{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 15,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.181640625,
      "epoch": 0.03361344537815126,
      "grad_norm": 1.7928742767831207,
      "learning_rate": 0.0,
      "loss": 1.3131,
      "mean_token_accuracy": 0.6369074434041977,
      "num_tokens": 75310.0,
      "step": 1
    },
    {
      "entropy": 1.119140625,
      "epoch": 0.06722689075630252,
      "grad_norm": 1.6506218424352948,
      "learning_rate": 3e-05,
      "loss": 1.3469,
      "mean_token_accuracy": 0.6300242394208908,
      "num_tokens": 153607.0,
      "step": 2
    },
    {
      "entropy": 1.1728515625,
      "epoch": 0.13445378151260504,
      "grad_norm": 1.3796606244503395,
      "learning_rate": 2.9482758620689654e-05,
      "loss": 1.289,
      "mean_token_accuracy": 0.6425867825746536,
      "num_tokens": 289000.0,
      "step": 4
    },
    {
      "entropy": 1.2216796875,
      "epoch": 0.20168067226890757,
      "grad_norm": 3.4206735699743493,
      "learning_rate": 2.8448275862068966e-05,
      "loss": 1.2113,
      "mean_token_accuracy": 0.6542532071471214,
      "num_tokens": 438702.0,
      "step": 6
    },
    {
      "entropy": 1.259765625,
      "epoch": 0.2689075630252101,
      "grad_norm": 2.2379649541100193,
      "learning_rate": 2.741379310344828e-05,
      "loss": 1.1519,
      "mean_token_accuracy": 0.663833349943161,
      "num_tokens": 580037.0,
      "step": 8
    },
    {
      "entropy": 1.2392578125,
      "epoch": 0.33613445378151263,
      "grad_norm": 1.1181315509763536,
      "learning_rate": 2.6379310344827588e-05,
      "loss": 1.097,
      "mean_token_accuracy": 0.6762372255325317,
      "num_tokens": 724254.0,
      "step": 10
    },
    {
      "entropy": 1.1494140625,
      "epoch": 0.40336134453781514,
      "grad_norm": 1.191042616939082,
      "learning_rate": 2.5344827586206897e-05,
      "loss": 1.088,
      "mean_token_accuracy": 0.6783676072955132,
      "num_tokens": 875036.0,
      "step": 12
    },
    {
      "entropy": 1.154296875,
      "epoch": 0.47058823529411764,
      "grad_norm": 1.249507656809331,
      "learning_rate": 2.4310344827586206e-05,
      "loss": 1.0712,
      "mean_token_accuracy": 0.676607720553875,
      "num_tokens": 1023337.0,
      "step": 14
    },
    {
      "epoch": 0.5042016806722689,
      "eval_entropy": 1.1395089285714286,
      "eval_loss": 1.0697113275527954,
      "eval_mean_token_accuracy": 0.6743263857705253,
      "eval_num_tokens": 1094042.0,
      "eval_runtime": 14.7587,
      "eval_samples_per_second": 3.388,
      "eval_steps_per_second": 0.474,
      "step": 15
    },
    {
      "entropy": 1.1630859375,
      "epoch": 0.5378151260504201,
      "grad_norm": 1.3489797487532325,
      "learning_rate": 2.327586206896552e-05,
      "loss": 1.0461,
      "mean_token_accuracy": 0.6843359917402267,
      "num_tokens": 1168826.0,
      "step": 16
    },
    {
      "entropy": 1.1298828125,
      "epoch": 0.6050420168067226,
      "grad_norm": 1.4108132020883717,
      "learning_rate": 2.2241379310344828e-05,
      "loss": 1.0388,
      "mean_token_accuracy": 0.6870746314525604,
      "num_tokens": 1322246.0,
      "step": 18
    },
    {
      "entropy": 1.1669921875,
      "epoch": 0.6722689075630253,
      "grad_norm": 1.3354043806449676,
      "learning_rate": 2.1206896551724137e-05,
      "loss": 1.0249,
      "mean_token_accuracy": 0.688920646905899,
