{
  "best_metric": 0.7847893238067627,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.07430340557275542,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002476780185758514,
      "eval_loss": 3.530684232711792,
      "eval_runtime": 53.0571,
      "eval_samples_per_second": 6.408,
      "eval_steps_per_second": 1.602,
      "step": 1
    },
    {
      "epoch": 0.007430340557275541,
      "grad_norm": 2.1541712284088135,
      "learning_rate": 0.00012,
      "loss": 3.4182,
      "step": 3
    },
    {
      "epoch": 0.01238390092879257,
      "eval_loss": 2.5307934284210205,
      "eval_runtime": 53.5568,
      "eval_samples_per_second": 6.348,
      "eval_steps_per_second": 1.587,
      "step": 5
    },
    {
      "epoch": 0.014860681114551083,
      "grad_norm": 2.7028632164001465,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.9839,
      "step": 6
    },
    {
      "epoch": 0.022291021671826627,
      "grad_norm": 2.3100998401641846,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.8144,
      "step": 9
    },
    {
      "epoch": 0.02476780185758514,
      "eval_loss": 1.1562076807022095,
      "eval_runtime": 53.9959,
      "eval_samples_per_second": 6.297,
      "eval_steps_per_second": 1.574,
      "step": 10
    },
    {
      "epoch": 0.029721362229102165,
      "grad_norm": 1.9548863172531128,
      "learning_rate": 0.000163742398974869,
      "loss": 1.3279,
      "step": 12
    },
    {
      "epoch": 0.03715170278637771,
      "grad_norm": 1.4647603034973145,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.1464,
      "step": 15
    },
    {
      "epoch": 0.03715170278637771,
      "eval_loss": 0.9805688261985779,
      "eval_runtime": 53.7891,
      "eval_samples_per_second": 6.321,
      "eval_steps_per_second": 1.58,
      "step": 15
    },
    {
      "epoch": 0.04458204334365325,
      "grad_norm": 1.6623939275741577,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.0108,
      "step": 18
    },
    {
      "epoch": 0.04953560371517028,
      "eval_loss": 0.8525367379188538,
      "eval_runtime": 53.8147,
      "eval_samples_per_second": 6.318,
      "eval_steps_per_second": 1.579,
      "step": 20
    },
    {
      "epoch": 0.05201238390092879,
      "grad_norm": 1.9752190113067627,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.9631,
      "step": 21
    },
    {
      "epoch": 0.05944272445820433,
      "grad_norm": 1.472144603729248,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.8413,
      "step": 24
    },
    {
      "epoch": 0.06191950464396285,
      "eval_loss": 0.7937929034233093,
      "eval_runtime": 54.226,
      "eval_samples_per_second": 6.27,
      "eval_steps_per_second": 1.568,
      "step": 25
    },
    {
      "epoch": 0.06687306501547988,
      "grad_norm": 1.0236313343048096,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.8092,
      "step": 27
    },
    {
      "epoch": 0.07430340557275542,
      "grad_norm": 0.6827451586723328,
      "learning_rate": 0.0,
      "loss": 0.8011,
      "step": 30
    },
    {
      "epoch": 0.07430340557275542,
      "eval_loss": 0.7847893238067627,
      "eval_runtime": 54.1048,
      "eval_samples_per_second": 6.284,
      "eval_steps_per_second": 1.571,
      "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": 2.219477097775104e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}