{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 200,
  "global_step": 613,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 1.3762401342391968,
      "learning_rate": 9.8e-05,
      "loss": 1.5317,
      "step": 50
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 4.053397178649902,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.3195,
      "step": 100
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 0.9375177621841431,
      "learning_rate": 0.00018089668615984406,
      "loss": 1.2279,
      "step": 150
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 1.0333521366119385,
      "learning_rate": 0.00016140350877192982,
      "loss": 1.2534,
      "step": 200
    },
    {
      "epoch": 0.32653061224489793,
      "eval_loss": 1.2725698947906494,
      "eval_runtime": 8.5122,
      "eval_samples_per_second": 23.496,
      "eval_steps_per_second": 2.937,
      "step": 200
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 1.3602248430252075,
      "learning_rate": 0.00014191033138401558,
      "loss": 1.2636,
      "step": 250
    },
    {
      "epoch": 0.4897959183673469,
      "grad_norm": 1.199912667274475,
      "learning_rate": 0.00012241715399610137,
      "loss": 1.2137,
      "step": 300
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.8509014248847961,
      "learning_rate": 0.00010292397660818713,
      "loss": 1.2283,
      "step": 350
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 0.7254706025123596,
      "learning_rate": 8.343079922027291e-05,
      "loss": 1.2312,
      "step": 400
    },
    {
      "epoch": 0.6530612244897959,
      "eval_loss": 1.2610524892807007,
      "eval_runtime": 8.5063,
      "eval_samples_per_second": 23.512,
      "eval_steps_per_second": 2.939,
      "step": 400
    },
    {
      "epoch": 0.7346938775510204,
      "grad_norm": 0.9536640048027039,
      "learning_rate": 6.393762183235867e-05,
      "loss": 1.2136,
      "step": 450
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 0.8071808218955994,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.2294,
      "step": 500
    },
    {
      "epoch": 0.8979591836734694,
      "grad_norm": 0.8645896911621094,
      "learning_rate": 2.4951267056530216e-05,
      "loss": 1.2072,
      "step": 550
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 0.8687503337860107,
      "learning_rate": 5.458089668615984e-06,
      "loss": 1.2058,
      "step": 600
    },
    {
      "epoch": 0.9795918367346939,
      "eval_loss": 1.252403736114502,
      "eval_runtime": 8.5086,
      "eval_samples_per_second": 23.505,
      "eval_steps_per_second": 2.938,
      "step": 600
    }
  ],
  "logging_steps": 50,
  "max_steps": 613,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.144810727112704e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}