{
  "best_metric": 0.4184398353099823,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0014826676155739406,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.930670462295763e-05,
      "grad_norm": 3.175028085708618,
      "learning_rate": 2e-05,
      "loss": 3.0196,
      "step": 1
    },
    {
      "epoch": 5.930670462295763e-05,
      "eval_loss": 3.4766604900360107,
      "eval_runtime": 1084.5298,
      "eval_samples_per_second": 6.547,
      "eval_steps_per_second": 3.273,
      "step": 1
    },
    {
      "epoch": 0.00011861340924591526,
      "grad_norm": 3.4241366386413574,
      "learning_rate": 4e-05,
      "loss": 3.3862,
      "step": 2
    },
    {
      "epoch": 0.00017792011386887289,
      "grad_norm": 1.9072884321212769,
      "learning_rate": 6e-05,
      "loss": 1.8831,
      "step": 3
    },
    {
      "epoch": 0.00023722681849183051,
      "grad_norm": 3.1376442909240723,
      "learning_rate": 8e-05,
      "loss": 2.8547,
      "step": 4
    },
    {
      "epoch": 0.0002965335231147881,
      "grad_norm": 2.9033186435699463,
      "learning_rate": 0.0001,
      "loss": 2.5522,
      "step": 5
    },
    {
      "epoch": 0.0002965335231147881,
      "eval_loss": 2.9956552982330322,
      "eval_runtime": 1072.7204,
      "eval_samples_per_second": 6.619,
      "eval_steps_per_second": 3.309,
      "step": 5
    },
    {
      "epoch": 0.00035584022773774577,
      "grad_norm": 3.9090983867645264,
      "learning_rate": 0.00012,
      "loss": 2.5803,
      "step": 6
    },
    {
      "epoch": 0.00041514693236070337,
      "grad_norm": 3.5850651264190674,
      "learning_rate": 0.00014,
      "loss": 2.1934,
      "step": 7
    },
    {
      "epoch": 0.00047445363698366103,
      "grad_norm": 3.548720359802246,
      "learning_rate": 0.00016,
      "loss": 1.6292,
      "step": 8
    },
    {
      "epoch": 0.0005337603416066186,
      "grad_norm": 2.7150440216064453,
      "learning_rate": 0.00018,
      "loss": 0.8561,
      "step": 9
    },
    {
      "epoch": 0.0005930670462295762,
      "grad_norm": 3.5200283527374268,
      "learning_rate": 0.0002,
      "loss": 1.1031,
      "step": 10
    },
    {
      "epoch": 0.0005930670462295762,
      "eval_loss": 1.184130072593689,
      "eval_runtime": 1064.0086,
      "eval_samples_per_second": 6.673,
      "eval_steps_per_second": 3.336,
      "step": 10
    },
    {
      "epoch": 0.0006523737508525338,
      "grad_norm": 4.106665134429932,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.7186,
      "step": 11
    },
    {
      "epoch": 0.0007116804554754915,
      "grad_norm": 2.682950973510742,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.6629,
      "step": 12
    },
    {
      "epoch": 0.0007709871600984491,
      "grad_norm": 2.9775516986846924,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.4503,
      "step": 13
    },
    {
      "epoch": 0.0008302938647214067,
      "grad_norm": 3.0503790378570557,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.446,
      "step": 14
    },
    {
      "epoch": 0.0008896005693443643,
      "grad_norm": 1.703140377998352,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.323,
      "step": 15
    },
    {
      "epoch": 0.0008896005693443643,
      "eval_loss": 0.33504584431648254,
      "eval_runtime": 1072.4211,
      "eval_samples_per_second": 6.621,
      "eval_steps_per_second": 3.31,
      "step": 15
    },
    {
      "epoch": 0.0009489072739673221,
      "grad_norm": 3.130513906478882,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.3606,
      "step": 16
    },
    {
      "epoch": 0.0010082139785902795,
      "grad_norm": 1.3841800689697266,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.3898,
      "step": 17
    },
    {
      "epoch": 0.0010675206832132373,
      "grad_norm": 1.2063566446304321,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.3137,
      "step": 18
    },
    {
      "epoch": 0.001126827387836195,
      "grad_norm": 2.978433609008789,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.2997,
      "step": 19
    },
    {
      "epoch": 0.0011861340924591525,
      "grad_norm": 1.0437448024749756,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.3152,
      "step": 20
    },
    {
      "epoch": 0.0011861340924591525,
      "eval_loss": 0.4184398353099823,
      "eval_runtime": 1085.3899,
      "eval_samples_per_second": 6.541,
      "eval_steps_per_second": 3.271,
      "step": 20
    },
    {
      "epoch": 0.0012454407970821102,
      "grad_norm": 1.3536689281463623,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.3067,
      "step": 21
    },
    {
      "epoch": 0.0013047475017050677,
      "grad_norm": 1.3476461172103882,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.3582,
      "step": 22
    },
    {
      "epoch": 0.0013640542063280254,
      "grad_norm": 0.9846263527870178,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.2339,
      "step": 23
    },
    {
      "epoch": 0.001423360910950983,
      "grad_norm": 0.764580488204956,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.2296,
      "step": 24
    },
    {
      "epoch": 0.0014826676155739406,
      "grad_norm": 1.3171172142028809,
      "learning_rate": 0.0,
      "loss": 0.359,
      "step": 25
    },
    {
      "epoch": 0.0014826676155739406,
      "eval_loss": 0.4272419810295105,
      "eval_runtime": 1060.7447,
      "eval_samples_per_second": 6.693,
      "eval_steps_per_second": 3.347,
      "step": 25
    }
  ],
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4901345257586688.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}