518072289154,
+      "loss": 0.7867,
+      "step": 1240
+    },
+    {
+      "epoch": 14.88,
+      "learning_rate": 0.00025843373493975903,
+      "loss": 0.7665,
+      "step": 1250
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 0.00025807228915662646,
+      "loss": 0.7284,
+      "step": 1260
+    },
+    {
+      "epoch": 15.12,
+      "learning_rate": 0.00025771084337349395,
+      "loss": 0.6533,
+      "step": 1270
+    },
+    {
+      "epoch": 15.24,
+      "learning_rate": 0.00025734939759036144,
+      "loss": 0.712,
+      "step": 1280
+    },
+    {
+      "epoch": 15.36,
+      "learning_rate": 0.0002569879518072289,
+      "loss": 0.7408,
+      "step": 1290
+    },
+    {
+      "epoch": 15.48,
+      "learning_rate": 0.00025662650602409636,
+      "loss": 0.6888,
+      "step": 1300
+    },
+    {
+      "epoch": 15.6,
+      "learning_rate": 0.00025626506024096384,
+      "loss": 0.7257,
+      "step": 1310
+    },
+    {
+      "epoch": 15.71,
+      "learning_rate": 0.00025590361445783133,
+      "loss": 0.687,
+      "step": 1320
+    },
+    {
+      "epoch": 15.83,
+      "learning_rate": 0.00025554216867469876,
+      "loss": 0.7182,
+      "step": 1330
+    },
+    {
+      "epoch": 15.95,
+      "learning_rate": 0.00025518072289156625,
+      "loss": 0.7337,
+      "step": 1340
+    },
+    {
+      "epoch": 16.07,
+      "learning_rate": 0.00025481927710843373,
+      "loss": 0.6581,
+      "step": 1350
+    },
+    {
+      "epoch": 16.19,
+      "learning_rate": 0.00025445783132530117,
+      "loss": 0.6839,
+      "step": 1360
+    },
+    {
+      "epoch": 16.31,
+      "learning_rate": 0.00025409638554216865,
+      "loss": 0.6336,
+      "step": 1370
+    },
+    {
+      "epoch": 16.43,
+      "learning_rate": 0.00025373493975903614,
+      "loss": 0.6679,
+      "step": 1380
+    },
+    {
+      "epoch": 16.55,
+      "learning_rate": 0.00025337349397590357,
+      "loss": 0.632,
+      "step": 1390
+    },
+    {
+      "epoch": 16.67,
+      "learning_rate": 0.00025301204819277106,
+      "loss": 0.6286,
+      "step": 1400
+    },
+    {
+      "epoch": 16.79,
+      "learning_rate": 0.00025265060240963855,
+      "loss": 0.7263,
+      "step": 1410
+    },
+    {
+      "epoch": 16.9,
+      "learning_rate": 0.000252289156626506,
+      "loss": 0.6465,
+      "step": 1420
+    },
+    {
+      "epoch": 17.02,
+      "learning_rate": 0.00025192771084337346,
+      "loss": 0.617,
+      "step": 1430
+    },
+    {
+      "epoch": 17.14,
+      "learning_rate": 0.00025156626506024095,
+      "loss": 0.599,
+      "step": 1440
+    },
+    {
+      "epoch": 17.26,
+      "learning_rate": 0.0002512048192771084,
+      "loss": 0.6203,
+      "step": 1450
+    },
+    {
+      "epoch": 17.38,
+      "learning_rate": 0.00025084337349397587,
+      "loss": 0.5545,
+      "step": 1460
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 0.00025048192771084336,
+      "loss": 0.6239,
+      "step": 1470
+    },
+    {
+      "epoch": 17.62,
+      "learning_rate": 0.0002501204819277108,
+      "loss": 0.5739,
+      "step": 1480
+    },
+    {
+      "epoch": 17.74,
+      "learning_rate": 0.00024975903614457833,
+      "loss": 0.6289,
+      "step": 1490
+    },
+    {
+      "epoch": 17.86,
+      "learning_rate": 0.00024939759036144576,
+      "loss": 0.5728,
+      "step": 1500
+    },
+    {
+      "epoch": 17.98,
+      "learning_rate": 0.00024903614457831325,
+      "loss": 0.6469,
+      "step": 1510
+    },
+    {
+      "epoch": 18.1,
+      "learning_rate": 0.00024867469879518074,
+      "loss": 0.5318,
+      "step": 1520
+    },
+    {
+      "epoch": 18.21,
+      "learning_rate": 0.00024831325301204817,
+      "loss": 0.4846,
+      "step": 1530
+    },
+    {
+      "epoch": 18.33,
+      "learning_rate": 0.00024795180722891565,
+      "loss": 0.5352,
+      "step": 1540
+    },
+    {
+      "epoch": 18.45,
+      "learning_rate": 0.00024759036144578314,
+      "loss": 0.5341,
+      "step": 1550
+    },
+    {
+      "epoch": 18.57,
+      "learning_rate": 0.0002472289156626506,
+      "loss": 0.57,
+      "step": 1560
+    },
+    {
+      "epoch": 18.69,
+      "learning_rate": 0.00024686746987951806,
+      "loss": 0.5228,
+      "step": 1570
+    },
+    {
+      "epoch": 18.81,
+      "learning_rate": 0.00024650602409638555,
+      "loss": 0.5857,
+      "step": 1580
+    },
+    {
+      "epoch": 18.93,
+      "learning_rate": 0.000246144578313253,
+      "loss": 0.5219,
+      "step": 1590
+    },
+    {
+      "epoch": 19.05,
+      "learning_rate": 0.00024578313253012046,
+      "loss": 0.5233,
+      "step": 1600
+    },
+    {
+      "epoch": 19.17,
+      "learning_rate": 0.00024542168674698795,
+      "loss": 0.4589,
+      "step": 1610
+    },
+    {
+      "epoch": 19.29,
+      "learning_rate": 0.0002450602409638554,
+      "loss": 0.5354,
+      "step": 1620
+    },
+    {
+      "epoch": 19.4,
+      "learning_rate": 0.00024469879518072287,
+      "loss": 0.4662,
+      "step": 1630
+    },
+    {
+      "epoch": 19.52,
+      "learning_rate": 0.00024433734939759036,
+      "loss": 0.465,
+      "step": 1640
+    },
+    {
+      "epoch": 19.64,
+      "learning_rate": 0.00024397590361445782,
+      "loss": 0.4602,
+      "step": 1650
+    },
+    {
+      "epoch": 19.76,
+      "learning_rate": 0.00024361445783132528,
+      "loss": 0.4851,
+      "step": 1660
+    },
+    {
+      "epoch": 19.88,
+      "learning_rate": 0.00024325301204819276,
+      "loss": 0.495,
+      "step": 1670
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 0.00024289156626506022,
+      "loss": 0.4556,
+      "step": 1680
+    },
+    {
+      "epoch": 20.12,
+      "learning_rate": 0.00024253012048192768,
+      "loss": 0.3657,
+      "step": 1690
+    },
+    {
+      "epoch": 20.24,
+      "learning_rate": 0.00024216867469879517,
+      "loss": 0.4285,
+      "step": 1700
+    },
+    {
+      "epoch": 20.36,
+      "learning_rate": 0.00024180722891566263,
+      "loss": 0.3793,
+      "step": 1710
+    },
+    {
+      "epoch": 20.48,
+      "learning_rate": 0.0002414457831325301,
+      "loss": 0.4846,
+      "step": 1720
+    },
+    {
+      "epoch": 20.6,
+      "learning_rate": 0.00024108433734939757,
+      "loss": 0.4543,
+      "step": 1730
+    },
+    {
+      "epoch": 20.71,
+      "learning_rate": 0.00024072289156626503,
+      "loss": 0.4694,
+      "step": 1740
+    },
+    {
+      "epoch": 20.83,
+      "learning_rate": 0.0002403614457831325,
+      "loss": 0.3779,
+      "step": 1750
+    },
+    {
+      "epoch": 20.95,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.431,
+      "step": 1760
+    },
+    {
+      "epoch": 21.07,
+      "learning_rate": 0.00023963855421686744,
+      "loss": 0.367,
+      "step": 1770
+    },
+    {
+      "epoch": 21.19,
+      "learning_rate": 0.0002392771084337349,
+      "loss": 0.4387,
+      "step": 1780
+    },
+    {
+      "epoch": 21.31,
+      "learning_rate": 0.0002389156626506024,
+      "loss": 0.3326,
+      "step": 1790
+    },
+    {
+      "epoch": 21.43,
+      "learning_rate": 0.00023855421686746987,
+      "loss": 0.3899,
+      "step": 1800
+    },
+    {
+      "epoch": 21.55,
+      "learning_rate": 0.00023819277108433733,
+      "loss": 0.3869,
+      "step": 1810
+    },
+    {
+      "epoch": 21.67,
+      "learning_rate": 0.00023783132530120482,
+      "loss": 0.3685,
+      "step": 1820
+    },
+    {
+      "epoch": 21.79,
+      "learning_rate": 0.00023746987951807228,
+      "loss": 0.3711,
+      "step": 1830
+    },
+    {
+      "epoch": 21.9,
+      "learning_rate": 0.00023710843373493974,
+      "loss": 0.3748,
+      "step": 1840
+    },
+    {
+      "epoch": 22.02,
+      "learning_rate": 0.00023674698795180722,
+      "loss": 0.3345,
+      "step": 1850
+    },
+    {
+      "epoch": 22.14,
+      "learning_rate": 0.00023638554216867468,
+      "loss": 0.3128,
+      "step": 1860
+    },
+    {
+      "epoch": 22.26,
+      "learning_rate": 0.00023602409638554214,
+      "loss": 0.348,
+      "step": 1870
+    },
+    {
+      "epoch": 22.38,
+      "learning_rate": 0.00023566265060240963,
+      "loss": 0.3506,
+      "step": 1880
+    },
+    {
+      "epoch": 22.5,
+      "learning_rate": 0.0002353012048192771,
+      "loss": 0.289,
+      "step": 1890
+    },
+    {
+      "epoch": 22.62,
+      "learning_rate": 0.00023493975903614455,
+      "loss": 0.3008,
+      "step": 1900
+    },
+    {
+      "epoch": 22.74,
+      "learning_rate": 0.00023457831325301203,
+      "loss": 0.3372,
+      "step": 1910
+    },
+    {
+      "epoch": 22.86,
+      "learning_rate": 0.0002342168674698795,
+      "loss": 0.3642,
+      "step": 1920
+    },
+    {
+      "epoch": 22.98,
