{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 50.0,
  "global_step": 3200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 30.29538917541504,
      "eval_mae": 3.445791244506836,
      "eval_mse": 30.29538917541504,
      "eval_rmse": 5.504124641418457,
      "eval_runtime": 0.1613,
      "eval_samples_per_second": 396.717,
      "eval_steps_per_second": 49.59,
      "step": 64
    },
    {
      "epoch": 2.0,
      "eval_loss": 22.2762508392334,
      "eval_mae": 2.9041895866394043,
      "eval_mse": 22.276248931884766,
      "eval_rmse": 4.7197723388671875,
      "eval_runtime": 0.1462,
      "eval_samples_per_second": 437.674,
      "eval_steps_per_second": 54.709,
      "step": 128
    },
    {
      "epoch": 3.0,
      "eval_loss": 19.444108963012695,
      "eval_mae": 2.726284980773926,
      "eval_mse": 19.444108963012695,
      "eval_rmse": 4.409547328948975,
      "eval_runtime": 0.2087,
      "eval_samples_per_second": 306.646,
      "eval_steps_per_second": 38.331,
      "step": 192
    },
    {
      "epoch": 4.0,
      "eval_loss": 17.12045669555664,
      "eval_mae": 2.5535168647766113,
      "eval_mse": 17.12045669555664,
      "eval_rmse": 4.1376872062683105,
      "eval_runtime": 0.3272,
      "eval_samples_per_second": 195.59,
      "eval_steps_per_second": 24.449,
      "step": 256
    },
    {
      "epoch": 5.0,
      "eval_loss": 16.316720962524414,
      "eval_mae": 2.692227840423584,
      "eval_mse": 16.316720962524414,
      "eval_rmse": 4.039396286010742,
      "eval_runtime": 0.4287,
      "eval_samples_per_second": 149.284,
      "eval_steps_per_second": 18.661,
      "step": 320
    },
    {
      "epoch": 6.0,
      "eval_loss": 15.293220520019531,
      "eval_mae": 2.601778268814087,
      "eval_mse": 15.293218612670898,
      "eval_rmse": 3.9106545448303223,
      "eval_runtime": 0.2956,
      "eval_samples_per_second": 216.483,
      "eval_steps_per_second": 27.06,
      "step": 384
    },
    {
      "epoch": 7.0,
      "eval_loss": 14.56900691986084,
      "eval_mae": 2.5558180809020996,
      "eval_mse": 14.569008827209473,
      "eval_rmse": 3.816937208175659,
      "eval_runtime": 0.4164,
      "eval_samples_per_second": 153.681,
      "eval_steps_per_second": 19.21,
      "step": 448
    },
    {
      "epoch": 7.81,
      "learning_rate": 8.4375e-06,
      "loss": 3.9689,
      "step": 500
    },
    {
      "epoch": 8.0,
      "eval_loss": 13.64460277557373,
      "eval_mae": 2.39548397064209,
      "eval_mse": 13.64460277557373,
      "eval_rmse": 3.6938600540161133,
      "eval_runtime": 0.4311,
      "eval_samples_per_second": 148.456,
      "eval_steps_per_second": 18.557,
      "step": 512
    },
    {
      "epoch": 9.0,
      "eval_loss": 13.105853080749512,
      "eval_mae": 2.4013423919677734,
      "eval_mse": 13.105853080749512,
      "eval_rmse": 3.6202006340026855,
      "eval_runtime": 0.4297,
      "eval_samples_per_second": 148.951,
      "eval_steps_per_second": 18.619,
      "step": 576
    },
    {
      "epoch": 10.0,
      "eval_loss": 13.048660278320312,
      "eval_mae": 2.3826305866241455,
      "eval_mse": 13.048660278320312,
      "eval_rmse": 3.612293004989624,
      "eval_runtime": 0.2978,
      "eval_samples_per_second": 214.88,
      "eval_steps_per_second": 26.86,
      "step": 640
    },
