{
  "best_metric": 0.5748075246810913,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 53,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018867924528301886,
      "grad_norm": 0.48597845435142517,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 0.3421,
      "step": 1
    },
    {
      "epoch": 0.018867924528301886,
      "eval_loss": 0.6406799554824829,
      "eval_runtime": 2.832,
      "eval_samples_per_second": 8.122,
      "eval_steps_per_second": 1.059,
      "step": 1
    },
    {
      "epoch": 0.03773584905660377,
      "grad_norm": 0.5640310049057007,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 0.425,
      "step": 2
    },
    {
      "epoch": 0.05660377358490566,
      "grad_norm": 0.6453654766082764,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.4574,
      "step": 3
    },
    {
      "epoch": 0.07547169811320754,
      "grad_norm": 0.6804544925689697,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.5156,
      "step": 4
    },
    {
      "epoch": 0.09433962264150944,
      "grad_norm": 1.0818705558776855,
      "learning_rate": 8.333333333333333e-07,
      "loss": 0.6777,
      "step": 5
    },
    {
      "epoch": 0.11320754716981132,
      "grad_norm": 0.8535451889038086,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.6579,
      "step": 6
    },
    {
      "epoch": 0.1320754716981132,
      "grad_norm": 0.8247125744819641,
      "learning_rate": 1.1666666666666668e-06,
      "loss": 0.688,
      "step": 7
    },
    {
      "epoch": 0.1509433962264151,
      "grad_norm": 1.0467246770858765,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 0.7773,
      "step": 8
    },
    {
      "epoch": 0.16981132075471697,
      "grad_norm": 0.9683018326759338,
      "learning_rate": 1.5e-06,
      "loss": 0.8131,
      "step": 9
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 1.2345473766326904,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.8966,
      "step": 10
    },
    {
      "epoch": 0.20754716981132076,
      "grad_norm": 1.0677118301391602,
      "learning_rate": 1.8333333333333333e-06,
      "loss": 0.7765,
      "step": 11
    },
    {
      "epoch": 0.22641509433962265,
      "grad_norm": 1.136951208114624,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.8055,
      "step": 12
    },
    {
      "epoch": 0.24528301886792453,
      "grad_norm": 1.4250284433364868,
      "learning_rate": 2.166666666666667e-06,
      "loss": 0.9786,
      "step": 13
    },
    {
      "epoch": 0.2641509433962264,
      "grad_norm": 0.49272510409355164,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 0.4151,
      "step": 14
    },
    {
      "epoch": 0.2830188679245283,
      "grad_norm": 0.5962244868278503,
      "learning_rate": 2.5e-06,
      "loss": 0.4406,
      "step": 15
    },
    {
      "epoch": 0.3018867924528302,
      "grad_norm": 0.7263503074645996,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.5044,
      "step": 16
    },
    {
      "epoch": 0.32075471698113206,
      "grad_norm": 0.6965276598930359,
      "learning_rate": 2.8333333333333335e-06,
      "loss": 0.5141,
      "step": 17
    },
    {
      "epoch": 0.33962264150943394,
      "grad_norm": 0.9575563073158264,
      "learning_rate": 3e-06,
      "loss": 0.6597,
      "step": 18
    },
    {
      "epoch": 0.3584905660377358,
      "grad_norm": 0.9825683236122131,
      "learning_rate": 3.1666666666666667e-06,
      "loss": 0.7005,
      "step": 19
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 0.8972132802009583,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.6616,
      "step": 20
    },
    {
      "epoch": 0.39622641509433965,
      "grad_norm": 0.988707959651947,
      "learning_rate": 3.5e-06,
      "loss": 0.7489,
      "step": 21
    },
    {
      "epoch": 0.41509433962264153,
      "grad_norm": 1.2205058336257935,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 0.811,
      "step": 22
    },
    {
      "epoch": 0.4339622641509434,
      "grad_norm": 1.2599449157714844,
      "learning_rate": 3.833333333333334e-06,
      "loss": 0.899,
      "step": 23
    },
    {
      "epoch": 0.4528301886792453,
      "grad_norm": 1.2012040615081787,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.8451,
      "step": 24
    },
    {
      "epoch": 0.4716981132075472,
      "grad_norm": 1.4091460704803467,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.9082,
      "step": 25
    },
    {
      "epoch": 0.49056603773584906,
      "grad_norm": 1.4249144792556763,
      "learning_rate": 4.333333333333334e-06,
      "loss": 0.8678,
      "step": 26
    },
    {
      "epoch": 0.5094339622641509,
      "grad_norm": 0.5048844218254089,
      "learning_rate": 4.5e-06,
      "loss": 0.3187,
      "step": 27
    },