+      "learning_rate": 0.00023385542168674695,
+      "loss": 0.3117,
+      "step": 1930
+    },
+    {
+      "epoch": 23.1,
+      "learning_rate": 0.00023349397590361444,
+      "loss": 0.3003,
+      "step": 1940
+    },
+    {
+      "epoch": 23.21,
+      "learning_rate": 0.0002331325301204819,
+      "loss": 0.2342,
+      "step": 1950
+    },
+    {
+      "epoch": 23.33,
+      "learning_rate": 0.00023277108433734936,
+      "loss": 0.3119,
+      "step": 1960
+    },
+    {
+      "epoch": 23.45,
+      "learning_rate": 0.00023240963855421687,
+      "loss": 0.2618,
+      "step": 1970
+    },
+    {
+      "epoch": 23.57,
+      "learning_rate": 0.00023204819277108433,
+      "loss": 0.3138,
+      "step": 1980
+    },
+    {
+      "epoch": 23.69,
+      "learning_rate": 0.00023168674698795176,
+      "loss": 0.2934,
+      "step": 1990
+    },
+    {
+      "epoch": 23.81,
+      "learning_rate": 0.00023132530120481928,
+      "loss": 0.2713,
+      "step": 2000
+    },
+    {
+      "epoch": 23.93,
+      "learning_rate": 0.00023096385542168674,
+      "loss": 0.3095,
+      "step": 2010
+    },
+    {
+      "epoch": 24.05,
+      "learning_rate": 0.0002306024096385542,
+      "loss": 0.2688,
+      "step": 2020
+    },
+    {
+      "epoch": 24.17,
+      "learning_rate": 0.00023024096385542168,
+      "loss": 0.2309,
+      "step": 2030
+    },
+    {
+      "epoch": 24.29,
+      "learning_rate": 0.00022987951807228914,
+      "loss": 0.2614,
+      "step": 2040
+    },
+    {
+      "epoch": 24.4,
+      "learning_rate": 0.0002295180722891566,
+      "loss": 0.2264,
+      "step": 2050
+    },
+    {
+      "epoch": 24.52,
+      "learning_rate": 0.0002291566265060241,
+      "loss": 0.2506,
+      "step": 2060
+    },
+    {
+      "epoch": 24.64,
+      "learning_rate": 0.00022879518072289155,
+      "loss": 0.2241,
+      "step": 2070
+    },
+    {
+      "epoch": 24.76,
+      "learning_rate": 0.000228433734939759,
+      "loss": 0.2882,
+      "step": 2080
+    },
+    {
+      "epoch": 24.88,
+      "learning_rate": 0.0002280722891566265,
+      "loss": 0.2868,
+      "step": 2090
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 0.00022771084337349395,
+      "loss": 0.284,
+      "step": 2100
+    },
+    {
+      "epoch": 25.12,
+      "learning_rate": 0.0002273493975903614,
+      "loss": 0.2088,
+      "step": 2110
+    },
+    {
+      "epoch": 25.24,
+      "learning_rate": 0.0002269879518072289,
+      "loss": 0.1954,
+      "step": 2120
+    },
+    {
+      "epoch": 25.36,
+      "learning_rate": 0.00022662650602409636,
+      "loss": 0.2121,
+      "step": 2130
+    },
+    {
+      "epoch": 25.48,
+      "learning_rate": 0.00022626506024096382,
+      "loss": 0.2345,
+      "step": 2140
+    },
+    {
+      "epoch": 25.6,
+      "learning_rate": 0.0002259036144578313,
+      "loss": 0.221,
+      "step": 2150
+    },
+    {
+      "epoch": 25.71,
+      "learning_rate": 0.00022554216867469876,
+      "loss": 0.2258,
+      "step": 2160
+    },
+    {
+      "epoch": 25.83,
+      "learning_rate": 0.00022518072289156622,
+      "loss": 0.2467,
+      "step": 2170
+    },
+    {
+      "epoch": 25.95,
+      "learning_rate": 0.00022481927710843374,
+      "loss": 0.2216,
+      "step": 2180
+    },
+    {
+      "epoch": 26.07,
+      "learning_rate": 0.0002244578313253012,
+      "loss": 0.2106,
+      "step": 2190
+    },
+    {
+      "epoch": 26.19,
+      "learning_rate": 0.00022409638554216866,
+      "loss": 0.2242,
+      "step": 2200
+    },
+    {
+      "epoch": 26.31,
+      "learning_rate": 0.00022373493975903614,
+      "loss": 0.1702,
+      "step": 2210
+    },
+    {
+      "epoch": 26.43,
+      "learning_rate": 0.0002233734939759036,
+      "loss": 0.2117,
+      "step": 2220
+    },
+    {
+      "epoch": 26.55,
+      "learning_rate": 0.00022301204819277106,
+      "loss": 0.1841,
+      "step": 2230
+    },
+    {
+      "epoch": 26.67,
+      "learning_rate": 0.00022265060240963855,
+      "loss": 0.1786,
+      "step": 2240
+    },
+    {
+      "epoch": 26.79,
+      "learning_rate": 0.000222289156626506,
+      "loss": 0.201,
+      "step": 2250
+    },
+    {
+      "epoch": 26.9,
+      "learning_rate": 0.00022192771084337347,
+      "loss": 0.1915,
+      "step": 2260
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00022156626506024095,
+      "loss": 0.1973,
+      "step": 2270
+    },
+    {
+      "epoch": 27.14,
+      "learning_rate": 0.0002212048192771084,
+      "loss": 0.1649,
+      "step": 2280
+    },
+    {
+      "epoch": 27.26,
+      "learning_rate": 0.00022084337349397587,
+      "loss": 0.1665,
+      "step": 2290
+    },
+    {
+      "epoch": 27.38,
+      "learning_rate": 0.00022048192771084336,
+      "loss": 0.2129,
+      "step": 2300
+    },
+    {
+      "epoch": 27.5,
+      "learning_rate": 0.00022012048192771082,
+      "loss": 0.194,
+      "step": 2310
+    },
+    {
+      "epoch": 27.62,
+      "learning_rate": 0.00021975903614457828,
+      "loss": 0.1684,
+      "step": 2320
+    },
+    {
+      "epoch": 27.74,
+      "learning_rate": 0.00021939759036144576,
+      "loss": 0.1312,
+      "step": 2330
+    },
+    {
+      "epoch": 27.86,
+      "learning_rate": 0.00021903614457831322,
+      "loss": 0.1711,
+      "step": 2340
+    },
+    {
+      "epoch": 27.98,
+      "learning_rate": 0.00021867469879518068,
+      "loss": 0.1863,
+      "step": 2350
+    },
+    {
+      "epoch": 28.1,
+      "learning_rate": 0.0002183132530120482,
+      "loss": 0.1425,
+      "step": 2360
+    },
+    {
+      "epoch": 28.21,
+      "learning_rate": 0.00021795180722891563,
+      "loss": 0.1293,
+      "step": 2370
+    },
+    {
+      "epoch": 28.33,
+      "learning_rate": 0.0002175903614457831,
+      "loss": 0.1406,
+      "step": 2380
+    },
+    {
+      "epoch": 28.45,
+      "learning_rate": 0.0002172289156626506,
+      "loss": 0.1583,
+      "step": 2390
+    },
+    {
+      "epoch": 28.57,
+      "learning_rate": 0.00021686746987951806,
+      "loss": 0.1706,
+      "step": 2400
+    },
+    {
+      "epoch": 28.69,
+      "learning_rate": 0.00021650602409638552,
+      "loss": 0.1629,
+      "step": 2410
+    },
+    {
+      "epoch": 28.81,
+      "learning_rate": 0.000216144578313253,
+      "loss": 0.1788,
+      "step": 2420
+    },
+    {
+      "epoch": 28.93,
+      "learning_rate": 0.00021578313253012047,
+      "loss": 0.1618,
+      "step": 2430
+    },
+    {
+      "epoch": 29.05,
+      "learning_rate": 0.00021542168674698793,
+      "loss": 0.1391,
+      "step": 2440
+    },
+    {
+      "epoch": 29.17,
+      "learning_rate": 0.00021506024096385541,
+      "loss": 0.1271,
+      "step": 2450
+    },
+    {
+      "epoch": 29.29,
+      "learning_rate": 0.00021469879518072287,
+      "loss": 0.1312,
+      "step": 2460
+    },
+    {
+      "epoch": 29.4,
+      "learning_rate": 0.00021433734939759033,
+      "loss": 0.1401,
+      "step": 2470
+    },
+    {
+      "epoch": 29.52,
+      "learning_rate": 0.00021397590361445782,
+      "loss": 0.1222,
+      "step": 2480
+    },
+    {
+      "epoch": 29.64,
+      "learning_rate": 0.00021361445783132528,
+      "loss": 0.1124,
+      "step": 2490
+    },
+    {
+      "epoch": 29.76,
+      "learning_rate": 0.00021325301204819274,
+      "loss": 0.1796,
+      "step": 2500
+    },
+    {
+      "epoch": 29.88,
+      "learning_rate": 0.00021289156626506022,
+      "loss": 0.1502,
+      "step": 2510
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 0.00021253012048192768,
+      "loss": 0.137,
+      "step": 2520
+    },
+    {
+      "epoch": 30.12,
+      "learning_rate": 0.00021216867469879514,
+      "loss": 0.1021,
+      "step": 2530
+    },
+    {
+      "epoch": 30.24,
+      "learning_rate": 0.00021180722891566263,
+      "loss": 0.129,
+      "step": 2540
+    },
+    {
+      "epoch": 30.36,
+      "learning_rate": 0.0002114457831325301,
+      "loss": 0.1119,
+      "step": 2550
+    },
+    {
+      "epoch": 30.48,
+      "learning_rate": 2.3802395209580838e-05,
+      "loss": 0.1135,
+      "step": 2560
+    },
+    {
+      "epoch": 30.6,
+      "learning_rate": 2.2679640718562872e-05,
+      "loss": 0.1224,
+      "step": 2570
+    },
+    {
+      "epoch": 30.71,
+      "learning_rate": 2.1556886227544907e-05,
+      "loss": 0.1004,
+      "step": 2580
+    },
+    {
+      "epoch": 30.83,
+      "learning_rate": 2.043413173652694e-05,
+      "loss": 0.1048,
+      "step": 2590
+    },
+    {
+      "epoch": 30.95,
+      "learning_rate": 1.931137724550898e-05,
+      "loss": 0.0978,
+      "step": 2600
+    }
+  ],
+  "max_steps": 2772,
+  "num_train_epochs": 33,
+  "total_flos": 1.5110634218132275e+18,
+  "trial_name": null,
+  "trial_params": null
+}