    {
      "epoch": 11.0,
      "eval_loss": 12.558533668518066,
      "eval_mae": 2.3683643341064453,
      "eval_mse": 12.55853271484375,
      "eval_rmse": 3.54380202293396,
      "eval_runtime": 0.4369,
      "eval_samples_per_second": 146.483,
      "eval_steps_per_second": 18.31,
      "step": 704
    },
    {
      "epoch": 12.0,
      "eval_loss": 12.03190803527832,
      "eval_mae": 2.2633650302886963,
      "eval_mse": 12.03190803527832,
      "eval_rmse": 3.4687039852142334,
      "eval_runtime": 0.4152,
      "eval_samples_per_second": 154.131,
      "eval_steps_per_second": 19.266,
      "step": 768
    },
    {
      "epoch": 13.0,
      "eval_loss": 12.05549144744873,
      "eval_mae": 2.288928508758545,
      "eval_mse": 12.05549144744873,
      "eval_rmse": 3.472101926803589,
      "eval_runtime": 0.4311,
      "eval_samples_per_second": 148.454,
      "eval_steps_per_second": 18.557,
      "step": 832
    },
    {
      "epoch": 14.0,
      "eval_loss": 11.724568367004395,
      "eval_mae": 2.2129979133605957,
      "eval_mse": 11.724568367004395,
      "eval_rmse": 3.4241156578063965,
      "eval_runtime": 0.4413,
      "eval_samples_per_second": 145.038,
      "eval_steps_per_second": 18.13,
      "step": 896
    },
    {
      "epoch": 15.0,
      "eval_loss": 11.610068321228027,
      "eval_mae": 2.238194227218628,
      "eval_mse": 11.610069274902344,
      "eval_rmse": 3.4073550701141357,
      "eval_runtime": 0.41,
      "eval_samples_per_second": 156.087,
      "eval_steps_per_second": 19.511,
      "step": 960
    },
    {
      "epoch": 15.62,
      "learning_rate": 6.875e-06,
      "loss": 0.8847,
      "step": 1000
    },
    {
      "epoch": 16.0,
      "eval_loss": 11.409879684448242,
      "eval_mae": 2.171018123626709,
      "eval_mse": 11.40987777709961,
      "eval_rmse": 3.3778510093688965,
      "eval_runtime": 0.4279,
      "eval_samples_per_second": 149.579,
      "eval_steps_per_second": 18.697,
      "step": 1024
    },
    {
      "epoch": 17.0,
      "eval_loss": 11.323513984680176,
      "eval_mae": 2.1948208808898926,
      "eval_mse": 11.323514938354492,
      "eval_rmse": 3.3650431632995605,
      "eval_runtime": 0.4359,
      "eval_samples_per_second": 146.809,
      "eval_steps_per_second": 18.351,
      "step": 1088
    },
    {
      "epoch": 18.0,
      "eval_loss": 10.922426223754883,
      "eval_mae": 2.1065478324890137,
      "eval_mse": 10.9224271774292,
      "eval_rmse": 3.3049094676971436,
      "eval_runtime": 0.4318,
      "eval_samples_per_second": 148.218,
      "eval_steps_per_second": 18.527,
      "step": 1152
    },
    {
      "epoch": 19.0,
      "eval_loss": 10.802040100097656,
      "eval_mae": 2.1256909370422363,
      "eval_mse": 10.80203914642334,
      "eval_rmse": 3.2866456508636475,
      "eval_runtime": 0.2822,
      "eval_samples_per_second": 226.81,
      "eval_steps_per_second": 28.351,
      "step": 1216
    },
    {
      "epoch": 20.0,
      "eval_loss": 10.668560981750488,
      "eval_mae": 2.102822780609131,
      "eval_mse": 10.668560981750488,
      "eval_rmse": 3.2662763595581055,
      "eval_runtime": 0.4297,
      "eval_samples_per_second": 148.924,
      "eval_steps_per_second": 18.616,
      "step": 1280
    },
    {
      "epoch": 21.0,
      "eval_loss": 10.928054809570312,
