{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.245136186770428,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1556420233463035,
      "grad_norm": 5.363790512084961,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 2.5426,
      "step": 10
    },
    {
      "epoch": 0.311284046692607,
      "grad_norm": 5.297606468200684,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.4551,
      "step": 20
    },
    {
      "epoch": 0.4669260700389105,
      "grad_norm": 1.6734049320220947,
      "learning_rate": 9.999999999999999e-06,
      "loss": 1.5765,
      "step": 30
    },
    {
      "epoch": 0.622568093385214,
      "grad_norm": 0.5996205806732178,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.9482,
      "step": 40
    },
    {
      "epoch": 0.7782101167315175,
      "grad_norm": 0.5326632857322693,
      "learning_rate": 1.4994303528285384e-05,
      "loss": 0.7767,
      "step": 50
    },
    {
      "epoch": 0.7782101167315175,
      "eval_loss": 0.7420370578765869,
      "eval_runtime": 75.0351,
      "eval_samples_per_second": 3.052,
      "eval_steps_per_second": 1.533,
      "step": 50
    },
    {
      "epoch": 0.933852140077821,
      "grad_norm": 0.47296807169914246,
      "learning_rate": 1.4948783661087592e-05,
      "loss": 0.6917,
      "step": 60
    },
    {
      "epoch": 1.0894941634241244,
      "grad_norm": 0.5496929883956909,
      "learning_rate": 1.485802041113141e-05,
      "loss": 0.5968,
      "step": 70
    },
    {
      "epoch": 1.245136186770428,
      "grad_norm": 0.5656551122665405,
      "learning_rate": 1.4722565067948796e-05,
      "loss": 0.5096,
      "step": 80
    },
    {
      "epoch": 1.4007782101167314,
      "grad_norm": 0.7151289582252502,
      "learning_rate": 1.454324037767081e-05,
      "loss": 0.5053,
      "step": 90
    },
    {
      "epoch": 1.556420233463035,
      "grad_norm": 0.7926196455955505,
      "learning_rate": 1.4321135545726069e-05,
      "loss": 0.4193,
      "step": 100
    },
    {
      "epoch": 1.556420233463035,
      "eval_loss": 0.4160374701023102,
      "eval_runtime": 75.0144,
      "eval_samples_per_second": 3.053,
      "eval_steps_per_second": 1.533,
      "step": 100
    },
    {
      "epoch": 1.7120622568093387,
      "grad_norm": 0.7219254970550537,
      "learning_rate": 1.4057599621084365e-05,
      "loss": 0.3695,
      "step": 110
    },
    {
      "epoch": 1.867704280155642,
      "grad_norm": 0.7828359007835388,
      "learning_rate": 1.3754233302229055e-05,
      "loss": 0.3554,
      "step": 120
    },
    {
      "epoch": 2.0233463035019454,
      "grad_norm": 0.6474707126617432,
      "learning_rate": 1.3412879214628194e-05,
      "loss": 0.3115,
      "step": 130
    },
    {
      "epoch": 2.178988326848249,
      "grad_norm": 0.8858464360237122,
      "learning_rate": 1.3035610718758362e-05,
      "loss": 0.2754,
      "step": 140
    },
    {
      "epoch": 2.3346303501945527,
      "grad_norm": 0.6484001278877258,
      "learning_rate": 1.2624719316660416e-05,
      "loss": 0.2815,
      "step": 150
    },
    {
      "epoch": 2.3346303501945527,
      "eval_loss": 0.3077065050601959,
      "eval_runtime": 74.9901,
      "eval_samples_per_second": 3.054,
      "eval_steps_per_second": 1.534,
      "step": 150
    },
    {
      "epoch": 2.490272373540856,
      "grad_norm": 0.9611061811447144,
      "learning_rate": 1.218270073351891e-05,
      "loss": 0.2641,
      "step": 160
    },
    {
      "epoch": 2.6459143968871595,
      "grad_norm": 1.0954933166503906,
      "learning_rate": 1.1712239758804626e-05,
      "loss": 0.2675,
      "step": 170
    },
    {
      "epoch": 2.801556420233463,
      "grad_norm": 0.7623236775398254,
      "learning_rate": 1.1216193939054056e-05,
      "loss": 0.26,
      "step": 180
    },
    {
      "epoch": 2.9571984435797667,
      "grad_norm": 0.8693030476570129,
      "learning_rate": 1.0697576221334781e-05,
      "loss": 0.2494,
      "step": 190
    },
    {
      "epoch": 3.11284046692607,
      "grad_norm": 0.9107272028923035,
      "learning_rate": 1.0159536652819018e-05,
      "loss": 0.2131,
      "step": 200
    },
    {
      "epoch": 3.11284046692607,
      "eval_loss": 0.26981863379478455,
      "eval_runtime": 75.23,
      "eval_samples_per_second": 3.044,
      "eval_steps_per_second": 1.529,
      "step": 200
    },
    {
      "epoch": 3.2684824902723735,
