{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9989861439675565,
  "global_step": 2217,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 3.310780333784393e-05,
      "loss": 0.255,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.288227334235454e-05,
      "loss": 0.2416,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.2656743346865135e-05,
      "loss": 0.232,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.243121335137573e-05,
      "loss": 0.2344,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.220568335588634e-05,
      "loss": 0.2296,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 3.1980153360396934e-05,
      "loss": 0.2471,
      "step": 60
    },
    {
      "epoch": 0.09,
      "learning_rate": 3.175462336490753e-05,
      "loss": 0.2212,
      "step": 70
    },
    {
      "epoch": 0.11,
      "learning_rate": 3.1529093369418136e-05,
      "loss": 0.2219,
      "step": 80
    },
    {
      "epoch": 0.12,
      "learning_rate": 3.1303563373928734e-05,
      "loss": 0.2305,
      "step": 90
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.107803337843934e-05,
      "loss": 0.2555,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 3.085250338294993e-05,
      "loss": 0.2398,
      "step": 110
    },
    {
      "epoch": 0.16,
      "learning_rate": 3.0626973387460534e-05,
      "loss": 0.2538,
      "step": 120
    },
    {
      "epoch": 0.18,
      "learning_rate": 3.0401443391971135e-05,
      "loss": 0.2271,
      "step": 130
    },
    {
      "epoch": 0.19,
      "learning_rate": 3.0175913396481732e-05,
      "loss": 0.2479,
      "step": 140
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.9950383400992333e-05,
      "loss": 0.2465,
      "step": 150
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.9724853405502934e-05,
      "loss": 0.2288,
      "step": 160
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.9499323410013535e-05,
      "loss": 0.2247,
      "step": 170
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.927379341452413e-05,
      "loss": 0.2442,
      "step": 180
    },
    {
      "epoch": 0.26,
      "learning_rate": 2.9048263419034734e-05,
      "loss": 0.2321,
      "step": 190
    },
    {
      "epoch": 0.27,
      "learning_rate": 2.8822733423545335e-05,
      "loss": 0.2342,
      "step": 200
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.8597203428055936e-05,
      "loss": 0.2342,
      "step": 210
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.837167343256653e-05,
      "loss": 0.2351,
      "step": 220
    },
    {
      "epoch": 0.31,
      "learning_rate": 2.814614343707713e-05,
      "loss": 0.2155,
      "step": 230
    },
    {
      "epoch": 0.32,
      "learning_rate": 2.7920613441587736e-05,
      "loss": 0.2517,
      "step": 240
    },
    {
      "epoch": 0.34,
      "learning_rate": 2.769508344609833e-05,
      "loss": 0.2431,
      "step": 250
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.746955345060893e-05,
      "loss": 0.2409,
      "step": 260
    },
    {
      "epoch": 0.36,
      "learning_rate": 2.7244023455119532e-05,
      "loss": 0.2458,
      "step": 270
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.7018493459630133e-05,
      "loss": 0.2268,
      "step": 280
    },
    {
      "epoch": 0.39,
      "learning_rate": 2.679296346414073e-05,
      "loss": 0.2256,
      "step": 290
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.6567433468651332e-05,
      "loss": 0.2408,
      "step": 300
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.6341903473161933e-05,
      "loss": 0.224,
      "step": 310
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.6116373477672534e-05,
      "loss": 0.2328,
      "step": 320
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.589084348218313e-05,
      "loss": 0.2359,
      "step": 330
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.5665313486693732e-05,
      "loss": 0.23,
      "step": 340
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.5439783491204333e-05,
      "loss": 0.2371,
      "step": 350
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.5214253495714928e-05,
      "loss": 0.2443,
      "step": 360
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.4988723500225532e-05,
      "loss": 0.2411,
      "step": 370
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.4763193504736133e-05,
      "loss": 0.2294,
      "step": 380
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.453766350924673e-05,
      "loss": 0.2108,
      "step": 390
    },
    {
      "epoch": 0.54,
      "learning_rate": 2.4312133513757332e-05,
      "loss": 0.2424,
      "step": 400
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.408660351826793e-05,
      "loss": 0.2246,
      "step": 410
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.386107352277853e-05,
      "loss": 0.2329,
      "step": 420
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.363554352728913e-05,
      "loss": 0.2497,
      "step": 430
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.341001353179973e-05,
      "loss": 0.2363,
      "step": 440
    },
    {
