{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2925402242808386,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005850804485616773,
      "grad_norm": 4.189145565032959,
      "learning_rate": 1.9607843137254904e-07,
      "loss": 0.6022,
      "step": 1
    },
    {
      "epoch": 0.011701608971233545,
      "grad_norm": 4.088385105133057,
      "learning_rate": 3.921568627450981e-07,
      "loss": 0.6105,
      "step": 2
    },
    {
      "epoch": 0.017552413456850317,
      "grad_norm": 4.105137348175049,
      "learning_rate": 5.882352941176471e-07,
      "loss": 0.6234,
      "step": 3
    },
    {
      "epoch": 0.02340321794246709,
      "grad_norm": 4.010756015777588,
      "learning_rate": 7.843137254901962e-07,
      "loss": 0.5629,
      "step": 4
    },
    {
      "epoch": 0.02925402242808386,
      "grad_norm": 4.201730728149414,
      "learning_rate": 9.80392156862745e-07,
      "loss": 0.6236,
      "step": 5
    },
    {
      "epoch": 0.035104826913700635,
      "grad_norm": 4.13097620010376,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 0.6058,
      "step": 6
    },
    {
      "epoch": 0.040955631399317405,
      "grad_norm": 3.753781318664551,
      "learning_rate": 1.3725490196078434e-06,
      "loss": 0.5798,
      "step": 7
    },
    {
      "epoch": 0.04680643588493418,
      "grad_norm": 3.1203114986419678,
      "learning_rate": 1.5686274509803923e-06,
      "loss": 0.5575,
      "step": 8
    },
    {
      "epoch": 0.05265724037055095,
      "grad_norm": 3.1326870918273926,
      "learning_rate": 1.7647058823529414e-06,
      "loss": 0.5794,
      "step": 9
    },
    {
      "epoch": 0.05850804485616772,
      "grad_norm": 3.01350736618042,
      "learning_rate": 1.96078431372549e-06,
      "loss": 0.5721,
      "step": 10
    },
    {
      "epoch": 0.0643588493417845,
      "grad_norm": 2.0586817264556885,
      "learning_rate": 2.1568627450980393e-06,
      "loss": 0.5389,
      "step": 11
    },
    {
      "epoch": 0.07020965382740127,
      "grad_norm": 2.056138753890991,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 0.5578,
      "step": 12
    },
    {
      "epoch": 0.07606045831301804,
      "grad_norm": 1.8458319902420044,
      "learning_rate": 2.549019607843137e-06,
      "loss": 0.5432,
      "step": 13
    },
    {
      "epoch": 0.08191126279863481,
      "grad_norm": 1.3385547399520874,
      "learning_rate": 2.7450980392156867e-06,
      "loss": 0.5375,
      "step": 14
    },
    {
      "epoch": 0.08776206728425158,
      "grad_norm": 2.10184383392334,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 0.4834,
      "step": 15
    },
    {
      "epoch": 0.09361287176986836,
      "grad_norm": 2.354717254638672,
      "learning_rate": 3.1372549019607846e-06,
      "loss": 0.5087,
      "step": 16
    },
    {
      "epoch": 0.09946367625548513,
      "grad_norm": 2.4186935424804688,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.5408,
      "step": 17
    },
    {
      "epoch": 0.1053144807411019,
      "grad_norm": 2.02093243598938,
      "learning_rate": 3.529411764705883e-06,
      "loss": 0.4967,
      "step": 18
    },
    {
      "epoch": 0.11116528522671867,
      "grad_norm": 1.9769740104675293,
      "learning_rate": 3.7254901960784316e-06,
      "loss": 0.5429,
      "step": 19
    },
    {
      "epoch": 0.11701608971233544,
      "grad_norm": 1.4087600708007812,
      "learning_rate": 3.92156862745098e-06,
      "loss": 0.4855,
      "step": 20
    },
    {
      "epoch": 0.12286689419795221,
      "grad_norm": 1.4071195125579834,
      "learning_rate": 4.11764705882353e-06,
      "loss": 0.4956,
      "step": 21
    },
    {
      "epoch": 0.128717698683569,
      "grad_norm": 1.4400174617767334,
      "learning_rate": 4.313725490196079e-06,
      "loss": 0.4966,
      "step": 22
    },
    {
      "epoch": 0.13456850316918575,
      "grad_norm": 1.2176562547683716,
      "learning_rate": 4.509803921568628e-06,
      "loss": 0.4892,
      "step": 23
    },
    {
      "epoch": 0.14041930765480254,
      "grad_norm": 1.0557763576507568,
      "learning_rate": 4.705882352941177e-06,
      "loss": 0.4664,
      "step": 24
    },
    {
      "epoch": 0.1462701121404193,
      "grad_norm": 1.0654219388961792,
      "learning_rate": 4.901960784313726e-06,
      "loss": 0.4427,
      "step": 25
    },
    {
      "epoch": 0.15212091662603608,
