{
  "best_metric": 0.8565148115158081,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.0256410256410255,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020512820512820513,
      "grad_norm": 86.62631225585938,
      "learning_rate": 2e-05,
      "loss": 70.1471,
      "step": 1
    },
    {
      "epoch": 0.020512820512820513,
      "eval_loss": 1.1606084108352661,
      "eval_runtime": 2.4761,
      "eval_samples_per_second": 20.193,
      "eval_steps_per_second": 5.25,
      "step": 1
    },
    {
      "epoch": 0.041025641025641026,
      "grad_norm": 169.72178649902344,
      "learning_rate": 4e-05,
      "loss": 76.1978,
      "step": 2
    },
    {
      "epoch": 0.06153846153846154,
      "grad_norm": 224.21322631835938,
      "learning_rate": 6e-05,
      "loss": 77.2054,
      "step": 3
    },
    {
      "epoch": 0.08205128205128205,
      "grad_norm": 117.42841339111328,
      "learning_rate": 8e-05,
      "loss": 67.7335,
      "step": 4
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 99.99711608886719,
      "learning_rate": 0.0001,
      "loss": 61.9343,
      "step": 5
    },
    {
      "epoch": 0.12307692307692308,
      "grad_norm": 80.5895004272461,
      "learning_rate": 9.998898745083595e-05,
      "loss": 58.4254,
      "step": 6
    },
    {
      "epoch": 0.14358974358974358,
      "grad_norm": 98.62382507324219,
      "learning_rate": 9.995595519339882e-05,
      "loss": 58.7728,
      "step": 7
    },
    {
      "epoch": 0.1641025641025641,
      "grad_norm": 77.48738098144531,
      "learning_rate": 9.990091939521571e-05,
      "loss": 59.8276,
      "step": 8
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 98.08352661132812,
      "learning_rate": 9.982390699337252e-05,
      "loss": 63.9527,
      "step": 9
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 89.5567626953125,
      "learning_rate": 9.972495568132979e-05,
      "loss": 65.547,
      "step": 10
    },
    {
      "epoch": 0.22564102564102564,
      "grad_norm": 94.18596649169922,
      "learning_rate": 9.960411389047366e-05,
      "loss": 68.6032,
      "step": 11
    },
    {
      "epoch": 0.24615384615384617,
      "grad_norm": 161.9555206298828,
      "learning_rate": 9.946144076641138e-05,
      "loss": 67.0602,
      "step": 12
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 64.71723175048828,
      "learning_rate": 9.929700614002265e-05,
      "loss": 65.1495,
      "step": 13
    },
    {
      "epoch": 0.28717948717948716,
      "grad_norm": 71.39453887939453,
      "learning_rate": 9.911089049328113e-05,
      "loss": 65.5682,
      "step": 14
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 88.2963638305664,
      "learning_rate": 9.890318491986281e-05,
      "loss": 62.6678,
      "step": 15
    },
    {
      "epoch": 0.3282051282051282,
      "grad_norm": 74.54248809814453,
      "learning_rate": 9.867399108056054e-05,
      "loss": 57.3027,
      "step": 16
    },
    {
      "epoch": 0.3487179487179487,
      "grad_norm": 57.77771759033203,
      "learning_rate": 9.842342115352646e-05,
      "loss": 54.3357,
      "step": 17
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 46.135955810546875,
      "learning_rate": 9.815159777936681e-05,
      "loss": 55.2862,
      "step": 18
    },
    {
      "epoch": 0.38974358974358975,
      "grad_norm": 51.60411071777344,
      "learning_rate": 9.785865400111593e-05,
      "loss": 55.9271,
      "step": 19
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 49.10125732421875,
      "learning_rate": 9.754473319911866e-05,
      "loss": 53.1128,
      "step": 20
    },
    {
      "epoch": 0.4307692307692308,
      "grad_norm": 59.726318359375,
      "learning_rate": 9.720998902085355e-05,
      "loss": 57.8446,
      "step": 21
    },
    {
      "epoch": 0.4512820512820513,
      "grad_norm": 83.58087921142578,
      "learning_rate": 9.685458530573033e-05,
      "loss": 58.1853,
      "step": 22
    },
    {
      "epoch": 0.4717948717948718,
      "grad_norm": 75.08509826660156,
      "learning_rate": 9.647869600489953e-05,
      "loss": 61.0301,
      "step": 23
    },
    {
      "epoch": 0.49230769230769234,
      "grad_norm": 109.88655090332031,
      "learning_rate": 9.60825050961125e-05,
      "loss": 65.8346,
      "step": 24
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 371.794921875,
      "learning_rate": 9.566620649367419e-05,
      "loss": 65.1721,
      "step": 25
    },
    {
      "epoch": 0.5128205128205128,
      "eval_loss": 0.9023745059967041,
      "eval_runtime": 2.4751,
      "eval_samples_per_second": 20.201,