      "epoch": 0.61,
      "learning_rate": 2.318448353631033e-05,
      "loss": 0.2322,
      "step": 450
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.2958953540820928e-05,
      "loss": 0.2233,
      "step": 460
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.2733423545331532e-05,
      "loss": 0.2386,
      "step": 470
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.250789354984213e-05,
      "loss": 0.2283,
      "step": 480
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.228236355435273e-05,
      "loss": 0.2178,
      "step": 490
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.205683355886333e-05,
      "loss": 0.2386,
      "step": 500
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.183130356337393e-05,
      "loss": 0.2261,
      "step": 510
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.160577356788453e-05,
      "loss": 0.2236,
      "step": 520
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.1380243572395128e-05,
      "loss": 0.2247,
      "step": 530
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.115471357690573e-05,
      "loss": 0.2361,
      "step": 540
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.0929183581416327e-05,
      "loss": 0.2198,
      "step": 550
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.070365358592693e-05,
      "loss": 0.2425,
      "step": 560
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.047812359043753e-05,
      "loss": 0.2273,
      "step": 570
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.025259359494813e-05,
      "loss": 0.2501,
      "step": 580
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0027063599458727e-05,
      "loss": 0.2364,
      "step": 590
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.980153360396933e-05,
      "loss": 0.2386,
      "step": 600
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.957600360847993e-05,
      "loss": 0.234,
      "step": 610
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.9350473612990527e-05,
      "loss": 0.2277,
      "step": 620
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.9124943617501128e-05,
      "loss": 0.2352,
      "step": 630
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.8899413622011726e-05,
      "loss": 0.2087,
      "step": 640
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.867388362652233e-05,
      "loss": 0.226,
      "step": 650
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.8448353631032928e-05,
      "loss": 0.2267,
      "step": 660
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.822282363554353e-05,
      "loss": 0.2257,
      "step": 670
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.7997293640054127e-05,
      "loss": 0.2315,
      "step": 680
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.7771763644564728e-05,
      "loss": 0.2219,
      "step": 690
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.754623364907533e-05,
      "loss": 0.2263,
      "step": 700
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.732070365358593e-05,
      "loss": 0.2072,
      "step": 710
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.7095173658096527e-05,
      "loss": 0.2179,
      "step": 720
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.6869643662607125e-05,
      "loss": 0.2359,
      "step": 730
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.19105975329875946,
      "eval_rouge1": 0.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.0,
      "eval_rougeLsum": 0.0,
      "eval_runtime": 72.427,
      "eval_samples_per_second": 5.619,
      "eval_steps_per_second": 2.817,
      "step": 739
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.664411366711773e-05,
      "loss": 0.2357,
      "step": 740
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.6418583671628327e-05,
      "loss": 0.2042,
      "step": 750
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.6193053676138928e-05,
      "loss": 0.2101,
      "step": 760
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.5967523680649526e-05,
      "loss": 0.1908,
      "step": 770
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.5741993685160127e-05,
      "loss": 0.2128,
      "step": 780
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.5516463689670728e-05,
      "loss": 0.1934,
      "step": 790
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.529093369418133e-05,
      "loss": 0.2087,
      "step": 800
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.5065403698691926e-05,
      "loss": 0.194,
      "step": 810
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.4839873703202526e-05,
      "loss": 0.1993,
      "step": 820
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.4614343707713127e-05,
      "loss": 0.1979,
      "step": 830
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.4388813712223726e-05,
      "loss": 0.2281,
      "step": 840
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.4163283716734327e-05,
      "loss": 0.205,
      "step": 850
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.3937753721244926e-05,
      "loss": 0.1895,
      "step": 860