      "eval_mae": 2.201329231262207,
      "eval_mse": 10.928054809570312,
      "eval_rmse": 3.3057608604431152,
      "eval_runtime": 0.4133,
      "eval_samples_per_second": 154.835,
      "eval_steps_per_second": 19.354,
      "step": 1344
    },
    {
      "epoch": 22.0,
      "eval_loss": 10.920714378356934,
      "eval_mae": 2.1609740257263184,
      "eval_mse": 10.920713424682617,
      "eval_rmse": 3.30465030670166,
      "eval_runtime": 0.4362,
      "eval_samples_per_second": 146.723,
      "eval_steps_per_second": 18.34,
      "step": 1408
    },
    {
      "epoch": 23.0,
      "eval_loss": 10.914674758911133,
      "eval_mae": 2.1464970111846924,
      "eval_mse": 10.914674758911133,
      "eval_rmse": 3.303736448287964,
      "eval_runtime": 0.3154,
      "eval_samples_per_second": 202.948,
      "eval_steps_per_second": 25.369,
      "step": 1472
    },
    {
      "epoch": 23.44,
      "learning_rate": 5.3125e-06,
      "loss": 0.6489,
      "step": 1500
    },
    {
      "epoch": 24.0,
      "eval_loss": 10.826024055480957,
      "eval_mae": 2.166719436645508,
      "eval_mse": 10.826024055480957,
      "eval_rmse": 3.290292501449585,
      "eval_runtime": 0.4282,
      "eval_samples_per_second": 149.463,
      "eval_steps_per_second": 18.683,
      "step": 1536
    },
    {
      "epoch": 25.0,
      "eval_loss": 10.914568901062012,
      "eval_mae": 2.1764001846313477,
      "eval_mse": 10.914569854736328,
      "eval_rmse": 3.303720712661743,
      "eval_runtime": 0.4401,
      "eval_samples_per_second": 145.428,
      "eval_steps_per_second": 18.178,
      "step": 1600
    },
    {
      "epoch": 26.0,
      "eval_loss": 11.035606384277344,
      "eval_mae": 2.2225704193115234,
      "eval_mse": 11.035605430603027,
      "eval_rmse": 3.321988105773926,
      "eval_runtime": 0.4326,
      "eval_samples_per_second": 147.959,
      "eval_steps_per_second": 18.495,
      "step": 1664
    },
    {
      "epoch": 27.0,
      "eval_loss": 11.038973808288574,
      "eval_mae": 2.2142393589019775,
      "eval_mse": 11.038971900939941,
      "eval_rmse": 3.3224947452545166,
      "eval_runtime": 0.435,
      "eval_samples_per_second": 147.12,
      "eval_steps_per_second": 18.39,
      "step": 1728
    },
    {
      "epoch": 28.0,
      "eval_loss": 11.178277015686035,
      "eval_mae": 2.2388522624969482,
      "eval_mse": 11.178277015686035,
      "eval_rmse": 3.343393087387085,
      "eval_runtime": 0.4403,
      "eval_samples_per_second": 145.349,
      "eval_steps_per_second": 18.169,
      "step": 1792
    },
    {
      "epoch": 29.0,
      "eval_loss": 10.676009178161621,
      "eval_mae": 2.163010358810425,
      "eval_mse": 10.676008224487305,
      "eval_rmse": 3.26741623878479,
      "eval_runtime": 0.4243,
      "eval_samples_per_second": 150.831,
      "eval_steps_per_second": 18.854,
      "step": 1856
    },
    {
      "epoch": 30.0,
      "eval_loss": 10.856060028076172,
      "eval_mae": 2.1758837699890137,
      "eval_mse": 10.856060981750488,
      "eval_rmse": 3.294853687286377,
      "eval_runtime": 0.4294,
      "eval_samples_per_second": 149.044,
      "eval_steps_per_second": 18.63,
      "step": 1920
    },
    {
      "epoch": 31.0,
      "eval_loss": 10.435661315917969,
      "eval_mae": 2.1428065299987793,
      "eval_mse": 10.435661315917969,
