{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03712641544458883,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00037126415444588826,
      "eval_loss": 4.464370250701904,
      "eval_runtime": 102.0524,
      "eval_samples_per_second": 44.458,
      "eval_steps_per_second": 5.566,
      "step": 1
    },
    {
      "epoch": 0.0011137924633376648,
      "grad_norm": 0.9076333045959473,
      "learning_rate": 1.5e-05,
      "loss": 4.3192,
      "step": 3
    },
    {
      "epoch": 0.0022275849266753297,
      "grad_norm": 0.9957979321479797,
      "learning_rate": 3e-05,
      "loss": 4.4682,
      "step": 6
    },
    {
      "epoch": 0.003341377390012994,
      "grad_norm": 0.9132924675941467,
      "learning_rate": 4.5e-05,
      "loss": 4.3804,
      "step": 9
    },
    {
      "epoch": 0.003341377390012994,
      "eval_loss": 4.441404342651367,
      "eval_runtime": 102.102,
      "eval_samples_per_second": 44.436,
      "eval_steps_per_second": 5.563,
      "step": 9
    },
    {
      "epoch": 0.004455169853350659,
      "grad_norm": 1.0117743015289307,
      "learning_rate": 4.993910125649561e-05,
      "loss": 4.3551,
      "step": 12
    },
    {
      "epoch": 0.005568962316688323,
      "grad_norm": 0.9917817711830139,
      "learning_rate": 4.962019382530521e-05,
      "loss": 4.2708,
      "step": 15
    },
    {
      "epoch": 0.006682754780025988,
      "grad_norm": 1.0605599880218506,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 4.2359,
      "step": 18
    },
    {
      "epoch": 0.006682754780025988,
      "eval_loss": 4.246806621551514,
      "eval_runtime": 102.1684,
      "eval_samples_per_second": 44.407,
      "eval_steps_per_second": 5.559,
      "step": 18
    },
    {
      "epoch": 0.007796547243363653,
      "grad_norm": 1.205475926399231,
      "learning_rate": 4.817959636416969e-05,
      "loss": 4.1931,
      "step": 21
    },
    {
      "epoch": 0.008910339706701319,
      "grad_norm": 1.218623399734497,
      "learning_rate": 4.707368982147318e-05,
      "loss": 4.0218,
      "step": 24
    },
    {
      "epoch": 0.010024132170038983,
      "grad_norm": 1.211789846420288,
      "learning_rate": 4.572593931387604e-05,
      "loss": 3.6903,
      "step": 27
    },
    {
      "epoch": 0.010024132170038983,
      "eval_loss": 3.9151904582977295,
      "eval_runtime": 102.1497,
      "eval_samples_per_second": 44.415,
      "eval_steps_per_second": 5.56,
      "step": 27
    },
    {
      "epoch": 0.011137924633376647,
      "grad_norm": 1.073923110961914,
      "learning_rate": 4.415111107797445e-05,
      "loss": 3.8025,
      "step": 30
    },
    {
      "epoch": 0.012251717096714312,
      "grad_norm": 1.2747162580490112,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 3.785,
      "step": 33
    },
    {
      "epoch": 0.013365509560051976,
      "grad_norm": 1.1728018522262573,
      "learning_rate": 4.039153688314145e-05,
      "loss": 3.6833,
      "step": 36
    },
    {
      "epoch": 0.013365509560051976,
      "eval_loss": 3.583631753921509,
      "eval_runtime": 102.0645,
      "eval_samples_per_second": 44.452,
      "eval_steps_per_second": 5.565,
      "step": 36
    },
    {
      "epoch": 0.014479302023389642,
      "grad_norm": 1.2889246940612793,
      "learning_rate": 3.824798160583012e-05,
      "loss": 3.4318,
      "step": 39
    },
    {
      "epoch": 0.015593094486727306,
      "grad_norm": 1.2840162515640259,
      "learning_rate": 3.5959278669726935e-05,
      "loss": 3.2355,
      "step": 42
    },
    {
      "epoch": 0.016706886950064972,
      "grad_norm": 1.1799660921096802,
      "learning_rate": 3.355050358314172e-05,
      "loss": 3.2583,
      "step": 45
    },
    {
      "epoch": 0.016706886950064972,
      "eval_loss": 3.3041188716888428,
      "eval_runtime": 102.1114,
      "eval_samples_per_second": 44.432,
      "eval_steps_per_second": 5.563,
      "step": 45
    },
    {
      "epoch": 0.017820679413402638,
      "grad_norm": 1.1542611122131348,
      "learning_rate": 3.104804738999169e-05,
      "loss": 3.3552,
      "step": 48
    },
    {
      "epoch": 0.0189344718767403,
      "grad_norm": 1.1231194734573364,
      "learning_rate": 2.8479327524001636e-05,