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.3712223725755527e-05,
      "loss": 0.1999,
      "step": 870
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.3486693730266125e-05,
      "loss": 0.204,
      "step": 880
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.3261163734776728e-05,
      "loss": 0.2026,
      "step": 890
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.3035633739287325e-05,
      "loss": 0.2291,
      "step": 900
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.2810103743797926e-05,
      "loss": 0.2036,
      "step": 910
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.2584573748308526e-05,
      "loss": 0.2065,
      "step": 920
    },
    {
      "epoch": 1.26,
      "learning_rate": 1.2359043752819125e-05,
      "loss": 0.2039,
      "step": 930
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.2133513757329726e-05,
      "loss": 0.208,
      "step": 940
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.1907983761840325e-05,
      "loss": 0.2177,
      "step": 950
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.1682453766350926e-05,
      "loss": 0.1943,
      "step": 960
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.1456923770861524e-05,
      "loss": 0.207,
      "step": 970
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.1231393775372125e-05,
      "loss": 0.2017,
      "step": 980
    },
    {
      "epoch": 1.34,
      "learning_rate": 1.1005863779882724e-05,
      "loss": 0.2115,
      "step": 990
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.0780333784393325e-05,
      "loss": 0.2098,
      "step": 1000
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.0554803788903925e-05,
      "loss": 0.2105,
      "step": 1010
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.0329273793414524e-05,
      "loss": 0.2149,
      "step": 1020
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.0103743797925125e-05,
      "loss": 0.2027,
      "step": 1030
    },
    {
      "epoch": 1.41,
      "learning_rate": 9.878213802435724e-06,
      "loss": 0.1887,
      "step": 1040
    },
    {
      "epoch": 1.42,
      "learning_rate": 9.652683806946325e-06,
      "loss": 0.1955,
      "step": 1050
    },
    {
      "epoch": 1.43,
      "learning_rate": 9.427153811456923e-06,
      "loss": 0.2065,
      "step": 1060
    },
    {
      "epoch": 1.45,
      "learning_rate": 9.201623815967524e-06,
      "loss": 0.2088,
      "step": 1070
    },
    {
      "epoch": 1.46,
      "learning_rate": 8.976093820478123e-06,
      "loss": 0.2119,
      "step": 1080
    },
    {
      "epoch": 1.47,
      "learning_rate": 8.750563824988724e-06,
      "loss": 0.2101,
      "step": 1090
    },
    {
      "epoch": 1.49,
      "learning_rate": 8.525033829499324e-06,
      "loss": 0.1985,
      "step": 1100
    },
    {
      "epoch": 1.5,
      "learning_rate": 8.299503834009923e-06,
      "loss": 0.2105,
      "step": 1110
    },
    {
      "epoch": 1.52,
      "learning_rate": 8.073973838520524e-06,
      "loss": 0.2121,
      "step": 1120
    },
    {
      "epoch": 1.53,
      "learning_rate": 7.848443843031123e-06,
      "loss": 0.1942,
      "step": 1130
    },
    {
      "epoch": 1.54,
      "learning_rate": 7.6229138475417236e-06,
      "loss": 0.1874,
      "step": 1140
    },
    {
      "epoch": 1.56,
      "learning_rate": 7.397383852052324e-06,
      "loss": 0.204,
      "step": 1150
    },
    {
      "epoch": 1.57,
      "learning_rate": 7.171853856562922e-06,
      "loss": 0.1883,
      "step": 1160
    },
    {
      "epoch": 1.58,
      "learning_rate": 6.946323861073522e-06,
      "loss": 0.2032,
      "step": 1170
    },
    {
      "epoch": 1.6,
      "learning_rate": 6.7207938655841226e-06,
      "loss": 0.1878,
      "step": 1180
    },
    {
      "epoch": 1.61,
      "learning_rate": 6.495263870094723e-06,
      "loss": 0.2057,
      "step": 1190
    },
    {
      "epoch": 1.62,
      "learning_rate": 6.269733874605323e-06,
      "loss": 0.2096,
      "step": 1200
    },
    {
      "epoch": 1.64,
      "learning_rate": 6.044203879115923e-06,
      "loss": 0.1872,
      "step": 1210
    },
    {
      "epoch": 1.65,
      "learning_rate": 5.8186738836265224e-06,
      "loss": 0.2072,
      "step": 1220
    },
    {
      "epoch": 1.66,
      "learning_rate": 5.593143888137122e-06,
      "loss": 0.2098,
      "step": 1230
    },
    {
      "epoch": 1.68,
      "learning_rate": 5.367613892647722e-06,
      "loss": 0.2255,
      "step": 1240
    },
    {
      "epoch": 1.69,
      "learning_rate": 5.142083897158322e-06,
      "loss": 0.1859,
      "step": 1250
    },
    {
      "epoch": 1.7,
      "learning_rate": 4.916553901668922e-06,
      "loss": 0.1849,
      "step": 1260
    },
    {
      "epoch": 1.72,
      "learning_rate": 4.6910239061795225e-06,
      "loss": 0.2022,
      "step": 1270
    },
    {
      "epoch": 1.73,
      "learning_rate": 4.465493910690122e-06,
      "loss": 0.1976,
      "step": 1280
    },
    {
      "epoch": 1.74,
      "learning_rate": 4.239963915200722e-06,
      "loss": 0.1988,
      "step": 1290
    },
    {
      "epoch": 1.76,
