{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 147,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.6612249977886677,
      "epoch": 0.03404255319148936,
      "grad_norm": 2.28125,
      "learning_rate": 8.000000000000001e-06,
      "loss": 5.1158195495605465,
      "mean_token_accuracy": 0.3411124350503087,
      "num_tokens": 12338.0,
      "step": 5
    },
    {
      "entropy": 1.7161438561975957,
      "epoch": 0.06808510638297872,
      "grad_norm": 3.421875,
      "learning_rate": 1.8e-05,
      "loss": 4.932054138183593,
      "mean_token_accuracy": 0.34090186562389135,
      "num_tokens": 24228.0,
      "step": 10
    },
    {
      "entropy": 1.8052345253527164,
      "epoch": 0.10212765957446808,
      "grad_norm": 1.9609375,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 4.3712615966796875,
      "mean_token_accuracy": 0.37591628544032574,
      "num_tokens": 36607.0,
      "step": 15
    },
    {
      "entropy": 2.1016422733664513,
      "epoch": 0.13617021276595745,
      "grad_norm": 1.5703125,
      "learning_rate": 3.8e-05,
      "loss": 3.642262268066406,
      "mean_token_accuracy": 0.4129604626446962,
      "num_tokens": 48067.0,
      "step": 20
    },
    {
      "entropy": 2.3243144676089287,
      "epoch": 0.1702127659574468,
      "grad_norm": 2.015625,
      "learning_rate": 4.8e-05,
      "loss": 2.9660737991333006,
      "mean_token_accuracy": 0.4782245371490717,
      "num_tokens": 59636.0,
      "step": 25
    },
    {
      "entropy": 2.302782629430294,
      "epoch": 0.20425531914893616,
      "grad_norm": 1.4296875,
      "learning_rate": 5.8e-05,
      "loss": 2.5412269592285157,
      "mean_token_accuracy": 0.5392776299268007,
      "num_tokens": 71707.0,
      "step": 30
    },
    {
      "entropy": 2.188954807817936,
      "epoch": 0.23829787234042554,
      "grad_norm": 0.71875,
      "learning_rate": 6.800000000000001e-05,
      "loss": 2.2308956146240235,
      "mean_token_accuracy": 0.5898199148476124,
      "num_tokens": 84024.0,
      "step": 35
    },
    {
      "entropy": 2.2109520554542543,
      "epoch": 0.2723404255319149,
      "grad_norm": 0.859375,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.964349365234375,
      "mean_token_accuracy": 0.6209986783564091,
      "num_tokens": 96306.0,
      "step": 40
    },
    {
      "entropy": 2.0961234346032143,
      "epoch": 0.30638297872340425,
      "grad_norm": 0.7265625,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.792983055114746,
      "mean_token_accuracy": 0.6284430582076311,
      "num_tokens": 108229.0,
      "step": 45
    },
    {
      "entropy": 1.671985263749957,
      "epoch": 0.3404255319148936,
      "grad_norm": 0.67578125,
      "learning_rate": 9.8e-05,
      "loss": 1.5038132667541504,
      "mean_token_accuracy": 0.6809367395937442,
      "num_tokens": 120313.0,
      "step": 50
    },
    {
      "entropy": 1.6443435620516538,
      "epoch": 0.37446808510638296,
      "grad_norm": 0.8125,
      "learning_rate": 9.958100506132127e-05,
      "loss": 1.4452999114990235,
      "mean_token_accuracy": 0.6813344601541758,
      "num_tokens": 132222.0,
      "step": 55
    },
    {
      "entropy": 1.4775371879339219,
      "epoch": 0.4085106382978723,
      "grad_norm": 0.5859375,
      "learning_rate": 9.789086620939936e-05,
      "loss": 1.3673093795776368,
      "mean_token_accuracy": 0.6939370810985566,
      "num_tokens": 144737.0,
      "step": 60
    },
    {
      "entropy": 1.362747695669532,
      "epoch": 0.4425531914893617,
      "grad_norm": 0.5390625,
      "learning_rate": 9.494758705426978e-05,
      "loss": 1.2551464080810546,
      "mean_token_accuracy": 0.718667059391737,
      "num_tokens": 156461.0,
      "step": 65
    },
    {
      "entropy": 1.4880228728055953,
      "epoch": 0.4765957446808511,
      "grad_norm": 0.609375,
      "learning_rate": 9.082818315286055e-05,
      "loss": 1.3538105010986328,
      "mean_token_accuracy": 0.7009879656136035,
      "num_tokens": 167343.0,
      "step": 70
    },
    {
      "entropy": 1.3466651082038879,
      "epoch": 0.5106382978723404,
      "grad_norm": 0.6796875,
      "learning_rate": 8.564044522734147e-05,
      "loss": 1.2858383178710937,
      "mean_token_accuracy": 0.7119019150733947,
