{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9912023460410557,
  "eval_steps": 10,
  "global_step": 340,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05865102639296188,
      "eval_loss": 0.38869303464889526,
      "eval_runtime": 33.6966,
      "eval_samples_per_second": 22.465,
      "eval_steps_per_second": 5.639,
      "step": 10
    },
    {
      "epoch": 0.11730205278592376,
      "grad_norm": 1.1477874212327048,
      "learning_rate": 3.92156862745098e-06,
      "loss": 0.4096,
      "step": 20
    },
    {
      "epoch": 0.11730205278592376,
      "eval_loss": 0.33711880445480347,
      "eval_runtime": 32.8785,
      "eval_samples_per_second": 23.024,
      "eval_steps_per_second": 5.779,
      "step": 20
    },
    {
      "epoch": 0.17595307917888564,
      "eval_loss": 0.2933129668235779,
      "eval_runtime": 32.8713,
      "eval_samples_per_second": 23.029,
      "eval_steps_per_second": 5.78,
      "step": 30
    },
    {
      "epoch": 0.23460410557184752,
      "grad_norm": 1.121589060878037,
      "learning_rate": 7.84313725490196e-06,
      "loss": 0.3048,
      "step": 40
    },
    {
      "epoch": 0.23460410557184752,
      "eval_loss": 0.25960347056388855,
      "eval_runtime": 32.9112,
      "eval_samples_per_second": 23.001,
      "eval_steps_per_second": 5.773,
      "step": 40
    },
    {
      "epoch": 0.2932551319648094,
      "eval_loss": 0.24025067687034607,
      "eval_runtime": 32.9388,
      "eval_samples_per_second": 22.982,
      "eval_steps_per_second": 5.768,
      "step": 50
    },
    {
      "epoch": 0.3519061583577713,
      "grad_norm": 1.0677324544458529,
      "learning_rate": 9.990516643685222e-06,
      "loss": 0.2471,
      "step": 60
    },
    {
      "epoch": 0.3519061583577713,
      "eval_loss": 0.228533536195755,
      "eval_runtime": 32.9199,
      "eval_samples_per_second": 22.995,
      "eval_steps_per_second": 5.772,
      "step": 60
    },
    {
      "epoch": 0.41055718475073316,
      "eval_loss": 0.21884050965309143,
      "eval_runtime": 32.9261,
      "eval_samples_per_second": 22.991,
      "eval_steps_per_second": 5.77,
      "step": 70
    },
    {
      "epoch": 0.46920821114369504,
      "grad_norm": 0.8221117546113363,
      "learning_rate": 9.901828808578846e-06,
      "loss": 0.2281,
      "step": 80
    },
    {
      "epoch": 0.46920821114369504,
      "eval_loss": 0.21087835729122162,
      "eval_runtime": 32.9118,
      "eval_samples_per_second": 23.001,
      "eval_steps_per_second": 5.773,
      "step": 80
    },
    {
      "epoch": 0.5278592375366569,
      "eval_loss": 0.2049574851989746,
      "eval_runtime": 33.0853,
      "eval_samples_per_second": 22.88,
      "eval_steps_per_second": 5.743,
      "step": 90
    },
    {
      "epoch": 0.5865102639296188,
      "grad_norm": 0.7863445026416022,
      "learning_rate": 9.721431493385322e-06,
      "loss": 0.2073,
      "step": 100
    },
    {
      "epoch": 0.5865102639296188,
      "eval_loss": 0.20104646682739258,
      "eval_runtime": 33.0368,
      "eval_samples_per_second": 22.914,
      "eval_steps_per_second": 5.751,
      "step": 100
    },
    {
      "epoch": 0.6451612903225806,
      "eval_loss": 0.19683966040611267,
      "eval_runtime": 32.895,
      "eval_samples_per_second": 23.013,
      "eval_steps_per_second": 5.776,
      "step": 110
    },
    {
      "epoch": 0.7038123167155426,
      "grad_norm": 0.7460954708103601,
      "learning_rate": 9.452699794345583e-06,
      "loss": 0.1911,
      "step": 120
