{
  "best_metric": 1.17902410030365,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 57,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 5.641470432281494,
      "learning_rate": 1e-05,
      "loss": 1.8152,
      "step": 1
    },
    {
      "epoch": 0.05263157894736842,
      "eval_loss": 2.4003829956054688,
      "eval_runtime": 1.4322,
      "eval_samples_per_second": 22.344,
      "eval_steps_per_second": 5.586,
      "step": 1
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 7.016218662261963,
      "learning_rate": 2e-05,
      "loss": 2.2306,
      "step": 2
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 7.468476295471191,
      "learning_rate": 3e-05,
      "loss": 2.4055,
      "step": 3
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 6.921858310699463,
      "learning_rate": 4e-05,
      "loss": 2.2311,
      "step": 4
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 5.700323581695557,
      "learning_rate": 5e-05,
      "loss": 1.2817,
      "step": 5
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 5.553191661834717,
      "learning_rate": 6e-05,
      "loss": 1.3695,
      "step": 6
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 5.111515998840332,
      "learning_rate": 7e-05,
      "loss": 1.571,
      "step": 7
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 5.205094814300537,
      "learning_rate": 8e-05,
      "loss": 1.3618,
      "step": 8
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 2.4604954719543457,
      "learning_rate": 9e-05,
      "loss": 1.1426,
      "step": 9
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 2.7724130153656006,
      "learning_rate": 0.0001,
      "loss": 1.2481,
      "step": 10
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 3.014984607696533,
      "learning_rate": 9.988834393115767e-05,
      "loss": 1.2398,
      "step": 11
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 2.933849334716797,
      "learning_rate": 9.9553874407739e-05,
      "loss": 1.2755,
      "step": 12
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 2.1021170616149902,
      "learning_rate": 9.899808525182935e-05,
      "loss": 1.2942,
      "step": 13
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 2.005964517593384,
      "learning_rate": 9.822345875271883e-05,
      "loss": 0.9789,
      "step": 14
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 2.327549695968628,
      "learning_rate": 9.723345458039594e-05,
      "loss": 1.2426,
      "step": 15
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 2.6125495433807373,
      "learning_rate": 9.603249433382144e-05,
      "loss": 1.271,
      "step": 16
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 1.9391018152236938,
      "learning_rate": 9.462594179299406e-05,
      "loss": 1.1135,
      "step": 17
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 1.9315905570983887,
      "learning_rate": 9.302007896300698e-05,
      "loss": 0.8405,
      "step": 18
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.251284599304199,
      "learning_rate": 9.122207801708802e-05,
      "loss": 1.1481,
      "step": 19
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 1.276843547821045,
      "learning_rate": 8.923996926393305e-05,
      "loss": 0.9004,
      "step": 20
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 1.6411747932434082,
      "learning_rate": 8.708260528239788e-05,
      "loss": 0.8815,
      "step": 21
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": 1.6848231554031372,
      "learning_rate": 8.475962138373213e-05,
      "loss": 0.8548,
      "step": 22
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 2.1725783348083496,
      "learning_rate": 8.228139257794012e-05,
      "loss": 0.9927,
      "step": 23
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 1.4698820114135742,
      "learning_rate": 7.965898723646776e-05,
      "loss": 0.7704,
      "step": 24
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 1.57767915725708,
      "learning_rate": 7.690411765816864e-05,
      "loss": 0.8826,
      "step": 25
    },
    {
      "epoch": 1.368421052631579,
      "grad_norm": 2.138045310974121,
      "learning_rate": 7.402908775933419e-05,
      "loss": 1.0096,
      "step": 26
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 1.977986216545105,
      "learning_rate": 7.104673812141675e-05,
      "loss": 0.7918,
      "step": 27
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 1.6806212663650513,
      "learning_rate": 6.797038864187564e-05,
      "loss": 0.8942,
      "step": 28
    },
    {
      "epoch": 1.526315789473684,
      "grad_norm": 1.8202488422393799,
      "learning_rate": 6.481377904428171e-05,
      "loss": 0.829,
      "step": 29
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 1.698825716972351,
      "learning_rate": 6.159100751337642e-05,