      "num_tokens": 178638.0,
      "step": 75
    },
    {
      "entropy": 1.2633912980556488,
      "epoch": 0.5446808510638298,
      "grad_norm": 0.69921875,
      "learning_rate": 7.952011865029614e-05,
      "loss": 1.1970553398132324,
      "mean_token_accuracy": 0.7300039514899254,
      "num_tokens": 190643.0,
      "step": 80
    },
    {
      "entropy": 1.2618269324302673,
      "epoch": 0.5787234042553191,
      "grad_norm": 0.66015625,
      "learning_rate": 7.262735145222696e-05,
      "loss": 1.1030343055725098,
      "mean_token_accuracy": 0.7353190571069718,
      "num_tokens": 202328.0,
      "step": 85
    },
    {
      "entropy": 1.2507698042318225,
      "epoch": 0.6127659574468085,
      "grad_norm": 0.66015625,
      "learning_rate": 6.514250379489753e-05,
      "loss": 1.133834457397461,
      "mean_token_accuracy": 0.7314565621316433,
      "num_tokens": 213840.0,
      "step": 90
    },
    {
      "entropy": 1.2799267198890447,
      "epoch": 0.6468085106382979,
      "grad_norm": 0.640625,
      "learning_rate": 5.726142856227452e-05,
      "loss": 1.1554755210876464,
      "mean_token_accuracy": 0.7302999064326287,
      "num_tokens": 225649.0,
      "step": 95
    },
    {
      "entropy": 1.1757509659975767,
      "epoch": 0.6808510638297872,
      "grad_norm": 0.7109375,
      "learning_rate": 4.919034655987493e-05,
      "loss": 1.060139274597168,
      "mean_token_accuracy": 0.7470736525952816,
      "num_tokens": 237320.0,
      "step": 100
    },
    {
      "entropy": 1.2040388137102127,
      "epoch": 0.7148936170212766,
      "grad_norm": 0.70703125,
      "learning_rate": 4.114045042103887e-05,
      "loss": 1.0966894149780273,
      "mean_token_accuracy": 0.7398598760366439,
      "num_tokens": 249781.0,
      "step": 105
    },
    {
      "entropy": 1.2984253257513045,
      "epoch": 0.7489361702127659,
      "grad_norm": 0.76953125,
      "learning_rate": 3.332237841745898e-05,
      "loss": 1.16298828125,
      "mean_token_accuracy": 0.7219951130449772,
      "num_tokens": 260474.0,
      "step": 110
    },
    {
      "entropy": 1.131225979141891,
      "epoch": 0.7829787234042553,
      "grad_norm": 0.578125,
      "learning_rate": 2.5940702775459747e-05,
      "loss": 1.010167694091797,
      "mean_token_accuracy": 0.75770732909441,
      "num_tokens": 271936.0,
      "step": 115
    },
    {
      "entropy": 1.1314816752448678,
      "epoch": 0.8170212765957446,
      "grad_norm": 0.6484375,
      "learning_rate": 1.9188576719953633e-05,
      "loss": 1.0260458946228028,
      "mean_token_accuracy": 0.7487939164042473,
      "num_tokens": 283647.0,
      "step": 120
    },
    {
      "entropy": 1.1653054066002368,
      "epoch": 0.851063829787234,
      "grad_norm": 0.8203125,
      "learning_rate": 1.3242680314639993e-05,
      "loss": 1.0705586433410645,
      "mean_token_accuracy": 0.748039523512125,
      "num_tokens": 294672.0,
      "step": 125
    },
    {
      "entropy": 1.2385535925626754,
      "epoch": 0.8851063829787233,
      "grad_norm": 0.875,
      "learning_rate": 8.25859734853645e-06,
      "loss": 1.117280864715576,
      "mean_token_accuracy": 0.7358166418969632,
      "num_tokens": 305646.0,
      "step": 130
    },
    {
      "entropy": 1.1569571590051055,
      "epoch": 0.9191489361702128,
      "grad_norm": 0.734375,
      "learning_rate": 4.366744239922998e-06,
      "loss": 1.0218097686767578,
      "mean_token_accuracy": 0.7512762233614921,
      "num_tokens": 317522.0,
      "step": 135
    },
    {
      "entropy": 1.2956396371126175,
      "epoch": 0.9531914893617022,
      "grad_norm": 0.640625,
      "learning_rate": 1.6689574843694433e-06,
      "loss": 1.1682409286499023,
      "mean_token_accuracy": 0.7267132062464953,
      "num_tokens": 328188.0,
      "step": 140
    },
    {
      "entropy": 1.1794268768280745,
      "epoch": 0.9872340425531915,
      "grad_norm": 0.796875,
      "learning_rate": 2.3582894166930268e-07,
      "loss": 1.0452459335327149,
      "mean_token_accuracy": 0.7454933904111385,
      "num_tokens": 340204.0,
      "step": 145
    }
  ],
  "logging_steps": 5,
  "max_steps": 147,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.64226666827776e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}