13b9/checkpoint-2600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccebab85e4dcd23b16c1544739b7d1206238f9ebf5151885432bf020c9346adf
+size 3707

13b9/checkpoint-2700/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

13b9/checkpoint-2700/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cea48a6f23e84f176da840bbb25cbab27712d268619e61c7b8f7a1905f082d8
+size 52696837

13b9/checkpoint-2700/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37eca9cb327161d0664faba4648161c3348b5f9b43dce2494a387655adc83ad3
+size 26329549

13b9/checkpoint-2700/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9041dbbb98d1e355e367d325aa060833e77c32c1413391c8f2c58c3c6b8d089d
+size 14575

13b9/checkpoint-2700/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4765951f05a8e198a09bb197b1b516d0bf93dbc9707332af6d7544b6ef97360a
+size 627

13b9/checkpoint-2700/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

13b9/checkpoint-2700/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

13b9/checkpoint-2700/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

13b9/checkpoint-2700/trainer_state.json

@@ -0,0 +1,1636 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 32.142857142857146,
+  "global_step": 2700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.3126,
+      "step": 10
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.3439,
+      "step": 20
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.3104,
+      "step": 30
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.2288,
+      "step": 40
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00015,
+      "loss": 1.1731,
+      "step": 50
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.1577,
+      "step": 60
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.1174,
+      "step": 70
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.0971,
+      "step": 80
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00027,
+      "loss": 1.0506,
+      "step": 90
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0003,
+      "loss": 1.0976,
+      "step": 100
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002996385542168674,
+      "loss": 1.125,
+      "step": 110
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00029927710843373495,
+      "loss": 1.0538,
+      "step": 120
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0002989156626506024,
+      "loss": 1.1258,
+      "step": 130
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00029855421686746987,
+      "loss": 1.0822,
+      "step": 140
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00029819277108433735,
+      "loss": 1.1109,
+      "step": 150
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.0002978313253012048,
+      "loss": 1.0948,
+      "step": 160
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.00029746987951807227,
+      "loss": 1.0414,
+      "step": 170
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.00029710843373493976,
+      "loss": 1.0601,
+      "step": 180
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.0002967469879518072,
+      "loss": 1.0577,
+      "step": 190
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 0.0002963855421686747,
+      "loss": 1.0807,
+      "step": 200
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.00029602409638554216,
+      "loss": 1.1074,
+      "step": 210
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 0.0002956626506024096,
+      "loss": 1.069,
+      "step": 220
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 0.0002953012048192771,
+      "loss": 1.0588,
+      "step": 230
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 0.00029493975903614457,
+      "loss": 1.1084,
+      "step": 240
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.000294578313253012,
+      "loss": 1.0767,
+      "step": 250
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 0.0002942168674698795,
+      "loss": 1.0462,
+      "step": 260
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 0.000293855421686747,
+      "loss": 1.0666,
+      "step": 270
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.0002934939759036144,
+      "loss": 1.0284,
+      "step": 280
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 0.0002931325301204819,
+      "loss": 1.0777,
+      "step": 290
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 0.0002927710843373494,
+      "loss": 1.0611,
+      "step": 300
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 0.00029240963855421687,
+      "loss": 1.0645,
+      "step": 310
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 0.0002920481927710843,
+      "loss": 1.0233,
+      "step": 320
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 0.0002916867469879518,
+      "loss": 1.0475,
+      "step": 330
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 0.00029132530120481927,
+      "loss": 1.0703,
+      "step": 340
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 0.0002909638554216867,
+      "loss": 1.0487,
+      "step": 350
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.0002906024096385542,
+      "loss": 1.0293,
+      "step": 360
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 0.0002902409638554217,
+      "loss": 1.037,
+      "step": 370
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 0.0002898795180722891,
+      "loss": 1.0678,
+      "step": 380
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 0.0002895180722891566,
+      "loss": 1.0603,
+      "step": 390
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 0.0002891566265060241,
+      "loss": 1.0428,
+      "step": 400
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 0.0002887951807228915,
+      "loss": 1.035,
+      "step": 410
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.000288433734939759,
+      "loss": 1.0401,
+      "step": 420
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 0.0002880722891566265,
+      "loss": 1.0475,
+      "step": 430
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 0.0002877108433734939,
+      "loss": 1.0064,
+      "step": 440
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 0.0002873493975903614,
+      "loss": 1.0432,
+      "step": 450
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 0.0002869879518072289,
+      "loss": 1.0251,
+      "step": 460
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 0.0002866265060240963,
+      "loss": 1.0731,
+      "step": 470
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.0002862650602409638,
+      "loss": 1.0108,
+      "step": 480
+    },
+    {
+      "epoch": 5.83,
+      "learning_rate": 0.0002859036144578313,
+      "loss": 1.0032,
+      "step": 490
+    },
+    {
+      "epoch": 5.95,
+      "learning_rate": 0.00028554216867469873,
+      "loss": 1.0084,
+      "step": 500
+    },
+    {
+      "epoch": 6.07,
+      "learning_rate": 0.00028518072289156627,
+      "loss": 1.011,
+      "step": 510
+    },
+    {
+      "epoch": 6.19,
+      "learning_rate": 0.0002848192771084337,
+      "loss": 1.0214,
+      "step": 520
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 0.0002844578313253012,
+      "loss": 1.0117,
+      "step": 530
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 0.0002840963855421687,
+      "loss": 1.0065,
+      "step": 540
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 0.0002837349397590361,
+      "loss": 1.0052,
+      "step": 550
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 0.0002833734939759036,
+      "loss": 1.0286,
+      "step": 560
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 0.0002830120481927711,
+      "loss": 0.9932,
+      "step": 570
+    },
+    {
+      "epoch": 6.9,
+      "learning_rate": 0.0002826506024096385,
+      "loss": 1.0117,
+      "step": 580
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 0.000282289156626506,
+      "loss": 0.9999,
+      "step": 590
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 0.0002819277108433735,
+      "loss": 0.992,
+      "step": 600
+    },
+    {
+      "epoch": 7.26,
+      "learning_rate": 0.0002815662650602409,
+      "loss": 1.0053,
+      "step": 610
+    },
+    {
+      "epoch": 7.38,
+      "learning_rate": 0.0002812048192771084,
+      "loss": 0.9967,
+      "step": 620
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 0.0002808433734939759,
+      "loss": 0.9603,
+      "step": 630
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 0.0002804819277108433,
+      "loss": 0.9778,
+      "step": 640
+    },
+    {
+      "epoch": 7.74,
+      "learning_rate": 0.0002801204819277108,
+      "loss": 1.0112,
+      "step": 650
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 0.0002797590361445783,
+      "loss": 0.9785,
+      "step": 660
+    },
+    {
+      "epoch": 7.98,
+      "learning_rate": 0.00027939759036144573,
+      "loss": 0.9976,
+      "step": 670
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 0.0002790361445783132,
+      "loss": 0.9728,
+      "step": 680
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 0.0002786746987951807,
+      "loss": 0.9541,
+      "step": 690
+    },
+    {
+      "epoch": 8.33,
+      "learning_rate": 0.0002783132530120482,
+      "loss": 0.9576,
+      "step": 700
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 0.0002779518072289156,
+      "loss": 0.9821,
+      "step": 710
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 0.0002775903614457831,
+      "loss": 0.9833,
+      "step": 720
+    },
+    {
+      "epoch": 8.69,
+      "learning_rate": 0.0002772289156626506,
+      "loss": 0.9733,
+      "step": 730
+    },
+    {
+      "epoch": 8.81,
+      "learning_rate": 0.00027686746987951803,
+      "loss": 0.9662,
+      "step": 740
+    },
+    {
+      "epoch": 8.93,
+      "learning_rate": 0.0002765060240963855,
+      "loss": 0.9954,
+      "step": 750
+    },
+    {
+      "epoch": 9.05,
+      "learning_rate": 0.000276144578313253,
+      "loss": 0.9656,
+      "step": 760
+    },
+    {
+      "epoch": 9.17,
+      "learning_rate": 0.00027578313253012044,
+      "loss": 0.9462,
+      "step": 770
+    },
+    {
+      "epoch": 9.29,
+      "learning_rate": 0.0002754216867469879,
+      "loss": 0.8893,
+      "step": 780
+    },
+    {
+      "epoch": 9.4,
+      "learning_rate": 0.0002750602409638554,
+      "loss": 0.967,
+      "step": 790
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 0.00027469879518072284,
+      "loss": 0.8942,
+      "step": 800
+    },
+    {
+      "epoch": 9.64,
+      "learning_rate": 0.00027433734939759033,
+      "loss": 0.9385,
+      "step": 810
+    },
+    {
+      "epoch": 9.76,
+      "learning_rate": 0.0002739759036144578,
+      "loss": 0.9863,
+      "step": 820
+    },
+    {
+      "epoch": 9.88,
+      "learning_rate": 0.00027361445783132525,
+      "loss": 0.945,
+      "step": 830
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.00027325301204819273,
+      "loss": 0.9697,
+      "step": 840
+    },
+    {
+      "epoch": 10.12,
+      "learning_rate": 0.0002728915662650602,
+      "loss": 0.9053,
+      "step": 850
+    },
+    {
+      "epoch": 10.24,
+      "learning_rate": 0.00027253012048192765,
+      "loss": 0.916,
+      "step": 860
+    },
+    {
+      "epoch": 10.36,
+      "learning_rate": 0.00027216867469879514,
+      "loss": 0.9316,
+      "step": 870
+    },
+    {
+      "epoch": 10.48,
+      "learning_rate": 0.0002718072289156626,
+      "loss": 0.9116,
+      "step": 880
+    },
+    {
+      "epoch": 10.6,
+      "learning_rate": 0.00027144578313253006,
+      "loss": 0.8975,
+      "step": 890
+    },
+    {
