{
  "best_metric": 2.594191312789917,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.12437810945273632,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004975124378109453,
      "grad_norm": 3.0430262088775635,
      "learning_rate": 0.0001,
      "loss": 3.2635,
      "step": 1
    },
    {
      "epoch": 0.004975124378109453,
      "eval_loss": 3.682396650314331,
      "eval_runtime": 6.5408,
      "eval_samples_per_second": 12.995,
      "eval_steps_per_second": 6.574,
      "step": 1
    },
    {
      "epoch": 0.009950248756218905,
      "grad_norm": 3.611407518386841,
      "learning_rate": 0.0002,
      "loss": 3.1135,
      "step": 2
    },
    {
      "epoch": 0.014925373134328358,
      "grad_norm": 3.713569402694702,
      "learning_rate": 0.00019978589232386035,
      "loss": 3.2019,
      "step": 3
    },
    {
      "epoch": 0.01990049751243781,
      "grad_norm": 3.7321176528930664,
      "learning_rate": 0.00019914448613738106,
      "loss": 2.8382,
      "step": 4
    },
    {
      "epoch": 0.024875621890547265,
      "grad_norm": 3.764651298522949,
      "learning_rate": 0.00019807852804032305,
      "loss": 2.8298,
      "step": 5
    },
    {
      "epoch": 0.029850746268656716,
      "grad_norm": 3.621135950088501,
      "learning_rate": 0.00019659258262890683,
      "loss": 3.1415,
      "step": 6
    },
    {
      "epoch": 0.03482587064676617,
      "grad_norm": 8.381474494934082,
      "learning_rate": 0.0001946930129495106,
      "loss": 2.8867,
      "step": 7
    },
    {
      "epoch": 0.03980099502487562,
      "grad_norm": 3.6087472438812256,
      "learning_rate": 0.0001923879532511287,
      "loss": 2.6187,
      "step": 8
    },
    {
      "epoch": 0.04477611940298507,
      "grad_norm": 4.97490119934082,
      "learning_rate": 0.00018968727415326884,
      "loss": 2.7751,
      "step": 9
    },
    {
      "epoch": 0.04975124378109453,
      "grad_norm": 3.8109967708587646,
      "learning_rate": 0.00018660254037844388,
      "loss": 2.9982,
      "step": 10
    },
    {
      "epoch": 0.05472636815920398,
      "grad_norm": 3.904412269592285,
      "learning_rate": 0.00018314696123025454,
      "loss": 2.9809,
      "step": 11
    },
    {
      "epoch": 0.05970149253731343,
      "grad_norm": 3.4200658798217773,
      "learning_rate": 0.00017933533402912354,
      "loss": 2.5012,
      "step": 12
    },
    {
      "epoch": 0.06467661691542288,
      "grad_norm": 4.79351806640625,
      "learning_rate": 0.00017518398074789775,
      "loss": 3.2791,
      "step": 13
    },
    {
      "epoch": 0.06965174129353234,
      "grad_norm": 4.197938919067383,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.7394,
      "step": 14
    },
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 3.96777081489563,
      "learning_rate": 0.00016593458151000688,
      "loss": 2.3632,
      "step": 15
    },
    {
      "epoch": 0.07960199004975124,
      "grad_norm": 3.868743658065796,
      "learning_rate": 0.00016087614290087208,
      "loss": 2.6906,
      "step": 16
    },
    {
      "epoch": 0.0845771144278607,
      "grad_norm": 4.248363018035889,
      "learning_rate": 0.00015555702330196023,
      "loss": 2.4091,
      "step": 17
    },
    {
      "epoch": 0.08955223880597014,
      "grad_norm": 4.386332035064697,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.0164,
      "step": 18
    },
    {
      "epoch": 0.0945273631840796,
      "grad_norm": 4.483827114105225,
      "learning_rate": 0.00014422886902190014,
      "loss": 2.6212,
      "step": 19
    },
    {
      "epoch": 0.09950248756218906,
      "grad_norm": 3.482344627380371,
      "learning_rate": 0.000138268343236509,
      "loss": 2.5468,
      "step": 20
    },
    {
      "epoch": 0.1044776119402985,
      "grad_norm": 3.7087607383728027,
      "learning_rate": 0.00013214394653031616,
      "loss": 2.5328,
      "step": 21
    },
    {
      "epoch": 0.10945273631840796,
      "grad_norm": 4.2484049797058105,
      "learning_rate": 0.00012588190451025207,
      "loss": 2.0708,
      "step": 22
    },
    {
      "epoch": 0.11442786069651742,
      "grad_norm": 4.827538967132568,
      "learning_rate": 0.00011950903220161285,
      "loss": 2.785,
      "step": 23
    },
    {
      "epoch": 0.11940298507462686,
      "grad_norm": 3.7040979862213135,
      "learning_rate": 0.00011305261922200519,
      "loss": 2.342,
      "step": 24
    },
    {
      "epoch": 0.12437810945273632,
      "grad_norm": 4.959524631500244,
      "learning_rate": 0.00010654031292301432,
      "loss": 2.704,
      "step": 25
    },
    {
      "epoch": 0.12437810945273632,
      "eval_loss": 2.594191312789917,
      "eval_runtime": 6.1599,
      "eval_samples_per_second": 13.799,
      "eval_steps_per_second": 6.981,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1802385752064000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}