      "grad_norm": 0.8639155626296997,
      "learning_rate": 5.098039215686274e-06,
      "loss": 0.4676,
      "step": 26
    },
    {
      "epoch": 0.15797172111165286,
      "grad_norm": 0.8091264963150024,
      "learning_rate": 5.294117647058824e-06,
      "loss": 0.4339,
      "step": 27
    },
    {
      "epoch": 0.16382252559726962,
      "grad_norm": 0.7697594165802002,
      "learning_rate": 5.4901960784313735e-06,
      "loss": 0.4164,
      "step": 28
    },
    {
      "epoch": 0.1696733300828864,
      "grad_norm": 0.8522382378578186,
      "learning_rate": 5.686274509803922e-06,
      "loss": 0.4512,
      "step": 29
    },
    {
      "epoch": 0.17552413456850316,
      "grad_norm": 0.7640376687049866,
      "learning_rate": 5.882352941176471e-06,
      "loss": 0.432,
      "step": 30
    },
    {
      "epoch": 0.18137493905411994,
      "grad_norm": 0.6247867941856384,
      "learning_rate": 6.07843137254902e-06,
      "loss": 0.408,
      "step": 31
    },
    {
      "epoch": 0.18722574353973673,
      "grad_norm": 0.6288900971412659,
      "learning_rate": 6.274509803921569e-06,
      "loss": 0.4611,
      "step": 32
    },
    {
      "epoch": 0.19307654802535348,
      "grad_norm": 0.6182562708854675,
      "learning_rate": 6.470588235294119e-06,
      "loss": 0.4257,
      "step": 33
    },
    {
      "epoch": 0.19892735251097027,
      "grad_norm": 0.6193389892578125,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.4063,
      "step": 34
    },
    {
      "epoch": 0.20477815699658702,
      "grad_norm": 0.6892727017402649,
      "learning_rate": 6.862745098039216e-06,
      "loss": 0.3967,
      "step": 35
    },
    {
      "epoch": 0.2106289614822038,
      "grad_norm": 0.6725057363510132,
      "learning_rate": 7.058823529411766e-06,
      "loss": 0.4428,
      "step": 36
    },
    {
      "epoch": 0.21647976596782056,
      "grad_norm": 0.5203535556793213,
      "learning_rate": 7.2549019607843145e-06,
      "loss": 0.4151,
      "step": 37
    },
    {
      "epoch": 0.22233057045343735,
      "grad_norm": 0.45232418179512024,
      "learning_rate": 7.450980392156863e-06,
      "loss": 0.3666,
      "step": 38
    },
    {
      "epoch": 0.22818137493905413,
      "grad_norm": 0.5872768759727478,
      "learning_rate": 7.647058823529411e-06,
      "loss": 0.4144,
      "step": 39
    },
    {
      "epoch": 0.2340321794246709,
      "grad_norm": 0.526172399520874,
      "learning_rate": 7.84313725490196e-06,
      "loss": 0.4346,
      "step": 40
    },
    {
      "epoch": 0.23988298391028767,
      "grad_norm": 0.5474228858947754,
      "learning_rate": 8.03921568627451e-06,
      "loss": 0.3965,
      "step": 41
    },
    {
      "epoch": 0.24573378839590443,
      "grad_norm": 0.46727877855300903,
      "learning_rate": 8.23529411764706e-06,
      "loss": 0.4417,
      "step": 42
    },
    {
      "epoch": 0.2515845928815212,
      "grad_norm": 0.40532198548316956,
      "learning_rate": 8.43137254901961e-06,
      "loss": 0.3851,
      "step": 43
    },
    {
      "epoch": 0.257435397367138,
      "grad_norm": 0.4897397458553314,
      "learning_rate": 8.627450980392157e-06,
      "loss": 0.4013,
      "step": 44
    },
    {
      "epoch": 0.26328620185275475,
      "grad_norm": 0.4565890431404114,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.3745,
      "step": 45
    },
    {
      "epoch": 0.2691370063383715,
      "grad_norm": 0.38417261838912964,
      "learning_rate": 9.019607843137256e-06,
      "loss": 0.3783,
      "step": 46
    },
    {
      "epoch": 0.2749878108239883,
      "grad_norm": 0.40912356972694397,
      "learning_rate": 9.215686274509804e-06,
      "loss": 0.3879,
      "step": 47
    },
    {
      "epoch": 0.2808386153096051,
      "grad_norm": 0.42792415618896484,
      "learning_rate": 9.411764705882354e-06,
      "loss": 0.3837,
      "step": 48
    },
    {
      "epoch": 0.28668941979522183,
      "grad_norm": 0.4394405484199524,
      "learning_rate": 9.607843137254903e-06,
      "loss": 0.4004,
      "step": 49
    },
    {
      "epoch": 0.2925402242808386,
      "grad_norm": 0.4622238576412201,
      "learning_rate": 9.803921568627451e-06,
      "loss": 0.409,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 510,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 9.284609818000097e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}