{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016256197675363732,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001625619767536373,
      "grad_norm": 0.9014779329299927,
      "learning_rate": 2e-05,
      "loss": 3.564,
      "step": 1
    },
    {
      "epoch": 0.0001625619767536373,
      "eval_loss": 0.9564012289047241,
      "eval_runtime": 116.1522,
      "eval_samples_per_second": 22.307,
      "eval_steps_per_second": 11.158,
      "step": 1
    },
    {
      "epoch": 0.0003251239535072746,
      "grad_norm": 1.5426355600357056,
      "learning_rate": 4e-05,
      "loss": 3.7399,
      "step": 2
    },
    {
      "epoch": 0.000487685930260912,
      "grad_norm": 1.198432445526123,
      "learning_rate": 6e-05,
      "loss": 3.8604,
      "step": 3
    },
    {
      "epoch": 0.000487685930260912,
      "eval_loss": 0.9547381401062012,
      "eval_runtime": 116.2655,
      "eval_samples_per_second": 22.285,
      "eval_steps_per_second": 11.147,
      "step": 3
    },
    {
      "epoch": 0.0006502479070145493,
      "grad_norm": 1.0430612564086914,
      "learning_rate": 8e-05,
      "loss": 3.7367,
      "step": 4
    },
    {
      "epoch": 0.0008128098837681866,
      "grad_norm": 1.248558521270752,
      "learning_rate": 0.0001,
      "loss": 3.9487,
      "step": 5
    },
    {
      "epoch": 0.000975371860521824,
      "grad_norm": 1.403568148612976,
      "learning_rate": 0.00012,
      "loss": 3.9923,
      "step": 6
    },
    {
      "epoch": 0.000975371860521824,
      "eval_loss": 0.940264105796814,
      "eval_runtime": 116.3852,
      "eval_samples_per_second": 22.262,
      "eval_steps_per_second": 11.135,
      "step": 6
    },
    {
      "epoch": 0.0011379338372754612,
      "grad_norm": 1.4722180366516113,
      "learning_rate": 0.00014,
      "loss": 3.7938,
      "step": 7
    },
    {
      "epoch": 0.0013004958140290985,
      "grad_norm": 1.291874647140503,
      "learning_rate": 0.00016,
      "loss": 3.8979,
      "step": 8
    },
    {
      "epoch": 0.001463057790782736,
      "grad_norm": 3.740861415863037,
      "learning_rate": 0.00018,
      "loss": 3.7692,
      "step": 9
    },
    {
      "epoch": 0.001463057790782736,
      "eval_loss": 0.8853321075439453,
      "eval_runtime": 116.2495,
      "eval_samples_per_second": 22.288,
      "eval_steps_per_second": 11.148,
      "step": 9
    },
    {
      "epoch": 0.0016256197675363732,
      "grad_norm": 1.4085177183151245,
      "learning_rate": 0.0002,
      "loss": 3.3796,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1710169792708608.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}