{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 269,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0037174721189591076,
      "grad_norm": 14.262325286865234,
      "learning_rate": 0.0,
      "loss": 3.044,
      "step": 1
    },
    {
      "epoch": 0.01858736059479554,
      "grad_norm": 13.0241060256958,
      "learning_rate": 2.962962962962963e-06,
      "loss": 3.0801,
      "step": 5
    },
    {
      "epoch": 0.03717472118959108,
      "grad_norm": 6.920816898345947,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.8515,
      "step": 10
    },
    {
      "epoch": 0.055762081784386616,
      "grad_norm": 4.249760627746582,
      "learning_rate": 1.037037037037037e-05,
      "loss": 2.469,
      "step": 15
    },
    {
      "epoch": 0.07434944237918216,
      "grad_norm": 5.996034145355225,
      "learning_rate": 1.4074074074074075e-05,
      "loss": 2.2633,
      "step": 20
    },
    {
      "epoch": 0.09293680297397769,
      "grad_norm": 8.92640495300293,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 2.152,
      "step": 25
    },
    {
      "epoch": 0.11152416356877323,
      "grad_norm": 8.087935447692871,
      "learning_rate": 1.9996629653035128e-05,
      "loss": 2.0381,
      "step": 30
    },
    {
      "epoch": 0.13011152416356878,
      "grad_norm": 6.582911968231201,
      "learning_rate": 1.995873933559535e-05,
      "loss": 1.9322,
      "step": 35
    },
    {
      "epoch": 0.14869888475836432,
      "grad_norm": 5.658934593200684,
      "learning_rate": 1.9878905881817254e-05,
      "loss": 1.8054,
      "step": 40
    },
    {
      "epoch": 0.16728624535315986,
      "grad_norm": 3.6228199005126953,
      "learning_rate": 1.975746552556772e-05,
      "loss": 1.7393,
      "step": 45
    },
    {
      "epoch": 0.18587360594795538,
      "grad_norm": 2.397761106491089,
      "learning_rate": 1.9594929736144978e-05,
      "loss": 1.6738,
      "step": 50
    },
    {
      "epoch": 0.20446096654275092,
      "grad_norm": 2.159792423248291,
      "learning_rate": 1.939198306412775e-05,
      "loss": 1.6584,
      "step": 55
    },
    {
      "epoch": 0.22304832713754646,
      "grad_norm": 2.4025373458862305,
      "learning_rate": 1.9149480258259535e-05,
      "loss": 1.6347,
      "step": 60
    },
    {
      "epoch": 0.241635687732342,
      "grad_norm": 2.0866482257843018,
      "learning_rate": 1.886844266551068e-05,
      "loss": 1.598,
      "step": 65
    },
    {
      "epoch": 0.26022304832713755,
      "grad_norm": 1.7645834684371948,
      "learning_rate": 1.8550053929480202e-05,
      "loss": 1.5923,
      "step": 70
    },
    {
      "epoch": 0.2788104089219331,
      "grad_norm": 1.642554759979248,
      "learning_rate": 1.8195655005254274e-05,
      "loss": 1.5452,
      "step": 75
    },
    {
      "epoch": 0.29739776951672864,
      "grad_norm": 1.5671523809432983,
      "learning_rate": 1.780673851171728e-05,
      "loss": 1.5275,
      "step": 80
    },
    {
      "epoch": 0.3159851301115242,
      "grad_norm": 1.6036931276321411,
      "learning_rate": 1.7384942445101772e-05,
      "loss": 1.5358,
      "step": 85
    },
    {
      "epoch": 0.3345724907063197,
      "grad_norm": 1.540089726448059,
      "learning_rate": 1.6932043280253892e-05,
      "loss": 1.5234,
      "step": 90
    },
    {
      "epoch": 0.35315985130111527,
      "grad_norm": 1.1673122644424438,