      "learning_rate": 4.014433919711322e-06,
      "loss": 0.1983,
      "step": 1300
    },
    {
      "epoch": 1.77,
      "learning_rate": 3.788903924221922e-06,
      "loss": 0.198,
      "step": 1310
    },
    {
      "epoch": 1.79,
      "learning_rate": 3.563373928732522e-06,
      "loss": 0.1967,
      "step": 1320
    },
    {
      "epoch": 1.8,
      "learning_rate": 3.3378439332431214e-06,
      "loss": 0.202,
      "step": 1330
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.112313937753721e-06,
      "loss": 0.1974,
      "step": 1340
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.8867839422643213e-06,
      "loss": 0.2045,
      "step": 1350
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.6612539467749215e-06,
      "loss": 0.1997,
      "step": 1360
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.435723951285521e-06,
      "loss": 0.1879,
      "step": 1370
    },
    {
      "epoch": 1.87,
      "learning_rate": 2.210193955796121e-06,
      "loss": 0.1983,
      "step": 1380
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.9846639603067207e-06,
      "loss": 0.1943,
      "step": 1390
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.7591339648173207e-06,
      "loss": 0.2045,
      "step": 1400
    },
    {
      "epoch": 1.91,
      "learning_rate": 1.5336039693279207e-06,
      "loss": 0.2134,
      "step": 1410
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.3080739738385204e-06,
      "loss": 0.2181,
      "step": 1420
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.0825439783491206e-06,
      "loss": 0.1993,
      "step": 1430
    },
    {
      "epoch": 1.95,
      "learning_rate": 8.570139828597205e-07,
      "loss": 0.1982,
      "step": 1440
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.314839873703203e-07,
      "loss": 0.1947,
      "step": 1450
    },
    {
      "epoch": 1.97,
      "learning_rate": 4.0595399188092017e-07,
      "loss": 0.199,
      "step": 1460
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.8042399639152008e-07,
      "loss": 0.2169,
      "step": 1470
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.20216532051563263,
      "eval_rouge1": 0.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.0,
      "eval_rougeLsum": 0.0,
      "eval_runtime": 80.504,
      "eval_samples_per_second": 5.056,
      "eval_steps_per_second": 2.534,
      "step": 1478
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0,
      "loss": 0.2106,
      "step": 1480
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0,
      "loss": 0.2036,
      "step": 1490
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0,
      "loss": 0.1853,
      "step": 1500
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0,
      "loss": 0.1873,
      "step": 1510
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0,
      "loss": 0.1814,
      "step": 1520
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0,
      "loss": 0.1864,
      "step": 1530
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0,
      "loss": 0.2106,
      "step": 1540
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0,
      "loss": 0.1789,
      "step": 1550
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0,
      "loss": 0.1834,
      "step": 1560
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0,
      "loss": 0.2044,
      "step": 1570
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0,
      "loss": 0.1963,
      "step": 1580
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0,
      "loss": 0.1981,
      "step": 1590
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0,
      "loss": 0.1989,
      "step": 1600
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0,
      "loss": 0.1933,
      "step": 1610
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0,
      "loss": 0.172,
      "step": 1620
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0,
      "loss": 0.1742,
      "step": 1630
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0,
      "loss": 0.2018,
      "step": 1640
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0,
      "loss": 0.198,
      "step": 1650
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0,
      "loss": 0.2013,
      "step": 1660
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0,
      "loss": 0.1997,
      "step": 1670
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0,
      "loss": 0.1926,
      "step": 1680
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0,
      "loss": 0.1905,
      "step": 1690
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0,
      "loss": 0.1649,
      "step": 1700
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0,
      "loss": 0.188,
      "step": 1710
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0,
      "loss": 0.1974,
      "step": 1720
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0,
      "loss": 0.179,
      "step": 1730
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0,
      "loss": 0.1846,
      "step": 1740
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0,
      "loss": 0.1856,
      "step": 1750
