{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.4705882352941178,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014705882352941176,
      "eval_loss": 0.851502537727356,
      "eval_runtime": 17.1345,
      "eval_samples_per_second": 6.712,
      "eval_steps_per_second": 0.875,
      "step": 1
    },
    {
      "epoch": 0.04411764705882353,
      "grad_norm": 0.49747511744499207,
      "learning_rate": 1.5e-05,
      "loss": 0.8488,
      "step": 3
    },
    {
      "epoch": 0.08823529411764706,
      "grad_norm": 0.5120547413825989,
      "learning_rate": 3e-05,
      "loss": 0.8632,
      "step": 6
    },
    {
      "epoch": 0.1323529411764706,
      "grad_norm": 0.43988457322120667,
      "learning_rate": 4.5e-05,
      "loss": 0.8061,
      "step": 9
    },
    {
      "epoch": 0.1323529411764706,
      "eval_loss": 0.7254419326782227,
      "eval_runtime": 17.3867,
      "eval_samples_per_second": 6.614,
      "eval_steps_per_second": 0.863,
      "step": 9
    },
    {
      "epoch": 0.17647058823529413,
      "grad_norm": 0.4664570689201355,
      "learning_rate": 4.993910125649561e-05,
      "loss": 0.6967,
      "step": 12
    },
    {
      "epoch": 0.22058823529411764,
      "grad_norm": 0.6955499649047852,
      "learning_rate": 4.962019382530521e-05,
      "loss": 0.5685,
      "step": 15
    },
    {
      "epoch": 0.2647058823529412,
      "grad_norm": 0.8682049512863159,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 0.4343,
      "step": 18
    },
    {
      "epoch": 0.2647058823529412,
      "eval_loss": 0.3259250223636627,
      "eval_runtime": 17.3828,
      "eval_samples_per_second": 6.616,
      "eval_steps_per_second": 0.863,
      "step": 18
    },
    {
      "epoch": 0.3088235294117647,
      "grad_norm": 0.4803406298160553,
      "learning_rate": 4.817959636416969e-05,
      "loss": 0.3142,
      "step": 21
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 0.4086674749851227,
      "learning_rate": 4.707368982147318e-05,
      "loss": 0.2366,
      "step": 24
    },
    {
      "epoch": 0.39705882352941174,
      "grad_norm": 0.29409703612327576,
      "learning_rate": 4.572593931387604e-05,
      "loss": 0.2209,
      "step": 27
    },
    {
      "epoch": 0.39705882352941174,
      "eval_loss": 0.1954878568649292,
      "eval_runtime": 17.3758,
      "eval_samples_per_second": 6.618,
      "eval_steps_per_second": 0.863,
      "step": 27
    },
    {
      "epoch": 0.4411764705882353,
      "grad_norm": 0.2741072475910187,
      "learning_rate": 4.415111107797445e-05,
      "loss": 0.1942,
      "step": 30
    },
    {
      "epoch": 0.4852941176470588,
      "grad_norm": 0.22216534614562988,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 0.1973,
      "step": 33
    },
    {
      "epoch": 0.5294117647058824,
      "grad_norm": 0.204613596200943,
      "learning_rate": 4.039153688314145e-05,
      "loss": 0.1892,
      "step": 36
    },
    {
      "epoch": 0.5294117647058824,
      "eval_loss": 0.167263001203537,
      "eval_runtime": 17.4022,
      "eval_samples_per_second": 6.608,
      "eval_steps_per_second": 0.862,
      "step": 36
    },
    {
      "epoch": 0.5735294117647058,
      "grad_norm": 0.19633035361766815,
      "learning_rate": 3.824798160583012e-05,
      "loss": 0.1902,
      "step": 39
    },
    {
      "epoch": 0.6176470588235294,
      "grad_norm": 0.19374072551727295,
      "learning_rate": 3.5959278669726935e-05,
      "loss": 0.1596,
      "step": 42
    },
    {
      "epoch": 0.6617647058823529,
      "grad_norm": 0.138106107711792,
      "learning_rate": 3.355050358314172e-05,
      "loss": 0.1574,
      "step": 45
    },
    {
      "epoch": 0.6617647058823529,
      "eval_loss": 0.1535487323999405,
      "eval_runtime": 17.4439,
      "eval_samples_per_second": 6.593,
      "eval_steps_per_second": 0.86,
      "step": 45
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.14004965126514435,
      "learning_rate": 3.104804738999169e-05,
      "loss": 0.1638,
      "step": 48
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.13989396393299103,
      "learning_rate": 2.8479327524001636e-05,
