{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04113430975381739,
  "eval_steps": 9,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00041549807832138777,
      "eval_loss": 1.8511379957199097,
      "eval_runtime": 172.9787,
      "eval_samples_per_second": 23.436,
      "eval_steps_per_second": 2.931,
      "step": 1
    },
    {
      "epoch": 0.0012464942349641633,
      "grad_norm": 1.777475118637085,
      "learning_rate": 1.5e-05,
      "loss": 1.818,
      "step": 3
    },
    {
      "epoch": 0.0024929884699283265,
      "grad_norm": 1.8006658554077148,
      "learning_rate": 3e-05,
      "loss": 1.8408,
      "step": 6
    },
    {
      "epoch": 0.00373948270489249,
      "grad_norm": 1.0692284107208252,
      "learning_rate": 4.5e-05,
      "loss": 1.6791,
      "step": 9
    },
    {
      "epoch": 0.00373948270489249,
      "eval_loss": 1.6404595375061035,
      "eval_runtime": 173.286,
      "eval_samples_per_second": 23.395,
      "eval_steps_per_second": 2.926,
      "step": 9
    },
    {
      "epoch": 0.004985976939856653,
      "grad_norm": 1.0822547674179077,
      "learning_rate": 4.993910125649561e-05,
      "loss": 1.6332,
      "step": 12
    },
    {
      "epoch": 0.0062324711748208165,
      "grad_norm": 1.250191330909729,
      "learning_rate": 4.962019382530521e-05,
      "loss": 1.434,
      "step": 15
    },
    {
      "epoch": 0.00747896540978498,
      "grad_norm": 0.860614001750946,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 1.3965,
      "step": 18
    },
    {
      "epoch": 0.00747896540978498,
      "eval_loss": 1.3805952072143555,
      "eval_runtime": 173.2368,
      "eval_samples_per_second": 23.401,
      "eval_steps_per_second": 2.927,
      "step": 18
    },
    {
      "epoch": 0.008725459644749143,
      "grad_norm": 0.87806636095047,
      "learning_rate": 4.817959636416969e-05,
      "loss": 1.3635,
      "step": 21
    },
    {
      "epoch": 0.009971953879713306,
      "grad_norm": 0.9511878490447998,
      "learning_rate": 4.707368982147318e-05,
      "loss": 1.2227,
      "step": 24
    },
    {
      "epoch": 0.01121844811467747,
      "grad_norm": 0.7667391896247864,
      "learning_rate": 4.572593931387604e-05,
      "loss": 1.2309,
      "step": 27
    },
    {
      "epoch": 0.01121844811467747,
      "eval_loss": 1.3263046741485596,
      "eval_runtime": 173.0661,
      "eval_samples_per_second": 23.425,
      "eval_steps_per_second": 2.93,
      "step": 27
    },
    {
      "epoch": 0.012464942349641633,
      "grad_norm": 0.8678608536720276,
      "learning_rate": 4.415111107797445e-05,
      "loss": 1.2841,
      "step": 30
    },
    {
      "epoch": 0.013711436584605797,
      "grad_norm": 0.8327022790908813,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 1.3818,
      "step": 33
    },
    {
      "epoch": 0.01495793081956996,
      "grad_norm": 0.7300451397895813,
      "learning_rate": 4.039153688314145e-05,
      "loss": 1.2803,
      "step": 36
    },
    {
      "epoch": 0.01495793081956996,
      "eval_loss": 1.2931612730026245,
      "eval_runtime": 173.3773,
      "eval_samples_per_second": 23.383,
      "eval_steps_per_second": 2.924,
      "step": 36
    },
    {
      "epoch": 0.016204425054534122,
      "grad_norm": 0.7869206666946411,
      "learning_rate": 3.824798160583012e-05,
      "loss": 1.3118,
      "step": 39
    },
    {
      "epoch": 0.017450919289498285,
      "grad_norm": 0.7900273203849792,
      "learning_rate": 3.5959278669726935e-05,
      "loss": 1.3342,
      "step": 42
    },
    {
      "epoch": 0.01869741352446245,
      "grad_norm": 0.7585929036140442,
      "learning_rate": 3.355050358314172e-05,
      "loss": 1.3283,
      "step": 45
    },
    {
      "epoch": 0.01869741352446245,
      "eval_loss": 1.2761189937591553,
      "eval_runtime": 173.391,
      "eval_samples_per_second": 23.381,
      "eval_steps_per_second": 2.924,
      "step": 45
    },
    {
      "epoch": 0.019943907759426612,
      "grad_norm": 0.771148145198822,
      "learning_rate": 3.104804738999169e-05,
      "loss": 1.2838,
      "step": 48
    },
    {
      "epoch": 0.021190401994390776,
      "grad_norm": 0.7722786068916321,
      "learning_rate": 2.8479327524001636e-05,
