{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014665982254161472,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00029331964508322946,
      "eval_loss": 1.2019259929656982,
      "eval_runtime": 92.5873,
      "eval_samples_per_second": 15.51,
      "eval_steps_per_second": 7.755,
      "step": 1
    },
    {
      "epoch": 0.0014665982254161473,
      "grad_norm": 0.19067971408367157,
      "learning_rate": 5e-05,
      "loss": 1.2085,
      "step": 5
    },
    {
      "epoch": 0.0029331964508322946,
      "grad_norm": 0.25900715589523315,
      "learning_rate": 0.0001,
      "loss": 1.2128,
      "step": 10
    },
    {
      "epoch": 0.0029331964508322946,
      "eval_loss": 1.1875132322311401,
      "eval_runtime": 92.6172,
      "eval_samples_per_second": 15.505,
      "eval_steps_per_second": 7.752,
      "step": 10
    },
    {
      "epoch": 0.004399794676248442,
      "grad_norm": 0.24131667613983154,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.1178,
      "step": 15
    },
    {
      "epoch": 0.005866392901664589,
      "grad_norm": 0.25273051857948303,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1167,
      "step": 20
    },
    {
      "epoch": 0.005866392901664589,
      "eval_loss": 1.1158852577209473,
      "eval_runtime": 92.7043,
      "eval_samples_per_second": 15.49,
      "eval_steps_per_second": 7.745,
      "step": 20
    },
    {
      "epoch": 0.007332991127080736,
      "grad_norm": 0.2933986485004425,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.1302,
      "step": 25
    },
    {
      "epoch": 0.008799589352496884,
      "grad_norm": 0.2545674443244934,
      "learning_rate": 5e-05,
      "loss": 1.2154,
      "step": 30
    },
    {
      "epoch": 0.008799589352496884,
      "eval_loss": 1.0693620443344116,
      "eval_runtime": 92.6898,
      "eval_samples_per_second": 15.493,
      "eval_steps_per_second": 7.746,
      "step": 30
    },
    {
      "epoch": 0.010266187577913031,
      "grad_norm": 0.3354320824146271,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.0942,
      "step": 35
    },
    {
      "epoch": 0.011732785803329178,
      "grad_norm": 0.32417094707489014,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.2064,
      "step": 40
    },
    {
      "epoch": 0.011732785803329178,
      "eval_loss": 1.0582767724990845,
      "eval_runtime": 93.007,
      "eval_samples_per_second": 15.44,
      "eval_steps_per_second": 7.72,
      "step": 40
    },
    {
      "epoch": 0.013199384028745325,
      "grad_norm": 0.31942957639694214,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.07,
      "step": 45
    },
    {
      "epoch": 0.014665982254161472,
      "grad_norm": 0.30771729350090027,
      "learning_rate": 0.0,
      "loss": 1.0629,
      "step": 50
    },
    {
      "epoch": 0.014665982254161472,
      "eval_loss": 1.0569509267807007,
      "eval_runtime": 93.3322,
      "eval_samples_per_second": 15.386,
      "eval_steps_per_second": 7.693,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8843877933907968.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}