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0,
      "loss": 0.1869,
      "step": 1760
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0,
      "loss": 0.1838,
      "step": 1770
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0,
      "loss": 0.1786,
      "step": 1780
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0,
      "loss": 0.1848,
      "step": 1790
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0,
      "loss": 0.2055,
      "step": 1800
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0,
      "loss": 0.1924,
      "step": 1810
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0,
      "loss": 0.1935,
      "step": 1820
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0,
      "loss": 0.1819,
      "step": 1830
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0,
      "loss": 0.1853,
      "step": 1840
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0,
      "loss": 0.194,
      "step": 1850
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0,
      "loss": 0.1757,
      "step": 1860
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0,
      "loss": 0.2099,
      "step": 1870
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0,
      "loss": 0.177,
      "step": 1880
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0,
      "loss": 0.1951,
      "step": 1890
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0,
      "loss": 0.2008,
      "step": 1900
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0,
      "loss": 0.1756,
      "step": 1910
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0,
      "loss": 0.201,
      "step": 1920
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0,
      "loss": 0.1919,
      "step": 1930
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0,
      "loss": 0.1882,
      "step": 1940
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0,
      "loss": 0.202,
      "step": 1950
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0,
      "loss": 0.191,
      "step": 1960
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0,
      "loss": 0.1776,
      "step": 1970
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.0,
      "loss": 0.1813,
      "step": 1980
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0,
      "loss": 0.1911,
      "step": 1990
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0,
      "loss": 0.1921,
      "step": 2000
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0,
      "loss": 0.1927,
      "step": 2010
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.0,
      "loss": 0.202,
      "step": 2020
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0,
      "loss": 0.1814,
      "step": 2030
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.0,
      "loss": 0.1868,
      "step": 2040
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0,
      "loss": 0.1784,
      "step": 2050
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0,
      "loss": 0.1932,
      "step": 2060
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0,
      "loss": 0.1857,
      "step": 2070
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.0,
      "loss": 0.2104,
      "step": 2080
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0,
      "loss": 0.1869,
      "step": 2090
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0,
      "loss": 0.1905,
      "step": 2100
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.0,
      "loss": 0.1778,
      "step": 2110
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.0,
      "loss": 0.1961,
      "step": 2120
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0,
      "loss": 0.1979,
      "step": 2130
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0,
      "loss": 0.2026,
      "step": 2140
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0,
      "loss": 0.1929,
      "step": 2150
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.0,
      "loss": 0.1891,
      "step": 2160
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0,
      "loss": 0.1844,
      "step": 2170
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.0,
      "loss": 0.1908,
      "step": 2180
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.0,
      "loss": 0.2041,
      "step": 2190
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0,
      "loss": 0.2078,
      "step": 2200
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.0,
      "loss": 0.1739,
      "step": 2210
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.20216532051563263,
      "eval_rouge1": 0.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.0,
      "eval_rougeLsum": 0.0,
      "eval_runtime": 75.4566,
      "eval_samples_per_second": 5.394,
      "eval_steps_per_second": 2.704,
      "step": 2217
    },
    {
      "epoch": 3.0,
      "step": 2217,
      "total_flos": 3.2211655354615726e+18,
      "train_loss": 0.2087684871917057,
      "train_runtime": 2567.1485,
      "train_samples_per_second": 6.916,
      "train_steps_per_second": 0.864
    }
  ],
  "max_steps": 2217,
  "num_train_epochs": 3,
  "total_flos": 3.2211655354615726e+18,
  "trial_name": null,
  "trial_params": null
}