{
  "best_metric": 0.6798481941223145,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0211864406779661,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001059322033898305,
      "grad_norm": 1.1843385696411133,
      "learning_rate": 2e-05,
      "loss": 6.9729,
      "step": 1
    },
    {
      "epoch": 0.001059322033898305,
      "eval_loss": 1.7519381046295166,
      "eval_runtime": 62.8857,
      "eval_samples_per_second": 6.329,
      "eval_steps_per_second": 3.164,
      "step": 1
    },
    {
      "epoch": 0.00211864406779661,
      "grad_norm": 1.2905192375183105,
      "learning_rate": 4e-05,
      "loss": 7.1004,
      "step": 2
    },
    {
      "epoch": 0.0031779661016949155,
      "grad_norm": 1.0775989294052124,
      "learning_rate": 6e-05,
      "loss": 6.7495,
      "step": 3
    },
    {
      "epoch": 0.00423728813559322,
      "grad_norm": 1.23506498336792,
      "learning_rate": 8e-05,
      "loss": 7.1814,
      "step": 4
    },
    {
      "epoch": 0.005296610169491525,
      "grad_norm": 1.3882372379302979,
      "learning_rate": 0.0001,
      "loss": 6.7127,
      "step": 5
    },
    {
      "epoch": 0.005296610169491525,
      "eval_loss": 1.679090142250061,
      "eval_runtime": 60.2715,
      "eval_samples_per_second": 6.603,
      "eval_steps_per_second": 3.302,
      "step": 5
    },
    {
      "epoch": 0.006355932203389831,
      "grad_norm": 1.625010371208191,
      "learning_rate": 0.00012,
      "loss": 6.3487,
      "step": 6
    },
    {
      "epoch": 0.007415254237288136,
      "grad_norm": 2.2204973697662354,
      "learning_rate": 0.00014,
      "loss": 6.4336,
      "step": 7
    },
    {
      "epoch": 0.00847457627118644,
      "grad_norm": 2.3018980026245117,
      "learning_rate": 0.00016,
      "loss": 5.7187,
      "step": 8
    },
    {
      "epoch": 0.009533898305084746,
      "grad_norm": 2.3406448364257812,
      "learning_rate": 0.00018,
      "loss": 6.1801,
      "step": 9
    },
    {
      "epoch": 0.01059322033898305,
      "grad_norm": 2.687272548675537,
      "learning_rate": 0.0002,
      "loss": 4.7409,
      "step": 10
    },
    {
      "epoch": 0.01059322033898305,
      "eval_loss": 1.1311993598937988,
      "eval_runtime": 59.8086,
      "eval_samples_per_second": 6.655,
      "eval_steps_per_second": 3.327,
      "step": 10
    },
    {
      "epoch": 0.011652542372881356,
      "grad_norm": 2.957493305206299,
      "learning_rate": 0.00019781476007338058,
      "loss": 4.0912,
      "step": 11
    },
    {
      "epoch": 0.012711864406779662,
      "grad_norm": 2.8493051528930664,
      "learning_rate": 0.0001913545457642601,
      "loss": 3.9196,
      "step": 12
    },
    {
      "epoch": 0.013771186440677966,
      "grad_norm": 2.804184675216675,
      "learning_rate": 0.00018090169943749476,
      "loss": 3.2003,
      "step": 13
    },
    {
      "epoch": 0.014830508474576272,
      "grad_norm": 3.1039199829101562,
      "learning_rate": 0.00016691306063588583,
      "loss": 2.7907,
      "step": 14
    },
    {
      "epoch": 0.015889830508474576,
      "grad_norm": 5.297954559326172,
      "learning_rate": 0.00015000000000000001,
      "loss": 5.4727,
      "step": 15
    },
    {
      "epoch": 0.015889830508474576,
      "eval_loss": 0.7405627369880676,
      "eval_runtime": 60.1344,
      "eval_samples_per_second": 6.619,
      "eval_steps_per_second": 3.309,
      "step": 15
    },
    {
      "epoch": 0.01694915254237288,
      "grad_norm": 3.4782044887542725,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.8036,
      "step": 16
    },
    {
      "epoch": 0.018008474576271187,
      "grad_norm": 2.544600248336792,
      "learning_rate": 0.00011045284632676536,
      "loss": 2.4763,
      "step": 17
    },
    {
      "epoch": 0.019067796610169493,
      "grad_norm": 4.462560176849365,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.682,
      "step": 18
    },
    {
      "epoch": 0.020127118644067795,
      "grad_norm": 2.4938857555389404,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.1245,
      "step": 19
    },
    {
      "epoch": 0.0211864406779661,
      "grad_norm": 3.4558427333831787,
      "learning_rate": 5.000000000000002e-05,
      "loss": 2.6024,
      "step": 20
    },
    {
      "epoch": 0.0211864406779661,
      "eval_loss": 0.6798481941223145,
      "eval_runtime": 60.5106,
      "eval_samples_per_second": 6.577,
      "eval_steps_per_second": 3.289,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6274650262732800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}