{
  "best_metric": 11.931747436523438,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.1423487544483986,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004744958481613286,
      "eval_loss": 11.932116508483887,
      "eval_runtime": 0.8506,
      "eval_samples_per_second": 209.264,
      "eval_steps_per_second": 52.904,
      "step": 1
    },
    {
      "epoch": 0.014234875444839857,
      "grad_norm": 0.02677612006664276,
      "learning_rate": 0.00012,
      "loss": 11.9319,
      "step": 3
    },
    {
      "epoch": 0.02372479240806643,
      "eval_loss": 11.932097434997559,
      "eval_runtime": 0.8543,
      "eval_samples_per_second": 208.355,
      "eval_steps_per_second": 52.674,
      "step": 5
    },
    {
      "epoch": 0.028469750889679714,
      "grad_norm": 0.03796449303627014,
      "learning_rate": 0.0001992114701314478,
      "loss": 11.9311,
      "step": 6
    },
    {
      "epoch": 0.042704626334519574,
      "grad_norm": 0.03717769309878349,
      "learning_rate": 0.00018763066800438636,
      "loss": 11.9322,
      "step": 9
    },
    {
      "epoch": 0.04744958481613286,
      "eval_loss": 11.93195915222168,
      "eval_runtime": 0.9139,
      "eval_samples_per_second": 194.77,
      "eval_steps_per_second": 49.24,
      "step": 10
    },
    {
      "epoch": 0.05693950177935943,
      "grad_norm": 0.037996333092451096,
      "learning_rate": 0.000163742398974869,
      "loss": 11.9331,
      "step": 12
    },
    {
      "epoch": 0.0711743772241993,
      "grad_norm": 0.040662698447704315,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.9289,
      "step": 15
    },
    {
      "epoch": 0.0711743772241993,
      "eval_loss": 11.931912422180176,
      "eval_runtime": 0.8673,
      "eval_samples_per_second": 205.239,
      "eval_steps_per_second": 51.886,
      "step": 15
    },
    {
      "epoch": 0.08540925266903915,
      "grad_norm": 0.04711554944515228,
      "learning_rate": 9.372094804706867e-05,
      "loss": 11.9324,
      "step": 18
    },
    {
      "epoch": 0.09489916963226572,
      "eval_loss": 11.931827545166016,
      "eval_runtime": 0.8984,
      "eval_samples_per_second": 198.131,
      "eval_steps_per_second": 50.089,
      "step": 20
    },
    {
      "epoch": 0.099644128113879,
      "grad_norm": 0.042521167546510696,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 11.9327,
      "step": 21
    },
    {
      "epoch": 0.11387900355871886,
      "grad_norm": 0.04662325605750084,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 11.9348,
      "step": 24
    },
    {
      "epoch": 0.11862396204033215,
      "eval_loss": 11.931800842285156,
      "eval_runtime": 0.8704,
      "eval_samples_per_second": 204.515,
      "eval_steps_per_second": 51.703,
      "step": 25
    },
    {
      "epoch": 0.12811387900355872,
      "grad_norm": 0.05982173606753349,
      "learning_rate": 7.022351411174866e-06,
      "loss": 11.9331,
      "step": 27
    },
    {
      "epoch": 0.1423487544483986,
      "grad_norm": 0.03850724920630455,
      "learning_rate": 0.0,
      "loss": 11.9307,
      "step": 30
    },
    {
      "epoch": 0.1423487544483986,
      "eval_loss": 11.931747436523438,
      "eval_runtime": 0.8532,
      "eval_samples_per_second": 208.63,
      "eval_steps_per_second": 52.744,
      "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": 22484090880.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}