{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04108885464817668,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002054442732408834,
      "grad_norm": 174.16879272460938,
      "learning_rate": 1e-05,
      "loss": 93.7032,
      "step": 1
    },
    {
      "epoch": 0.002054442732408834,
      "eval_loss": 2.998701333999634,
      "eval_runtime": 291.3939,
      "eval_samples_per_second": 11.256,
      "eval_steps_per_second": 2.814,
      "step": 1
    },
    {
      "epoch": 0.004108885464817668,
      "grad_norm": 185.02249145507812,
      "learning_rate": 2e-05,
      "loss": 96.5026,
      "step": 2
    },
    {
      "epoch": 0.0061633281972265025,
      "grad_norm": 166.1304931640625,
      "learning_rate": 3e-05,
      "loss": 94.5685,
      "step": 3
    },
    {
      "epoch": 0.008217770929635337,
      "grad_norm": 163.54811096191406,
      "learning_rate": 4e-05,
      "loss": 91.1858,
      "step": 4
    },
    {
      "epoch": 0.01027221366204417,
      "grad_norm": 137.41305541992188,
      "learning_rate": 5e-05,
      "loss": 90.2512,
      "step": 5
    },
    {
      "epoch": 0.01027221366204417,
      "eval_loss": 2.595139265060425,
      "eval_runtime": 291.9524,
      "eval_samples_per_second": 11.235,
      "eval_steps_per_second": 2.809,
      "step": 5
    },
    {
      "epoch": 0.012326656394453005,
      "grad_norm": 123.82645416259766,
      "learning_rate": 6e-05,
      "loss": 85.2479,
      "step": 6
    },
    {
      "epoch": 0.014381099126861838,
      "grad_norm": 148.07144165039062,
      "learning_rate": 7e-05,
      "loss": 79.2969,
      "step": 7
    },
    {
      "epoch": 0.016435541859270673,
      "grad_norm": 127.11111450195312,
      "learning_rate": 8e-05,
      "loss": 73.8599,
      "step": 8
    },
    {
      "epoch": 0.01848998459167951,
      "grad_norm": 146.44976806640625,
      "learning_rate": 9e-05,
      "loss": 74.0257,
      "step": 9
    },
    {
      "epoch": 0.02054442732408834,
      "grad_norm": 166.2652130126953,
      "learning_rate": 0.0001,
      "loss": 73.5464,
      "step": 10
    },
    {
      "epoch": 0.02054442732408834,
      "eval_loss": 2.1906113624572754,
      "eval_runtime": 291.9218,
      "eval_samples_per_second": 11.236,
      "eval_steps_per_second": 2.809,
      "step": 10
    },
    {
      "epoch": 0.022598870056497175,
      "grad_norm": 182.4556884765625,
      "learning_rate": 9.755282581475769e-05,
      "loss": 68.4839,
      "step": 11
    },
    {
      "epoch": 0.02465331278890601,
      "grad_norm": 198.03158569335938,
      "learning_rate": 9.045084971874738e-05,
      "loss": 67.4511,
      "step": 12
    },
    {
      "epoch": 0.02670775552131484,
      "grad_norm": 212.62405395507812,
      "learning_rate": 7.938926261462366e-05,
      "loss": 64.195,
      "step": 13
    },
    {
      "epoch": 0.028762198253723677,
      "grad_norm": 215.69439697265625,
      "learning_rate": 6.545084971874738e-05,
      "loss": 62.9509,
      "step": 14
    },
    {
      "epoch": 0.030816640986132512,
      "grad_norm": 143.1745147705078,
      "learning_rate": 5e-05,
      "loss": 62.3859,
      "step": 15
    },
    {
      "epoch": 0.030816640986132512,
      "eval_loss": 1.8680182695388794,
      "eval_runtime": 291.9506,
      "eval_samples_per_second": 11.235,
      "eval_steps_per_second": 2.809,
      "step": 15
    },
    {
      "epoch": 0.03287108371854135,
      "grad_norm": 89.2127456665039,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 62.5249,
      "step": 16
    },
    {
      "epoch": 0.03492552645095018,
      "grad_norm": 77.51390075683594,
      "learning_rate": 2.061073738537635e-05,
      "loss": 59.9075,
      "step": 17
    },
    {
      "epoch": 0.03697996918335902,
      "grad_norm": 63.38047790527344,
      "learning_rate": 9.549150281252633e-06,
      "loss": 58.074,
      "step": 18
    },
    {
      "epoch": 0.03903441191576785,
      "grad_norm": 67.86468505859375,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 56.1145,
      "step": 19
    },
    {
      "epoch": 0.04108885464817668,
      "grad_norm": 66.08454895019531,
      "learning_rate": 0.0,
      "loss": 58.0635,
      "step": 20
    },
    {
      "epoch": 0.04108885464817668,
      "eval_loss": 1.7998082637786865,
      "eval_runtime": 291.8631,
      "eval_samples_per_second": 11.238,
      "eval_steps_per_second": 2.81,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.500033945521357e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}