{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0046280226773111185,
  "eval_steps": 1,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00046280226773111186,
      "grad_norm": 1.9790486097335815,
      "learning_rate": 2e-05,
      "loss": 5.8906,
      "step": 1
    },
    {
      "epoch": 0.00046280226773111186,
      "eval_loss": 5.601900100708008,
      "eval_runtime": 17.6094,
      "eval_samples_per_second": 51.677,
      "eval_steps_per_second": 25.838,
      "step": 1
    },
    {
      "epoch": 0.0009256045354622237,
      "grad_norm": 1.6375300884246826,
      "learning_rate": 4e-05,
      "loss": 5.052,
      "step": 2
    },
    {
      "epoch": 0.0009256045354622237,
      "eval_loss": 5.600701808929443,
      "eval_runtime": 17.0754,
      "eval_samples_per_second": 53.293,
      "eval_steps_per_second": 26.646,
      "step": 2
    },
    {
      "epoch": 0.0013884068031933356,
      "grad_norm": 1.5836906433105469,
      "learning_rate": 6e-05,
      "loss": 4.8669,
      "step": 3
    },
    {
      "epoch": 0.0013884068031933356,
      "eval_loss": 5.597599983215332,
      "eval_runtime": 17.0811,
      "eval_samples_per_second": 53.275,
      "eval_steps_per_second": 26.638,
      "step": 3
    },
    {
      "epoch": 0.0018512090709244474,
      "grad_norm": 1.690783143043518,
      "learning_rate": 8e-05,
      "loss": 5.6607,
      "step": 4
    },
    {
      "epoch": 0.0018512090709244474,
      "eval_loss": 5.591892719268799,
      "eval_runtime": 17.1298,
      "eval_samples_per_second": 53.124,
      "eval_steps_per_second": 26.562,
      "step": 4
    },
    {
      "epoch": 0.0023140113386555593,
      "grad_norm": 1.4310377836227417,
      "learning_rate": 0.0001,
      "loss": 4.7033,
      "step": 5
    },
    {
      "epoch": 0.0023140113386555593,
      "eval_loss": 5.578213214874268,
      "eval_runtime": 17.0825,
      "eval_samples_per_second": 53.271,
      "eval_steps_per_second": 26.635,
      "step": 5
    },
    {
      "epoch": 0.0027768136063866713,
      "grad_norm": 1.90717351436615,
      "learning_rate": 0.00012,
      "loss": 5.7995,
      "step": 6
    },
    {
      "epoch": 0.0027768136063866713,
      "eval_loss": 5.5544233322143555,
      "eval_runtime": 17.0818,
      "eval_samples_per_second": 53.273,
      "eval_steps_per_second": 26.637,
      "step": 6
    },
    {
      "epoch": 0.0032396158741177833,
      "grad_norm": 1.6457782983779907,
      "learning_rate": 0.00014,
      "loss": 5.7634,
      "step": 7
    },
    {
      "epoch": 0.0032396158741177833,
      "eval_loss": 5.521738529205322,
      "eval_runtime": 17.0922,
      "eval_samples_per_second": 53.241,
      "eval_steps_per_second": 26.62,
      "step": 7
    },
    {
      "epoch": 0.003702418141848895,
      "grad_norm": 1.550390601158142,
      "learning_rate": 0.00016,
      "loss": 4.7882,
      "step": 8
    },
    {
      "epoch": 0.003702418141848895,
      "eval_loss": 5.473212718963623,
      "eval_runtime": 17.096,
      "eval_samples_per_second": 53.229,
      "eval_steps_per_second": 26.614,
      "step": 8
    },
    {
      "epoch": 0.004165220409580007,
      "grad_norm": 1.82877779006958,
      "learning_rate": 0.00018,
      "loss": 5.2751,
      "step": 9
    },
    {
      "epoch": 0.004165220409580007,
      "eval_loss": 5.407704830169678,
      "eval_runtime": 17.093,
      "eval_samples_per_second": 53.238,
      "eval_steps_per_second": 26.619,
      "step": 9
    },
    {
      "epoch": 0.0046280226773111185,
      "grad_norm": 1.564656376838684,
      "learning_rate": 0.0002,
      "loss": 5.33,
      "step": 10
    },
    {
      "epoch": 0.0046280226773111185,
      "eval_loss": 5.328363418579102,
      "eval_runtime": 17.103,
      "eval_samples_per_second": 53.207,
      "eval_steps_per_second": 26.603,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 137170601902080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}