      "loss": 0.7224,
      "step": 30
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 2.045192241668701,
      "learning_rate": 5.831646772915651e-05,
      "loss": 0.8145,
      "step": 31
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": 1.6247888803482056,
      "learning_rate": 5.5004784581204927e-05,
      "loss": 0.8722,
      "step": 32
    },
    {
      "epoch": 1.736842105263158,
      "grad_norm": 1.9170387983322144,
      "learning_rate": 5.167074885038373e-05,
      "loss": 0.8959,
      "step": 33
    },
    {
      "epoch": 1.7894736842105263,
      "grad_norm": 1.7588573694229126,
      "learning_rate": 4.832925114961629e-05,
      "loss": 0.7805,
      "step": 34
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 2.1556222438812256,
      "learning_rate": 4.4995215418795085e-05,
      "loss": 0.8822,
      "step": 35
    },
    {
      "epoch": 1.8947368421052633,
      "grad_norm": 1.806931972503662,
      "learning_rate": 4.1683532270843504e-05,
      "loss": 0.8529,
      "step": 36
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 1.471117615699768,
      "learning_rate": 3.840899248662358e-05,
      "loss": 0.522,
      "step": 37
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.146503448486328,
      "learning_rate": 3.5186220955718306e-05,
      "loss": 0.8268,
      "step": 38
    },
    {
      "epoch": 2.0526315789473686,
      "grad_norm": 1.1273983716964722,
      "learning_rate": 3.202961135812437e-05,
      "loss": 0.6134,
      "step": 39
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 1.3619683980941772,
      "learning_rate": 2.895326187858326e-05,
      "loss": 0.6049,
      "step": 40
    },
    {
      "epoch": 2.1578947368421053,
      "grad_norm": 1.564672589302063,
      "learning_rate": 2.5970912240665813e-05,
      "loss": 0.6477,
      "step": 41
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": 1.7352532148361206,
      "learning_rate": 2.3095882341831372e-05,
      "loss": 0.5832,
      "step": 42
    },
    {
      "epoch": 2.263157894736842,
      "grad_norm": 1.3710906505584717,
      "learning_rate": 2.0341012763532243e-05,
      "loss": 0.6772,
      "step": 43
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 1.586318850517273,
      "learning_rate": 1.771860742205988e-05,
      "loss": 0.7559,
      "step": 44
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 1.4341673851013184,
      "learning_rate": 1.5240378616267886e-05,
      "loss": 0.4653,
      "step": 45
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": 1.5436069965362549,
      "learning_rate": 1.2917394717602121e-05,
      "loss": 0.4211,
      "step": 46
    },
    {
      "epoch": 2.473684210526316,
      "grad_norm": 1.3379137516021729,
      "learning_rate": 1.0760030736066951e-05,
      "loss": 0.4711,
      "step": 47
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": 1.7431352138519287,
      "learning_rate": 8.777921982911996e-06,
      "loss": 0.5765,
      "step": 48
    },
    {
      "epoch": 2.5789473684210527,
      "grad_norm": 1.564483880996704,
      "learning_rate": 6.979921036993042e-06,
      "loss": 0.6245,
      "step": 49
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 2.1554219722747803,
      "learning_rate": 5.374058207005944e-06,
      "loss": 0.631,
      "step": 50
    },
    {
      "epoch": 2.6315789473684212,
      "eval_loss": 1.17902410030365,
      "eval_runtime": 1.4441,
      "eval_samples_per_second": 22.16,
      "eval_steps_per_second": 5.54,
      "step": 50
    },
    {
      "epoch": 2.6842105263157894,
      "grad_norm": 1.3527997732162476,
      "learning_rate": 3.967505666178556e-06,
      "loss": 0.5721,
      "step": 51
    },
    {
      "epoch": 2.736842105263158,
      "grad_norm": 1.6944499015808105,
      "learning_rate": 2.7665454196040664e-06,
      "loss": 0.5942,
      "step": 52
    },
    {
      "epoch": 2.7894736842105265,
      "grad_norm": 1.7159970998764038,
      "learning_rate": 1.7765412472811771e-06,
      "loss": 0.6168,
      "step": 53
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 1.695430874824524,
      "learning_rate": 1.0019147481706625e-06,
      "loss": 0.5101,
      "step": 54
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 1.4705897569656372,
      "learning_rate": 4.461255922609986e-07,
      "loss": 0.632,
      "step": 55
    },
    {
      "epoch": 2.9473684210526314,
      "grad_norm": 1.322156548500061,
      "learning_rate": 1.1165606884234181e-07,
      "loss": 0.4171,
      "step": 56
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.7574959993362427,
      "learning_rate": 0.0,
      "loss": 0.5181,
      "step": 57
    }
  ],
  "logging_steps": 1,
  "max_steps": 57,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.338589547115315e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}