{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.648967551622419,
  "eval_steps": 50,
  "global_step": 480,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11799410029498525,
      "grad_norm": 0.20195358991622925,
      "learning_rate": 0.0003,
      "loss": 1.9738,
      "step": 10
    },
    {
      "epoch": 0.2359882005899705,
      "grad_norm": 0.1426803171634674,
      "learning_rate": 0.0002963855421686747,
      "loss": 1.5063,
      "step": 20
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 0.15137845277786255,
      "learning_rate": 0.0002927710843373494,
      "loss": 1.3522,
      "step": 30
    },
    {
      "epoch": 0.471976401179941,
      "grad_norm": 0.14357119798660278,
      "learning_rate": 0.0002891566265060241,
      "loss": 1.2434,
      "step": 40
    },
    {
      "epoch": 0.5899705014749262,
      "grad_norm": 0.13860304653644562,
      "learning_rate": 0.00028554216867469873,
      "loss": 1.1816,
      "step": 50
    },
    {
      "epoch": 0.5899705014749262,
      "eval_loss": 1.159853458404541,
      "eval_runtime": 18.5086,
      "eval_samples_per_second": 8.861,
      "eval_steps_per_second": 0.756,
      "step": 50
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 0.13697050511837006,
      "learning_rate": 0.0002819277108433735,
      "loss": 1.1465,
      "step": 60
    },
    {
      "epoch": 0.8259587020648967,
      "grad_norm": 0.12234006822109222,
      "learning_rate": 0.0002783132530120482,
      "loss": 1.1006,
      "step": 70
    },
    {
      "epoch": 0.943952802359882,
      "grad_norm": 0.1310320794582367,
      "learning_rate": 0.00027469879518072284,
      "loss": 1.0819,
      "step": 80
    },
    {
      "epoch": 1.0589970501474926,
      "grad_norm": 0.12331829220056534,
      "learning_rate": 0.0002710843373493976,
      "loss": 1.044,
      "step": 90
    },
    {
      "epoch": 1.176991150442478,
      "grad_norm": 0.11900211870670319,
      "learning_rate": 0.00026746987951807225,
      "loss": 1.0244,
      "step": 100
    },
    {
      "epoch": 1.176991150442478,
      "eval_loss": 1.0301724672317505,
      "eval_runtime": 18.427,
      "eval_samples_per_second": 8.9,
      "eval_steps_per_second": 0.76,
      "step": 100
    },
    {
      "epoch": 1.294985250737463,
      "grad_norm": 0.13372938334941864,
      "learning_rate": 0.00026385542168674695,
      "loss": 1.0084,
      "step": 110
    },
    {
      "epoch": 1.4129793510324484,
      "grad_norm": 0.12052427977323532,
      "learning_rate": 0.00026024096385542165,
      "loss": 0.9994,
      "step": 120
    },
    {
      "epoch": 1.5309734513274336,
      "grad_norm": 0.11335684359073639,
      "learning_rate": 0.00025662650602409636,
      "loss": 0.9798,
      "step": 130
    },
    {
      "epoch": 1.648967551622419,
      "grad_norm": 0.13653819262981415,
      "learning_rate": 0.00025301204819277106,
      "loss": 0.9601,
      "step": 140
    },
    {
      "epoch": 1.7669616519174043,
      "grad_norm": 0.11394950747489929,
      "learning_rate": 0.00024939759036144576,
      "loss": 0.9586,
      "step": 150
    },
    {
      "epoch": 1.7669616519174043,
      "eval_loss": 0.9602091908454895,
      "eval_runtime": 18.4269,
      "eval_samples_per_second": 8.9,
      "eval_steps_per_second": 0.76,
      "step": 150
    },
    {
      "epoch": 1.8849557522123894,
      "grad_norm": 0.1154383197426796,
      "learning_rate": 0.00024578313253012046,
      "loss": 0.95,
      "step": 160