      "eval_rmse": 3.2304275035858154,
      "eval_runtime": 0.4438,
      "eval_samples_per_second": 144.195,
      "eval_steps_per_second": 18.024,
      "step": 1984
    },
    {
      "epoch": 31.25,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.5499,
      "step": 2000
    },
    {
      "epoch": 32.0,
      "eval_loss": 10.568000793457031,
      "eval_mae": 2.1557540893554688,
      "eval_mse": 10.568000793457031,
      "eval_rmse": 3.2508461475372314,
      "eval_runtime": 0.4281,
      "eval_samples_per_second": 149.484,
      "eval_steps_per_second": 18.686,
      "step": 2048
    },
    {
      "epoch": 33.0,
      "eval_loss": 10.61816120147705,
      "eval_mae": 2.1454195976257324,
      "eval_mse": 10.618160247802734,
      "eval_rmse": 3.258551836013794,
      "eval_runtime": 0.418,
      "eval_samples_per_second": 153.1,
      "eval_steps_per_second": 19.137,
      "step": 2112
    },
    {
      "epoch": 34.0,
      "eval_loss": 10.70760726928711,
      "eval_mae": 2.185828924179077,
      "eval_mse": 10.707606315612793,
      "eval_rmse": 3.272247791290283,
      "eval_runtime": 0.4346,
      "eval_samples_per_second": 147.25,
      "eval_steps_per_second": 18.406,
      "step": 2176
    },
    {
      "epoch": 35.0,
      "eval_loss": 10.65221118927002,
      "eval_mae": 2.1475348472595215,
      "eval_mse": 10.65221118927002,
      "eval_rmse": 3.263772487640381,
      "eval_runtime": 0.4365,
      "eval_samples_per_second": 146.633,
      "eval_steps_per_second": 18.329,
      "step": 2240
    },
    {
      "epoch": 36.0,
      "eval_loss": 10.60755443572998,
      "eval_mae": 2.1597788333892822,
      "eval_mse": 10.607553482055664,
      "eval_rmse": 3.2569239139556885,
      "eval_runtime": 0.3132,
      "eval_samples_per_second": 204.312,
      "eval_steps_per_second": 25.539,
      "step": 2304
    },
    {
      "epoch": 37.0,
      "eval_loss": 10.558968544006348,
      "eval_mae": 2.1506295204162598,
      "eval_mse": 10.558967590332031,
      "eval_rmse": 3.2494564056396484,
      "eval_runtime": 0.4253,
      "eval_samples_per_second": 150.493,
      "eval_steps_per_second": 18.812,
      "step": 2368
    },
    {
      "epoch": 38.0,
      "eval_loss": 10.674619674682617,
      "eval_mae": 2.1740453243255615,
      "eval_mse": 10.674619674682617,
      "eval_rmse": 3.2672035694122314,
      "eval_runtime": 0.4355,
      "eval_samples_per_second": 146.966,
      "eval_steps_per_second": 18.371,
      "step": 2432
    },
    {
      "epoch": 39.0,
      "eval_loss": 10.524478912353516,
      "eval_mae": 2.1458582878112793,
      "eval_mse": 10.5244779586792,
      "eval_rmse": 3.244145154953003,
      "eval_runtime": 0.4374,
      "eval_samples_per_second": 146.309,
      "eval_steps_per_second": 18.289,
      "step": 2496
    },
    {
      "epoch": 39.06,
      "learning_rate": 2.1875000000000002e-06,
      "loss": 0.5012,
      "step": 2500
    },
    {
      "epoch": 40.0,
      "eval_loss": 10.667997360229492,
      "eval_mae": 2.155714273452759,
      "eval_mse": 10.667997360229492,
      "eval_rmse": 3.2661900520324707,
      "eval_runtime": 0.3418,
      "eval_samples_per_second": 187.219,
      "eval_steps_per_second": 23.402,
      "step": 2560
    },
    {
      "epoch": 41.0,
      "eval_loss": 10.641304016113281,