+      "epoch": 10.71,
+      "learning_rate": 0.0002710843373493976,
+      "loss": 0.9206,
+      "step": 900
+    },
+    {
+      "epoch": 10.83,
+      "learning_rate": 0.00027072289156626503,
+      "loss": 0.9543,
+      "step": 910
+    },
+    {
+      "epoch": 10.95,
+      "learning_rate": 0.0002703614457831325,
+      "loss": 0.8909,
+      "step": 920
+    },
+    {
+      "epoch": 11.07,
+      "learning_rate": 0.00027,
+      "loss": 0.8982,
+      "step": 930
+    },
+    {
+      "epoch": 11.19,
+      "learning_rate": 0.00026963855421686744,
+      "loss": 0.9051,
+      "step": 940
+    },
+    {
+      "epoch": 11.31,
+      "learning_rate": 0.0002692771084337349,
+      "loss": 0.8927,
+      "step": 950
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 0.0002689156626506024,
+      "loss": 0.8364,
+      "step": 960
+    },
+    {
+      "epoch": 11.55,
+      "learning_rate": 0.00026855421686746984,
+      "loss": 0.9083,
+      "step": 970
+    },
+    {
+      "epoch": 11.67,
+      "learning_rate": 0.00026819277108433733,
+      "loss": 0.9085,
+      "step": 980
+    },
+    {
+      "epoch": 11.79,
+      "learning_rate": 0.0002678313253012048,
+      "loss": 0.8402,
+      "step": 990
+    },
+    {
+      "epoch": 11.9,
+      "learning_rate": 0.00026746987951807225,
+      "loss": 0.8964,
+      "step": 1000
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00026710843373493973,
+      "loss": 0.8608,
+      "step": 1010
+    },
+    {
+      "epoch": 12.14,
+      "learning_rate": 0.0002667469879518072,
+      "loss": 0.8442,
+      "step": 1020
+    },
+    {
+      "epoch": 12.26,
+      "learning_rate": 0.00026638554216867465,
+      "loss": 0.8686,
+      "step": 1030
+    },
+    {
+      "epoch": 12.38,
+      "learning_rate": 0.00026602409638554214,
+      "loss": 0.8222,
+      "step": 1040
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 0.0002656626506024096,
+      "loss": 0.8634,
+      "step": 1050
+    },
+    {
+      "epoch": 12.62,
+      "learning_rate": 0.00026530120481927706,
+      "loss": 0.8106,
+      "step": 1060
+    },
+    {
+      "epoch": 12.74,
+      "learning_rate": 0.00026493975903614454,
+      "loss": 0.8377,
+      "step": 1070
+    },
+    {
+      "epoch": 12.86,
+      "learning_rate": 0.00026457831325301203,
+      "loss": 0.8477,
+      "step": 1080
+    },
+    {
+      "epoch": 12.98,
+      "learning_rate": 0.00026421686746987946,
+      "loss": 0.8738,
+      "step": 1090
+    },
+    {
+      "epoch": 13.1,
+      "learning_rate": 0.00026385542168674695,
+      "loss": 0.8378,
+      "step": 1100
+    },
+    {
+      "epoch": 13.21,
+      "learning_rate": 0.00026349397590361444,
+      "loss": 0.7851,
+      "step": 1110
+    },
+    {
+      "epoch": 13.33,
+      "learning_rate": 0.0002631325301204819,
+      "loss": 0.8583,
+      "step": 1120
+    },
+    {
+      "epoch": 13.45,
+      "learning_rate": 0.00026277108433734936,
+      "loss": 0.7784,
+      "step": 1130
+    },
+    {
+      "epoch": 13.57,
+      "learning_rate": 0.00026240963855421684,
+      "loss": 0.8323,
+      "step": 1140
+    },
+    {
+      "epoch": 13.69,
+      "learning_rate": 0.00026204819277108433,
+      "loss": 0.7988,
+      "step": 1150
+    },
+    {
+      "epoch": 13.81,
+      "learning_rate": 0.0002616867469879518,
+      "loss": 0.7671,
+      "step": 1160
+    },
+    {
+      "epoch": 13.93,
+      "learning_rate": 0.00026132530120481925,
+      "loss": 0.8336,
+      "step": 1170
+    },
+    {
+      "epoch": 14.05,
+      "learning_rate": 0.00026096385542168673,
+      "loss": 0.7438,
+      "step": 1180
+    },
+    {
+      "epoch": 14.17,
+      "learning_rate": 0.0002606024096385542,
+      "loss": 0.7234,
+      "step": 1190
+    },
+    {
+      "epoch": 14.29,
+      "learning_rate": 0.00026024096385542165,
+      "loss": 0.7257,
+      "step": 1200
+    },
+    {
+      "epoch": 14.4,
+      "learning_rate": 0.00025987951807228914,
+      "loss": 0.7833,
+      "step": 1210
+    },
+    {
+      "epoch": 14.52,
+      "learning_rate": 0.0002595180722891566,
+      "loss": 0.77,
+      "step": 1220
+    },
+    {
+      "epoch": 14.64,
+      "learning_rate": 0.00025915662650602406,
+      "loss": 0.7756,
+      "step": 1230
+    },
+    {
+      "epoch": 14.76,
+      "learning_rate": 0.00025879518072289154,
+      "loss": 0.7867,
+      "step": 1240
+    },
+    {
+      "epoch": 14.88,
+      "learning_rate": 0.00025843373493975903,
+      "loss": 0.7665,
+      "step": 1250
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 0.00025807228915662646,
+      "loss": 0.7284,
+      "step": 1260
+    },
+    {
+      "epoch": 15.12,
+      "learning_rate": 0.00025771084337349395,
+      "loss": 0.6533,
+      "step": 1270
+    },
+    {
+      "epoch": 15.24,
+      "learning_rate": 0.00025734939759036144,
+      "loss": 0.712,
+      "step": 1280
+    },
+    {
+      "epoch": 15.36,
+      "learning_rate": 0.0002569879518072289,
+      "loss": 0.7408,
+      "step": 1290
+    },
+    {
+      "epoch": 15.48,
+      "learning_rate": 0.00025662650602409636,
+      "loss": 0.6888,
+      "step": 1300
+    },
+    {
+      "epoch": 15.6,
+      "learning_rate": 0.00025626506024096384,
+      "loss": 0.7257,
+      "step": 1310
+    },
+    {
+      "epoch": 15.71,
+      "learning_rate": 0.00025590361445783133,
+      "loss": 0.687,
+      "step": 1320
+    },
+    {
+      "epoch": 15.83,
+      "learning_rate": 0.00025554216867469876,
+      "loss": 0.7182,
+      "step": 1330
+    },
+    {
+      "epoch": 15.95,
+      "learning_rate": 0.00025518072289156625,
+      "loss": 0.7337,
+      "step": 1340
+    },
+    {
+      "epoch": 16.07,
+      "learning_rate": 0.00025481927710843373,
+      "loss": 0.6581,
+      "step": 1350
+    },
+    {
+      "epoch": 16.19,
+      "learning_rate": 0.00025445783132530117,
+      "loss": 0.6839,
+      "step": 1360
+    },
+    {
+      "epoch": 16.31,
+      "learning_rate": 0.00025409638554216865,
+      "loss": 0.6336,
+      "step": 1370
+    },
+    {
+      "epoch": 16.43,
+      "learning_rate": 0.00025373493975903614,
+      "loss": 0.6679,
+      "step": 1380
+    },
+    {
+      "epoch": 16.55,
+      "learning_rate": 0.00025337349397590357,
+      "loss": 0.632,
+      "step": 1390
+    },
+    {
+      "epoch": 16.67,
+      "learning_rate": 0.00025301204819277106,
+      "loss": 0.6286,
+      "step": 1400
+    },
+    {
+      "epoch": 16.79,
+      "learning_rate": 0.00025265060240963855,
+      "loss": 0.7263,
+      "step": 1410
+    },
+    {
+      "epoch": 16.9,
+      "learning_rate": 0.000252289156626506,
+      "loss": 0.6465,
+      "step": 1420
+    },
+    {
+      "epoch": 17.02,
+      "learning_rate": 0.00025192771084337346,
+      "loss": 0.617,
+      "step": 1430
+    },
+    {
+      "epoch": 17.14,
+      "learning_rate": 0.00025156626506024095,
+      "loss": 0.599,
+      "step": 1440
+    },
+    {
+      "epoch": 17.26,
+      "learning_rate": 0.0002512048192771084,
+      "loss": 0.6203,
+      "step": 1450
+    },
+    {
+      "epoch": 17.38,
+      "learning_rate": 0.00025084337349397587,
+      "loss": 0.5545,
+      "step": 1460
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 0.00025048192771084336,
+      "loss": 0.6239,
+      "step": 1470
+    },
+    {
+      "epoch": 17.62,
+      "learning_rate": 0.0002501204819277108,
+      "loss": 0.5739,
+      "step": 1480
+    },
+    {
+      "epoch": 17.74,
+      "learning_rate": 0.00024975903614457833,
+      "loss": 0.6289,
+      "step": 1490
+    },
+    {
+      "epoch": 17.86,
+      "learning_rate": 0.00024939759036144576,
+      "loss": 0.5728,
+      "step": 1500
+    },
+    {
+      "epoch": 17.98,
+      "learning_rate": 0.00024903614457831325,
+      "loss": 0.6469,
+      "step": 1510
+    },
+    {
+      "epoch": 18.1,
+      "learning_rate": 0.00024867469879518074,
+      "loss": 0.5318,
+      "step": 1520
+    },
+    {
+      "epoch": 18.21,
+      "learning_rate": 0.00024831325301204817,
+      "loss": 0.4846,
+      "step": 1530
+    },
+    {
+      "epoch": 18.33,
+      "learning_rate": 0.00024795180722891565,
+      "loss": 0.5352,
+      "step": 1540
+    },
+    {
+      "epoch": 18.45,
+      "learning_rate": 0.00024759036144578314,
+      "loss": 0.5341,
+      "step": 1550
+    },
+    {
+      "epoch": 18.57,
+      "learning_rate": 0.0002472289156626506,
+      "loss": 0.57,
+      "step": 1560
+    },
+    {
+      "epoch": 18.69,
+      "learning_rate": 0.00024686746987951806,
+      "loss": 0.5228,
+      "step": 1570
+    },
+    {
+      "epoch": 18.81,
+      "learning_rate": 0.00024650602409638555,
+      "loss": 0.5857,
+      "step": 1580
+    },
+    {
+      "epoch": 18.93,
+      "learning_rate": 0.000246144578313253,
+      "loss": 0.5219,
+      "step": 1590
+    },
+    {
+      "epoch": 19.05,
+      "learning_rate": 0.00024578313253012046,
+      "loss": 0.5233,
+      "step": 1600
+    },
+    {
+      "epoch": 19.17,
+      "learning_rate": 0.00024542168674698795,
+      "loss": 0.4589,
+      "step": 1610
+    },
+    {
+      "epoch": 19.29,
+      "learning_rate": 0.0002450602409638554,
+      "loss": 0.5354,
+      "step": 1620
+    },
+    {
+      "epoch": 19.4,
+      "learning_rate": 0.00024469879518072287,
+      "loss": 0.4662,
+      "step": 1630
+    },
+    {
+      "epoch": 19.52,
+      "learning_rate": 0.00024433734939759036,
+      "loss": 0.465,
+      "step": 1640
+    },
+    {
+      "epoch": 19.64,
+      "learning_rate": 0.00024397590361445782,
+      "loss": 0.4602,
+      "step": 1650
+    },
+    {
+      "epoch": 19.76,
+      "learning_rate": 0.00024361445783132528,
+      "loss": 0.4851,
+      "step": 1660
+    },
+    {
+      "epoch": 19.88,
+      "learning_rate": 0.00024325301204819276,
+      "loss": 0.495,
+      "step": 1670
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 0.00024289156626506022,
+      "loss": 0.4556,
+      "step": 1680
+    },
+    {
+      "epoch": 20.12,
+      "learning_rate": 0.00024253012048192768,
+      "loss": 0.3657,
+      "step": 1690
+    },
+    {
+      "epoch": 20.24,
+      "learning_rate": 0.00024216867469879517,
+      "loss": 0.4285,
+      "step": 1700
+    },
+    {
+      "epoch": 20.36,
+      "learning_rate": 0.00024180722891566263,
+      "loss": 0.3793,
+      "step": 1710
+    },
+    {
+      "epoch": 20.48,
+      "learning_rate": 0.0002414457831325301,
+      "loss": 0.4846,
+      "step": 1720
+    },
+    {
+      "epoch": 20.6,
+      "learning_rate": 0.00024108433734939757,
+      "loss": 0.4543,
+      "step": 1730
+    },
+    {
+      "epoch": 20.71,
+      "learning_rate": 0.00024072289156626503,
+      "loss": 0.4694,
+      "step": 1740
+    },
+    {
+      "epoch": 20.83,
+      "learning_rate": 0.0002403614457831325,
+      "loss": 0.3779,
+      "step": 1750
+    },
+    {
+      "epoch": 20.95,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.431,
+      "step": 1760
+    },
+    {
+      "epoch": 21.07,
+      "learning_rate": 0.00023963855421686744,
+      "loss": 0.367,
+      "step": 1770
+    },
+    {
+      "epoch": 21.19,
+      "learning_rate": 0.0002392771084337349,
+      "loss": 0.4387,
+      "step": 1780
+    },
+    {
+      "epoch": 21.31,
+      "learning_rate": 0.0002389156626506024,
+      "loss": 0.3326,
+      "step": 1790
+    },
+    {
+      "epoch": 21.43,
+      "learning_rate": 0.00023855421686746987,
+      "loss": 0.3899,
+      "step": 1800
+    },
+    {
+      "epoch": 21.55,
