{
  "best_metric": 2.115447759628296,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 2.0125786163522013,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08050314465408805,
      "grad_norm": 0.6041520833969116,
      "learning_rate": 0.0002989354846774545,
      "loss": 2.6016,
      "step": 1
    },
    {
      "epoch": 0.08050314465408805,
      "eval_loss": 2.5483391284942627,
      "eval_runtime": 0.3035,
      "eval_samples_per_second": 164.719,
      "eval_steps_per_second": 42.827,
      "step": 1
    },
    {
      "epoch": 0.1610062893081761,
      "grad_norm": 0.4586615562438965,
      "learning_rate": 0.0002957587267523652,
      "loss": 2.613,
      "step": 2
    },
    {
      "epoch": 0.24150943396226415,
      "grad_norm": 0.540018618106842,
      "learning_rate": 0.00029051982559491393,
      "loss": 2.6847,
      "step": 3
    },
    {
      "epoch": 0.3220125786163522,
      "grad_norm": 0.4558205008506775,
      "learning_rate": 0.00028330140180592156,
      "loss": 2.4227,
      "step": 4
    },
    {
      "epoch": 0.4025157232704403,
      "grad_norm": 0.3680214583873749,
      "learning_rate": 0.00027421729424061787,
      "loss": 2.4519,
      "step": 5
    },
    {
      "epoch": 0.4830188679245283,
      "grad_norm": 0.4242393672466278,
      "learning_rate": 0.0002634107647018905,
      "loss": 2.5548,
      "step": 6
    },
    {
      "epoch": 0.5635220125786163,
      "grad_norm": 0.5190682411193848,
      "learning_rate": 0.00025105223861607306,
      "loss": 2.3866,
      "step": 7
    },
    {
      "epoch": 0.6440251572327044,
      "grad_norm": 0.39296650886535645,
      "learning_rate": 0.00023733661732216452,
      "loss": 2.3512,
      "step": 8
    },
    {
      "epoch": 0.7245283018867924,
      "grad_norm": 0.38818106055259705,
      "learning_rate": 0.00022248020436128478,
      "loss": 2.4139,
      "step": 9
    },
    {
      "epoch": 0.8050314465408805,
      "grad_norm": 0.3671814799308777,
      "learning_rate": 0.00020671729424061788,
      "loss": 2.409,
      "step": 10
    },
    {
      "epoch": 0.8855345911949686,
      "grad_norm": 0.3352302014827728,
      "learning_rate": 0.00019029647746907283,
      "loss": 2.281,
      "step": 11
    },
    {
      "epoch": 0.9660377358490566,
      "grad_norm": 0.5149916410446167,
      "learning_rate": 0.0001734767201364573,
      "loss": 2.3389,
      "step": 12
    },
    {
      "epoch": 1.0465408805031446,
      "grad_norm": 0.7806757688522339,
      "learning_rate": 0.0001565232798635427,
      "loss": 3.9794,
      "step": 13
    },
    {
      "epoch": 1.1270440251572327,
      "grad_norm": 0.5463436841964722,
      "learning_rate": 0.00013970352253092714,
      "loss": 2.1307,
      "step": 14
    },
    {
      "epoch": 1.2075471698113207,
      "grad_norm": 0.6771302819252014,
      "learning_rate": 0.00012328270575938212,
      "loss": 2.3206,
      "step": 15
    },
    {
      "epoch": 1.2880503144654087,
      "grad_norm": 0.4971172511577606,
      "learning_rate": 0.00010751979563871518,
      "loss": 2.3657,
      "step": 16
    },
    {
      "epoch": 1.3685534591194968,
      "grad_norm": 0.4461110532283783,
      "learning_rate": 9.266338267783541e-05,
      "loss": 2.1339,
      "step": 17
    },
    {
      "epoch": 1.449056603773585,
      "grad_norm": 0.2902529835700989,
      "learning_rate": 7.894776138392688e-05,
      "loss": 2.2233,
      "step": 18
    },
    {
      "epoch": 1.529559748427673,
      "grad_norm": 0.2932526171207428,
      "learning_rate": 6.658923529810946e-05,
      "loss": 2.3412,
      "step": 19
    },
    {
      "epoch": 1.610062893081761,
      "grad_norm": 0.4572833776473999,
      "learning_rate": 5.578270575938211e-05,
      "loss": 2.081,
      "step": 20
    },
    {
      "epoch": 1.6905660377358491,
      "grad_norm": 0.2661089301109314,
      "learning_rate": 4.669859819407844e-05,
      "loss": 2.3255,
      "step": 21
    },
    {
      "epoch": 1.7710691823899372,
      "grad_norm": 0.40115484595298767,
      "learning_rate": 3.948017440508607e-05,
      "loss": 2.2999,
      "step": 22
    },
    {
      "epoch": 1.8515723270440252,
      "grad_norm": 0.2471986562013626,
      "learning_rate": 3.4241273247634805e-05,
      "loss": 2.0734,
      "step": 23
    },
    {
      "epoch": 1.9320754716981132,
      "grad_norm": 0.2944956421852112,
      "learning_rate": 3.10645153225455e-05,
      "loss": 2.2152,
      "step": 24
    },
    {
      "epoch": 2.0125786163522013,
      "grad_norm": 0.4555993676185608,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 3.6559,
      "step": 25
    },
    {
      "epoch": 2.0125786163522013,
      "eval_loss": 2.115447759628296,
      "eval_runtime": 0.3001,
      "eval_samples_per_second": 166.599,
      "eval_steps_per_second": 43.316,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.11070068867072e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}