      "grad_norm": 0.7745103240013123,
      "learning_rate": 9.605343247620892e-06,
      "loss": 0.2036,
      "step": 210
    },
    {
      "epoch": 3.424124513618677,
      "grad_norm": 0.9593366980552673,
      "learning_rate": 9.038362137110888e-06,
      "loss": 0.2013,
      "step": 220
    },
    {
      "epoch": 3.5797665369649807,
      "grad_norm": 1.2859652042388916,
      "learning_rate": 8.462037124273056e-06,
      "loss": 0.195,
      "step": 230
    },
    {
      "epoch": 3.735408560311284,
      "grad_norm": 1.0107340812683105,
      "learning_rate": 7.879868766290346e-06,
      "loss": 0.1884,
      "step": 240
    },
    {
      "epoch": 3.8910505836575875,
      "grad_norm": 0.8121142387390137,
      "learning_rate": 7.2953931124089755e-06,
      "loss": 0.2117,
      "step": 250
    },
    {
      "epoch": 3.8910505836575875,
      "eval_loss": 0.25344181060791016,
      "eval_runtime": 75.1186,
      "eval_samples_per_second": 3.049,
      "eval_steps_per_second": 1.531,
      "step": 250
    },
    {
      "epoch": 4.046692607003891,
      "grad_norm": 0.7917193174362183,
      "learning_rate": 6.71216022622653e-06,
      "loss": 0.2004,
      "step": 260
    },
    {
      "epoch": 4.202334630350195,
      "grad_norm": 1.1348683834075928,
      "learning_rate": 6.133712622857887e-06,
      "loss": 0.1652,
      "step": 270
    },
    {
      "epoch": 4.357976653696498,
      "grad_norm": 1.1503227949142456,
      "learning_rate": 5.563563751950078e-06,
      "loss": 0.1647,
      "step": 280
    },
    {
      "epoch": 4.5136186770428015,
      "grad_norm": 0.8282884359359741,
      "learning_rate": 5.005176657238754e-06,
      "loss": 0.1613,
      "step": 290
    },
    {
      "epoch": 4.669260700389105,
      "grad_norm": 1.0249297618865967,
      "learning_rate": 4.461942942266561e-06,
      "loss": 0.1512,
      "step": 300
    },
    {
      "epoch": 4.669260700389105,
      "eval_loss": 0.2489164173603058,
      "eval_runtime": 75.279,
      "eval_samples_per_second": 3.042,
      "eval_steps_per_second": 1.528,
      "step": 300
    },
    {
      "epoch": 4.824902723735408,
      "grad_norm": 0.966607391834259,
      "learning_rate": 3.937162170024189e-06,
      "loss": 0.1582,
      "step": 310
    },
    {
      "epoch": 4.980544747081712,
      "grad_norm": 0.8376232385635376,
      "learning_rate": 3.4340218216391697e-06,
      "loss": 0.1485,
      "step": 320
    },
    {
      "epoch": 5.136186770428016,
      "grad_norm": 0.9548529386520386,
      "learning_rate": 2.955577935841975e-06,
      "loss": 0.1427,
      "step": 330
    },
    {
      "epoch": 5.291828793774319,
      "grad_norm": 0.9749653935432434,
      "learning_rate": 2.5047365468038768e-06,
      "loss": 0.1335,
      "step": 340
    },
    {
      "epoch": 5.447470817120623,
      "grad_norm": 1.2298961877822876,
      "learning_rate": 2.0842360330918544e-06,
      "loss": 0.1235,
      "step": 350
    },
    {
      "epoch": 5.447470817120623,
      "eval_loss": 0.2625938951969147,
      "eval_runtime": 74.8495,
      "eval_samples_per_second": 3.059,
      "eval_steps_per_second": 1.536,
      "step": 350
    },
    {
      "epoch": 5.622568093385214,
      "grad_norm": 0.8807490468025208,
      "learning_rate": 1.6966304849517184e-06,
      "loss": 0.1272,
      "step": 360
    },
    {
      "epoch": 5.778210116731517,
      "grad_norm": 1.1307696104049683,
      "learning_rate": 1.3442741909454295e-06,
      "loss": 0.1251,
      "step": 370
    },
    {
      "epoch": 5.933852140077821,
      "grad_norm": 0.9986845254898071,
      "learning_rate": 1.0293073381696139e-06,
      "loss": 0.1363,
      "step": 380
    },
    {
      "epoch": 6.089494163424124,
      "grad_norm": 0.9564828872680664,
      "learning_rate": 7.536430129112046e-07,
      "loss": 0.1134,
      "step": 390
    },
    {
      "epoch": 6.245136186770428,
      "grad_norm": 1.1241580247879028,
      "learning_rate": 5.189555806972418e-07,
      "loss": 0.126,
      "step": 400
    },
    {
      "epoch": 6.245136186770428,
      "eval_loss": 0.26281753182411194,
      "eval_runtime": 56.6473,
      "eval_samples_per_second": 4.043,
      "eval_steps_per_second": 2.03,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 448,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.877988944368894e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}