{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04156275976724855,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008312551953449709,
      "eval_loss": 1.6690250635147095,
      "eval_runtime": 31.8713,
      "eval_samples_per_second": 15.908,
      "eval_steps_per_second": 7.97,
      "step": 1
    },
    {
      "epoch": 0.004156275976724855,
      "grad_norm": 13.511648178100586,
      "learning_rate": 5e-05,
      "loss": 6.5265,
      "step": 5
    },
    {
      "epoch": 0.00831255195344971,
      "grad_norm": 11.825039863586426,
      "learning_rate": 0.0001,
      "loss": 5.8111,
      "step": 10
    },
    {
      "epoch": 0.00831255195344971,
      "eval_loss": 1.2978507280349731,
      "eval_runtime": 32.0052,
      "eval_samples_per_second": 15.841,
      "eval_steps_per_second": 7.936,
      "step": 10
    },
    {
      "epoch": 0.012468827930174564,
      "grad_norm": 19.295320510864258,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.9983,
      "step": 15
    },
    {
      "epoch": 0.01662510390689942,
      "grad_norm": 14.160016059875488,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.7368,
      "step": 20
    },
    {
      "epoch": 0.01662510390689942,
      "eval_loss": 1.143140196800232,
      "eval_runtime": 32.156,
      "eval_samples_per_second": 15.767,
      "eval_steps_per_second": 7.899,
      "step": 20
    },
    {
      "epoch": 0.020781379883624274,
      "grad_norm": 14.056801795959473,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.3062,
      "step": 25
    },
    {
      "epoch": 0.02493765586034913,
      "grad_norm": 11.807455062866211,
      "learning_rate": 5e-05,
      "loss": 4.4379,
      "step": 30
    },
    {
      "epoch": 0.02493765586034913,
      "eval_loss": 1.13102388381958,
      "eval_runtime": 32.3127,
      "eval_samples_per_second": 15.69,
      "eval_steps_per_second": 7.861,
      "step": 30
    },
    {
      "epoch": 0.029093931837073983,
      "grad_norm": 14.067438125610352,
      "learning_rate": 3.086582838174551e-05,
      "loss": 4.766,
      "step": 35
    },
    {
      "epoch": 0.03325020781379884,
      "grad_norm": 13.664603233337402,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 4.6996,
      "step": 40
    },
    {
      "epoch": 0.03325020781379884,
      "eval_loss": 1.12453293800354,
      "eval_runtime": 32.3026,
      "eval_samples_per_second": 15.695,
      "eval_steps_per_second": 7.863,
      "step": 40
    },
    {
      "epoch": 0.03740648379052369,
      "grad_norm": 16.15739631652832,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 4.8997,
      "step": 45
    },
    {
      "epoch": 0.04156275976724855,
      "grad_norm": 13.962651252746582,
      "learning_rate": 0.0,
      "loss": 4.355,
      "step": 50
    },
    {
      "epoch": 0.04156275976724855,
      "eval_loss": 1.1229740381240845,
      "eval_runtime": 32.1421,
      "eval_samples_per_second": 15.774,
      "eval_steps_per_second": 7.902,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8767214400307200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}