{
  "best_metric": 1.4048820734024048,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.002549557014468736,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.498523381562454e-05,
      "eval_loss": 1.7723931074142456,
      "eval_runtime": 948.687,
      "eval_samples_per_second": 5.223,
      "eval_steps_per_second": 2.612,
      "step": 1
    },
    {
      "epoch": 0.0002549557014468736,
      "grad_norm": 0.4695388376712799,
      "learning_rate": 6e-05,
      "loss": 1.6701,
      "step": 3
    },
    {
      "epoch": 0.00042492616907812265,
      "eval_loss": 1.741461992263794,
      "eval_runtime": 953.8966,
      "eval_samples_per_second": 5.194,
      "eval_steps_per_second": 2.598,
      "step": 5
    },
    {
      "epoch": 0.0005099114028937472,
      "grad_norm": 0.5784434676170349,
      "learning_rate": 0.00012,
      "loss": 1.5659,
      "step": 6
    },
    {
      "epoch": 0.0007648671043406208,
      "grad_norm": 0.44574055075645447,
      "learning_rate": 0.00018,
      "loss": 1.4913,
      "step": 9
    },
    {
      "epoch": 0.0008498523381562453,
      "eval_loss": 1.493849277496338,
      "eval_runtime": 953.3797,
      "eval_samples_per_second": 5.197,
      "eval_steps_per_second": 2.599,
      "step": 10
    },
    {
      "epoch": 0.0010198228057874943,
      "grad_norm": 0.3167478144168854,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.5165,
      "step": 12
    },
    {
      "epoch": 0.001274778507234368,
      "grad_norm": 0.27598023414611816,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.5946,
      "step": 15
    },
    {
      "epoch": 0.001274778507234368,
      "eval_loss": 1.4441362619400024,
      "eval_runtime": 953.5297,
      "eval_samples_per_second": 5.196,
      "eval_steps_per_second": 2.599,
      "step": 15
    },
    {
      "epoch": 0.0015297342086812416,
      "grad_norm": 0.25095218420028687,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.3116,
      "step": 18
    },
    {
      "epoch": 0.0016997046763124906,
      "eval_loss": 1.4170926809310913,
      "eval_runtime": 953.0296,
      "eval_samples_per_second": 5.199,
      "eval_steps_per_second": 2.6,
      "step": 20
    },
    {
      "epoch": 0.0017846899101281153,
      "grad_norm": 0.25035661458969116,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.3807,
      "step": 21
    },
    {
      "epoch": 0.0020396456115749887,
      "grad_norm": 0.1905255913734436,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.3176,
      "step": 24
    },
    {
      "epoch": 0.0021246308453906136,
      "eval_loss": 1.4069769382476807,
      "eval_runtime": 952.9081,
      "eval_samples_per_second": 5.2,
      "eval_steps_per_second": 2.6,
      "step": 25
    },
    {
      "epoch": 0.0022946013130218626,
      "grad_norm": 0.23602157831192017,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.2595,
      "step": 27
    },
    {
      "epoch": 0.002549557014468736,
      "grad_norm": 0.21652282774448395,
      "learning_rate": 0.0,
      "loss": 1.3646,
      "step": 30
    },
    {
      "epoch": 0.002549557014468736,
      "eval_loss": 1.4048820734024048,
      "eval_runtime": 952.4873,
      "eval_samples_per_second": 5.202,
      "eval_steps_per_second": 2.602,
      "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": 2.666072729714688e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}