{
  "best_metric": 0.7523407340049744,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.4979253112033195,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016597510373443983,
      "eval_loss": 0.9781717658042908,
      "eval_runtime": 1.475,
      "eval_samples_per_second": 34.576,
      "eval_steps_per_second": 8.813,
      "step": 1
    },
    {
      "epoch": 0.04979253112033195,
      "grad_norm": 0.5929073691368103,
      "learning_rate": 0.00012,
      "loss": 3.4971,
      "step": 3
    },
    {
      "epoch": 0.08298755186721991,
      "eval_loss": 0.951536238193512,
      "eval_runtime": 1.4731,
      "eval_samples_per_second": 34.621,
      "eval_steps_per_second": 8.825,
      "step": 5
    },
    {
      "epoch": 0.0995850622406639,
      "grad_norm": 0.8033410906791687,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.7891,
      "step": 6
    },
    {
      "epoch": 0.14937759336099585,
      "grad_norm": 0.8104145526885986,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.3946,
      "step": 9
    },
    {
      "epoch": 0.16597510373443983,
      "eval_loss": 0.8440332412719727,
      "eval_runtime": 1.4766,
      "eval_samples_per_second": 34.539,
      "eval_steps_per_second": 8.804,
      "step": 10
    },
    {
      "epoch": 0.1991701244813278,
      "grad_norm": 1.1058402061462402,
      "learning_rate": 0.000163742398974869,
      "loss": 3.708,
      "step": 12
    },
    {
      "epoch": 0.24896265560165975,
      "grad_norm": 1.3736001253128052,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.6856,
      "step": 15
    },
    {
      "epoch": 0.24896265560165975,
      "eval_loss": 0.8092417120933533,
      "eval_runtime": 1.4781,
      "eval_samples_per_second": 34.504,
      "eval_steps_per_second": 8.795,
      "step": 15
    },
    {
      "epoch": 0.2987551867219917,
      "grad_norm": 1.0854389667510986,
      "learning_rate": 9.372094804706867e-05,
      "loss": 3.0305,
      "step": 18
    },
    {
      "epoch": 0.33195020746887965,
      "eval_loss": 0.7681506276130676,
      "eval_runtime": 1.4779,
      "eval_samples_per_second": 34.508,
      "eval_steps_per_second": 8.796,
      "step": 20
    },
    {
      "epoch": 0.34854771784232363,
      "grad_norm": 0.6307705640792847,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.9407,
      "step": 21
    },
    {
      "epoch": 0.3983402489626556,
      "grad_norm": 0.712988018989563,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.9777,
      "step": 24
    },
    {
      "epoch": 0.4149377593360996,
      "eval_loss": 0.7552775144577026,
      "eval_runtime": 1.4738,
      "eval_samples_per_second": 34.605,
      "eval_steps_per_second": 8.821,
      "step": 25
    },
    {
      "epoch": 0.44813278008298757,
      "grad_norm": 0.851246178150177,
      "learning_rate": 7.022351411174866e-06,
      "loss": 3.1521,
      "step": 27
    },
    {
      "epoch": 0.4979253112033195,
      "grad_norm": 1.9206782579421997,
      "learning_rate": 0.0,
      "loss": 3.5759,
      "step": 30
    },
    {
      "epoch": 0.4979253112033195,
      "eval_loss": 0.7523407340049744,
      "eval_runtime": 1.4728,
      "eval_samples_per_second": 34.629,
      "eval_steps_per_second": 8.827,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3665720160288768.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}