{
  "best_metric": 0.42355671525001526,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0021300615587790486,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.520246235116194e-05,
      "grad_norm": 14.938115119934082,
      "learning_rate": 2e-05,
      "loss": 3.9898,
      "step": 1
    },
    {
      "epoch": 8.520246235116194e-05,
      "eval_loss": 4.1432342529296875,
      "eval_runtime": 487.4397,
      "eval_samples_per_second": 10.139,
      "eval_steps_per_second": 5.069,
      "step": 1
    },
    {
      "epoch": 0.00017040492470232388,
      "grad_norm": 20.35617446899414,
      "learning_rate": 4e-05,
      "loss": 5.2571,
      "step": 2
    },
    {
      "epoch": 0.00025560738705348587,
      "grad_norm": 11.273299217224121,
      "learning_rate": 6e-05,
      "loss": 3.1554,
      "step": 3
    },
    {
      "epoch": 0.00034080984940464777,
      "grad_norm": 13.890028953552246,
      "learning_rate": 8e-05,
      "loss": 2.9328,
      "step": 4
    },
    {
      "epoch": 0.0004260123117558097,
      "grad_norm": 14.092949867248535,
      "learning_rate": 0.0001,
      "loss": 3.2873,
      "step": 5
    },
    {
      "epoch": 0.0004260123117558097,
      "eval_loss": 3.6745121479034424,
      "eval_runtime": 483.4031,
      "eval_samples_per_second": 10.223,
      "eval_steps_per_second": 5.112,
      "step": 5
    },
    {
      "epoch": 0.0005112147741069717,
      "grad_norm": 8.267870903015137,
      "learning_rate": 0.00012,
      "loss": 3.3901,
      "step": 6
    },
    {
      "epoch": 0.0005964172364581337,
      "grad_norm": 5.932241439819336,
      "learning_rate": 0.00014,
      "loss": 2.455,
      "step": 7
    },
    {
      "epoch": 0.0006816196988092955,
      "grad_norm": 8.17934513092041,
      "learning_rate": 0.00016,
      "loss": 3.0762,
      "step": 8
    },
    {
      "epoch": 0.0007668221611604575,
      "grad_norm": 6.161928176879883,
      "learning_rate": 0.00018,
      "loss": 2.4496,
      "step": 9
    },
    {
      "epoch": 0.0008520246235116195,
      "grad_norm": 7.789601802825928,
      "learning_rate": 0.0002,
      "loss": 2.5487,
      "step": 10
    },
    {
      "epoch": 0.0008520246235116195,
      "eval_loss": 2.009469509124756,
      "eval_runtime": 483.7922,
      "eval_samples_per_second": 10.215,
      "eval_steps_per_second": 5.108,
      "step": 10
    },
    {
      "epoch": 0.0009372270858627814,
      "grad_norm": 7.095274448394775,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.804,
      "step": 11
    },
    {
      "epoch": 0.0010224295482139435,
      "grad_norm": 7.472821235656738,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.546,
      "step": 12
    },
    {
      "epoch": 0.0011076320105651053,
      "grad_norm": 8.946196556091309,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.6611,
      "step": 13
    },
    {
      "epoch": 0.0011928344729162674,
      "grad_norm": 9.248509407043457,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.7886,
      "step": 14
    },
    {
      "epoch": 0.0012780369352674292,
      "grad_norm": 5.092668533325195,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.9369,
      "step": 15
    },
    {
      "epoch": 0.0012780369352674292,
      "eval_loss": 0.9628341197967529,
      "eval_runtime": 485.7206,
      "eval_samples_per_second": 10.175,
      "eval_steps_per_second": 5.087,
      "step": 15
    },
    {
      "epoch": 0.001363239397618591,
      "grad_norm": 7.571272850036621,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.0683,
      "step": 16
    },
    {
      "epoch": 0.0014484418599697531,
      "grad_norm": 6.461460590362549,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.929,
      "step": 17
    },
    {
      "epoch": 0.001533644322320915,
      "grad_norm": 4.5205206871032715,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.6159,
      "step": 18
    },
    {
      "epoch": 0.001618846784672077,
      "grad_norm": 3.7055180072784424,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.487,
      "step": 19
    },
    {
      "epoch": 0.001704049247023239,
      "grad_norm": 3.816122055053711,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.5038,
      "step": 20
    },
    {
      "epoch": 0.001704049247023239,
      "eval_loss": 0.45222973823547363,
      "eval_runtime": 486.2889,
      "eval_samples_per_second": 10.163,
      "eval_steps_per_second": 5.081,
      "step": 20
    },
    {
      "epoch": 0.001789251709374401,
      "grad_norm": 3.6809463500976562,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.502,
      "step": 21
    },
    {
      "epoch": 0.0018744541717255628,
      "grad_norm": 2.1427297592163086,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.347,
      "step": 22
    },
    {
      "epoch": 0.001959656634076725,
      "grad_norm": 2.23321795463562,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.1978,
      "step": 23
    },
    {
      "epoch": 0.002044859096427887,
      "grad_norm": 3.3327629566192627,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.4026,
      "step": 24
    },
    {
      "epoch": 0.0021300615587790486,
      "grad_norm": 3.6156723499298096,
      "learning_rate": 0.0,
      "loss": 0.4378,
      "step": 25
    },
    {
      "epoch": 0.0021300615587790486,
      "eval_loss": 0.42355671525001526,
      "eval_runtime": 483.5763,
      "eval_samples_per_second": 10.22,
      "eval_steps_per_second": 5.11,
      "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": 191809506508800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}