+      "learning_rate": 0.00023819277108433733,
+      "loss": 0.3869,
+      "step": 1810
+    },
+    {
+      "epoch": 21.67,
+      "learning_rate": 0.00023783132530120482,
+      "loss": 0.3685,
+      "step": 1820
+    },
+    {
+      "epoch": 21.79,
+      "learning_rate": 0.00023746987951807228,
+      "loss": 0.3711,
+      "step": 1830
+    },
+    {
+      "epoch": 21.9,
+      "learning_rate": 0.00023710843373493974,
+      "loss": 0.3748,
+      "step": 1840
+    },
+    {
+      "epoch": 22.02,
+      "learning_rate": 0.00023674698795180722,
+      "loss": 0.3345,
+      "step": 1850
+    },
+    {
+      "epoch": 22.14,
+      "learning_rate": 0.00023638554216867468,
+      "loss": 0.3128,
+      "step": 1860
+    },
+    {
+      "epoch": 22.26,
+      "learning_rate": 0.00023602409638554214,
+      "loss": 0.348,
+      "step": 1870
+    },
+    {
+      "epoch": 22.38,
+      "learning_rate": 0.00023566265060240963,
+      "loss": 0.3506,
+      "step": 1880
+    },
+    {
+      "epoch": 22.5,
+      "learning_rate": 0.0002353012048192771,
+      "loss": 0.289,
+      "step": 1890
+    },
+    {
+      "epoch": 22.62,
+      "learning_rate": 0.00023493975903614455,
+      "loss": 0.3008,
+      "step": 1900
+    },
+    {
+      "epoch": 22.74,
+      "learning_rate": 0.00023457831325301203,
+      "loss": 0.3372,
+      "step": 1910
+    },
+    {
+      "epoch": 22.86,
+      "learning_rate": 0.0002342168674698795,
+      "loss": 0.3642,
+      "step": 1920
+    },
+    {
+      "epoch": 22.98,
+      "learning_rate": 0.00023385542168674695,
+      "loss": 0.3117,
+      "step": 1930
+    },
+    {
+      "epoch": 23.1,
+      "learning_rate": 0.00023349397590361444,
+      "loss": 0.3003,
+      "step": 1940
+    },
+    {
+      "epoch": 23.21,
+      "learning_rate": 0.0002331325301204819,
+      "loss": 0.2342,
+      "step": 1950
+    },
+    {
+      "epoch": 23.33,
+      "learning_rate": 0.00023277108433734936,
+      "loss": 0.3119,
+      "step": 1960
+    },
+    {
+      "epoch": 23.45,
+      "learning_rate": 0.00023240963855421687,
+      "loss": 0.2618,
+      "step": 1970
+    },
+    {
+      "epoch": 23.57,
+      "learning_rate": 0.00023204819277108433,
+      "loss": 0.3138,
+      "step": 1980
+    },
+    {
+      "epoch": 23.69,
+      "learning_rate": 0.00023168674698795176,
+      "loss": 0.2934,
+      "step": 1990
+    },
+    {
+      "epoch": 23.81,
+      "learning_rate": 0.00023132530120481928,
+      "loss": 0.2713,
+      "step": 2000
+    },
+    {
+      "epoch": 23.93,
+      "learning_rate": 0.00023096385542168674,
+      "loss": 0.3095,
+      "step": 2010
+    },
+    {
+      "epoch": 24.05,
+      "learning_rate": 0.0002306024096385542,
+      "loss": 0.2688,
+      "step": 2020
+    },
+    {
+      "epoch": 24.17,
+      "learning_rate": 0.00023024096385542168,
+      "loss": 0.2309,
+      "step": 2030
+    },
+    {
+      "epoch": 24.29,
+      "learning_rate": 0.00022987951807228914,
+      "loss": 0.2614,
+      "step": 2040
+    },
+    {
+      "epoch": 24.4,
+      "learning_rate": 0.0002295180722891566,
+      "loss": 0.2264,
+      "step": 2050
+    },
+    {
+      "epoch": 24.52,
+      "learning_rate": 0.0002291566265060241,
+      "loss": 0.2506,
+      "step": 2060
+    },
+    {
+      "epoch": 24.64,
+      "learning_rate": 0.00022879518072289155,
+      "loss": 0.2241,
+      "step": 2070
+    },
+    {
+      "epoch": 24.76,
+      "learning_rate": 0.000228433734939759,
+      "loss": 0.2882,
+      "step": 2080
+    },
+    {
+      "epoch": 24.88,
+      "learning_rate": 0.0002280722891566265,
+      "loss": 0.2868,
+      "step": 2090
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 0.00022771084337349395,
+      "loss": 0.284,
+      "step": 2100
+    },
+    {
+      "epoch": 25.12,
+      "learning_rate": 0.0002273493975903614,
+      "loss": 0.2088,
+      "step": 2110
+    },
+    {
+      "epoch": 25.24,
+      "learning_rate": 0.0002269879518072289,
+      "loss": 0.1954,
+      "step": 2120
+    },
+    {
+      "epoch": 25.36,
+      "learning_rate": 0.00022662650602409636,
+      "loss": 0.2121,
+      "step": 2130
+    },
+    {
+      "epoch": 25.48,
+      "learning_rate": 0.00022626506024096382,
+      "loss": 0.2345,
+      "step": 2140
+    },
+    {
+      "epoch": 25.6,
+      "learning_rate": 0.0002259036144578313,
+      "loss": 0.221,
+      "step": 2150
+    },
+    {
+      "epoch": 25.71,
+      "learning_rate": 0.00022554216867469876,
+      "loss": 0.2258,
+      "step": 2160
+    },
+    {
+      "epoch": 25.83,
+      "learning_rate": 0.00022518072289156622,
+      "loss": 0.2467,
+      "step": 2170
+    },
+    {
+      "epoch": 25.95,
+      "learning_rate": 0.00022481927710843374,
+      "loss": 0.2216,
+      "step": 2180
+    },
+    {
+      "epoch": 26.07,
+      "learning_rate": 0.0002244578313253012,
+      "loss": 0.2106,
+      "step": 2190
+    },
+    {
+      "epoch": 26.19,
+      "learning_rate": 0.00022409638554216866,
+      "loss": 0.2242,
+      "step": 2200
+    },
+    {
+      "epoch": 26.31,
+      "learning_rate": 0.00022373493975903614,
+      "loss": 0.1702,
+      "step": 2210
+    },
+    {
+      "epoch": 26.43,
+      "learning_rate": 0.0002233734939759036,
+      "loss": 0.2117,
+      "step": 2220
+    },
+    {
+      "epoch": 26.55,
+      "learning_rate": 0.00022301204819277106,
+      "loss": 0.1841,
+      "step": 2230
+    },
+    {
+      "epoch": 26.67,
+      "learning_rate": 0.00022265060240963855,
+      "loss": 0.1786,
+      "step": 2240
+    },
+    {
+      "epoch": 26.79,
+      "learning_rate": 0.000222289156626506,
+      "loss": 0.201,
+      "step": 2250
+    },
+    {
+      "epoch": 26.9,
+      "learning_rate": 0.00022192771084337347,
+      "loss": 0.1915,
+      "step": 2260
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00022156626506024095,
+      "loss": 0.1973,
+      "step": 2270
+    },
+    {
+      "epoch": 27.14,
+      "learning_rate": 0.0002212048192771084,
+      "loss": 0.1649,
+      "step": 2280
+    },
+    {
+      "epoch": 27.26,
+      "learning_rate": 0.00022084337349397587,
+      "loss": 0.1665,
+      "step": 2290
+    },
+    {
+      "epoch": 27.38,
+      "learning_rate": 0.00022048192771084336,
+      "loss": 0.2129,
+      "step": 2300
+    },
+    {
+      "epoch": 27.5,
+      "learning_rate": 0.00022012048192771082,
+      "loss": 0.194,
+      "step": 2310
+    },
+    {
+      "epoch": 27.62,
+      "learning_rate": 0.00021975903614457828,
+      "loss": 0.1684,
+      "step": 2320
+    },
+    {
+      "epoch": 27.74,
+      "learning_rate": 0.00021939759036144576,
+      "loss": 0.1312,
+      "step": 2330
+    },
+    {
+      "epoch": 27.86,
+      "learning_rate": 0.00021903614457831322,
+      "loss": 0.1711,
+      "step": 2340
+    },
+    {
+      "epoch": 27.98,
+      "learning_rate": 0.00021867469879518068,
+      "loss": 0.1863,
+      "step": 2350
+    },
+    {
+      "epoch": 28.1,
+      "learning_rate": 0.0002183132530120482,
+      "loss": 0.1425,
+      "step": 2360
+    },
+    {
+      "epoch": 28.21,
+      "learning_rate": 0.00021795180722891563,
+      "loss": 0.1293,
+      "step": 2370
+    },
+    {
+      "epoch": 28.33,
+      "learning_rate": 0.0002175903614457831,
+      "loss": 0.1406,
+      "step": 2380
+    },
+    {
+      "epoch": 28.45,
+      "learning_rate": 0.0002172289156626506,
+      "loss": 0.1583,
+      "step": 2390
+    },
+    {
+      "epoch": 28.57,
+      "learning_rate": 0.00021686746987951806,
+      "loss": 0.1706,
+      "step": 2400
+    },
+    {
+      "epoch": 28.69,
+      "learning_rate": 0.00021650602409638552,
+      "loss": 0.1629,
+      "step": 2410
+    },
+    {
+      "epoch": 28.81,
+      "learning_rate": 0.000216144578313253,
+      "loss": 0.1788,
+      "step": 2420
+    },
+    {
+      "epoch": 28.93,
+      "learning_rate": 0.00021578313253012047,
+      "loss": 0.1618,
+      "step": 2430
+    },
+    {
+      "epoch": 29.05,
+      "learning_rate": 0.00021542168674698793,
+      "loss": 0.1391,
+      "step": 2440
+    },
+    {
+      "epoch": 29.17,
+      "learning_rate": 0.00021506024096385541,
+      "loss": 0.1271,
+      "step": 2450
+    },
+    {
+      "epoch": 29.29,
+      "learning_rate": 0.00021469879518072287,
+      "loss": 0.1312,
+      "step": 2460
+    },
+    {
+      "epoch": 29.4,
+      "learning_rate": 0.00021433734939759033,
+      "loss": 0.1401,
+      "step": 2470
+    },
+    {
+      "epoch": 29.52,
+      "learning_rate": 0.00021397590361445782,
+      "loss": 0.1222,
+      "step": 2480
+    },
+    {
+      "epoch": 29.64,
+      "learning_rate": 0.00021361445783132528,
+      "loss": 0.1124,
+      "step": 2490
+    },
+    {
+      "epoch": 29.76,
+      "learning_rate": 0.00021325301204819274,
+      "loss": 0.1796,
+      "step": 2500
+    },
+    {
+      "epoch": 29.88,
+      "learning_rate": 0.00021289156626506022,
+      "loss": 0.1502,
+      "step": 2510
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 0.00021253012048192768,
+      "loss": 0.137,
+      "step": 2520
+    },
+    {
+      "epoch": 30.12,
+      "learning_rate": 0.00021216867469879514,
+      "loss": 0.1021,
+      "step": 2530
+    },
+    {
+      "epoch": 30.24,
+      "learning_rate": 0.00021180722891566263,
+      "loss": 0.129,
+      "step": 2540
+    },
+    {
+      "epoch": 30.36,
+      "learning_rate": 0.0002114457831325301,
+      "loss": 0.1119,
+      "step": 2550
+    },
+    {
+      "epoch": 30.48,
+      "learning_rate": 2.3802395209580838e-05,
+      "loss": 0.1135,
+      "step": 2560
+    },
+    {
+      "epoch": 30.6,
+      "learning_rate": 2.2679640718562872e-05,
+      "loss": 0.1224,
+      "step": 2570
+    },
+    {
+      "epoch": 30.71,
+      "learning_rate": 2.1556886227544907e-05,
+      "loss": 0.1004,
+      "step": 2580
+    },
+    {
+      "epoch": 30.83,
+      "learning_rate": 2.043413173652694e-05,
+      "loss": 0.1048,
+      "step": 2590
+    },
+    {
+      "epoch": 30.95,
+      "learning_rate": 1.931137724550898e-05,
+      "loss": 0.0978,
+      "step": 2600
+    },
+    {
+      "epoch": 31.07,
+      "learning_rate": 1.8188622754491017e-05,
+      "loss": 0.0981,
+      "step": 2610
+    },
+    {
+      "epoch": 31.19,
+      "learning_rate": 1.7065868263473052e-05,
+      "loss": 0.0979,
+      "step": 2620
+    },
+    {
+      "epoch": 31.31,
+      "learning_rate": 1.594311377245509e-05,
+      "loss": 0.103,
+      "step": 2630
+    },
+    {
+      "epoch": 31.43,
+      "learning_rate": 1.4820359281437124e-05,
+      "loss": 0.1065,
+      "step": 2640
+    },
+    {
+      "epoch": 31.55,
+      "learning_rate": 1.369760479041916e-05,
+      "loss": 0.0912,
+      "step": 2650
+    },
+    {
+      "epoch": 31.67,
+      "learning_rate": 1.2574850299401195e-05,
+      "loss": 0.0927,
+      "step": 2660
+    },
+    {
+      "epoch": 31.79,
+      "learning_rate": 1.1452095808383233e-05,
+      "loss": 0.0942,
+      "step": 2670
+    },
+    {
+      "epoch": 31.9,
+      "learning_rate": 1.032934131736527e-05,
+      "loss": 0.0896,
+      "step": 2680
+    },
+    {
+      "epoch": 32.02,
+      "learning_rate": 9.206586826347304e-06,
+      "loss": 0.0965,
+      "step": 2690
+    },
+    {
+      "epoch": 32.14,
+      "learning_rate": 8.08383233532934e-06,
+      "loss": 0.0943,
+      "step": 2700
+    }
+  ],
+  "max_steps": 2772,
+  "num_train_epochs": 33,
+  "total_flos": 1.5684921338658816e+18,
+  "trial_name": null,
+  "trial_params": null
+}

