{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 99999999,
  "global_step": 5614,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017815388041420778,
      "grad_norm": 232.1993865966797,
      "learning_rate": 5e-05,
      "loss": 175.5579,
      "step": 1
    },
    {
      "epoch": 0.00017815388041420778,
      "eval_accuracy": 0.018891725076294615,
      "eval_loss": 10.400674819946289,
      "eval_runtime": 157.3868,
      "eval_samples_per_second": 63.55,
      "eval_steps_per_second": 7.949,
      "step": 1
    },
    {
      "epoch": 0.00035630776082841556,
      "grad_norm": 114.17350769042969,
      "learning_rate": 4.99910936943356e-05,
      "loss": 160.0191,
      "step": 2
    },
    {
      "epoch": 0.00035630776082841556,
      "eval_accuracy": 0.01293475420262966,
      "eval_loss": 10.170297622680664,
      "eval_runtime": 161.9764,
      "eval_samples_per_second": 61.75,
      "eval_steps_per_second": 7.723,
      "step": 2
    },
    {
      "epoch": 0.0007126155216568311,
      "grad_norm": 51.90617370605469,
      "learning_rate": 4.9973281083006775e-05,
      "loss": 152.5677,
      "step": 4
    },
    {
      "epoch": 0.0007126155216568311,
      "eval_accuracy": 0.022687935531173334,
      "eval_loss": 9.972246170043945,
      "eval_runtime": 181.1968,
      "eval_samples_per_second": 55.2,
      "eval_steps_per_second": 6.904,
      "step": 4
    },
    {
      "epoch": 0.0014252310433136622,
      "grad_norm": 79.16446685791016,
      "learning_rate": 4.993765586034913e-05,
      "loss": 145.6416,
      "step": 8
    },
    {
      "epoch": 0.0014252310433136622,
      "eval_accuracy": 0.08070331192803473,
      "eval_loss": 10.352470397949219,
      "eval_runtime": 167.7318,
      "eval_samples_per_second": 59.631,
      "eval_steps_per_second": 7.458,
      "step": 8
    },
    {
      "epoch": 0.0028504620866273245,
      "grad_norm": 62.1901969909668,
      "learning_rate": 4.9866405415033846e-05,
      "loss": 139.5395,
      "step": 16
    },
    {
      "epoch": 0.0028504620866273245,
      "eval_accuracy": 0.09230773591127327,
      "eval_loss": 9.133565902709961,
      "eval_runtime": 167.1804,
      "eval_samples_per_second": 59.828,
      "eval_steps_per_second": 7.483,
      "step": 16
    },
    {
      "epoch": 0.005700924173254649,
      "grad_norm": 48.63093566894531,
      "learning_rate": 4.972390452440328e-05,
      "loss": 113.2903,
      "step": 32
    },
    {
      "epoch": 0.005700924173254649,
      "eval_accuracy": 0.12488157305000389,
      "eval_loss": 8.238554954528809,
      "eval_runtime": 159.9917,
      "eval_samples_per_second": 62.516,
      "eval_steps_per_second": 7.819,
      "step": 32
    },
    {
      "epoch": 0.011401848346509298,
      "grad_norm": 30.36475372314453,
      "learning_rate": 4.9438902743142145e-05,
      "loss": 92.4312,
      "step": 64
    },
    {
      "epoch": 0.011401848346509298,
      "eval_accuracy": 0.13147976465313,
      "eval_loss": 7.147886276245117,
      "eval_runtime": 166.5905,
      "eval_samples_per_second": 60.039,
      "eval_steps_per_second": 7.509,
      "step": 64
    },
    {
      "epoch": 0.022803696693018596,
      "grad_norm": 53.339027404785156,
      "learning_rate": 4.886889918061988e-05,
      "loss": 63.2434,
      "step": 128
    },
    {
      "epoch": 0.022803696693018596,
      "eval_accuracy": 0.16450072644317668,
      "eval_loss": 6.494359493255615,
      "eval_runtime": 168.6415,
      "eval_samples_per_second": 59.309,
      "eval_steps_per_second": 7.418,
      "step": 128
    },
    {
      "epoch": 0.04560739338603719,
      "grad_norm": 12.019591331481934,
      "learning_rate": 4.7728892055575344e-05,
      "loss": 57.3288,
      "step": 256
    },
    {
      "epoch": 0.04560739338603719,
      "eval_accuracy": 0.14192156681078252,
      "eval_loss": 6.2028303146362305,
      "eval_runtime": 180.9015,
      "eval_samples_per_second": 55.29,
      "eval_steps_per_second": 6.915,
      "step": 256
    },
    {
      "epoch": 0.09121478677207438,
      "grad_norm": 14.86228084564209,
      "learning_rate": 4.544887780548628e-05,
      "loss": 55.0041,
      "step": 512
    },
    {
      "epoch": 0.09121478677207438,
      "eval_accuracy": 0.16740767193579856,
      "eval_loss": 5.706745147705078,
      "eval_runtime": 182.3289,
      "eval_samples_per_second": 54.857,
      "eval_steps_per_second": 6.861,
      "step": 512
    },
    {
      "epoch": 0.18242957354414877,
      "grad_norm": 13.710566520690918,
      "learning_rate": 4.0888849305308155e-05,
      "loss": 50.6182,
      "step": 1024
    },
    {
      "epoch": 0.18242957354414877,
      "eval_accuracy": 0.19536239379690046,
      "eval_loss": 5.437285423278809,
      "eval_runtime": 159.2749,
      "eval_samples_per_second": 62.797,
      "eval_steps_per_second": 7.854,
      "step": 1024
    },
    {
      "epoch": 0.36485914708829753,
      "grad_norm": 23.54279327392578,
      "learning_rate": 3.17687923049519e-05,
      "loss": 46.5895,
      "step": 2048
    },
    {
      "epoch": 0.36485914708829753,
      "eval_accuracy": 0.12475931011256204,
      "eval_loss": 6.226956844329834,
      "eval_runtime": 165.8237,
      "eval_samples_per_second": 60.317,
      "eval_steps_per_second": 7.544,
      "step": 2048
    },
    {
      "epoch": 0.7297182941765951,
      "grad_norm": 26.13650894165039,
      "learning_rate": 1.3528678304239403e-05,
      "loss": 55.4762,
      "step": 4096
    },
    {
      "epoch": 0.7297182941765951,
      "eval_accuracy": 0.2658144812875157,
      "eval_loss": 4.172967433929443,
      "eval_runtime": 161.3436,
      "eval_samples_per_second": 61.992,
      "eval_steps_per_second": 7.754,
      "step": 4096
    }
  ],
  "logging_steps": 99999999,
  "max_steps": 5614,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 99999999,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.75465675718656e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}