      "num_tokens": 1464063.0,
      "step": 20
    },
    {
      "entropy": 1.16015625,
      "epoch": 0.7394957983193278,
      "grad_norm": 1.666062653107746,
      "learning_rate": 2.017241379310345e-05,
      "loss": 1.0323,
      "mean_token_accuracy": 0.6870173960924149,
      "num_tokens": 1600863.0,
      "step": 22
    },
    {
      "entropy": 1.1806640625,
      "epoch": 0.8067226890756303,
      "grad_norm": 1.2035574738536507,
      "learning_rate": 1.9137931034482762e-05,
      "loss": 1.0128,
      "mean_token_accuracy": 0.6902513056993484,
      "num_tokens": 1772011.0,
      "step": 24
    },
    {
      "entropy": 1.1025390625,
      "epoch": 0.8739495798319328,
      "grad_norm": 1.0664858711055925,
      "learning_rate": 1.8103448275862068e-05,
      "loss": 1.014,
      "mean_token_accuracy": 0.6933257803320885,
      "num_tokens": 1928733.0,
      "step": 26
    },
    {
      "entropy": 1.12744140625,
      "epoch": 0.9411764705882353,
      "grad_norm": 1.070630709251991,
      "learning_rate": 1.706896551724138e-05,
      "loss": 0.994,
      "mean_token_accuracy": 0.6967712193727493,
      "num_tokens": 2068126.0,
      "step": 28
    },
    {
      "entropy": 1.1819196428571428,
      "epoch": 1.0,
      "grad_norm": 2.6295169243673575,
      "learning_rate": 1.603448275862069e-05,
      "loss": 0.9902,
      "mean_token_accuracy": 0.6980065788541522,
      "num_tokens": 2182360.0,
      "step": 30
    },
    {
      "epoch": 1.0,
      "eval_entropy": 1.125,
      "eval_loss": 1.0098644495010376,
      "eval_mean_token_accuracy": 0.6880264622824532,
      "eval_num_tokens": 2182360.0,
      "eval_runtime": 14.5734,
      "eval_samples_per_second": 3.431,
      "eval_steps_per_second": 0.48,
      "step": 30
    },
    {
      "entropy": 1.099609375,
      "epoch": 1.0672268907563025,
      "grad_norm": 2.050074542522579,
      "learning_rate": 1.5e-05,
      "loss": 0.8933,
      "mean_token_accuracy": 0.7218180298805237,
      "num_tokens": 2325564.0,
      "step": 32
    },
    {
      "entropy": 1.16015625,
      "epoch": 1.134453781512605,
      "grad_norm": 1.0945630850199306,
      "learning_rate": 1.396551724137931e-05,
      "loss": 0.9022,
      "mean_token_accuracy": 0.7185544371604919,
      "num_tokens": 2478474.0,
      "step": 34
    },
    {
      "entropy": 1.0927734375,
      "epoch": 1.2016806722689075,
      "grad_norm": 1.4418349180955692,
      "learning_rate": 1.293103448275862e-05,
      "loss": 0.8661,
      "mean_token_accuracy": 0.7244188115000725,
      "num_tokens": 2626615.0,
      "step": 36
    },
    {
      "entropy": 1.052734375,
      "epoch": 1.26890756302521,
      "grad_norm": 1.1722563745135475,
      "learning_rate": 1.1896551724137931e-05,
      "loss": 0.8564,
      "mean_token_accuracy": 0.7331436201930046,
      "num_tokens": 2778957.0,
      "step": 38
    },
    {
      "entropy": 1.0771484375,
      "epoch": 1.3361344537815127,
      "grad_norm": 1.2206493994010927,
      "learning_rate": 1.0862068965517242e-05,
      "loss": 0.8483,
      "mean_token_accuracy": 0.731599785387516,
      "num_tokens": 2934688.0,
      "step": 40
    },
    {
      "entropy": 1.03759765625,
      "epoch": 1.403361344537815,
      "grad_norm": 1.213607284992565,
      "learning_rate": 9.827586206896551e-06,
      "loss": 0.8423,
      "mean_token_accuracy": 0.7331928312778473,
      "num_tokens": 3078722.0,