      "loss": 3.2313,
      "step": 51
    },
    {
      "epoch": 0.020048264340077965,
      "grad_norm": 1.2060445547103882,
      "learning_rate": 2.587248741756253e-05,
      "loss": 3.1961,
      "step": 54
    },
    {
      "epoch": 0.020048264340077965,
      "eval_loss": 3.080096960067749,
      "eval_runtime": 102.2394,
      "eval_samples_per_second": 44.376,
      "eval_steps_per_second": 5.556,
      "step": 54
    },
    {
      "epoch": 0.02116205680341563,
      "grad_norm": 1.0807676315307617,
      "learning_rate": 2.3256088156396868e-05,
      "loss": 3.0027,
      "step": 57
    },
    {
      "epoch": 0.022275849266753293,
      "grad_norm": 1.1301020383834839,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 2.9808,
      "step": 60
    },
    {
      "epoch": 0.02338964173009096,
      "grad_norm": 0.9327682852745056,
      "learning_rate": 1.8109066104575023e-05,
      "loss": 3.0352,
      "step": 63
    },
    {
      "epoch": 0.02338964173009096,
      "eval_loss": 2.921823501586914,
      "eval_runtime": 102.3331,
      "eval_samples_per_second": 44.336,
      "eval_steps_per_second": 5.551,
      "step": 63
    },
    {
      "epoch": 0.024503434193428625,
      "grad_norm": 1.1941728591918945,
      "learning_rate": 1.56348351646022e-05,
      "loss": 2.8402,
      "step": 66
    },
    {
      "epoch": 0.02561722665676629,
      "grad_norm": 1.0488781929016113,
      "learning_rate": 1.3263210930352737e-05,
      "loss": 2.7516,
      "step": 69
    },
    {
      "epoch": 0.026731019120103953,
      "grad_norm": 0.9377260804176331,
      "learning_rate": 1.1020177413231334e-05,
      "loss": 3.0401,
      "step": 72
    },
    {
      "epoch": 0.026731019120103953,
      "eval_loss": 2.823646306991577,
      "eval_runtime": 102.3141,
      "eval_samples_per_second": 44.344,
      "eval_steps_per_second": 5.552,
      "step": 72
    },
    {
      "epoch": 0.02784481158344162,
      "grad_norm": 1.002527117729187,
      "learning_rate": 8.930309757836517e-06,
      "loss": 2.8263,
      "step": 75
    },
    {
      "epoch": 0.028958604046779284,
      "grad_norm": 1.0062321424484253,
      "learning_rate": 7.016504991533726e-06,
      "loss": 2.7205,
      "step": 78
    },
    {
      "epoch": 0.03007239651011695,
      "grad_norm": 0.9706265330314636,
      "learning_rate": 5.299731159831953e-06,
      "loss": 2.7307,
      "step": 81
    },
    {
      "epoch": 0.03007239651011695,
      "eval_loss": 2.7717268466949463,
      "eval_runtime": 102.3153,
      "eval_samples_per_second": 44.343,
      "eval_steps_per_second": 5.551,
      "step": 81
    },
    {
      "epoch": 0.031186188973454612,
      "grad_norm": 0.9139003157615662,
      "learning_rate": 3.798797596089351e-06,
      "loss": 2.7478,
      "step": 84
    },
    {
      "epoch": 0.032299981436792274,
      "grad_norm": 0.9888792634010315,
      "learning_rate": 2.5301488425208296e-06,
      "loss": 2.7967,
      "step": 87
    },
    {
      "epoch": 0.033413773900129944,
      "grad_norm": 0.8691554665565491,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 2.7622,
      "step": 90
    },
    {
      "epoch": 0.033413773900129944,
      "eval_loss": 2.7512753009796143,
      "eval_runtime": 102.3046,
      "eval_samples_per_second": 44.348,
      "eval_steps_per_second": 5.552,
      "step": 90
    },
    {
      "epoch": 0.034527566363467606,
      "grad_norm": 0.8410691022872925,
      "learning_rate": 7.426068431000882e-07,
      "loss": 2.5786,
      "step": 93
    },
    {
      "epoch": 0.035641358826805275,
      "grad_norm": 0.9793163537979126,
      "learning_rate": 2.4329828146074095e-07,
      "loss": 2.6365,
      "step": 96
    },
    {
      "epoch": 0.03675515129014294,
      "grad_norm": 0.8763136267662048,
      "learning_rate": 1.522932452260595e-08,
      "loss": 2.9456,
      "step": 99
    },
    {
      "epoch": 0.03675515129014294,
      "eval_loss": 2.747492551803589,
      "eval_runtime": 102.3186,
      "eval_samples_per_second": 44.342,
      "eval_steps_per_second": 5.551,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 9932351078400000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}