      "eval_mae": 2.174771547317505,
      "eval_mse": 10.641304016113281,
      "eval_rmse": 3.262101173400879,
      "eval_runtime": 0.4419,
      "eval_samples_per_second": 144.834,
      "eval_steps_per_second": 18.104,
      "step": 2624
    },
    {
      "epoch": 42.0,
      "eval_loss": 10.72380542755127,
      "eval_mae": 2.2047784328460693,
      "eval_mse": 10.723804473876953,
      "eval_rmse": 3.274722099304199,
      "eval_runtime": 0.4025,
      "eval_samples_per_second": 158.999,
      "eval_steps_per_second": 19.875,
      "step": 2688
    },
    {
      "epoch": 43.0,
      "eval_loss": 10.794100761413574,
      "eval_mae": 2.212890863418579,
      "eval_mse": 10.79410171508789,
      "eval_rmse": 3.285437822341919,
      "eval_runtime": 0.4371,
      "eval_samples_per_second": 146.435,
      "eval_steps_per_second": 18.304,
      "step": 2752
    },
    {
      "epoch": 44.0,
      "eval_loss": 10.679245948791504,
      "eval_mae": 2.199676513671875,
      "eval_mse": 10.679245948791504,
      "eval_rmse": 3.267911672592163,
      "eval_runtime": 0.4079,
      "eval_samples_per_second": 156.894,
      "eval_steps_per_second": 19.612,
      "step": 2816
    },
    {
      "epoch": 45.0,
      "eval_loss": 10.524163246154785,
      "eval_mae": 2.1674587726593018,
      "eval_mse": 10.524163246154785,
      "eval_rmse": 3.2440967559814453,
      "eval_runtime": 0.2984,
      "eval_samples_per_second": 214.505,
      "eval_steps_per_second": 26.813,
      "step": 2880
    },
    {
      "epoch": 46.0,
      "eval_loss": 10.532914161682129,
      "eval_mae": 2.177356481552124,
      "eval_mse": 10.532913208007812,
      "eval_rmse": 3.2454450130462646,
      "eval_runtime": 0.4463,
      "eval_samples_per_second": 143.398,
      "eval_steps_per_second": 17.925,
      "step": 2944
    },
    {
      "epoch": 46.88,
      "learning_rate": 6.25e-07,
      "loss": 0.471,
      "step": 3000
    },
    {
      "epoch": 47.0,
      "eval_loss": 10.552495002746582,
      "eval_mae": 2.182786464691162,
      "eval_mse": 10.552494049072266,
      "eval_rmse": 3.248460292816162,
      "eval_runtime": 0.3828,
      "eval_samples_per_second": 167.191,
      "eval_steps_per_second": 20.899,
      "step": 3008
    },
    {
      "epoch": 48.0,
      "eval_loss": 10.577668190002441,
      "eval_mae": 2.177499294281006,
      "eval_mse": 10.577667236328125,
      "eval_rmse": 3.2523326873779297,
      "eval_runtime": 0.4436,
      "eval_samples_per_second": 144.276,
      "eval_steps_per_second": 18.035,
      "step": 3072
    },
    {
      "epoch": 49.0,
      "eval_loss": 10.599947929382324,
      "eval_mae": 2.184239625930786,
      "eval_mse": 10.59994888305664,
      "eval_rmse": 3.255756378173828,
      "eval_runtime": 0.2975,
      "eval_samples_per_second": 215.1,
      "eval_steps_per_second": 26.888,
      "step": 3136
    },
    {
      "epoch": 50.0,
      "eval_loss": 10.600202560424805,
      "eval_mae": 2.1849870681762695,
      "eval_mse": 10.600202560424805,
      "eval_rmse": 3.2557952404022217,
      "eval_runtime": 0.4398,
      "eval_samples_per_second": 145.517,
      "eval_steps_per_second": 18.19,
      "step": 3200
    }
  ],
  "max_steps": 3200,
  "num_train_epochs": 50,
  "total_flos": 1692195608947200.0,
  "trial_name": null,
  "trial_params": null
}