{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009989178390077416,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033297261300258056,
      "eval_loss": 2.9086782932281494,
      "eval_runtime": 18.7487,
      "eval_samples_per_second": 67.471,
      "eval_steps_per_second": 33.762,
      "step": 1
    },
    {
      "epoch": 0.0009989178390077415,
      "grad_norm": 6.129505634307861,
      "learning_rate": 3e-05,
      "loss": 12.3931,
      "step": 3
    },
    {
      "epoch": 0.0016648630650129028,
      "eval_loss": 2.895609140396118,
      "eval_runtime": 17.9489,
      "eval_samples_per_second": 70.478,
      "eval_steps_per_second": 35.267,
      "step": 5
    },
    {
      "epoch": 0.001997835678015483,
      "grad_norm": 4.335046291351318,
      "learning_rate": 6e-05,
      "loss": 12.4854,
      "step": 6
    },
    {
      "epoch": 0.002996753517023225,
      "grad_norm": 4.665907382965088,
      "learning_rate": 9e-05,
      "loss": 11.4776,
      "step": 9
    },
    {
      "epoch": 0.0033297261300258055,
      "eval_loss": 2.8543288707733154,
      "eval_runtime": 17.6632,
      "eval_samples_per_second": 71.618,
      "eval_steps_per_second": 35.837,
      "step": 10
    },
    {
      "epoch": 0.003995671356030966,
      "grad_norm": 4.6682515144348145,
      "learning_rate": 9.755282581475769e-05,
      "loss": 12.2199,
      "step": 12
    },
    {
      "epoch": 0.004994589195038708,
      "grad_norm": 3.9350109100341797,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.5342,
      "step": 15
    },
    {
      "epoch": 0.004994589195038708,
      "eval_loss": 2.8267624378204346,
      "eval_runtime": 17.7401,
      "eval_samples_per_second": 71.307,
      "eval_steps_per_second": 35.682,
      "step": 15
    },
    {
      "epoch": 0.00599350703404645,
      "grad_norm": 4.3555073738098145,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.0662,
      "step": 18
    },
    {
      "epoch": 0.006659452260051611,
      "eval_loss": 2.8134405612945557,
      "eval_runtime": 17.6551,
      "eval_samples_per_second": 71.651,
      "eval_steps_per_second": 35.854,
      "step": 20
    },
    {
      "epoch": 0.006992424873054191,
      "grad_norm": 5.134154319763184,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 10.609,
      "step": 21
    },
    {
      "epoch": 0.007991342712061932,
      "grad_norm": 4.343358516693115,
      "learning_rate": 2.061073738537635e-05,
      "loss": 11.3791,
      "step": 24
    },
    {
      "epoch": 0.008324315325064514,
      "eval_loss": 2.8060555458068848,
      "eval_runtime": 17.8185,
      "eval_samples_per_second": 70.993,
      "eval_steps_per_second": 35.525,
      "step": 25
    },
    {
      "epoch": 0.008990260551069674,
      "grad_norm": 4.7815423011779785,
      "learning_rate": 5.449673790581611e-06,
      "loss": 10.3554,
      "step": 27
    },
    {
      "epoch": 0.009989178390077416,
      "grad_norm": 4.206421375274658,
      "learning_rate": 0.0,
      "loss": 11.2497,
      "step": 30
    },
    {
      "epoch": 0.009989178390077416,
      "eval_loss": 2.8042778968811035,
      "eval_runtime": 17.5007,
      "eval_samples_per_second": 72.283,
      "eval_steps_per_second": 36.17,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 465459228966912.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}