13b9/checkpoint-2700/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccebab85e4dcd23b16c1544739b7d1206238f9ebf5151885432bf020c9346adf
+size 3707

13b9/finetune_args.json

@@ -0,0 +1,30 @@
+{
+  "micro_batch_size": 2,
+  "gradient_accumulation_steps": 2,
+  "num_train_epochs": 33,
+  "learning_rate": 0.0003,
+  "cutoff_len": 2500,
+  "val_set_size": 0,
+  "lora_r": 8,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "lora_target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "lora_modules_to_save": [],
+  "train_on_inputs": true,
+  "group_by_length": false,
+  "load_in_8bit": true,
+  "fp16": false,
+  "bf16": true,
+  "gradient_checkpointing": false,
+  "save_steps": 100,
+  "save_total_limit": 100,
+  "logging_steps": 10,
+  "additional_training_arguments": null,
+  "additional_lora_config": null,
+  "resume_from_checkpoint": "/content/drive/My Drive/Colab Data/LLaMA-LoRA Tuner/lora_models/13b5/checkpoint-2550"
+}

13b9/info.json

@@ -0,0 +1,11 @@
+{
+  "base_model": "sharpbai/Llama-2-13b-hf",
+  "prompt_template": "user_and_ai",
+  "dataset_name": "simple.json",
+  "dataset_rows": 335,
+  "trained_on_machine": "9c8fd9be693a",
+  "timestamp": 1695898930.9098132,
+  "continued_from_model": "13b5",
+  "continued_from_checkpoint": "checkpoint-2550",
+  "tuner_version": "d83a6747"
+}

13b9/runs/Sep28_11-02-45_9c8fd9be693a/1695898966.2522771/events.out.tfevents.1695898966.9c8fd9be693a.2934.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8fa0e4544ac49f2ccf4f3dadd18f6c4cbd0b12b9ce593ca8d211a838151cf0
+size 6030

13b9/runs/Sep28_11-02-45_9c8fd9be693a/events.out.tfevents.1695898966.9c8fd9be693a.2934.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d42818d69b861ec4b13411c10983996b0c6dfcf06144336b8ec95158b42c8c8
+size 7945

13b9/train_output.json

@@ -0,0 +1,12 @@
+[
+  2772,
+  0.007915083082422378,
+  {
+    "train_runtime": 2005.6988,
+    "train_samples_per_second": 5.512,
+    "train_steps_per_second": 1.382,
+    "total_flos": 1.6099719938337178e+18,
+    "train_loss": 0.007915083082422378,
+    "epoch": 33.0
+  }
+]

13b9/trainer_args.json

@@ -0,0 +1,115 @@
+{
+  "output_dir": "/content/drive/My Drive/Colab Data/LLaMA-LoRA Tuner/lora_models/13b9",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "evaluation_strategy": "no",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 2,
+  "per_device_eval_batch_size": 8,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 2,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "learning_rate": 0.0003,
+  "weight_decay": 0.0,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 33,
+  "max_steps": -1,
+  "lr_scheduler_type": "linear",
+  "warmup_ratio": 0.0,
+  "warmup_steps": 100,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/content/drive/My Drive/Colab Data/LLaMA-LoRA Tuner/lora_models/13b9/runs/Sep28_11-02-45_9c8fd9be693a",
+  "logging_strategy": "steps",
+  "logging_first_step": false,
+  "logging_steps": 10,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 100,
+  "save_total_limit": 100,
+  "save_safetensors": false,
+  "save_on_each_node": false,
+  "no_cuda": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": null,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "cuda_amp",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": -1,
+  "xpu_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": [],
+  "dataloader_drop_last": false,
+  "eval_steps": null,
+  "dataloader_num_workers": 0,
+  "past_index": -1,
+  "run_name": "/content/drive/My Drive/Colab Data/LLaMA-LoRA Tuner/lora_models/13b9",
+  "disable_tqdm": false,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": null,
+  "greater_is_better": null,
+  "ignore_data_skip": false,
+  "sharded_ddp": [],
+  "fsdp": [],
+  "fsdp_min_num_params": 0,
+  "fsdp_config": {
+    "fsdp_min_num_params": 0,
+    "xla": false,
+    "xla_fsdp_grad_ckpt": false
+  },
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard"
+  ],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "dataloader_pin_memory": true,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": false,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_token": "<HUB_TOKEN>",
+  "hub_private_repo": false,
+  "gradient_checkpointing": false,
+  "include_inputs_for_metrics": false,
+  "fp16_backend": "auto",
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 1800,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null
+}