    },
    {
      "epoch": 0.7038123167155426,
      "eval_loss": 0.1945473700761795,
      "eval_runtime": 32.8944,
      "eval_samples_per_second": 23.013,
      "eval_steps_per_second": 5.776,
      "step": 120
    },
    {
      "epoch": 0.7624633431085044,
      "eval_loss": 0.1912163645029068,
      "eval_runtime": 32.9495,
      "eval_samples_per_second": 22.975,
      "eval_steps_per_second": 5.766,
      "step": 130
    },
    {
      "epoch": 0.8211143695014663,
      "grad_norm": 0.7504426793167469,
      "learning_rate": 9.100661476680379e-06,
      "loss": 0.1876,
      "step": 140
    },
    {
      "epoch": 0.8211143695014663,
      "eval_loss": 0.18776217103004456,
      "eval_runtime": 32.9203,
      "eval_samples_per_second": 22.995,
      "eval_steps_per_second": 5.772,
      "step": 140
    },
    {
      "epoch": 0.8797653958944281,
      "eval_loss": 0.18520714342594147,
      "eval_runtime": 32.8973,
      "eval_samples_per_second": 23.011,
      "eval_steps_per_second": 5.776,
      "step": 150
    },
    {
      "epoch": 0.9384164222873901,
      "grad_norm": 0.7748459339656144,
      "learning_rate": 8.671902908935942e-06,
      "loss": 0.1887,
      "step": 160
    },
    {
      "epoch": 0.9384164222873901,
      "eval_loss": 0.18254177272319794,
      "eval_runtime": 32.8779,
      "eval_samples_per_second": 23.025,
      "eval_steps_per_second": 5.779,
      "step": 160
    },
    {
      "epoch": 0.9970674486803519,
      "eval_loss": 0.18051140010356903,
      "eval_runtime": 32.9923,
      "eval_samples_per_second": 22.945,
      "eval_steps_per_second": 5.759,
      "step": 170
    },
    {
      "epoch": 1.0527859237536656,
      "grad_norm": 0.9218927864042982,
      "learning_rate": 8.174445837049614e-06,
      "loss": 0.1553,
      "step": 180
    },
    {
      "epoch": 1.0527859237536656,
      "eval_loss": 0.18640676140785217,
      "eval_runtime": 32.9183,
      "eval_samples_per_second": 22.996,
      "eval_steps_per_second": 5.772,
      "step": 180
    },
    {
      "epoch": 1.1114369501466275,
      "eval_loss": 0.18077336251735687,
      "eval_runtime": 32.8676,
      "eval_samples_per_second": 23.032,
      "eval_steps_per_second": 5.781,
      "step": 190
    },
    {
      "epoch": 1.1700879765395895,
      "grad_norm": 0.9109052804191333,
      "learning_rate": 7.617597303598754e-06,
      "loss": 0.1332,
      "step": 200
    },
    {
      "epoch": 1.1700879765395895,
      "eval_loss": 0.1823471635580063,
      "eval_runtime": 32.9625,
      "eval_samples_per_second": 22.965,
      "eval_steps_per_second": 5.764,
      "step": 200
    },
    {
      "epoch": 1.2287390029325513,
      "eval_loss": 0.17943565547466278,
      "eval_runtime": 32.9683,
      "eval_samples_per_second": 22.961,
      "eval_steps_per_second": 5.763,
      "step": 210
    },
    {
      "epoch": 1.2873900293255132,
      "grad_norm": 0.8287150136550924,
      "learning_rate": 7.011775520129363e-06,
      "loss": 0.1349,
      "step": 220
    },
    {
      "epoch": 1.2873900293255132,
      "eval_loss": 0.17819999158382416,
      "eval_runtime": 32.9652,
      "eval_samples_per_second": 22.964,
      "eval_steps_per_second": 5.764,
      "step": 220
    },
    {
      "epoch": 1.3460410557184752,
      "eval_loss": 0.1771620512008667,
      "eval_runtime": 32.8691,
      "eval_samples_per_second": 23.031,
      "eval_steps_per_second": 5.781,
      "step": 230
    },
    {
      "epoch": 1.404692082111437,
      "grad_norm": 0.7173372889400553,