    {
      "epoch": 0.5283018867924528,
      "grad_norm": 0.5248401761054993,
      "learning_rate": 4.666666666666667e-06,
      "loss": 0.3534,
      "step": 28
    },
    {
      "epoch": 0.5471698113207547,
      "grad_norm": 0.7878013849258423,
      "learning_rate": 4.833333333333333e-06,
      "loss": 0.5735,
      "step": 29
    },
    {
      "epoch": 0.5660377358490566,
      "grad_norm": 0.891715943813324,
      "learning_rate": 5e-06,
      "loss": 0.5955,
      "step": 30
    },
    {
      "epoch": 0.5849056603773585,
      "grad_norm": 0.9417240619659424,
      "learning_rate": 4.976714865090827e-06,
      "loss": 0.5604,
      "step": 31
    },
    {
      "epoch": 0.6037735849056604,
      "grad_norm": 0.9506474733352661,
      "learning_rate": 4.907293218369499e-06,
      "loss": 0.6435,
      "step": 32
    },
    {
      "epoch": 0.6226415094339622,
      "grad_norm": 1.0318093299865723,
      "learning_rate": 4.793028253763633e-06,
      "loss": 0.6832,
      "step": 33
    },
    {
      "epoch": 0.6415094339622641,
      "grad_norm": 1.2492221593856812,
      "learning_rate": 4.636048511366222e-06,
      "loss": 0.7548,
      "step": 34
    },
    {
      "epoch": 0.660377358490566,
      "grad_norm": 1.2087585926055908,
      "learning_rate": 4.43927822676105e-06,
      "loss": 0.7447,
      "step": 35
    },
    {
      "epoch": 0.6792452830188679,
      "grad_norm": 1.3125813007354736,
      "learning_rate": 4.206382858046636e-06,
      "loss": 0.7538,
      "step": 36
    },
    {
      "epoch": 0.6981132075471698,
      "grad_norm": 1.3117985725402832,
      "learning_rate": 3.941700805287169e-06,
      "loss": 0.7759,
      "step": 37
    },
    {
      "epoch": 0.7169811320754716,
      "grad_norm": 1.2447526454925537,
      "learning_rate": 3.650162594327881e-06,
      "loss": 0.7522,
      "step": 38
    },
    {
      "epoch": 0.7358490566037735,
      "grad_norm": 1.4026564359664917,
      "learning_rate": 3.3371990304274654e-06,
      "loss": 0.9015,
      "step": 39
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 0.49723052978515625,
      "learning_rate": 3.0086400326315853e-06,
      "loss": 0.3198,
      "step": 40
    },
    {
      "epoch": 0.7735849056603774,
      "grad_norm": 0.5736966133117676,
      "learning_rate": 2.670606033411678e-06,
      "loss": 0.3623,
      "step": 41
    },
    {
      "epoch": 0.7924528301886793,
      "grad_norm": 0.734040379524231,
      "learning_rate": 2.3293939665883233e-06,
      "loss": 0.4454,
      "step": 42
    },
    {
      "epoch": 0.8113207547169812,
      "grad_norm": 0.9669572114944458,
      "learning_rate": 1.991359967368416e-06,
      "loss": 0.5139,
      "step": 43
    },
    {
      "epoch": 0.8301886792452831,
      "grad_norm": 0.9351544380187988,
      "learning_rate": 1.6628009695725348e-06,
      "loss": 0.5852,
      "step": 44
    },
    {
      "epoch": 0.8490566037735849,
      "grad_norm": 1.0754104852676392,
      "learning_rate": 1.3498374056721198e-06,
      "loss": 0.6787,
      "step": 45
    },
    {
      "epoch": 0.8679245283018868,
      "grad_norm": 1.090160608291626,
      "learning_rate": 1.0582991947128324e-06,
      "loss": 0.5953,
      "step": 46
    },
    {
      "epoch": 0.8867924528301887,
      "grad_norm": 1.2168736457824707,
      "learning_rate": 7.936171419533653e-07,
      "loss": 0.7085,
      "step": 47
    },
    {
      "epoch": 0.9056603773584906,
      "grad_norm": 1.2602514028549194,
      "learning_rate": 5.607217732389503e-07,
      "loss": 0.7373,
      "step": 48
    },
    {
      "epoch": 0.9245283018867925,
      "grad_norm": 1.1412434577941895,
      "learning_rate": 3.639514886337786e-07,
      "loss": 0.66,
      "step": 49
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 1.175021767616272,
      "learning_rate": 2.0697174623636795e-07,
      "loss": 0.6905,
      "step": 50
    },
    {
      "epoch": 0.9433962264150944,
      "eval_loss": 0.5748075246810913,
      "eval_runtime": 1.8375,
      "eval_samples_per_second": 12.517,
      "eval_steps_per_second": 1.633,
      "step": 50
    },
    {
      "epoch": 0.9622641509433962,
      "grad_norm": 1.3350242376327515,
      "learning_rate": 9.270678163050218e-08,
      "loss": 0.8224,
      "step": 51
    },
    {
      "epoch": 0.9811320754716981,
      "grad_norm": 1.543525218963623,
      "learning_rate": 2.3285134909173113e-08,
      "loss": 0.8941,
      "step": 52
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.1590365171432495,
      "learning_rate": 0.0,
      "loss": 0.5639,
      "step": 53
    }
  ],
  "logging_steps": 1,
  "max_steps": 53,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.1177510641270784e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}