{
  "best_metric": 0.8372765183448792,
  "best_model_checkpoint": "/content/Nasa_Mars_Model_Outputs/checkpoint-10",
  "epoch": 0.05001705126747755,
  "eval_steps": 10,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004547004660679777,
      "grad_norm": 8.836596488952637,
      "learning_rate": 2e-05,
      "loss": 0.6073,
      "step": 10
    },
    {
      "epoch": 0.004547004660679777,
      "eval_loss": 0.8372765183448792,
      "eval_runtime": 20.6797,
      "eval_samples_per_second": 2.418,
      "eval_steps_per_second": 2.418,
      "step": 10
    },
    {
      "epoch": 0.009094009321359554,
      "grad_norm": 9.525543212890625,
      "learning_rate": 4e-05,
      "loss": 0.5308,
      "step": 20
    },
    {
      "epoch": 0.009094009321359554,
      "eval_loss": 0.8388195037841797,
      "eval_runtime": 20.8936,
      "eval_samples_per_second": 2.393,
      "eval_steps_per_second": 2.393,
      "step": 20
    },
    {
      "epoch": 0.013641013982039332,
      "grad_norm": 8.243130683898926,
      "learning_rate": 6e-05,
      "loss": 0.4263,
      "step": 30
    },
    {
      "epoch": 0.013641013982039332,
      "eval_loss": 0.9063456654548645,
      "eval_runtime": 20.8341,
      "eval_samples_per_second": 2.4,
      "eval_steps_per_second": 2.4,
      "step": 30
    },
    {
      "epoch": 0.018188018642719107,
      "grad_norm": 5.157824993133545,
      "learning_rate": 8e-05,
      "loss": 0.3455,
      "step": 40
    },
    {
      "epoch": 0.018188018642719107,
      "eval_loss": 0.9459993839263916,
      "eval_runtime": 20.8498,
      "eval_samples_per_second": 2.398,
      "eval_steps_per_second": 2.398,
      "step": 40
    },
    {
      "epoch": 0.022735023303398886,
      "grad_norm": 9.51492977142334,
      "learning_rate": 0.0001,
      "loss": 0.317,
      "step": 50
    },
    {
      "epoch": 0.022735023303398886,
      "eval_loss": 0.9320575594902039,
      "eval_runtime": 20.8158,
      "eval_samples_per_second": 2.402,
      "eval_steps_per_second": 2.402,
      "step": 50
    },
    {
      "epoch": 0.027282027964078664,
      "grad_norm": 8.233291625976562,
      "learning_rate": 9.977000919963202e-05,
      "loss": 0.3006,
      "step": 60
    },
    {
      "epoch": 0.027282027964078664,
      "eval_loss": 0.9950161576271057,
      "eval_runtime": 20.7989,
      "eval_samples_per_second": 2.404,
      "eval_steps_per_second": 2.404,
      "step": 60
    },
    {
      "epoch": 0.03182903262475844,
      "grad_norm": 11.2651948928833,
      "learning_rate": 9.954001839926403e-05,
      "loss": 0.3331,
      "step": 70
    },
    {
      "epoch": 0.03182903262475844,
      "eval_loss": 0.9437124729156494,
      "eval_runtime": 20.8698,
      "eval_samples_per_second": 2.396,
      "eval_steps_per_second": 2.396,
      "step": 70
    },
    {
      "epoch": 0.036376037285438215,
      "grad_norm": 7.479197025299072,
      "learning_rate": 9.931002759889605e-05,
      "loss": 0.2957,
      "step": 80
    },
    {
      "epoch": 0.036376037285438215,
      "eval_loss": 0.9456791877746582,
      "eval_runtime": 20.8644,
      "eval_samples_per_second": 2.396,
      "eval_steps_per_second": 2.396,
      "step": 80
    },
    {
      "epoch": 0.040923041946118,
      "grad_norm": 8.659111976623535,
      "learning_rate": 9.908003679852806e-05,
      "loss": 0.3325,
      "step": 90
    },
    {
      "epoch": 0.040923041946118,
      "eval_loss": 0.9326030015945435,
      "eval_runtime": 20.8374,
      "eval_samples_per_second": 2.4,
      "eval_steps_per_second": 2.4,
      "step": 90
    },
    {
      "epoch": 0.04547004660679777,
      "grad_norm": 4.722876071929932,
      "learning_rate": 9.885004599816008e-05,
      "loss": 0.2857,
      "step": 100
    },
    {
      "epoch": 0.04547004660679777,
      "eval_loss": 0.9288083910942078,
      "eval_runtime": 20.844,
      "eval_samples_per_second": 2.399,
      "eval_steps_per_second": 2.399,
      "step": 100
    },
    {
      "epoch": 0.05001705126747755,
      "grad_norm": 6.449366569519043,
      "learning_rate": 9.86200551977921e-05,
      "loss": 0.3643,
      "step": 110
    },
    {
      "epoch": 0.05001705126747755,
      "eval_loss": 0.9256532192230225,
      "eval_runtime": 20.8316,
      "eval_samples_per_second": 2.4,
      "eval_steps_per_second": 2.4,
      "step": 110
    }
  ],
  "logging_steps": 10,
  "max_steps": 4398,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9148674554486016.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}