      "learning_rate": 1.644994848866964e-05,
      "loss": 1.5211,
      "step": 95
    },
    {
      "epoch": 0.37174721189591076,
      "grad_norm": 1.3127870559692383,
      "learning_rate": 1.5940688504813664e-05,
      "loss": 1.5038,
      "step": 100
    },
    {
      "epoch": 0.37174721189591076,
      "eval_loss": 1.5038524866104126,
      "eval_runtime": 5.4348,
      "eval_samples_per_second": 171.303,
      "eval_steps_per_second": 5.52,
      "step": 100
    },
    {
      "epoch": 0.3903345724907063,
      "grad_norm": 1.1808836460113525,
      "learning_rate": 1.5406408174555978e-05,
      "loss": 1.4911,
      "step": 105
    },
    {
      "epoch": 0.40892193308550184,
      "grad_norm": 8.379034042358398,
      "learning_rate": 1.4849357721743169e-05,
      "loss": 1.4598,
      "step": 110
    },
    {
      "epoch": 0.4275092936802974,
      "grad_norm": 1.090346097946167,
      "learning_rate": 1.4271883270950073e-05,
      "loss": 1.4944,
      "step": 115
    },
    {
      "epoch": 0.44609665427509293,
      "grad_norm": 1.1020578145980835,
      "learning_rate": 1.3676416966327201e-05,
      "loss": 1.4808,
      "step": 120
    },
    {
      "epoch": 0.4646840148698885,
      "grad_norm": 1.1537312269210815,
      "learning_rate": 1.3065466728160253e-05,
      "loss": 1.4493,
      "step": 125
    },
    {
      "epoch": 0.483271375464684,
      "grad_norm": 0.9695990085601807,
      "learning_rate": 1.2441605690283915e-05,
      "loss": 1.456,
      "step": 130
    },
    {
      "epoch": 0.5018587360594795,
      "grad_norm": 1.1512304544448853,
      "learning_rate": 1.1807461362836382e-05,
      "loss": 1.4493,
      "step": 135
    },
    {
      "epoch": 0.5204460966542751,
      "grad_norm": 1.1557819843292236,
      "learning_rate": 1.1165704565997593e-05,
      "loss": 1.4528,
      "step": 140
    },
    {
      "epoch": 0.5390334572490706,
      "grad_norm": 0.9956693053245544,
      "learning_rate": 1.0519038181319e-05,
      "loss": 1.4129,
      "step": 145
    },
    {
      "epoch": 0.5576208178438662,
      "grad_norm": 0.9141682982444763,
      "learning_rate": 9.870185768020694e-06,
      "loss": 1.4179,
      "step": 150
    },
    {
      "epoch": 0.5762081784386617,
      "grad_norm": 1.0787816047668457,
      "learning_rate": 9.221880092200601e-06,
      "loss": 1.4139,
      "step": 155
    },
    {
      "epoch": 0.5947955390334573,
      "grad_norm": 1.0250240564346313,
      "learning_rate": 8.576851617267151e-06,
      "loss": 1.3976,
      "step": 160
    },
    {
      "epoch": 0.6133828996282528,
      "grad_norm": 0.9707216024398804,
      "learning_rate": 7.93781700407012e-06,
      "loss": 1.4043,
      "step": 165
    },
    {
      "epoch": 0.6319702602230484,
      "grad_norm": 1.020119309425354,
      "learning_rate": 7.307467669163655e-06,
      "loss": 1.4153,
      "step": 170
    },
    {
      "epoch": 0.6505576208178439,
      "grad_norm": 1.0523854494094849,
      "learning_rate": 6.688458449390438e-06,
      "loss": 1.3896,
      "step": 175
    },
    {
      "epoch": 0.6691449814126395,
      "grad_norm": 1.0011796951293945,
      "learning_rate": 6.083396420528298e-06,
      "loss": 1.3938,
      "step": 180
    },
    {
      "epoch": 0.6877323420074349,
      "grad_norm": 0.9738273024559021,
      "learning_rate": 5.494829917091733e-06,
      "loss": 1.371,
      "step": 185
