{
  "best_metric": 1.82403564453125,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.009961647656522389,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019923295313044778,
      "grad_norm": 1.2284634113311768,
      "learning_rate": 1e-05,
      "loss": 2.9428,
      "step": 1
    },
    {
      "epoch": 0.00019923295313044778,
      "eval_loss": 4.057371616363525,
      "eval_runtime": 602.6822,
      "eval_samples_per_second": 14.027,
      "eval_steps_per_second": 3.508,
      "step": 1
    },
    {
      "epoch": 0.00039846590626089557,
      "grad_norm": 1.68904447555542,
      "learning_rate": 2e-05,
      "loss": 3.5104,
      "step": 2
    },
    {
      "epoch": 0.0005976988593913434,
      "grad_norm": 1.1529206037521362,
      "learning_rate": 3e-05,
      "loss": 2.5356,
      "step": 3
    },
    {
      "epoch": 0.0007969318125217911,
      "grad_norm": 1.5264250040054321,
      "learning_rate": 4e-05,
      "loss": 3.2004,
      "step": 4
    },
    {
      "epoch": 0.0009961647656522388,
      "grad_norm": 1.771896481513977,
      "learning_rate": 5e-05,
      "loss": 3.2337,
      "step": 5
    },
    {
      "epoch": 0.0011953977187826868,
      "grad_norm": 1.5935925245285034,
      "learning_rate": 6e-05,
      "loss": 3.3152,
      "step": 6
    },
    {
      "epoch": 0.0013946306719131345,
      "grad_norm": 1.6249325275421143,
      "learning_rate": 7e-05,
      "loss": 2.8173,
      "step": 7
    },
    {
      "epoch": 0.0015938636250435823,
      "grad_norm": 1.6689910888671875,
      "learning_rate": 8e-05,
      "loss": 2.8131,
      "step": 8
    },
    {
      "epoch": 0.00179309657817403,
      "grad_norm": 1.5419508218765259,
      "learning_rate": 9e-05,
      "loss": 2.5659,
      "step": 9
    },
    {
      "epoch": 0.0019923295313044776,
      "grad_norm": 1.5755772590637207,
      "learning_rate": 0.0001,
      "loss": 2.3418,
      "step": 10
    },
    {
      "epoch": 0.0021915624844349255,
      "grad_norm": 1.8057647943496704,
      "learning_rate": 9.99983777858264e-05,
      "loss": 2.3202,
      "step": 11
    },
    {
      "epoch": 0.0023907954375653735,
      "grad_norm": 1.9575777053833008,
      "learning_rate": 9.999351124856874e-05,
      "loss": 2.4932,
      "step": 12
    },
    {
      "epoch": 0.002590028390695821,
      "grad_norm": 1.9527984857559204,
      "learning_rate": 9.998540070400966e-05,
      "loss": 1.8685,
      "step": 13
    },
    {
      "epoch": 0.002789261343826269,
      "grad_norm": 1.5637708902359009,
      "learning_rate": 9.997404667843075e-05,
      "loss": 1.831,
      "step": 14
    },
    {
      "epoch": 0.0029884942969567166,
      "grad_norm": 1.2870111465454102,
      "learning_rate": 9.995944990857849e-05,
      "loss": 2.0248,
      "step": 15
    },
    {
      "epoch": 0.0031877272500871645,
      "grad_norm": 1.454819679260254,
      "learning_rate": 9.994161134161634e-05,
      "loss": 1.9433,
      "step": 16
    },
    {
      "epoch": 0.003386960203217612,
      "grad_norm": 1.470567226409912,
      "learning_rate": 9.992053213506334e-05,
      "loss": 1.8326,
      "step": 17
    },
    {
      "epoch": 0.00358619315634806,
      "grad_norm": 1.2251739501953125,
      "learning_rate": 9.989621365671902e-05,
      "loss": 1.9384,
      "step": 18
    },
    {
      "epoch": 0.0037854261094785076,
      "grad_norm": 1.148119568824768,
      "learning_rate": 9.986865748457457e-05,
      "loss": 1.9556,
      "step": 19
    },
    {
      "epoch": 0.003984659062608955,
      "grad_norm": 1.022918939590454,
      "learning_rate": 9.983786540671051e-05,
      "loss": 1.7457,
      "step": 20
    },
    {
      "epoch": 0.0041838920157394035,
      "grad_norm": 1.0495177507400513,
      "learning_rate": 9.980383942118066e-05,
      "loss": 1.7567,
      "step": 21
    },
    {
      "epoch": 0.004383124968869851,
      "grad_norm": 1.1652737855911255,
      "learning_rate": 9.976658173588244e-05,
      "loss": 1.7853,
      "step": 22
    },
    {
      "epoch": 0.004582357922000299,
      "grad_norm": 1.1292279958724976,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.6153,
      "step": 23
    },
    {
      "epoch": 0.004781590875130747,
      "grad_norm": 1.0591461658477783,
      "learning_rate": 9.968238114591566e-05,
      "loss": 2.0229,
      "step": 24
    },
    {
      "epoch": 0.0049808238282611945,
      "grad_norm": 1.0844651460647583,
      "learning_rate": 9.96354437049027e-05,
      "loss": 1.8225,
      "step": 25
    },
    {
      "epoch": 0.005180056781391642,
      "grad_norm": 1.2742100954055786,
