{
  "best_metric": 2.0945186614990234,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 2.2334217506631298,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08488063660477453,
      "grad_norm": 0.11538974195718765,
      "learning_rate": 5e-05,
      "loss": 2.2741,
      "step": 1
    },
    {
      "epoch": 0.08488063660477453,
      "eval_loss": 2.1513023376464844,
      "eval_runtime": 6.6285,
      "eval_samples_per_second": 7.543,
      "eval_steps_per_second": 1.961,
      "step": 1
    },
    {
      "epoch": 0.16976127320954906,
      "grad_norm": 0.17335651814937592,
      "learning_rate": 0.0001,
      "loss": 2.1605,
      "step": 2
    },
    {
      "epoch": 0.2546419098143236,
      "grad_norm": 0.14212526381015778,
      "learning_rate": 9.980803793327656e-05,
      "loss": 2.2177,
      "step": 3
    },
    {
      "epoch": 0.3395225464190981,
      "grad_norm": 0.10073097050189972,
      "learning_rate": 9.923378948577559e-05,
      "loss": 2.2715,
      "step": 4
    },
    {
      "epoch": 0.4244031830238727,
      "grad_norm": 0.1450101137161255,
      "learning_rate": 9.828215394277687e-05,
      "loss": 2.1431,
      "step": 5
    },
    {
      "epoch": 0.5092838196286472,
      "grad_norm": 0.13063274323940277,
      "learning_rate": 9.6961250323196e-05,
      "loss": 2.233,
      "step": 6
    },
    {
      "epoch": 0.5941644562334217,
      "grad_norm": 0.10091730952262878,
      "learning_rate": 9.528234811097782e-05,
      "loss": 2.2441,
      "step": 7
    },
    {
      "epoch": 0.6790450928381963,
      "grad_norm": 0.11386176198720932,
      "learning_rate": 9.325977110783264e-05,
      "loss": 2.1384,
      "step": 8
    },
    {
      "epoch": 0.7639257294429708,
      "grad_norm": 0.07708155363798141,
      "learning_rate": 9.091077522761079e-05,
      "loss": 2.2585,
      "step": 9
    },
    {
      "epoch": 0.8488063660477454,
      "grad_norm": 0.07687578350305557,
      "learning_rate": 8.825540127492967e-05,
      "loss": 2.1812,
      "step": 10
    },
    {
      "epoch": 0.9336870026525199,
      "grad_norm": 0.11479948461055756,
      "learning_rate": 8.531630396409507e-05,
      "loss": 2.137,
      "step": 11
    },
    {
      "epoch": 1.0742705570291777,
      "grad_norm": 0.18556855618953705,
      "learning_rate": 8.211855863706654e-05,
      "loss": 4.1666,
      "step": 12
    },
    {
      "epoch": 1.1591511936339522,
      "grad_norm": 0.07303278893232346,
      "learning_rate": 7.868944732948101e-05,
      "loss": 2.2348,
      "step": 13
    },
    {
      "epoch": 1.2440318302387268,
      "grad_norm": 0.07755976170301437,
      "learning_rate": 7.505822600994424e-05,
      "loss": 1.8351,
      "step": 14
    },
    {
      "epoch": 1.3289124668435013,
      "grad_norm": 0.07641968131065369,
      "learning_rate": 7.12558749784219e-05,
      "loss": 2.4315,
      "step": 15
    },
    {
      "epoch": 1.4137931034482758,
      "grad_norm": 0.08880927413702011,
      "learning_rate": 6.731483455324374e-05,
      "loss": 2.1508,
      "step": 16
    },
    {
      "epoch": 1.4986737400530503,
      "grad_norm": 0.07519613206386566,
      "learning_rate": 6.326872830174567e-05,
      "loss": 1.937,
      "step": 17
    },
    {
      "epoch": 1.5835543766578248,
      "grad_norm": 0.07305863499641418,
      "learning_rate": 5.9152076175848594e-05,
      "loss": 2.4231,
      "step": 18
    },
    {
      "epoch": 1.6684350132625996,
      "grad_norm": 0.088906429708004,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.0867,
      "step": 19
    },
    {
      "epoch": 1.7533156498673739,
      "grad_norm": 0.06970585137605667,
      "learning_rate": 5.0847923824151424e-05,
      "loss": 2.0865,
      "step": 20
    },
    {
      "epoch": 1.8381962864721486,
      "grad_norm": 0.07360448688268661,
      "learning_rate": 4.673127169825433e-05,
      "loss": 2.3488,
      "step": 21
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.10024575889110565,
      "learning_rate": 4.268516544675628e-05,
      "loss": 2.1209,
      "step": 22
    },
    {
      "epoch": 2.0636604774535807,
      "grad_norm": 0.19106365740299225,
      "learning_rate": 3.8744125021578126e-05,
      "loss": 4.1671,
      "step": 23
    },
    {
      "epoch": 2.1485411140583555,
      "grad_norm": 0.07870066910982132,
      "learning_rate": 3.494177399005578e-05,
      "loss": 2.2506,
      "step": 24
    },
    {
      "epoch": 2.2334217506631298,
      "grad_norm": 0.07224322110414505,
      "learning_rate": 3.1310552670518986e-05,
      "loss": 1.4278,
      "step": 25
    },
    {
      "epoch": 2.2334217506631298,
      "eval_loss": 2.0945186614990234,
      "eval_runtime": 6.27,
      "eval_samples_per_second": 7.974,
      "eval_steps_per_second": 2.073,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 36,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 4.145953126492406e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}