    },
    {
      "epoch": 0.7063197026022305,
      "grad_norm": 0.9486119151115417,
      "learning_rate": 4.925237799533445e-06,
      "loss": 1.3906,
      "step": 190
    },
    {
      "epoch": 0.724907063197026,
      "grad_norm": 0.9746046662330627,
      "learning_rate": 4.377019014049223e-06,
      "loss": 1.3798,
      "step": 195
    },
    {
      "epoch": 0.7434944237918215,
      "grad_norm": 0.9329619407653809,
      "learning_rate": 3.852482488956992e-06,
      "loss": 1.3595,
      "step": 200
    },
    {
      "epoch": 0.7434944237918215,
      "eval_loss": 1.3681989908218384,
      "eval_runtime": 5.3831,
      "eval_samples_per_second": 172.95,
      "eval_steps_per_second": 5.573,
      "step": 200
    },
    {
      "epoch": 0.7620817843866171,
      "grad_norm": 1.0122321844100952,
      "learning_rate": 3.3538374102033865e-06,
      "loss": 1.3626,
      "step": 205
    },
    {
      "epoch": 0.7806691449814126,
      "grad_norm": 0.9424676895141602,
      "learning_rate": 2.8831839169543998e-06,
      "loss": 1.3451,
      "step": 210
    },
    {
      "epoch": 0.7992565055762082,
      "grad_norm": 0.9907885193824768,
      "learning_rate": 2.4425042564574186e-06,
      "loss": 1.371,
      "step": 215
    },
    {
      "epoch": 0.8178438661710037,
      "grad_norm": 0.9360305666923523,
      "learning_rate": 2.03365443542764e-06,
      "loss": 1.348,
      "step": 220
    },
    {
      "epoch": 0.8364312267657993,
      "grad_norm": 1.073083519935608,
      "learning_rate": 1.6583564031206357e-06,
      "loss": 1.3557,
      "step": 225
    },
    {
      "epoch": 0.8550185873605948,
      "grad_norm": 0.9857882857322693,
      "learning_rate": 1.3181907990135624e-06,
      "loss": 1.3387,
      "step": 230
    },
    {
      "epoch": 0.8736059479553904,
      "grad_norm": 0.9631243348121643,
      "learning_rate": 1.0145902956395449e-06,
      "loss": 1.3554,
      "step": 235
    },
    {
      "epoch": 0.8921933085501859,
      "grad_norm": 1.0025112628936768,
      "learning_rate": 7.488335646131628e-07,
      "loss": 1.3396,
      "step": 240
    },
    {
      "epoch": 0.9107806691449815,
      "grad_norm": 0.9768189191818237,
      "learning_rate": 5.22039891260262e-07,
      "loss": 1.3361,
      "step": 245
    },
    {
      "epoch": 0.929368029739777,
      "grad_norm": 0.9644155502319336,
      "learning_rate": 3.3516446053363015e-07,
      "loss": 1.3138,
      "step": 250
    },
    {
      "epoch": 0.9479553903345725,
      "grad_norm": 0.9707642197608948,
      "learning_rate": 1.889943340687961e-07,
      "loss": 1.3315,
      "step": 255
    },
    {
      "epoch": 0.966542750929368,
      "grad_norm": 1.0248664617538452,
      "learning_rate": 8.41451353233369e-08,
      "loss": 1.3724,
      "step": 260
    },
    {
      "epoch": 0.9851301115241635,
      "grad_norm": 0.9727205634117126,
      "learning_rate": 2.10584567608918e-08,
      "loss": 1.3296,
      "step": 265
    },
    {
      "epoch": 1.0,
      "step": 269,
      "total_flos": 1.000686074462208e+17,
      "train_loss": 1.5741833559199336,
      "train_runtime": 402.4792,
      "train_samples_per_second": 42.723,
      "train_steps_per_second": 0.668
    }
  ],
  "logging_steps": 5,
  "max_steps": 269,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.000686074462208e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}