{
  "best_metric": 1.3527735471725464,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.03311532411623479,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013246129646493916,
      "grad_norm": 1.6896806955337524,
      "learning_rate": 5e-05,
      "loss": 1.8853,
      "step": 1
    },
    {
      "epoch": 0.0013246129646493916,
      "eval_loss": 2.9228813648223877,
      "eval_runtime": 104.7571,
      "eval_samples_per_second": 48.55,
      "eval_steps_per_second": 6.071,
      "step": 1
    },
    {
      "epoch": 0.002649225929298783,
      "grad_norm": 2.716233491897583,
      "learning_rate": 0.0001,
      "loss": 2.6317,
      "step": 2
    },
    {
      "epoch": 0.0039738388939481745,
      "grad_norm": 2.624985694885254,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.6739,
      "step": 3
    },
    {
      "epoch": 0.005298451858597566,
      "grad_norm": 2.169276714324951,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.5246,
      "step": 4
    },
    {
      "epoch": 0.006623064823246957,
      "grad_norm": 1.8879032135009766,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.3163,
      "step": 5
    },
    {
      "epoch": 0.007947677787896349,
      "grad_norm": 1.8610759973526,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.1461,
      "step": 6
    },
    {
      "epoch": 0.00927229075254574,
      "grad_norm": 1.7441582679748535,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.0269,
      "step": 7
    },
    {
      "epoch": 0.010596903717195133,
      "grad_norm": 1.4809761047363281,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.9799,
      "step": 8
    },
    {
      "epoch": 0.011921516681844524,
      "grad_norm": 1.6304855346679688,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.785,
      "step": 9
    },
    {
      "epoch": 0.013246129646493915,
      "grad_norm": 1.3047534227371216,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.76,
      "step": 10
    },
    {
      "epoch": 0.014570742611143307,
      "grad_norm": 1.04607093334198,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.8074,
      "step": 11
    },
    {
      "epoch": 0.015895355575792698,
      "grad_norm": 0.9902725219726562,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.8008,
      "step": 12
    },
    {
      "epoch": 0.01721996854044209,
      "grad_norm": 1.4731831550598145,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.3515,
      "step": 13
    },
    {
      "epoch": 0.01854458150509148,
      "grad_norm": 1.0245866775512695,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.5224,
      "step": 14
    },
    {
      "epoch": 0.01986919446974087,
      "grad_norm": 0.9316340088844299,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.5249,
      "step": 15
    },
    {
      "epoch": 0.021193807434390265,
      "grad_norm": 0.9975677728652954,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.4459,
      "step": 16
    },
    {
      "epoch": 0.022518420399039656,
      "grad_norm": 0.8698291182518005,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.4791,
      "step": 17
    },
    {
      "epoch": 0.023843033363689047,
      "grad_norm": 0.8500425219535828,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.4864,
      "step": 18
    },
    {
      "epoch": 0.025167646328338438,
      "grad_norm": 0.8855979442596436,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.4568,
      "step": 19
    },
    {
      "epoch": 0.02649225929298783,
      "grad_norm": 0.7662312984466553,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3977,
      "step": 20
    },
    {
      "epoch": 0.02781687225763722,
      "grad_norm": 0.8068965673446655,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.4062,
      "step": 21
    },
    {
      "epoch": 0.029141485222286614,
      "grad_norm": 0.751783549785614,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.3403,
      "step": 22
    },
    {
      "epoch": 0.030466098186936005,
      "grad_norm": 0.7751783132553101,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.3394,
      "step": 23
    },
    {
      "epoch": 0.031790711151585396,
      "grad_norm": 0.9629535675048828,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.5133,
      "step": 24
    },
    {
      "epoch": 0.03311532411623479,
      "grad_norm": 1.074066162109375,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.7629,
      "step": 25
    },
    {
      "epoch": 0.03311532411623479,
      "eval_loss": 1.3527735471725464,
      "eval_runtime": 104.8313,
      "eval_samples_per_second": 48.516,
      "eval_steps_per_second": 6.067,
      "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": 4.16708196040704e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}