{
  "best_metric": 2.0129618644714355,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.07423904974016332,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014847809948032665,
      "grad_norm": 0.38478878140449524,
      "learning_rate": 1e-05,
      "loss": 2.1167,
      "step": 1
    },
    {
      "epoch": 0.0014847809948032665,
      "eval_loss": 2.15017032623291,
      "eval_runtime": 52.6512,
      "eval_samples_per_second": 86.171,
      "eval_steps_per_second": 5.394,
      "step": 1
    },
    {
      "epoch": 0.002969561989606533,
      "grad_norm": 0.44478335976600647,
      "learning_rate": 2e-05,
      "loss": 2.0261,
      "step": 2
    },
    {
      "epoch": 0.004454342984409799,
      "grad_norm": 0.4396665692329407,
      "learning_rate": 3e-05,
      "loss": 2.1107,
      "step": 3
    },
    {
      "epoch": 0.005939123979213066,
      "grad_norm": 0.3937435448169708,
      "learning_rate": 4e-05,
      "loss": 2.1302,
      "step": 4
    },
    {
      "epoch": 0.007423904974016332,
      "grad_norm": 0.36997291445732117,
      "learning_rate": 5e-05,
      "loss": 2.0641,
      "step": 5
    },
    {
      "epoch": 0.008908685968819599,
      "grad_norm": 0.33418500423431396,
      "learning_rate": 6e-05,
      "loss": 2.0832,
      "step": 6
    },
    {
      "epoch": 0.010393466963622866,
      "grad_norm": 0.3295334279537201,
      "learning_rate": 7e-05,
      "loss": 2.0553,
      "step": 7
    },
    {
      "epoch": 0.011878247958426132,
      "grad_norm": 0.323632150888443,
      "learning_rate": 8e-05,
      "loss": 2.0556,
      "step": 8
    },
    {
      "epoch": 0.013363028953229399,
      "grad_norm": 0.3482978641986847,
      "learning_rate": 9e-05,
      "loss": 2.1089,
      "step": 9
    },
    {
      "epoch": 0.014847809948032665,
      "grad_norm": 0.38115793466567993,
      "learning_rate": 0.0001,
      "loss": 2.1441,
      "step": 10
    },
    {
      "epoch": 0.016332590942835932,
      "grad_norm": 0.37201857566833496,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.1967,
      "step": 11
    },
    {
      "epoch": 0.017817371937639197,
      "grad_norm": 0.3628121018409729,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.1804,
      "step": 12
    },
    {
      "epoch": 0.019302152932442463,
      "grad_norm": 0.301399290561676,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.2342,
      "step": 13
    },
    {
      "epoch": 0.020786933927245732,
      "grad_norm": 0.39368724822998047,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.958,
      "step": 14
    },
    {
      "epoch": 0.022271714922048998,
      "grad_norm": 0.28724896907806396,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.9894,
      "step": 15
    },
    {
      "epoch": 0.023756495916852263,
      "grad_norm": 0.27313336730003357,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.0118,
      "step": 16
    },
    {
      "epoch": 0.025241276911655532,
      "grad_norm": 0.2967425584793091,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.989,
      "step": 17
    },
    {
      "epoch": 0.026726057906458798,
      "grad_norm": 0.29300904273986816,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.0379,
      "step": 18
    },
    {
      "epoch": 0.028210838901262063,
      "grad_norm": 0.29489371180534363,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.0324,
      "step": 19
    },
    {
      "epoch": 0.02969561989606533,
      "grad_norm": 0.28660160303115845,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.0173,
      "step": 20
    },
    {
      "epoch": 0.031180400890868598,
      "grad_norm": 0.28985676169395447,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.1266,
      "step": 21
    },
    {
      "epoch": 0.032665181885671864,
      "grad_norm": 0.29200324416160583,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.078,
      "step": 22
    },
    {
      "epoch": 0.03414996288047513,
      "grad_norm": 0.3007466495037079,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.0785,
      "step": 23
    },
    {
      "epoch": 0.035634743875278395,
      "grad_norm": 0.31664276123046875,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.1601,
      "step": 24
    },
    {
      "epoch": 0.03711952487008166,
      "grad_norm": 0.35239487886428833,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.2085,
      "step": 25
    },
    {
