{
  "best_metric": 1.3124490976333618,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.06591957811470006,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026367831245880024,
      "grad_norm": 1.401543378829956,
      "learning_rate": 2e-05,
      "loss": 2.0049,
      "step": 1
    },
    {
      "epoch": 0.0026367831245880024,
      "eval_loss": 1.9893897771835327,
      "eval_runtime": 62.9574,
      "eval_samples_per_second": 2.541,
      "eval_steps_per_second": 1.271,
      "step": 1
    },
    {
      "epoch": 0.005273566249176005,
      "grad_norm": 1.4308735132217407,
      "learning_rate": 4e-05,
      "loss": 1.8449,
      "step": 2
    },
    {
      "epoch": 0.007910349373764008,
      "grad_norm": 1.7150732278823853,
      "learning_rate": 6e-05,
      "loss": 2.1379,
      "step": 3
    },
    {
      "epoch": 0.01054713249835201,
      "grad_norm": 1.6402350664138794,
      "learning_rate": 8e-05,
      "loss": 1.9778,
      "step": 4
    },
    {
      "epoch": 0.013183915622940013,
      "grad_norm": 1.3847346305847168,
      "learning_rate": 0.0001,
      "loss": 1.9557,
      "step": 5
    },
    {
      "epoch": 0.013183915622940013,
      "eval_loss": 1.8407901525497437,
      "eval_runtime": 62.9514,
      "eval_samples_per_second": 2.542,
      "eval_steps_per_second": 1.271,
      "step": 5
    },
    {
      "epoch": 0.015820698747528016,
      "grad_norm": 1.6706628799438477,
      "learning_rate": 0.00012,
      "loss": 1.9638,
      "step": 6
    },
    {
      "epoch": 0.01845748187211602,
      "grad_norm": 1.3307857513427734,
      "learning_rate": 0.00014,
      "loss": 1.4869,
      "step": 7
    },
    {
      "epoch": 0.02109426499670402,
      "grad_norm": 1.5097020864486694,
      "learning_rate": 0.00016,
      "loss": 1.8163,
      "step": 8
    },
    {
      "epoch": 0.023731048121292023,
      "grad_norm": 1.8996268510818481,
      "learning_rate": 0.00018,
      "loss": 1.8971,
      "step": 9
    },
    {
      "epoch": 0.026367831245880026,
      "grad_norm": 1.6847840547561646,
      "learning_rate": 0.0002,
      "loss": 1.7186,
      "step": 10
    },
    {
      "epoch": 0.026367831245880026,
      "eval_loss": 1.5257115364074707,
      "eval_runtime": 62.802,
      "eval_samples_per_second": 2.548,
      "eval_steps_per_second": 1.274,
      "step": 10
    },
    {
      "epoch": 0.02900461437046803,
      "grad_norm": 1.5318021774291992,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.6642,
      "step": 11
    },
    {
      "epoch": 0.03164139749505603,
      "grad_norm": 1.45635187625885,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.5256,
      "step": 12
    },
    {
      "epoch": 0.034278180619644036,
      "grad_norm": 1.5707160234451294,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.4718,
      "step": 13
    },
    {
      "epoch": 0.03691496374423204,
      "grad_norm": 1.549959659576416,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.3821,
      "step": 14
    },
    {
      "epoch": 0.03955174686882004,
      "grad_norm": 1.504858374595642,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.3755,
      "step": 15
    },
    {
      "epoch": 0.03955174686882004,
      "eval_loss": 1.3683379888534546,
      "eval_runtime": 63.2429,
      "eval_samples_per_second": 2.53,
      "eval_steps_per_second": 1.265,
      "step": 15
    },
    {
      "epoch": 0.04218852999340804,
      "grad_norm": 1.1318060159683228,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.3286,
      "step": 16
    },
    {
      "epoch": 0.04482531311799604,
      "grad_norm": 1.4922255277633667,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.4127,
      "step": 17
    },
    {
      "epoch": 0.047462096242584045,
      "grad_norm": 1.369985580444336,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.4094,
      "step": 18
    },
    {
      "epoch": 0.05009887936717205,
      "grad_norm": 1.2594324350357056,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.2905,
      "step": 19
    },
    {
      "epoch": 0.05273566249176005,
      "grad_norm": 1.3561158180236816,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.4573,
      "step": 20
    },
    {
      "epoch": 0.05273566249176005,
      "eval_loss": 1.327634572982788,
      "eval_runtime": 62.9794,
      "eval_samples_per_second": 2.541,
      "eval_steps_per_second": 1.27,
      "step": 20
    },
    {
      "epoch": 0.055372445616348055,
      "grad_norm": 1.0853641033172607,
      "learning_rate": 3.308693936411421e-05,
      "loss": 1.2419,
      "step": 21
    },
    {
      "epoch": 0.05800922874093606,
      "grad_norm": 1.3395389318466187,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.4187,
      "step": 22
    },
    {
      "epoch": 0.06064601186552406,
      "grad_norm": 1.185535192489624,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.5871,
      "step": 23
    },
    {
      "epoch": 0.06328279499011207,
      "grad_norm": 1.1613945960998535,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.4171,
      "step": 24
    },
    {
      "epoch": 0.06591957811470006,
      "grad_norm": 1.4646044969558716,
      "learning_rate": 0.0,
      "loss": 1.5096,
      "step": 25
    },
    {
      "epoch": 0.06591957811470006,
      "eval_loss": 1.3124490976333618,
      "eval_runtime": 62.856,
      "eval_samples_per_second": 2.545,
      "eval_steps_per_second": 1.273,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9555457081344000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}