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.12450100481510162,
      "learning_rate": 0.00024216867469879517,
      "loss": 0.9272,
      "step": 170
    },
    {
      "epoch": 2.117994100294985,
      "grad_norm": 0.10410638153553009,
      "learning_rate": 0.00023855421686746987,
      "loss": 0.9071,
      "step": 180
    },
    {
      "epoch": 2.2359882005899703,
      "grad_norm": 0.12171204388141632,
      "learning_rate": 0.00023493975903614455,
      "loss": 0.9032,
      "step": 190
    },
    {
      "epoch": 2.353982300884956,
      "grad_norm": 0.12321081757545471,
      "learning_rate": 0.00023132530120481928,
      "loss": 0.8935,
      "step": 200
    },
    {
      "epoch": 2.353982300884956,
      "eval_loss": 0.9177303910255432,
      "eval_runtime": 18.4239,
      "eval_samples_per_second": 8.902,
      "eval_steps_per_second": 0.76,
      "step": 200
    },
    {
      "epoch": 2.471976401179941,
      "grad_norm": 0.10513285547494888,
      "learning_rate": 0.00022771084337349395,
      "loss": 0.8834,
      "step": 210
    },
    {
      "epoch": 2.589970501474926,
      "grad_norm": 0.12400174885988235,
      "learning_rate": 0.00022409638554216866,
      "loss": 0.8927,
      "step": 220
    },
    {
      "epoch": 2.7079646017699117,
      "grad_norm": 0.12554600834846497,
      "learning_rate": 0.00022048192771084336,
      "loss": 0.8787,
      "step": 230
    },
    {
      "epoch": 2.825958702064897,
      "grad_norm": 0.11129195988178253,
      "learning_rate": 0.00021686746987951806,
      "loss": 0.8715,
      "step": 240
    },
    {
      "epoch": 2.943952802359882,
      "grad_norm": 0.09794709086418152,
      "learning_rate": 0.00021325301204819274,
      "loss": 0.8739,
      "step": 250
    },
    {
      "epoch": 2.943952802359882,
      "eval_loss": 0.8860040307044983,
      "eval_runtime": 18.4949,
      "eval_samples_per_second": 8.867,
      "eval_steps_per_second": 0.757,
      "step": 250
    },
    {
      "epoch": 3.0589970501474926,
      "grad_norm": 0.10913146287202835,
      "learning_rate": 0.00020963855421686747,
      "loss": 0.8555,
      "step": 260
    },
    {
      "epoch": 3.1769911504424777,
      "grad_norm": 0.10241620987653732,
      "learning_rate": 0.00020602409638554214,
      "loss": 0.8415,
      "step": 270
    },
    {
      "epoch": 3.2949852507374633,
      "grad_norm": 0.10102570056915283,
      "learning_rate": 0.00020240963855421685,
      "loss": 0.8389,
      "step": 280
    },
    {
      "epoch": 3.4129793510324484,
      "grad_norm": 0.11023970693349838,
      "learning_rate": 0.00019879518072289155,
      "loss": 0.8326,
      "step": 290
    },
    {
      "epoch": 3.5309734513274336,
      "grad_norm": 0.11006706953048706,
      "learning_rate": 0.00019518072289156625,
      "loss": 0.8233,
      "step": 300
    },
    {
      "epoch": 3.5309734513274336,
      "eval_loss": 0.8637099862098694,
      "eval_runtime": 18.4424,
      "eval_samples_per_second": 8.893,
      "eval_steps_per_second": 0.759,
      "step": 300
    },
    {
      "epoch": 3.6489675516224187,
      "grad_norm": 0.1085994690656662,
      "learning_rate": 0.00019156626506024093,
      "loss": 0.8246,
      "step": 310
    },
    {
      "epoch": 3.7669616519174043,
      "grad_norm": 0.10803534090518951,
      "learning_rate": 0.00018795180722891566,
      "loss": 0.826,
      "step": 320
    },
    {
      "epoch": 3.8849557522123894,
      "grad_norm": 0.1013474091887474,
      "learning_rate": 0.00018433734939759034,