      "eval_steps_per_second": 5.252,
      "step": 25
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 72.81143188476562,
      "learning_rate": 9.523000395353242e-05,
      "loss": 61.1996,
      "step": 26
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 79.45490264892578,
      "learning_rate": 9.477411097355024e-05,
      "loss": 55.9212,
      "step": 27
    },
    {
      "epoch": 0.5743589743589743,
      "grad_norm": 60.01797866821289,
      "learning_rate": 9.429875068901018e-05,
      "loss": 54.4924,
      "step": 28
    },
    {
      "epoch": 0.5948717948717949,
      "grad_norm": 58.746456146240234,
      "learning_rate": 9.380415576340125e-05,
      "loss": 53.7485,
      "step": 29
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 41.1815185546875,
      "learning_rate": 9.329056827454279e-05,
      "loss": 53.355,
      "step": 30
    },
    {
      "epoch": 0.6358974358974359,
      "grad_norm": 41.690147399902344,
      "learning_rate": 9.27582395961002e-05,
      "loss": 53.0229,
      "step": 31
    },
    {
      "epoch": 0.6564102564102564,
      "grad_norm": 37.58351135253906,
      "learning_rate": 9.22074302745509e-05,
      "loss": 52.7548,
      "step": 32
    },
    {
      "epoch": 0.676923076923077,
      "grad_norm": 76.97421264648438,
      "learning_rate": 9.163840990166085e-05,
      "loss": 56.9977,
      "step": 33
    },
    {
      "epoch": 0.6974358974358974,
      "grad_norm": 74.90629577636719,
      "learning_rate": 9.105145698253366e-05,
      "loss": 57.3899,
      "step": 34
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 64.42181396484375,
      "learning_rate": 9.044685879929732e-05,
      "loss": 57.688,
      "step": 35
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 100.76221466064453,
      "learning_rate": 8.98249112704948e-05,
      "loss": 64.6104,
      "step": 36
    },
    {
      "epoch": 0.7589743589743589,
      "grad_norm": 34.374786376953125,
      "learning_rate": 8.918591880624782e-05,
      "loss": 61.4561,
      "step": 37
    },
    {
      "epoch": 0.7794871794871795,
      "grad_norm": 56.67704391479492,
      "learning_rate": 8.853019415926429e-05,
      "loss": 60.2719,
      "step": 38
    },
    {
      "epoch": 0.8,
      "grad_norm": 63.6683464050293,
      "learning_rate": 8.785805827176255e-05,
      "loss": 52.9461,
      "step": 39
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 52.915809631347656,
      "learning_rate": 8.716984011838731e-05,
      "loss": 54.199,
      "step": 40
    },
    {
      "epoch": 0.841025641025641,
      "grad_norm": 36.469722747802734,
      "learning_rate": 8.646587654519414e-05,
      "loss": 50.3218,
      "step": 41
    },
    {
      "epoch": 0.8615384615384616,
      "grad_norm": 51.19331741333008,
      "learning_rate": 8.57465121047812e-05,
      "loss": 51.637,
      "step": 42
    },
    {
      "epoch": 0.882051282051282,
      "grad_norm": 35.982391357421875,
      "learning_rate": 8.501209888764928e-05,
      "loss": 51.5347,
      "step": 43
    },
    {
      "epoch": 0.9025641025641026,
      "grad_norm": 54.286808013916016,
      "learning_rate": 8.426299634987217e-05,
      "loss": 52.7197,
      "step": 44
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 43.39719772338867,
      "learning_rate": 8.349957113716212e-05,
      "loss": 52.1823,
      "step": 45
    },
    {
      "epoch": 0.9435897435897436,
      "grad_norm": 46.373233795166016,
      "learning_rate": 8.27221969054164e-05,
      "loss": 54.4859,
      "step": 46
    },
    {
      "epoch": 0.9641025641025641,
      "grad_norm": 61.711978912353516,
      "learning_rate": 8.193125413783259e-05,
      "loss": 61.241,
      "step": 47
    },
    {
      "epoch": 0.9846153846153847,
      "grad_norm": 74.2352523803711,
      "learning_rate": 8.112712995868243e-05,
      "loss": 60.6412,
      "step": 48
    },
    {
      "epoch": 1.005128205128205,
      "grad_norm": 42.651710510253906,
      "learning_rate": 8.031021794383513e-05,
      "loss": 54.8344,
      "step": 49
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 65.62483215332031,
      "learning_rate": 7.948091792812296e-05,
      "loss": 58.6391,
      "step": 50
    },
    {
      "epoch": 1.0256410256410255,
      "eval_loss": 0.8565148115158081,
      "eval_runtime": 2.4768,
      "eval_samples_per_second": 20.187,
      "eval_steps_per_second": 5.249,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 147,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 1.198420290049147e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}