{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001463057790782736,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001625619767536373,
      "grad_norm": 2.5117485523223877,
      "learning_rate": 2e-05,
      "loss": 2.5487,
      "step": 1
    },
    {
      "epoch": 0.0001625619767536373,
      "eval_loss": 2.569087266921997,
      "eval_runtime": 60.1302,
      "eval_samples_per_second": 43.09,
      "eval_steps_per_second": 21.553,
      "step": 1
    },
    {
      "epoch": 0.0003251239535072746,
      "grad_norm": 2.795823574066162,
      "learning_rate": 4e-05,
      "loss": 2.7399,
      "step": 2
    },
    {
      "epoch": 0.000487685930260912,
      "grad_norm": 2.526634454727173,
      "learning_rate": 6e-05,
      "loss": 2.8967,
      "step": 3
    },
    {
      "epoch": 0.000487685930260912,
      "eval_loss": 2.552489757537842,
      "eval_runtime": 59.9224,
      "eval_samples_per_second": 43.239,
      "eval_steps_per_second": 21.628,
      "step": 3
    },
    {
      "epoch": 0.0006502479070145493,
      "grad_norm": 2.624401807785034,
      "learning_rate": 8e-05,
      "loss": 2.4723,
      "step": 4
    },
    {
      "epoch": 0.0008128098837681866,
      "grad_norm": 2.232449531555176,
      "learning_rate": 0.0001,
      "loss": 2.1829,
      "step": 5
    },
    {
      "epoch": 0.000975371860521824,
      "grad_norm": 2.4832470417022705,
      "learning_rate": 0.00012,
      "loss": 2.5521,
      "step": 6
    },
    {
      "epoch": 0.000975371860521824,
      "eval_loss": 2.3244712352752686,
      "eval_runtime": 59.91,
      "eval_samples_per_second": 43.248,
      "eval_steps_per_second": 21.632,
      "step": 6
    },
    {
      "epoch": 0.0011379338372754612,
      "grad_norm": 2.2147326469421387,
      "learning_rate": 0.00014,
      "loss": 2.1623,
      "step": 7
    },
    {
      "epoch": 0.0013004958140290985,
      "grad_norm": 2.1398725509643555,
      "learning_rate": 0.00016,
      "loss": 2.1486,
      "step": 8
    },
    {
      "epoch": 0.001463057790782736,
      "grad_norm": 1.8721078634262085,
      "learning_rate": 0.00018,
      "loss": 1.9405,
      "step": 9
    },
    {
      "epoch": 0.001463057790782736,
      "eval_loss": 2.027778387069702,
      "eval_runtime": 59.9832,
      "eval_samples_per_second": 43.195,
      "eval_steps_per_second": 21.606,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 697505855569920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}