{
  "best_metric": 1.732652187347412,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.02464268112370626,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004928536224741252,
      "grad_norm": 16.37380599975586,
      "learning_rate": 1e-05,
      "loss": 6.995,
      "step": 1
    },
    {
      "epoch": 0.0004928536224741252,
      "eval_loss": 1.744011402130127,
      "eval_runtime": 259.1339,
      "eval_samples_per_second": 13.186,
      "eval_steps_per_second": 3.299,
      "step": 1
    },
    {
      "epoch": 0.0009857072449482504,
      "grad_norm": 16.33266830444336,
      "learning_rate": 2e-05,
      "loss": 7.1083,
      "step": 2
    },
    {
      "epoch": 0.0014785608674223755,
      "grad_norm": 15.080232620239258,
      "learning_rate": 3e-05,
      "loss": 6.7867,
      "step": 3
    },
    {
      "epoch": 0.001971414489896501,
      "grad_norm": 10.568120956420898,
      "learning_rate": 4e-05,
      "loss": 6.3311,
      "step": 4
    },
    {
      "epoch": 0.0024642681123706258,
      "grad_norm": 10.395201683044434,
      "learning_rate": 5e-05,
      "loss": 6.2016,
      "step": 5
    },
    {
      "epoch": 0.002957121734844751,
      "grad_norm": 11.448528289794922,
      "learning_rate": 6e-05,
      "loss": 6.5881,
      "step": 6
    },
    {
      "epoch": 0.0034499753573188764,
      "grad_norm": 8.285737037658691,
      "learning_rate": 7e-05,
      "loss": 6.178,
      "step": 7
    },
    {
      "epoch": 0.003942828979793002,
      "grad_norm": 6.383825302124023,
      "learning_rate": 8e-05,
      "loss": 5.9585,
      "step": 8
    },
    {
      "epoch": 0.004435682602267127,
      "grad_norm": 7.123228073120117,
      "learning_rate": 9e-05,
      "loss": 6.3599,
      "step": 9
    },
    {
      "epoch": 0.0049285362247412515,
      "grad_norm": 6.691042423248291,
      "learning_rate": 0.0001,
      "loss": 5.9879,
      "step": 10
    },
    {
      "epoch": 0.005421389847215377,
      "grad_norm": 6.677425861358643,
      "learning_rate": 9.999316524962345e-05,
      "loss": 6.0902,
      "step": 11
    },
    {
      "epoch": 0.005914243469689502,
      "grad_norm": 6.691093921661377,
      "learning_rate": 9.997266286704631e-05,
      "loss": 6.13,
      "step": 12
    },
    {
      "epoch": 0.006407097092163627,
      "grad_norm": 6.412749290466309,
      "learning_rate": 9.993849845741524e-05,
      "loss": 5.9985,
      "step": 13
    },
    {
      "epoch": 0.006899950714637753,
      "grad_norm": 6.398421287536621,
      "learning_rate": 9.989068136093873e-05,
      "loss": 6.0254,
      "step": 14
    },
    {
      "epoch": 0.007392804337111878,
      "grad_norm": 6.084516525268555,
      "learning_rate": 9.98292246503335e-05,
      "loss": 6.1664,
      "step": 15
    },
    {
      "epoch": 0.007885657959586003,
      "grad_norm": 5.95521354675293,
      "learning_rate": 9.975414512725057e-05,
      "loss": 5.8991,
      "step": 16
    },
    {
      "epoch": 0.008378511582060127,
      "grad_norm": 5.627572536468506,
      "learning_rate": 9.966546331768191e-05,
      "loss": 6.0787,
      "step": 17
    },
    {
      "epoch": 0.008871365204534253,
      "grad_norm": 5.7911248207092285,
      "learning_rate": 9.956320346634876e-05,
      "loss": 6.2035,
      "step": 18
    },
    {
      "epoch": 0.009364218827008379,
      "grad_norm": 6.241641044616699,
      "learning_rate": 9.944739353007344e-05,
      "loss": 6.0726,
      "step": 19
    },
    {
      "epoch": 0.009857072449482503,
      "grad_norm": 5.327273845672607,
      "learning_rate": 9.931806517013612e-05,
      "loss": 6.2332,
      "step": 20
    },
    {
      "epoch": 0.010349926071956629,
      "grad_norm": 5.308168411254883,
      "learning_rate": 9.917525374361912e-05,
      "loss": 6.0171,
      "step": 21
    },
    {
      "epoch": 0.010842779694430755,
      "grad_norm": 5.032196998596191,
      "learning_rate": 9.901899829374047e-05,
      "loss": 5.8416,
      "step": 22
    },
    {
      "epoch": 0.011335633316904879,
      "grad_norm": 4.981048583984375,
      "learning_rate": 9.884934153917997e-05,
      "loss": 5.5985,
      "step": 23
    },
    {
      "epoch": 0.011828486939379004,
      "grad_norm": 5.130867004394531,
      "learning_rate": 9.86663298624003e-05,
      "loss": 6.1288,
      "step": 24
    },
    {
      "epoch": 0.01232134056185313,
      "grad_norm": 4.848458766937256,
      "learning_rate": 9.847001329696653e-05,
      "loss": 5.8318,
      "step": 25
    },
    {
      "epoch": 0.012814194184327254,