      "loss": 0.1545,
      "step": 51
    },
    {
      "epoch": 0.7941176470588235,
      "grad_norm": 0.18269434571266174,
      "learning_rate": 2.587248741756253e-05,
      "loss": 0.1738,
      "step": 54
    },
    {
      "epoch": 0.7941176470588235,
      "eval_loss": 0.14321838319301605,
      "eval_runtime": 17.406,
      "eval_samples_per_second": 6.607,
      "eval_steps_per_second": 0.862,
      "step": 54
    },
    {
      "epoch": 0.8382352941176471,
      "grad_norm": 0.16118720173835754,
      "learning_rate": 2.3256088156396868e-05,
      "loss": 0.1492,
      "step": 57
    },
    {
      "epoch": 0.8823529411764706,
      "grad_norm": 0.14809435606002808,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 0.1662,
      "step": 60
    },
    {
      "epoch": 0.9264705882352942,
      "grad_norm": 0.14554592967033386,
      "learning_rate": 1.8109066104575023e-05,
      "loss": 0.1641,
      "step": 63
    },
    {
      "epoch": 0.9264705882352942,
      "eval_loss": 0.13681022822856903,
      "eval_runtime": 17.3622,
      "eval_samples_per_second": 6.624,
      "eval_steps_per_second": 0.864,
      "step": 63
    },
    {
      "epoch": 0.9705882352941176,
      "grad_norm": 0.13518203794956207,
      "learning_rate": 1.56348351646022e-05,
      "loss": 0.1611,
      "step": 66
    },
    {
      "epoch": 1.0147058823529411,
      "grad_norm": 0.13351187109947205,
      "learning_rate": 1.3263210930352737e-05,
      "loss": 0.1525,
      "step": 69
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 0.1250705122947693,
      "learning_rate": 1.1020177413231334e-05,
      "loss": 0.1333,
      "step": 72
    },
    {
      "epoch": 1.0588235294117647,
      "eval_loss": 0.13294555246829987,
      "eval_runtime": 17.428,
      "eval_samples_per_second": 6.599,
      "eval_steps_per_second": 0.861,
      "step": 72
    },
    {
      "epoch": 1.1029411764705883,
      "grad_norm": 0.12626980245113373,
      "learning_rate": 8.930309757836517e-06,
      "loss": 0.1452,
      "step": 75
    },
    {
      "epoch": 1.1470588235294117,
      "grad_norm": 0.19401168823242188,
      "learning_rate": 7.016504991533726e-06,
      "loss": 0.1409,
      "step": 78
    },
    {
      "epoch": 1.1911764705882353,
      "grad_norm": 0.13765017688274384,
      "learning_rate": 5.299731159831953e-06,
      "loss": 0.1361,
      "step": 81
    },
    {
      "epoch": 1.1911764705882353,
      "eval_loss": 0.1305573731660843,
      "eval_runtime": 17.413,
      "eval_samples_per_second": 6.604,
      "eval_steps_per_second": 0.861,
      "step": 81
    },
    {
      "epoch": 1.2352941176470589,
      "grad_norm": 0.15578369796276093,
      "learning_rate": 3.798797596089351e-06,
      "loss": 0.125,
      "step": 84
    },
    {
      "epoch": 1.2794117647058822,
      "grad_norm": 0.14650852978229523,
      "learning_rate": 2.5301488425208296e-06,
      "loss": 0.1454,
      "step": 87
    },
    {
      "epoch": 1.3235294117647058,
      "grad_norm": 0.16093911230564117,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 0.1642,
      "step": 90
    },
    {
      "epoch": 1.3235294117647058,
      "eval_loss": 0.1295652836561203,
      "eval_runtime": 17.4313,
      "eval_samples_per_second": 6.597,
      "eval_steps_per_second": 0.861,
      "step": 90
    },
    {
      "epoch": 1.3676470588235294,
      "grad_norm": 0.14731736481189728,
      "learning_rate": 7.426068431000882e-07,
      "loss": 0.1479,
      "step": 93
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.1577821522951126,
      "learning_rate": 2.4329828146074095e-07,
      "loss": 0.1197,
      "step": 96
    },
    {
      "epoch": 1.4558823529411764,
      "grad_norm": 0.15286415815353394,
      "learning_rate": 1.522932452260595e-08,
      "loss": 0.1588,
      "step": 99
    },
    {
      "epoch": 1.4558823529411764,
      "eval_loss": 0.12933845818042755,
      "eval_runtime": 17.4499,
      "eval_samples_per_second": 6.59,
      "eval_steps_per_second": 0.86,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.961057620510638e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}