13b9/trainer_log_history.jsonl

@@ -0,0 +1,278 @@
+{"epoch": 0.12, "learning_rate": 2.9999999999999997e-05, "loss": 1.3126, "step": 10}
+{"epoch": 0.24, "learning_rate": 5.9999999999999995e-05, "loss": 1.3439, "step": 20}
+{"epoch": 0.36, "learning_rate": 8.999999999999999e-05, "loss": 1.3104, "step": 30}
+{"epoch": 0.48, "learning_rate": 0.00011999999999999999, "loss": 1.2288, "step": 40}
+{"epoch": 0.6, "learning_rate": 0.00015, "loss": 1.1731, "step": 50}
+{"epoch": 0.71, "learning_rate": 0.00017999999999999998, "loss": 1.1577, "step": 60}
+{"epoch": 0.83, "learning_rate": 0.00020999999999999998, "loss": 1.1174, "step": 70}
+{"epoch": 0.95, "learning_rate": 0.00023999999999999998, "loss": 1.0971, "step": 80}
+{"epoch": 1.07, "learning_rate": 0.00027, "loss": 1.0506, "step": 90}
+{"epoch": 1.19, "learning_rate": 0.0003, "loss": 1.0976, "step": 100}
+{"epoch": 1.31, "learning_rate": 0.0002996385542168674, "loss": 1.125, "step": 110}
+{"epoch": 1.43, "learning_rate": 0.00029927710843373495, "loss": 1.0538, "step": 120}
+{"epoch": 1.55, "learning_rate": 0.0002989156626506024, "loss": 1.1258, "step": 130}
+{"epoch": 1.67, "learning_rate": 0.00029855421686746987, "loss": 1.0822, "step": 140}
+{"epoch": 1.79, "learning_rate": 0.00029819277108433735, "loss": 1.1109, "step": 150}
+{"epoch": 1.9, "learning_rate": 0.0002978313253012048, "loss": 1.0948, "step": 160}
+{"epoch": 2.02, "learning_rate": 0.00029746987951807227, "loss": 1.0414, "step": 170}
+{"epoch": 2.14, "learning_rate": 0.00029710843373493976, "loss": 1.0601, "step": 180}
+{"epoch": 2.26, "learning_rate": 0.0002967469879518072, "loss": 1.0577, "step": 190}
+{"epoch": 2.38, "learning_rate": 0.0002963855421686747, "loss": 1.0807, "step": 200}
+{"epoch": 2.5, "learning_rate": 0.00029602409638554216, "loss": 1.1074, "step": 210}
+{"epoch": 2.62, "learning_rate": 0.0002956626506024096, "loss": 1.069, "step": 220}
+{"epoch": 2.74, "learning_rate": 0.0002953012048192771, "loss": 1.0588, "step": 230}
+{"epoch": 2.86, "learning_rate": 0.00029493975903614457, "loss": 1.1084, "step": 240}
+{"epoch": 2.98, "learning_rate": 0.000294578313253012, "loss": 1.0767, "step": 250}
+{"epoch": 3.1, "learning_rate": 0.0002942168674698795, "loss": 1.0462, "step": 260}
+{"epoch": 3.21, "learning_rate": 0.000293855421686747, "loss": 1.0666, "step": 270}
+{"epoch": 3.33, "learning_rate": 0.0002934939759036144, "loss": 1.0284, "step": 280}
+{"epoch": 3.45, "learning_rate": 0.0002931325301204819, "loss": 1.0777, "step": 290}
+{"epoch": 3.57, "learning_rate": 0.0002927710843373494, "loss": 1.0611, "step": 300}
+{"epoch": 3.69, "learning_rate": 0.00029240963855421687, "loss": 1.0645, "step": 310}
+{"epoch": 3.81, "learning_rate": 0.0002920481927710843, "loss": 1.0233, "step": 320}
+{"epoch": 3.93, "learning_rate": 0.0002916867469879518, "loss": 1.0475, "step": 330}
+{"epoch": 4.05, "learning_rate": 0.00029132530120481927, "loss": 1.0703, "step": 340}
+{"epoch": 4.17, "learning_rate": 0.0002909638554216867, "loss": 1.0487, "step": 350}
+{"epoch": 4.29, "learning_rate": 0.0002906024096385542, "loss": 1.0293, "step": 360}
+{"epoch": 4.4, "learning_rate": 0.0002902409638554217, "loss": 1.037, "step": 370}
+{"epoch": 4.52, "learning_rate": 0.0002898795180722891, "loss": 1.0678, "step": 380}
+{"epoch": 4.64, "learning_rate": 0.0002895180722891566, "loss": 1.0603, "step": 390}
+{"epoch": 4.76, "learning_rate": 0.0002891566265060241, "loss": 1.0428, "step": 400}
+{"epoch": 4.88, "learning_rate": 0.0002887951807228915, "loss": 1.035, "step": 410}
+{"epoch": 5.0, "learning_rate": 0.000288433734939759, "loss": 1.0401, "step": 420}
+{"epoch": 5.12, "learning_rate": 0.0002880722891566265, "loss": 1.0475, "step": 430}
+{"epoch": 5.24, "learning_rate": 0.0002877108433734939, "loss": 1.0064, "step": 440}
+{"epoch": 5.36, "learning_rate": 0.0002873493975903614, "loss": 1.0432, "step": 450}
+{"epoch": 5.48, "learning_rate": 0.0002869879518072289, "loss": 1.0251, "step": 460}
+{"epoch": 5.6, "learning_rate": 0.0002866265060240963, "loss": 1.0731, "step": 470}
+{"epoch": 5.71, "learning_rate": 0.0002862650602409638, "loss": 1.0108, "step": 480}
+{"epoch": 5.83, "learning_rate": 0.0002859036144578313, "loss": 1.0032, "step": 490}
+{"epoch": 5.95, "learning_rate": 0.00028554216867469873, "loss": 1.0084, "step": 500}
+{"epoch": 6.07, "learning_rate": 0.00028518072289156627, "loss": 1.011, "step": 510}
+{"epoch": 6.19, "learning_rate": 0.0002848192771084337, "loss": 1.0214, "step": 520}
+{"epoch": 6.31, "learning_rate": 0.0002844578313253012, "loss": 1.0117, "step": 530}
+{"epoch": 6.43, "learning_rate": 0.0002840963855421687, "loss": 1.0065, "step": 540}
+{"epoch": 6.55, "learning_rate": 0.0002837349397590361, "loss": 1.0052, "step": 550}
+{"epoch": 6.67, "learning_rate": 0.0002833734939759036, "loss": 1.0286, "step": 560}
+{"epoch": 6.79, "learning_rate": 0.0002830120481927711, "loss": 0.9932, "step": 570}
+{"epoch": 6.9, "learning_rate": 0.0002826506024096385, "loss": 1.0117, "step": 580}
+{"epoch": 7.02, "learning_rate": 0.000282289156626506, "loss": 0.9999, "step": 590}
+{"epoch": 7.14, "learning_rate": 0.0002819277108433735, "loss": 0.992, "step": 600}
+{"epoch": 7.26, "learning_rate": 0.0002815662650602409, "loss": 1.0053, "step": 610}
+{"epoch": 7.38, "learning_rate": 0.0002812048192771084, "loss": 0.9967, "step": 620}
+{"epoch": 7.5, "learning_rate": 0.0002808433734939759, "loss": 0.9603, "step": 630}
+{"epoch": 7.62, "learning_rate": 0.0002804819277108433, "loss": 0.9778, "step": 640}
+{"epoch": 7.74, "learning_rate": 0.0002801204819277108, "loss": 1.0112, "step": 650}
+{"epoch": 7.86, "learning_rate": 0.0002797590361445783, "loss": 0.9785, "step": 660}
+{"epoch": 7.98, "learning_rate": 0.00027939759036144573, "loss": 0.9976, "step": 670}
+{"epoch": 8.1, "learning_rate": 0.0002790361445783132, "loss": 0.9728, "step": 680}
+{"epoch": 8.21, "learning_rate": 0.0002786746987951807, "loss": 0.9541, "step": 690}
+{"epoch": 8.33, "learning_rate": 0.0002783132530120482, "loss": 0.9576, "step": 700}
+{"epoch": 8.45, "learning_rate": 0.0002779518072289156, "loss": 0.9821, "step": 710}
+{"epoch": 8.57, "learning_rate": 0.0002775903614457831, "loss": 0.9833, "step": 720}
+{"epoch": 8.69, "learning_rate": 0.0002772289156626506, "loss": 0.9733, "step": 730}
+{"epoch": 8.81, "learning_rate": 0.00027686746987951803, "loss": 0.9662, "step": 740}
+{"epoch": 8.93, "learning_rate": 0.0002765060240963855, "loss": 0.9954, "step": 750}
+{"epoch": 9.05, "learning_rate": 0.000276144578313253, "loss": 0.9656, "step": 760}
+{"epoch": 9.17, "learning_rate": 0.00027578313253012044, "loss": 0.9462, "step": 770}
+{"epoch": 9.29, "learning_rate": 0.0002754216867469879, "loss": 0.8893, "step": 780}
+{"epoch": 9.4, "learning_rate": 0.0002750602409638554, "loss": 0.967, "step": 790}
+{"epoch": 9.52, "learning_rate": 0.00027469879518072284, "loss": 0.8942, "step": 800}
+{"epoch": 9.64, "learning_rate": 0.00027433734939759033, "loss": 0.9385, "step": 810}
+{"epoch": 9.76, "learning_rate": 0.0002739759036144578, "loss": 0.9863, "step": 820}
+{"epoch": 9.88, "learning_rate": 0.00027361445783132525, "loss": 0.945, "step": 830}
+{"epoch": 10.0, "learning_rate": 0.00027325301204819273, "loss": 0.9697, "step": 840}
+{"epoch": 10.12, "learning_rate": 0.0002728915662650602, "loss": 0.9053, "step": 850}
+{"epoch": 10.24, "learning_rate": 0.00027253012048192765, "loss": 0.916, "step": 860}
+{"epoch": 10.36, "learning_rate": 0.00027216867469879514, "loss": 0.9316, "step": 870}
+{"epoch": 10.48, "learning_rate": 0.0002718072289156626, "loss": 0.9116, "step": 880}
+{"epoch": 10.6, "learning_rate": 0.00027144578313253006, "loss": 0.8975, "step": 890}
+{"epoch": 10.71, "learning_rate": 0.0002710843373493976, "loss": 0.9206, "step": 900}
+{"epoch": 10.83, "learning_rate": 0.00027072289156626503, "loss": 0.9543, "step": 910}
+{"epoch": 10.95, "learning_rate": 0.0002703614457831325, "loss": 0.8909, "step": 920}
+{"epoch": 11.07, "learning_rate": 0.00027, "loss": 0.8982, "step": 930}
+{"epoch": 11.19, "learning_rate": 0.00026963855421686744, "loss": 0.9051, "step": 940}
+{"epoch": 11.31, "learning_rate": 0.0002692771084337349, "loss": 0.8927, "step": 950}
+{"epoch": 11.43, "learning_rate": 0.0002689156626506024, "loss": 0.8364, "step": 960}
+{"epoch": 11.55, "learning_rate": 0.00026855421686746984, "loss": 0.9083, "step": 970}
+{"epoch": 11.67, "learning_rate": 0.00026819277108433733, "loss": 0.9085, "step": 980}
+{"epoch": 11.79, "learning_rate": 0.0002678313253012048, "loss": 0.8402, "step": 990}
+{"epoch": 11.9, "learning_rate": 0.00026746987951807225, "loss": 0.8964, "step": 1000}
+{"epoch": 12.02, "learning_rate": 0.00026710843373493973, "loss": 0.8608, "step": 1010}
+{"epoch": 12.14, "learning_rate": 0.0002667469879518072, "loss": 0.8442, "step": 1020}
+{"epoch": 12.26, "learning_rate": 0.00026638554216867465, "loss": 0.8686, "step": 1030}
+{"epoch": 12.38, "learning_rate": 0.00026602409638554214, "loss": 0.8222, "step": 1040}
+{"epoch": 12.5, "learning_rate": 0.0002656626506024096, "loss": 0.8634, "step": 1050}
+{"epoch": 12.62, "learning_rate": 0.00026530120481927706, "loss": 0.8106, "step": 1060}
+{"epoch": 12.74, "learning_rate": 0.00026493975903614454, "loss": 0.8377, "step": 1070}
+{"epoch": 12.86, "learning_rate": 0.00026457831325301203, "loss": 0.8477, "step": 1080}
+{"epoch": 12.98, "learning_rate": 0.00026421686746987946, "loss": 0.8738, "step": 1090}
+{"epoch": 13.1, "learning_rate": 0.00026385542168674695, "loss": 0.8378, "step": 1100}
+{"epoch": 13.21, "learning_rate": 0.00026349397590361444, "loss": 0.7851, "step": 1110}
+{"epoch": 13.33, "learning_rate": 0.0002631325301204819, "loss": 0.8583, "step": 1120}
+{"epoch": 13.45, "learning_rate": 0.00026277108433734936, "loss": 0.7784, "step": 1130}
+{"epoch": 13.57, "learning_rate": 0.00026240963855421684, "loss": 0.8323, "step": 1140}
+{"epoch": 13.69, "learning_rate": 0.00026204819277108433, "loss": 0.7988, "step": 1150}
+{"epoch": 13.81, "learning_rate": 0.0002616867469879518, "loss": 0.7671, "step": 1160}
+{"epoch": 13.93, "learning_rate": 0.00026132530120481925, "loss": 0.8336, "step": 1170}
+{"epoch": 14.05, "learning_rate": 0.00026096385542168673, "loss": 0.7438, "step": 1180}
+{"epoch": 14.17, "learning_rate": 0.0002606024096385542, "loss": 0.7234, "step": 1190}
+{"epoch": 14.29, "learning_rate": 0.00026024096385542165, "loss": 0.7257, "step": 1200}
+{"epoch": 14.4, "learning_rate": 0.00025987951807228914, "loss": 0.7833, "step": 1210}
+{"epoch": 14.52, "learning_rate": 0.0002595180722891566, "loss": 0.77, "step": 1220}
+{"epoch": 14.64, "learning_rate": 0.00025915662650602406, "loss": 0.7756, "step": 1230}
+{"epoch": 14.76, "learning_rate": 0.00025879518072289154, "loss": 0.7867, "step": 1240}
+{"epoch": 14.88, "learning_rate": 0.00025843373493975903, "loss": 0.7665, "step": 1250}
+{"epoch": 15.0, "learning_rate": 0.00025807228915662646, "loss": 0.7284, "step": 1260}
+{"epoch": 15.12, "learning_rate": 0.00025771084337349395, "loss": 0.6533, "step": 1270}
+{"epoch": 15.24, "learning_rate": 0.00025734939759036144, "loss": 0.712, "step": 1280}
+{"epoch": 15.36, "learning_rate": 0.0002569879518072289, "loss": 0.7408, "step": 1290}
+{"epoch": 15.48, "learning_rate": 0.00025662650602409636, "loss": 0.6888, "step": 1300}
+{"epoch": 15.6, "learning_rate": 0.00025626506024096384, "loss": 0.7257, "step": 1310}
+{"epoch": 15.71, "learning_rate": 0.00025590361445783133, "loss": 0.687, "step": 1320}
+{"epoch": 15.83, "learning_rate": 0.00025554216867469876, "loss": 0.7182, "step": 1330}
+{"epoch": 15.95, "learning_rate": 0.00025518072289156625, "loss": 0.7337, "step": 1340}
+{"epoch": 16.07, "learning_rate": 0.00025481927710843373, "loss": 0.6581, "step": 1350}
+{"epoch": 16.19, "learning_rate": 0.00025445783132530117, "loss": 0.6839, "step": 1360}
+{"epoch": 16.31, "learning_rate": 0.00025409638554216865, "loss": 0.6336, "step": 1370}
+{"epoch": 16.43, "learning_rate": 0.00025373493975903614, "loss": 0.6679, "step": 1380}
+{"epoch": 16.55, "learning_rate": 0.00025337349397590357, "loss": 0.632, "step": 1390}
+{"epoch": 16.67, "learning_rate": 0.00025301204819277106, "loss": 0.6286, "step": 1400}
+{"epoch": 16.79, "learning_rate": 0.00025265060240963855, "loss": 0.7263, "step": 1410}
