{
  "best_metric": 1.7614490985870361,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.008036001285760206,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003214400514304082,
      "grad_norm": 2.25677752494812,
      "learning_rate": 2e-05,
      "loss": 8.3539,
      "step": 1
    },
    {
      "epoch": 0.0003214400514304082,
      "eval_loss": 2.018449544906616,
      "eval_runtime": 317.1466,
      "eval_samples_per_second": 4.131,
      "eval_steps_per_second": 2.065,
      "step": 1
    },
    {
      "epoch": 0.0006428801028608164,
      "grad_norm": 2.09689998626709,
      "learning_rate": 4e-05,
      "loss": 7.2565,
      "step": 2
    },
    {
      "epoch": 0.0009643201542912247,
      "grad_norm": 1.7768841981887817,
      "learning_rate": 6e-05,
      "loss": 7.9064,
      "step": 3
    },
    {
      "epoch": 0.0012857602057216328,
      "grad_norm": 2.285568952560425,
      "learning_rate": 8e-05,
      "loss": 8.4581,
      "step": 4
    },
    {
      "epoch": 0.0016072002571520412,
      "grad_norm": 2.4067046642303467,
      "learning_rate": 0.0001,
      "loss": 9.0425,
      "step": 5
    },
    {
      "epoch": 0.0016072002571520412,
      "eval_loss": 1.9907472133636475,
      "eval_runtime": 245.6007,
      "eval_samples_per_second": 5.334,
      "eval_steps_per_second": 2.667,
      "step": 5
    },
    {
      "epoch": 0.0019286403085824494,
      "grad_norm": 1.7757352590560913,
      "learning_rate": 0.00012,
      "loss": 7.5752,
      "step": 6
    },
    {
      "epoch": 0.0022500803600128574,
      "grad_norm": 1.9240570068359375,
      "learning_rate": 0.00014,
      "loss": 7.3663,
      "step": 7
    },
    {
      "epoch": 0.0025715204114432656,
      "grad_norm": 3.2321372032165527,
      "learning_rate": 0.00016,
      "loss": 8.6779,
      "step": 8
    },
    {
      "epoch": 0.0028929604628736743,
      "grad_norm": 2.912095308303833,
      "learning_rate": 0.00018,
      "loss": 6.9415,
      "step": 9
    },
    {
      "epoch": 0.0032144005143040825,
      "grad_norm": 2.9719862937927246,
      "learning_rate": 0.0002,
      "loss": 7.9388,
      "step": 10
    },
    {
      "epoch": 0.0032144005143040825,
      "eval_loss": 1.837178349494934,
      "eval_runtime": 245.486,
      "eval_samples_per_second": 5.336,
      "eval_steps_per_second": 2.668,
      "step": 10
    },
    {
      "epoch": 0.0035358405657344907,
      "grad_norm": 3.1442389488220215,
      "learning_rate": 0.00019781476007338058,
      "loss": 7.5973,
      "step": 11
    },
    {
      "epoch": 0.003857280617164899,
      "grad_norm": 2.9277398586273193,
      "learning_rate": 0.0001913545457642601,
      "loss": 6.729,
      "step": 12
    },
    {
      "epoch": 0.004178720668595307,
      "grad_norm": 2.930840492248535,
      "learning_rate": 0.00018090169943749476,
      "loss": 7.53,
      "step": 13
    },
    {
      "epoch": 0.004500160720025715,
      "grad_norm": 3.4834635257720947,
      "learning_rate": 0.00016691306063588583,
      "loss": 7.2058,
      "step": 14
    },
    {
      "epoch": 0.0048216007714561235,
      "grad_norm": 4.19149112701416,
      "learning_rate": 0.00015000000000000001,
      "loss": 7.0573,
      "step": 15
    },
    {
      "epoch": 0.0048216007714561235,
      "eval_loss": 1.829241156578064,
      "eval_runtime": 244.9163,
      "eval_samples_per_second": 5.349,
      "eval_steps_per_second": 2.674,
      "step": 15
    },
    {
      "epoch": 0.005143040822886531,
      "grad_norm": 3.4479832649230957,
      "learning_rate": 0.00013090169943749476,
      "loss": 8.0653,
      "step": 16
    },
    {
      "epoch": 0.00546448087431694,
      "grad_norm": 4.002652645111084,
      "learning_rate": 0.00011045284632676536,
      "loss": 6.5003,
      "step": 17
    },
    {
      "epoch": 0.0057859209257473485,
      "grad_norm": 3.030047655105591,
      "learning_rate": 8.954715367323468e-05,
      "loss": 7.5556,
      "step": 18
    },
    {
      "epoch": 0.006107360977177756,
      "grad_norm": 3.8863916397094727,
      "learning_rate": 6.909830056250527e-05,
      "loss": 5.7633,
      "step": 19
    },
    {
      "epoch": 0.006428801028608165,
      "grad_norm": 3.2730555534362793,
      "learning_rate": 5.000000000000002e-05,
      "loss": 7.2346,
      "step": 20
    },
    {
      "epoch": 0.006428801028608165,
      "eval_loss": 1.7709662914276123,
      "eval_runtime": 244.8426,
      "eval_samples_per_second": 5.35,
      "eval_steps_per_second": 2.675,
      "step": 20
    },
    {
      "epoch": 0.006750241080038573,
      "grad_norm": 2.53360652923584,
      "learning_rate": 3.308693936411421e-05,
      "loss": 6.6023,
      "step": 21
    },
    {
      "epoch": 0.007071681131468981,
      "grad_norm": 2.14629864692688,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 6.6719,
      "step": 22
    },
    {
      "epoch": 0.007393121182899389,
      "grad_norm": 2.85324764251709,
      "learning_rate": 8.645454235739903e-06,
      "loss": 6.5182,
      "step": 23
    },
    {
      "epoch": 0.007714561234329798,
      "grad_norm": 2.843808650970459,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 7.1167,
      "step": 24
    },
    {
      "epoch": 0.008036001285760206,
      "grad_norm": 3.727983236312866,
      "learning_rate": 0.0,
      "loss": 7.3145,
      "step": 25
    },
    {
      "epoch": 0.008036001285760206,
      "eval_loss": 1.7614490985870361,
      "eval_runtime": 246.737,
      "eval_samples_per_second": 5.309,
      "eval_steps_per_second": 2.655,
      "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": 9842178486435840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}