      "learning_rate": 6.368314950360416e-06,
      "loss": 0.1333,
      "step": 240
    },
    {
      "epoch": 1.404692082111437,
      "eval_loss": 0.17452633380889893,
      "eval_runtime": 32.8914,
      "eval_samples_per_second": 23.015,
      "eval_steps_per_second": 5.777,
      "step": 240
    },
    {
      "epoch": 1.4633431085043989,
      "eval_loss": 0.17504557967185974,
      "eval_runtime": 32.8301,
      "eval_samples_per_second": 23.058,
      "eval_steps_per_second": 5.787,
      "step": 250
    },
    {
      "epoch": 1.5219941348973607,
      "grad_norm": 0.874094982171954,
      "learning_rate": 5.699254251008524e-06,
      "loss": 0.1338,
      "step": 260
    },
    {
      "epoch": 1.5219941348973607,
      "eval_loss": 0.17338429391384125,
      "eval_runtime": 32.8983,
      "eval_samples_per_second": 23.01,
      "eval_steps_per_second": 5.775,
      "step": 260
    },
    {
      "epoch": 1.5806451612903225,
      "eval_loss": 0.171478271484375,
      "eval_runtime": 32.8244,
      "eval_samples_per_second": 23.062,
      "eval_steps_per_second": 5.788,
      "step": 270
    },
    {
      "epoch": 1.6392961876832843,
      "grad_norm": 0.7979095239427625,
      "learning_rate": 5.017111037698477e-06,
      "loss": 0.1267,
      "step": 280
    },
    {
      "epoch": 1.6392961876832843,
      "eval_loss": 0.17220577597618103,
      "eval_runtime": 32.7725,
      "eval_samples_per_second": 23.099,
      "eval_steps_per_second": 5.798,
      "step": 280
    },
    {
      "epoch": 1.6979472140762464,
      "eval_loss": 0.16855686902999878,
      "eval_runtime": 32.8059,
      "eval_samples_per_second": 23.075,
      "eval_steps_per_second": 5.792,
      "step": 290
    },
    {
      "epoch": 1.7565982404692082,
      "grad_norm": 0.705233520985163,
      "learning_rate": 4.334647689917734e-06,
      "loss": 0.1317,
      "step": 300
    },
    {
      "epoch": 1.7565982404692082,
      "eval_loss": 0.1680660992860794,
      "eval_runtime": 32.9544,
      "eval_samples_per_second": 22.971,
      "eval_steps_per_second": 5.766,
      "step": 300
    },
    {
      "epoch": 1.8152492668621703,
      "eval_loss": 0.16704507172107697,
      "eval_runtime": 32.8838,
      "eval_samples_per_second": 23.02,
      "eval_steps_per_second": 5.778,
      "step": 310
    },
    {
      "epoch": 1.873900293255132,
      "grad_norm": 0.7535701160217406,
      "learning_rate": 3.6646325766256423e-06,
      "loss": 0.1251,
      "step": 320
    },
    {
      "epoch": 1.873900293255132,
      "eval_loss": 0.16622412204742432,
      "eval_runtime": 32.8893,
      "eval_samples_per_second": 23.017,
      "eval_steps_per_second": 5.777,
      "step": 320
    },
    {
      "epoch": 1.932551319648094,
      "eval_loss": 0.16477644443511963,
      "eval_runtime": 33.006,
      "eval_samples_per_second": 22.935,
      "eval_steps_per_second": 5.757,
      "step": 330
    },
    {
      "epoch": 1.9912023460410557,
      "grad_norm": 0.7373647805377234,
      "learning_rate": 3.019601169804216e-06,
      "loss": 0.1186,
      "step": 340
    },
    {
      "epoch": 1.9912023460410557,
      "eval_loss": 0.1639869511127472,
      "eval_runtime": 32.9932,
      "eval_samples_per_second": 22.944,
      "eval_steps_per_second": 5.759,
      "step": 340
    }
  ],
  "logging_steps": 20,
  "max_steps": 510,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 31189214167040.0,
  "train_batch_size": 5,
  "trial_name": null,
  "trial_params": null
}