+{"epoch": 16.9, "learning_rate": 0.000252289156626506, "loss": 0.6465, "step": 1420}
+{"epoch": 17.02, "learning_rate": 0.00025192771084337346, "loss": 0.617, "step": 1430}
+{"epoch": 17.14, "learning_rate": 0.00025156626506024095, "loss": 0.599, "step": 1440}
+{"epoch": 17.26, "learning_rate": 0.0002512048192771084, "loss": 0.6203, "step": 1450}
+{"epoch": 17.38, "learning_rate": 0.00025084337349397587, "loss": 0.5545, "step": 1460}
+{"epoch": 17.5, "learning_rate": 0.00025048192771084336, "loss": 0.6239, "step": 1470}
+{"epoch": 17.62, "learning_rate": 0.0002501204819277108, "loss": 0.5739, "step": 1480}
+{"epoch": 17.74, "learning_rate": 0.00024975903614457833, "loss": 0.6289, "step": 1490}
+{"epoch": 17.86, "learning_rate": 0.00024939759036144576, "loss": 0.5728, "step": 1500}
+{"epoch": 17.98, "learning_rate": 0.00024903614457831325, "loss": 0.6469, "step": 1510}
+{"epoch": 18.1, "learning_rate": 0.00024867469879518074, "loss": 0.5318, "step": 1520}
+{"epoch": 18.21, "learning_rate": 0.00024831325301204817, "loss": 0.4846, "step": 1530}
+{"epoch": 18.33, "learning_rate": 0.00024795180722891565, "loss": 0.5352, "step": 1540}
+{"epoch": 18.45, "learning_rate": 0.00024759036144578314, "loss": 0.5341, "step": 1550}
+{"epoch": 18.57, "learning_rate": 0.0002472289156626506, "loss": 0.57, "step": 1560}
+{"epoch": 18.69, "learning_rate": 0.00024686746987951806, "loss": 0.5228, "step": 1570}
+{"epoch": 18.81, "learning_rate": 0.00024650602409638555, "loss": 0.5857, "step": 1580}
+{"epoch": 18.93, "learning_rate": 0.000246144578313253, "loss": 0.5219, "step": 1590}
+{"epoch": 19.05, "learning_rate": 0.00024578313253012046, "loss": 0.5233, "step": 1600}
+{"epoch": 19.17, "learning_rate": 0.00024542168674698795, "loss": 0.4589, "step": 1610}
+{"epoch": 19.29, "learning_rate": 0.0002450602409638554, "loss": 0.5354, "step": 1620}
+{"epoch": 19.4, "learning_rate": 0.00024469879518072287, "loss": 0.4662, "step": 1630}
+{"epoch": 19.52, "learning_rate": 0.00024433734939759036, "loss": 0.465, "step": 1640}
+{"epoch": 19.64, "learning_rate": 0.00024397590361445782, "loss": 0.4602, "step": 1650}
+{"epoch": 19.76, "learning_rate": 0.00024361445783132528, "loss": 0.4851, "step": 1660}
+{"epoch": 19.88, "learning_rate": 0.00024325301204819276, "loss": 0.495, "step": 1670}
+{"epoch": 20.0, "learning_rate": 0.00024289156626506022, "loss": 0.4556, "step": 1680}
+{"epoch": 20.12, "learning_rate": 0.00024253012048192768, "loss": 0.3657, "step": 1690}
+{"epoch": 20.24, "learning_rate": 0.00024216867469879517, "loss": 0.4285, "step": 1700}
+{"epoch": 20.36, "learning_rate": 0.00024180722891566263, "loss": 0.3793, "step": 1710}
+{"epoch": 20.48, "learning_rate": 0.0002414457831325301, "loss": 0.4846, "step": 1720}
+{"epoch": 20.6, "learning_rate": 0.00024108433734939757, "loss": 0.4543, "step": 1730}
+{"epoch": 20.71, "learning_rate": 0.00024072289156626503, "loss": 0.4694, "step": 1740}
+{"epoch": 20.83, "learning_rate": 0.0002403614457831325, "loss": 0.3779, "step": 1750}
+{"epoch": 20.95, "learning_rate": 0.00023999999999999998, "loss": 0.431, "step": 1760}
+{"epoch": 21.07, "learning_rate": 0.00023963855421686744, "loss": 0.367, "step": 1770}
+{"epoch": 21.19, "learning_rate": 0.0002392771084337349, "loss": 0.4387, "step": 1780}
+{"epoch": 21.31, "learning_rate": 0.0002389156626506024, "loss": 0.3326, "step": 1790}
+{"epoch": 21.43, "learning_rate": 0.00023855421686746987, "loss": 0.3899, "step": 1800}
+{"epoch": 21.55, "learning_rate": 0.00023819277108433733, "loss": 0.3869, "step": 1810}
+{"epoch": 21.67, "learning_rate": 0.00023783132530120482, "loss": 0.3685, "step": 1820}
+{"epoch": 21.79, "learning_rate": 0.00023746987951807228, "loss": 0.3711, "step": 1830}
+{"epoch": 21.9, "learning_rate": 0.00023710843373493974, "loss": 0.3748, "step": 1840}
+{"epoch": 22.02, "learning_rate": 0.00023674698795180722, "loss": 0.3345, "step": 1850}
+{"epoch": 22.14, "learning_rate": 0.00023638554216867468, "loss": 0.3128, "step": 1860}
+{"epoch": 22.26, "learning_rate": 0.00023602409638554214, "loss": 0.348, "step": 1870}
+{"epoch": 22.38, "learning_rate": 0.00023566265060240963, "loss": 0.3506, "step": 1880}
+{"epoch": 22.5, "learning_rate": 0.0002353012048192771, "loss": 0.289, "step": 1890}
+{"epoch": 22.62, "learning_rate": 0.00023493975903614455, "loss": 0.3008, "step": 1900}
+{"epoch": 22.74, "learning_rate": 0.00023457831325301203, "loss": 0.3372, "step": 1910}
+{"epoch": 22.86, "learning_rate": 0.0002342168674698795, "loss": 0.3642, "step": 1920}
+{"epoch": 22.98, "learning_rate": 0.00023385542168674695, "loss": 0.3117, "step": 1930}
+{"epoch": 23.1, "learning_rate": 0.00023349397590361444, "loss": 0.3003, "step": 1940}
+{"epoch": 23.21, "learning_rate": 0.0002331325301204819, "loss": 0.2342, "step": 1950}
+{"epoch": 23.33, "learning_rate": 0.00023277108433734936, "loss": 0.3119, "step": 1960}
+{"epoch": 23.45, "learning_rate": 0.00023240963855421687, "loss": 0.2618, "step": 1970}
+{"epoch": 23.57, "learning_rate": 0.00023204819277108433, "loss": 0.3138, "step": 1980}
+{"epoch": 23.69, "learning_rate": 0.00023168674698795176, "loss": 0.2934, "step": 1990}
+{"epoch": 23.81, "learning_rate": 0.00023132530120481928, "loss": 0.2713, "step": 2000}
+{"epoch": 23.93, "learning_rate": 0.00023096385542168674, "loss": 0.3095, "step": 2010}
+{"epoch": 24.05, "learning_rate": 0.0002306024096385542, "loss": 0.2688, "step": 2020}
+{"epoch": 24.17, "learning_rate": 0.00023024096385542168, "loss": 0.2309, "step": 2030}
+{"epoch": 24.29, "learning_rate": 0.00022987951807228914, "loss": 0.2614, "step": 2040}
+{"epoch": 24.4, "learning_rate": 0.0002295180722891566, "loss": 0.2264, "step": 2050}
+{"epoch": 24.52, "learning_rate": 0.0002291566265060241, "loss": 0.2506, "step": 2060}
+{"epoch": 24.64, "learning_rate": 0.00022879518072289155, "loss": 0.2241, "step": 2070}
+{"epoch": 24.76, "learning_rate": 0.000228433734939759, "loss": 0.2882, "step": 2080}
+{"epoch": 24.88, "learning_rate": 0.0002280722891566265, "loss": 0.2868, "step": 2090}
+{"epoch": 25.0, "learning_rate": 0.00022771084337349395, "loss": 0.284, "step": 2100}
+{"epoch": 25.12, "learning_rate": 0.0002273493975903614, "loss": 0.2088, "step": 2110}
+{"epoch": 25.24, "learning_rate": 0.0002269879518072289, "loss": 0.1954, "step": 2120}
+{"epoch": 25.36, "learning_rate": 0.00022662650602409636, "loss": 0.2121, "step": 2130}
+{"epoch": 25.48, "learning_rate": 0.00022626506024096382, "loss": 0.2345, "step": 2140}
+{"epoch": 25.6, "learning_rate": 0.0002259036144578313, "loss": 0.221, "step": 2150}
+{"epoch": 25.71, "learning_rate": 0.00022554216867469876, "loss": 0.2258, "step": 2160}
+{"epoch": 25.83, "learning_rate": 0.00022518072289156622, "loss": 0.2467, "step": 2170}
+{"epoch": 25.95, "learning_rate": 0.00022481927710843374, "loss": 0.2216, "step": 2180}
+{"epoch": 26.07, "learning_rate": 0.0002244578313253012, "loss": 0.2106, "step": 2190}
+{"epoch": 26.19, "learning_rate": 0.00022409638554216866, "loss": 0.2242, "step": 2200}
+{"epoch": 26.31, "learning_rate": 0.00022373493975903614, "loss": 0.1702, "step": 2210}
+{"epoch": 26.43, "learning_rate": 0.0002233734939759036, "loss": 0.2117, "step": 2220}
+{"epoch": 26.55, "learning_rate": 0.00022301204819277106, "loss": 0.1841, "step": 2230}
+{"epoch": 26.67, "learning_rate": 0.00022265060240963855, "loss": 0.1786, "step": 2240}
+{"epoch": 26.79, "learning_rate": 0.000222289156626506, "loss": 0.201, "step": 2250}
+{"epoch": 26.9, "learning_rate": 0.00022192771084337347, "loss": 0.1915, "step": 2260}
+{"epoch": 27.02, "learning_rate": 0.00022156626506024095, "loss": 0.1973, "step": 2270}
+{"epoch": 27.14, "learning_rate": 0.0002212048192771084, "loss": 0.1649, "step": 2280}
+{"epoch": 27.26, "learning_rate": 0.00022084337349397587, "loss": 0.1665, "step": 2290}
+{"epoch": 27.38, "learning_rate": 0.00022048192771084336, "loss": 0.2129, "step": 2300}
+{"epoch": 27.5, "learning_rate": 0.00022012048192771082, "loss": 0.194, "step": 2310}
+{"epoch": 27.62, "learning_rate": 0.00021975903614457828, "loss": 0.1684, "step": 2320}
+{"epoch": 27.74, "learning_rate": 0.00021939759036144576, "loss": 0.1312, "step": 2330}
+{"epoch": 27.86, "learning_rate": 0.00021903614457831322, "loss": 0.1711, "step": 2340}
+{"epoch": 27.98, "learning_rate": 0.00021867469879518068, "loss": 0.1863, "step": 2350}
+{"epoch": 28.1, "learning_rate": 0.0002183132530120482, "loss": 0.1425, "step": 2360}
+{"epoch": 28.21, "learning_rate": 0.00021795180722891563, "loss": 0.1293, "step": 2370}
+{"epoch": 28.33, "learning_rate": 0.0002175903614457831, "loss": 0.1406, "step": 2380}
+{"epoch": 28.45, "learning_rate": 0.0002172289156626506, "loss": 0.1583, "step": 2390}
+{"epoch": 28.57, "learning_rate": 0.00021686746987951806, "loss": 0.1706, "step": 2400}
+{"epoch": 28.69, "learning_rate": 0.00021650602409638552, "loss": 0.1629, "step": 2410}
+{"epoch": 28.81, "learning_rate": 0.000216144578313253, "loss": 0.1788, "step": 2420}
+{"epoch": 28.93, "learning_rate": 0.00021578313253012047, "loss": 0.1618, "step": 2430}
+{"epoch": 29.05, "learning_rate": 0.00021542168674698793, "loss": 0.1391, "step": 2440}
+{"epoch": 29.17, "learning_rate": 0.00021506024096385541, "loss": 0.1271, "step": 2450}
+{"epoch": 29.29, "learning_rate": 0.00021469879518072287, "loss": 0.1312, "step": 2460}
+{"epoch": 29.4, "learning_rate": 0.00021433734939759033, "loss": 0.1401, "step": 2470}
+{"epoch": 29.52, "learning_rate": 0.00021397590361445782, "loss": 0.1222, "step": 2480}
+{"epoch": 29.64, "learning_rate": 0.00021361445783132528, "loss": 0.1124, "step": 2490}
+{"epoch": 29.76, "learning_rate": 0.00021325301204819274, "loss": 0.1796, "step": 2500}
+{"epoch": 29.88, "learning_rate": 0.00021289156626506022, "loss": 0.1502, "step": 2510}
+{"epoch": 30.0, "learning_rate": 0.00021253012048192768, "loss": 0.137, "step": 2520}
+{"epoch": 30.12, "learning_rate": 0.00021216867469879514, "loss": 0.1021, "step": 2530}
+{"epoch": 30.24, "learning_rate": 0.00021180722891566263, "loss": 0.129, "step": 2540}
+{"epoch": 30.36, "learning_rate": 0.0002114457831325301, "loss": 0.1119, "step": 2550}
+{"loss": 0.1135, "learning_rate": 2.3802395209580838e-05, "epoch": 30.48, "step": 2560}
+{"loss": 0.1224, "learning_rate": 2.2679640718562872e-05, "epoch": 30.6, "step": 2570}
+{"loss": 0.1004, "learning_rate": 2.1556886227544907e-05, "epoch": 30.71, "step": 2580}
+{"loss": 0.1048, "learning_rate": 2.043413173652694e-05, "epoch": 30.83, "step": 2590}
+{"loss": 0.0978, "learning_rate": 1.931137724550898e-05, "epoch": 30.95, "step": 2600}
+{"loss": 0.0981, "learning_rate": 1.8188622754491017e-05, "epoch": 31.07, "step": 2610}
+{"loss": 0.0979, "learning_rate": 1.7065868263473052e-05, "epoch": 31.19, "step": 2620}
+{"loss": 0.103, "learning_rate": 1.594311377245509e-05, "epoch": 31.31, "step": 2630}
+{"loss": 0.1065, "learning_rate": 1.4820359281437124e-05, "epoch": 31.43, "step": 2640}
+{"loss": 0.0912, "learning_rate": 1.369760479041916e-05, "epoch": 31.55, "step": 2650}
+{"loss": 0.0927, "learning_rate": 1.2574850299401195e-05, "epoch": 31.67, "step": 2660}
+{"loss": 0.0942, "learning_rate": 1.1452095808383233e-05, "epoch": 31.79, "step": 2670}
+{"loss": 0.0896, "learning_rate": 1.032934131736527e-05, "epoch": 31.9, "step": 2680}
+{"loss": 0.0965, "learning_rate": 9.206586826347304e-06, "epoch": 32.02, "step": 2690}
+{"loss": 0.0943, "learning_rate": 8.08383233532934e-06, "epoch": 32.14, "step": 2700}
+{"loss": 0.0866, "learning_rate": 6.961077844311377e-06, "epoch": 32.26, "step": 2710}
+{"loss": 0.1012, "learning_rate": 5.838323353293413e-06, "epoch": 32.38, "step": 2720}
+{"loss": 0.1023, "learning_rate": 4.7155688622754485e-06, "epoch": 32.5, "step": 2730}
+{"loss": 0.0856, "learning_rate": 3.5928143712574848e-06, "epoch": 32.62, "step": 2740}
+{"loss": 0.1008, "learning_rate": 2.470059880239521e-06, "epoch": 32.74, "step": 2750}
+{"loss": 0.0932, "learning_rate": 1.3473053892215567e-06, "epoch": 32.86, "step": 2760}
+{"loss": 0.1046, "learning_rate": 2.245508982035928e-07, "epoch": 32.98, "step": 2770}
+{"train_runtime": 2005.6988, "train_samples_per_second": 5.512, "train_steps_per_second": 1.382, "total_flos": 1.6099719938337178e+18, "train_loss": 0.007915083082422378, "epoch": 33.0, "step": 2772}