      "loss": 0.8286,
      "step": 330
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.11949065327644348,
      "learning_rate": 0.00018072289156626507,
      "loss": 0.822,
      "step": 340
    },
    {
      "epoch": 4.117994100294985,
      "grad_norm": 0.10211551189422607,
      "learning_rate": 0.00017710843373493974,
      "loss": 0.7956,
      "step": 350
    },
    {
      "epoch": 4.117994100294985,
      "eval_loss": 0.8463084697723389,
      "eval_runtime": 18.4912,
      "eval_samples_per_second": 8.869,
      "eval_steps_per_second": 0.757,
      "step": 350
    },
    {
      "epoch": 4.23598820058997,
      "grad_norm": 0.09929126501083374,
      "learning_rate": 0.00017349397590361444,
      "loss": 0.7919,
      "step": 360
    },
    {
      "epoch": 4.353982300884955,
      "grad_norm": 0.10217483341693878,
      "learning_rate": 0.00016987951807228915,
      "loss": 0.795,
      "step": 370
    },
    {
      "epoch": 4.4719764011799406,
      "grad_norm": 0.10732585191726685,
      "learning_rate": 0.00016626506024096385,
      "loss": 0.7951,
      "step": 380
    },
    {
      "epoch": 4.589970501474927,
      "grad_norm": 0.09474306553602219,
      "learning_rate": 0.00016265060240963853,
      "loss": 0.7932,
      "step": 390
    },
    {
      "epoch": 4.707964601769912,
      "grad_norm": 0.10201520472764969,
      "learning_rate": 0.00015903614457831326,
      "loss": 0.7859,
      "step": 400
    },
    {
      "epoch": 4.707964601769912,
      "eval_loss": 0.8334778547286987,
      "eval_runtime": 18.4535,
      "eval_samples_per_second": 8.887,
      "eval_steps_per_second": 0.759,
      "step": 400
    },
    {
      "epoch": 4.825958702064897,
      "grad_norm": 0.09956536442041397,
      "learning_rate": 0.00015542168674698793,
      "loss": 0.7908,
      "step": 410
    },
    {
      "epoch": 4.943952802359882,
      "grad_norm": 0.10082168132066727,
      "learning_rate": 0.00015180722891566264,
      "loss": 0.783,
      "step": 420
    },
    {
      "epoch": 5.058997050147493,
      "grad_norm": 0.10280101001262665,
      "learning_rate": 0.00014819277108433734,
      "loss": 0.7728,
      "step": 430
    },
    {
      "epoch": 5.176991150442478,
      "grad_norm": 0.09640956670045853,
      "learning_rate": 0.00014457831325301204,
      "loss": 0.7627,
      "step": 440
    },
    {
      "epoch": 5.294985250737463,
      "grad_norm": 0.09960771352052689,
      "learning_rate": 0.00014096385542168674,
      "loss": 0.7631,
      "step": 450
    },
    {
      "epoch": 5.294985250737463,
      "eval_loss": 0.8229261040687561,
      "eval_runtime": 18.4466,
      "eval_samples_per_second": 8.891,
      "eval_steps_per_second": 0.759,
      "step": 450
    },
    {
      "epoch": 5.412979351032448,
      "grad_norm": 0.10458113998174667,
      "learning_rate": 0.00013734939759036142,
      "loss": 0.7589,
      "step": 460
    },
    {
      "epoch": 5.530973451327434,
      "grad_norm": 0.10363869369029999,
      "learning_rate": 0.00013373493975903612,
      "loss": 0.7628,
      "step": 470
    },
    {
      "epoch": 5.648967551622419,
      "grad_norm": 0.09949172288179398,
      "learning_rate": 0.00013012048192771083,
      "loss": 0.7581,
      "step": 480
    }
  ],
  "logging_steps": 10,
  "max_steps": 840,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 120,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.077553394543231e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}