      "step": 42
    },
    {
      "entropy": 1.0634765625,
      "epoch": 1.4705882352941178,
      "grad_norm": 1.8432998759311154,
      "learning_rate": 8.793103448275862e-06,
      "loss": 0.8403,
      "mean_token_accuracy": 0.7300194650888443,
      "num_tokens": 3222738.0,
      "step": 44
    },
    {
      "epoch": 1.504201680672269,
      "eval_entropy": 1.05859375,
      "eval_loss": 0.999748706817627,
      "eval_mean_token_accuracy": 0.6920892340796334,
      "eval_num_tokens": 3300341.0,
      "eval_runtime": 14.5813,
      "eval_samples_per_second": 3.429,
      "eval_steps_per_second": 0.48,
      "step": 45
    },
    {
      "entropy": 1.060546875,
      "epoch": 1.53781512605042,
      "grad_norm": 1.2747974851902248,
      "learning_rate": 7.758620689655173e-06,
      "loss": 0.8441,
      "mean_token_accuracy": 0.7343461066484451,
      "num_tokens": 3379604.0,
      "step": 46
    },
    {
      "entropy": 1.03125,
      "epoch": 1.6050420168067228,
      "grad_norm": 1.5541516528133,
      "learning_rate": 6.724137931034483e-06,
      "loss": 0.8433,
      "mean_token_accuracy": 0.7312941700220108,
      "num_tokens": 3524464.0,
      "step": 48
    },
    {
      "entropy": 1.099609375,
      "epoch": 1.6722689075630253,
      "grad_norm": 1.4541114741349364,
      "learning_rate": 5.689655172413793e-06,
      "loss": 0.8468,
      "mean_token_accuracy": 0.7327947691082954,
      "num_tokens": 3671601.0,
      "step": 50
    },
    {
      "entropy": 1.0830078125,
      "epoch": 1.7394957983193278,
      "grad_norm": 1.3250573197747766,
      "learning_rate": 4.655172413793104e-06,
      "loss": 0.8337,
      "mean_token_accuracy": 0.7332699969410896,
      "num_tokens": 3831435.0,
      "step": 52
    },
    {
      "entropy": 1.060546875,
      "epoch": 1.8067226890756303,
      "grad_norm": 1.9274897237742625,
      "learning_rate": 3.620689655172414e-06,
      "loss": 0.8375,
      "mean_token_accuracy": 0.7363650351762772,
      "num_tokens": 3970690.0,
      "step": 54
    },
    {
      "entropy": 1.0380859375,
      "epoch": 1.8739495798319328,
      "grad_norm": 1.3947288532125532,
      "learning_rate": 2.5862068965517246e-06,
      "loss": 0.8176,
      "mean_token_accuracy": 0.7397993430495262,
      "num_tokens": 4116319.0,
      "step": 56
    },
    {
      "entropy": 1.0576171875,
      "epoch": 1.9411764705882353,
      "grad_norm": 1.2609408019593042,
      "learning_rate": 1.5517241379310346e-06,
      "loss": 0.8193,
      "mean_token_accuracy": 0.7374719008803368,
      "num_tokens": 4261278.0,
      "step": 58
    },
    {
      "entropy": 1.0569196428571428,
      "epoch": 2.0,
      "grad_norm": 2.203503634167548,
      "learning_rate": 5.172413793103448e-07,
      "loss": 0.8165,
      "mean_token_accuracy": 0.7374913011278424,
      "num_tokens": 4371243.0,
      "step": 60
    },
    {
      "epoch": 2.0,
      "eval_entropy": 1.0647321428571428,
      "eval_loss": 0.9897834658622742,
      "eval_mean_token_accuracy": 0.6942669238362994,
      "eval_num_tokens": 4371243.0,
      "eval_runtime": 14.5645,
      "eval_samples_per_second": 3.433,
      "eval_steps_per_second": 0.481,
      "step": 60
    }
  ],
  "logging_steps": 2,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 30,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 209132409847808.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}