      "epoch": 0.038604305864884926,
      "grad_norm": 0.24031668901443481,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.9822,
      "step": 26
    },
    {
      "epoch": 0.0400890868596882,
      "grad_norm": 0.2429058849811554,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.9006,
      "step": 27
    },
    {
      "epoch": 0.041573867854491464,
      "grad_norm": 0.22939959168434143,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.9815,
      "step": 28
    },
    {
      "epoch": 0.04305864884929473,
      "grad_norm": 0.23532599210739136,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.991,
      "step": 29
    },
    {
      "epoch": 0.044543429844097995,
      "grad_norm": 0.24697649478912354,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.0062,
      "step": 30
    },
    {
      "epoch": 0.04602821083890126,
      "grad_norm": 0.27173495292663574,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.9554,
      "step": 31
    },
    {
      "epoch": 0.047512991833704527,
      "grad_norm": 0.2755003869533539,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.006,
      "step": 32
    },
    {
      "epoch": 0.04899777282850779,
      "grad_norm": 0.26322251558303833,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.0641,
      "step": 33
    },
    {
      "epoch": 0.050482553823311065,
      "grad_norm": 0.2873618006706238,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.0246,
      "step": 34
    },
    {
      "epoch": 0.05196733481811433,
      "grad_norm": 0.2915358245372772,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.0805,
      "step": 35
    },
    {
      "epoch": 0.053452115812917596,
      "grad_norm": 0.2966706454753876,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.0495,
      "step": 36
    },
    {
      "epoch": 0.05493689680772086,
      "grad_norm": 0.33095332980155945,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.1258,
      "step": 37
    },
    {
      "epoch": 0.05642167780252413,
      "grad_norm": 0.2613125443458557,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.1623,
      "step": 38
    },
    {
      "epoch": 0.05790645879732739,
      "grad_norm": 0.2278221845626831,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.9022,
      "step": 39
    },
    {
      "epoch": 0.05939123979213066,
      "grad_norm": 0.24880492687225342,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.9832,
      "step": 40
    },
    {
      "epoch": 0.06087602078693393,
      "grad_norm": 0.24073165655136108,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.9382,
      "step": 41
    },
    {
      "epoch": 0.062360801781737196,
      "grad_norm": 0.24341227114200592,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.0172,
      "step": 42
    },
    {
      "epoch": 0.06384558277654045,
      "grad_norm": 0.24885092675685883,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.958,
      "step": 43
    },
    {
      "epoch": 0.06533036377134373,
      "grad_norm": 0.2509358525276184,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.9621,
      "step": 44
    },
    {
      "epoch": 0.066815144766147,
      "grad_norm": 0.2590627372264862,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.929,
      "step": 45
    },
    {
      "epoch": 0.06829992576095026,
      "grad_norm": 0.2795308530330658,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.0423,
      "step": 46
    },
    {
      "epoch": 0.06978470675575353,
      "grad_norm": 0.28098785877227783,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.001,
      "step": 47
    },
    {
      "epoch": 0.07126948775055679,
      "grad_norm": 0.30104294419288635,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.9982,
      "step": 48
    },
    {
      "epoch": 0.07275426874536006,
      "grad_norm": 0.3143393397331238,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.0799,
      "step": 49
    },
    {
      "epoch": 0.07423904974016332,
      "grad_norm": 0.33249884843826294,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.1751,
      "step": 50
    },
    {
      "epoch": 0.07423904974016332,
      "eval_loss": 2.0129618644714355,
      "eval_runtime": 19.5295,
      "eval_samples_per_second": 232.315,
      "eval_steps_per_second": 14.542,
      "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": 5.885129827077325e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}