      "learning_rate": 9.95852854910781e-05,
      "loss": 2.1446,
      "step": 26
    },
    {
      "epoch": 0.00537928973452209,
      "grad_norm": 1.0586717128753662,
      "learning_rate": 9.953190975913647e-05,
      "loss": 1.8019,
      "step": 27
    },
    {
      "epoch": 0.005578522687652538,
      "grad_norm": 0.8670190572738647,
      "learning_rate": 9.947531997255256e-05,
      "loss": 1.8777,
      "step": 28
    },
    {
      "epoch": 0.005777755640782986,
      "grad_norm": 1.0841562747955322,
      "learning_rate": 9.941551980335652e-05,
      "loss": 1.8035,
      "step": 29
    },
    {
      "epoch": 0.005976988593913433,
      "grad_norm": 1.0292096138000488,
      "learning_rate": 9.935251313189564e-05,
      "loss": 1.8991,
      "step": 30
    },
    {
      "epoch": 0.006176221547043881,
      "grad_norm": 0.9672908782958984,
      "learning_rate": 9.928630404658255e-05,
      "loss": 1.8272,
      "step": 31
    },
    {
      "epoch": 0.006375454500174329,
      "grad_norm": 0.9663026332855225,
      "learning_rate": 9.921689684362989e-05,
      "loss": 1.9222,
      "step": 32
    },
    {
      "epoch": 0.006574687453304777,
      "grad_norm": 0.8640333414077759,
      "learning_rate": 9.914429602677162e-05,
      "loss": 1.9071,
      "step": 33
    },
    {
      "epoch": 0.006773920406435224,
      "grad_norm": 0.9674398303031921,
      "learning_rate": 9.906850630697068e-05,
      "loss": 2.113,
      "step": 34
    },
    {
      "epoch": 0.0069731533595656725,
      "grad_norm": 0.9393993616104126,
      "learning_rate": 9.898953260211338e-05,
      "loss": 1.8711,
      "step": 35
    },
    {
      "epoch": 0.00717238631269612,
      "grad_norm": 0.9489927291870117,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.0426,
      "step": 36
    },
    {
      "epoch": 0.007371619265826568,
      "grad_norm": 1.1132601499557495,
      "learning_rate": 9.882205394146361e-05,
      "loss": 2.3052,
      "step": 37
    },
    {
      "epoch": 0.007570852218957015,
      "grad_norm": 1.2090137004852295,
      "learning_rate": 9.87335598531214e-05,
      "loss": 2.0266,
      "step": 38
    },
    {
      "epoch": 0.0077700851720874636,
      "grad_norm": 1.0615320205688477,
      "learning_rate": 9.864190351391822e-05,
      "loss": 2.1822,
      "step": 39
    },
    {
      "epoch": 0.00796931812521791,
      "grad_norm": 0.9923949837684631,
      "learning_rate": 9.85470908713026e-05,
      "loss": 1.9442,
      "step": 40
    },
    {
      "epoch": 0.008168551078348359,
      "grad_norm": 1.0683104991912842,
      "learning_rate": 9.844912807753104e-05,
      "loss": 2.1782,
      "step": 41
    },
    {
      "epoch": 0.008367784031478807,
      "grad_norm": 1.1865333318710327,
      "learning_rate": 9.834802148926882e-05,
      "loss": 2.1076,
      "step": 42
    },
    {
      "epoch": 0.008567016984609254,
      "grad_norm": 0.9799418449401855,
      "learning_rate": 9.824377766717759e-05,
      "loss": 2.0544,
      "step": 43
    },
    {
      "epoch": 0.008766249937739702,
      "grad_norm": 1.0477815866470337,
      "learning_rate": 9.813640337548954e-05,
      "loss": 1.9788,
      "step": 44
    },
    {
      "epoch": 0.00896548289087015,
      "grad_norm": 0.9999564290046692,
      "learning_rate": 9.802590558156862e-05,
      "loss": 2.12,
      "step": 45
    },
    {
      "epoch": 0.009164715844000597,
      "grad_norm": 0.998177170753479,
      "learning_rate": 9.791229145545831e-05,
      "loss": 2.039,
      "step": 46
    },
    {
      "epoch": 0.009363948797131046,
      "grad_norm": 1.1539019346237183,
      "learning_rate": 9.779556836941645e-05,
      "loss": 2.3537,
      "step": 47
    },
    {
      "epoch": 0.009563181750261494,
      "grad_norm": 1.0150654315948486,
      "learning_rate": 9.767574389743682e-05,
      "loss": 2.0415,
      "step": 48
    },
    {
      "epoch": 0.00976241470339194,
      "grad_norm": 1.0183194875717163,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0481,
      "step": 49
    },
    {
      "epoch": 0.009961647656522389,
      "grad_norm": 0.9892953038215637,
      "learning_rate": 9.742682209735727e-05,
      "loss": 2.1764,
      "step": 50
    },
    {
      "epoch": 0.009961647656522389,
      "eval_loss": 1.82403564453125,
      "eval_runtime": 607.5197,
      "eval_samples_per_second": 13.916,
      "eval_steps_per_second": 3.48,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 400,
  "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": 7.1094434267136e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}