      "grad_norm": 5.0001397132873535,
      "learning_rate": 9.826044551386744e-05,
      "loss": 5.9925,
      "step": 26
    },
    {
      "epoch": 0.01330704780680138,
      "grad_norm": 5.232586860656738,
      "learning_rate": 9.803768380684242e-05,
      "loss": 6.2745,
      "step": 27
    },
    {
      "epoch": 0.013799901429275506,
      "grad_norm": 5.037934303283691,
      "learning_rate": 9.780178907671789e-05,
      "loss": 5.8795,
      "step": 28
    },
    {
      "epoch": 0.01429275505174963,
      "grad_norm": 5.175755500793457,
      "learning_rate": 9.755282581475769e-05,
      "loss": 6.1939,
      "step": 29
    },
    {
      "epoch": 0.014785608674223755,
      "grad_norm": 5.293409824371338,
      "learning_rate": 9.729086208503174e-05,
      "loss": 5.9304,
      "step": 30
    },
    {
      "epoch": 0.015278462296697881,
      "grad_norm": 4.89537239074707,
      "learning_rate": 9.701596950580806e-05,
      "loss": 5.7866,
      "step": 31
    },
    {
      "epoch": 0.015771315919172007,
      "grad_norm": 5.026119232177734,
      "learning_rate": 9.672822322997305e-05,
      "loss": 5.9492,
      "step": 32
    },
    {
      "epoch": 0.016264169541646133,
      "grad_norm": 5.800846576690674,
      "learning_rate": 9.642770192448536e-05,
      "loss": 5.5961,
      "step": 33
    },
    {
      "epoch": 0.016757023164120255,
      "grad_norm": 4.967105388641357,
      "learning_rate": 9.611448774886924e-05,
      "loss": 5.9876,
      "step": 34
    },
    {
      "epoch": 0.01724987678659438,
      "grad_norm": 4.971159934997559,
      "learning_rate": 9.578866633275288e-05,
      "loss": 5.9039,
      "step": 35
    },
    {
      "epoch": 0.017742730409068506,
      "grad_norm": 5.209476470947266,
      "learning_rate": 9.545032675245813e-05,
      "loss": 5.9231,
      "step": 36
    },
    {
      "epoch": 0.018235584031542632,
      "grad_norm": 5.320252418518066,
      "learning_rate": 9.509956150664796e-05,
      "loss": 5.8169,
      "step": 37
    },
    {
      "epoch": 0.018728437654016758,
      "grad_norm": 5.2738142013549805,
      "learning_rate": 9.473646649103818e-05,
      "loss": 6.002,
      "step": 38
    },
    {
      "epoch": 0.019221291276490884,
      "grad_norm": 5.119503021240234,
      "learning_rate": 9.43611409721806e-05,
      "loss": 5.931,
      "step": 39
    },
    {
      "epoch": 0.019714144898965006,
      "grad_norm": 5.318321704864502,
      "learning_rate": 9.397368756032445e-05,
      "loss": 5.9097,
      "step": 40
    },
    {
      "epoch": 0.020206998521439132,
      "grad_norm": 5.050459861755371,
      "learning_rate": 9.357421218136386e-05,
      "loss": 6.1257,
      "step": 41
    },
    {
      "epoch": 0.020699852143913258,
      "grad_norm": 5.593949794769287,
      "learning_rate": 9.316282404787871e-05,
      "loss": 6.2968,
      "step": 42
    },
    {
      "epoch": 0.021192705766387383,
      "grad_norm": 5.589847087860107,
      "learning_rate": 9.273963562927695e-05,
      "loss": 6.233,
      "step": 43
    },
    {
      "epoch": 0.02168555938886151,
      "grad_norm": 5.743232727050781,
      "learning_rate": 9.230476262104677e-05,
      "loss": 5.9828,
      "step": 44
    },
    {
      "epoch": 0.022178413011335635,
      "grad_norm": 5.6376848220825195,
      "learning_rate": 9.185832391312644e-05,
      "loss": 6.1437,
      "step": 45
    },
    {
      "epoch": 0.022671266633809757,
      "grad_norm": 11.450542449951172,
      "learning_rate": 9.140044155740101e-05,
      "loss": 6.2194,
      "step": 46
    },
    {
      "epoch": 0.023164120256283883,
      "grad_norm": 6.774994373321533,
      "learning_rate": 9.093124073433463e-05,
      "loss": 6.1023,
      "step": 47
    },
    {
      "epoch": 0.02365697387875801,
      "grad_norm": 5.768123626708984,
      "learning_rate": 9.045084971874738e-05,
      "loss": 6.2419,
      "step": 48
    },
    {
      "epoch": 0.024149827501232134,
      "grad_norm": 7.388202667236328,
      "learning_rate": 8.995939984474624e-05,
      "loss": 6.5133,
      "step": 49
    },
    {
      "epoch": 0.02464268112370626,
      "grad_norm": 7.236172676086426,
      "learning_rate": 8.945702546981969e-05,
      "loss": 6.2176,
      "step": 50
    },
    {
      "epoch": 0.02464268112370626,
      "eval_loss": 1.732652187347412,
      "eval_runtime": 260.9809,
      "eval_samples_per_second": 13.093,
      "eval_steps_per_second": 3.276,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 7.22654807898194e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}