      "loss": 1.275,
      "step": 51
    },
    {
      "epoch": 0.02243689622935494,
      "grad_norm": 0.6512364745140076,
      "learning_rate": 2.587248741756253e-05,
      "loss": 1.2904,
      "step": 54
    },
    {
      "epoch": 0.02243689622935494,
      "eval_loss": 1.2634623050689697,
      "eval_runtime": 173.3264,
      "eval_samples_per_second": 23.389,
      "eval_steps_per_second": 2.925,
      "step": 54
    },
    {
      "epoch": 0.023683390464319103,
      "grad_norm": 0.6592357754707336,
      "learning_rate": 2.3256088156396868e-05,
      "loss": 1.1956,
      "step": 57
    },
    {
      "epoch": 0.024929884699283266,
      "grad_norm": 0.7468481063842773,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 1.1456,
      "step": 60
    },
    {
      "epoch": 0.02617637893424743,
      "grad_norm": 0.7203512787818909,
      "learning_rate": 1.8109066104575023e-05,
      "loss": 1.2657,
      "step": 63
    },
    {
      "epoch": 0.02617637893424743,
      "eval_loss": 1.2559400796890259,
      "eval_runtime": 173.1498,
      "eval_samples_per_second": 23.413,
      "eval_steps_per_second": 2.928,
      "step": 63
    },
    {
      "epoch": 0.027422873169211593,
      "grad_norm": 0.7282468676567078,
      "learning_rate": 1.56348351646022e-05,
      "loss": 1.2672,
      "step": 66
    },
    {
      "epoch": 0.028669367404175757,
      "grad_norm": 0.7473340630531311,
      "learning_rate": 1.3263210930352737e-05,
      "loss": 1.2848,
      "step": 69
    },
    {
      "epoch": 0.02991586163913992,
      "grad_norm": 0.7327454686164856,
      "learning_rate": 1.1020177413231334e-05,
      "loss": 1.1748,
      "step": 72
    },
    {
      "epoch": 0.02991586163913992,
      "eval_loss": 1.2513723373413086,
      "eval_runtime": 173.4391,
      "eval_samples_per_second": 23.374,
      "eval_steps_per_second": 2.923,
      "step": 72
    },
    {
      "epoch": 0.031162355874104083,
      "grad_norm": 0.7824718356132507,
      "learning_rate": 8.930309757836517e-06,
      "loss": 1.2939,
      "step": 75
    },
    {
      "epoch": 0.032408850109068243,
      "grad_norm": 0.8748393654823303,
      "learning_rate": 7.016504991533726e-06,
      "loss": 1.3708,
      "step": 78
    },
    {
      "epoch": 0.03365534434403241,
      "grad_norm": 0.8517729043960571,
      "learning_rate": 5.299731159831953e-06,
      "loss": 1.2588,
      "step": 81
    },
    {
      "epoch": 0.03365534434403241,
      "eval_loss": 1.2487555742263794,
      "eval_runtime": 173.4798,
      "eval_samples_per_second": 23.369,
      "eval_steps_per_second": 2.923,
      "step": 81
    },
    {
      "epoch": 0.03490183857899657,
      "grad_norm": 0.756130576133728,
      "learning_rate": 3.798797596089351e-06,
      "loss": 1.1985,
      "step": 84
    },
    {
      "epoch": 0.03614833281396074,
      "grad_norm": 0.6856725811958313,
      "learning_rate": 2.5301488425208296e-06,
      "loss": 1.3398,
      "step": 87
    },
    {
      "epoch": 0.0373948270489249,
      "grad_norm": 0.7697836756706238,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 1.2417,
      "step": 90
    },
    {
      "epoch": 0.0373948270489249,
      "eval_loss": 1.2476898431777954,
      "eval_runtime": 173.4624,
      "eval_samples_per_second": 23.371,
      "eval_steps_per_second": 2.923,
      "step": 90
    },
    {
      "epoch": 0.038641321283889064,
      "grad_norm": 0.6640880703926086,
      "learning_rate": 7.426068431000882e-07,
      "loss": 1.1677,
      "step": 93
    },
    {
      "epoch": 0.039887815518853224,
      "grad_norm": 0.6997036933898926,
      "learning_rate": 2.4329828146074095e-07,
      "loss": 1.2645,
      "step": 96
    },
    {
      "epoch": 0.04113430975381739,
      "grad_norm": 0.7629795074462891,
      "learning_rate": 1.522932452260595e-08,
      "loss": 1.2683,
      "step": 99
    },
    {
      "epoch": 0.04113430975381739,
      "eval_loss": 1.2474870681762695,
      "eval_runtime": 173.4461,
      "eval_samples_per_second": 23.373,
      "eval_steps_per_second": 2.923,
      "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.001087196286157e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}