{
  "best_metric": 7.067266941070557,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.12886597938144329,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002577319587628866,
      "grad_norm": 8.932095527648926,
      "learning_rate": 5e-05,
      "loss": 8.769,
      "step": 1
    },
    {
      "epoch": 0.002577319587628866,
      "eval_loss": 7.7042412757873535,
      "eval_runtime": 27.296,
      "eval_samples_per_second": 95.765,
      "eval_steps_per_second": 11.98,
      "step": 1
    },
    {
      "epoch": 0.005154639175257732,
      "grad_norm": 5.1865434646606445,
      "learning_rate": 0.0001,
      "loss": 8.594,
      "step": 2
    },
    {
      "epoch": 0.007731958762886598,
      "grad_norm": 4.275647163391113,
      "learning_rate": 9.989294616193017e-05,
      "loss": 8.2291,
      "step": 3
    },
    {
      "epoch": 0.010309278350515464,
      "grad_norm": 3.744438409805298,
      "learning_rate": 9.957224306869053e-05,
      "loss": 8.3425,
      "step": 4
    },
    {
      "epoch": 0.01288659793814433,
      "grad_norm": 2.634883403778076,
      "learning_rate": 9.903926402016153e-05,
      "loss": 7.6405,
      "step": 5
    },
    {
      "epoch": 0.015463917525773196,
      "grad_norm": 2.6033172607421875,
      "learning_rate": 9.829629131445342e-05,
      "loss": 7.5428,
      "step": 6
    },
    {
      "epoch": 0.01804123711340206,
      "grad_norm": 2.397871255874634,
      "learning_rate": 9.73465064747553e-05,
      "loss": 7.5443,
      "step": 7
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 2.1589975357055664,
      "learning_rate": 9.619397662556435e-05,
      "loss": 7.2973,
      "step": 8
    },
    {
      "epoch": 0.023195876288659795,
      "grad_norm": 1.9659868478775024,
      "learning_rate": 9.484363707663442e-05,
      "loss": 7.2995,
      "step": 9
    },
    {
      "epoch": 0.02577319587628866,
      "grad_norm": 1.8988659381866455,
      "learning_rate": 9.330127018922194e-05,
      "loss": 6.9992,
      "step": 10
    },
    {
      "epoch": 0.028350515463917526,
      "grad_norm": 1.7255256175994873,
      "learning_rate": 9.157348061512727e-05,
      "loss": 7.0953,
      "step": 11
    },
    {
      "epoch": 0.030927835051546393,
      "grad_norm": 1.986493706703186,
      "learning_rate": 8.966766701456177e-05,
      "loss": 7.0552,
      "step": 12
    },
    {
      "epoch": 0.03350515463917526,
      "grad_norm": 3.806684732437134,
      "learning_rate": 8.759199037394887e-05,
      "loss": 7.6275,
      "step": 13
    },
    {
      "epoch": 0.03608247422680412,
      "grad_norm": 4.209149360656738,
      "learning_rate": 8.535533905932738e-05,
      "loss": 7.7068,
      "step": 14
    },
    {
      "epoch": 0.03865979381443299,
      "grad_norm": 2.2306342124938965,
      "learning_rate": 8.296729075500344e-05,
      "loss": 7.7352,
      "step": 15
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 1.6664167642593384,
      "learning_rate": 8.043807145043604e-05,
      "loss": 7.5366,
      "step": 16
    },
    {
      "epoch": 0.04381443298969072,
      "grad_norm": 1.4569931030273438,
      "learning_rate": 7.777851165098012e-05,
      "loss": 7.4936,
      "step": 17
    },
    {
      "epoch": 0.04639175257731959,
      "grad_norm": 1.2213176488876343,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.4877,
      "step": 18
    },
    {
      "epoch": 0.04896907216494845,
      "grad_norm": 1.2630321979522705,
      "learning_rate": 7.211443451095007e-05,
      "loss": 7.3076,
      "step": 19
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 1.1982954740524292,
      "learning_rate": 6.91341716182545e-05,
      "loss": 7.1835,
      "step": 20
    },
    {
      "epoch": 0.05412371134020619,
      "grad_norm": 1.179440975189209,
      "learning_rate": 6.607197326515808e-05,
      "loss": 7.0129,
      "step": 21
    },
    {
      "epoch": 0.05670103092783505,
      "grad_norm": 1.2165639400482178,
      "learning_rate": 6.294095225512603e-05,
      "loss": 6.8845,
      "step": 22
    },
    {
      "epoch": 0.059278350515463915,
      "grad_norm": 1.1670974493026733,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 6.9454,
      "step": 23
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 1.096975326538086,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 6.9278,
      "step": 24
    },
    {
      "epoch": 0.06443298969072164,
      "grad_norm": 1.54706609249115,
      "learning_rate": 5.327015646150716e-05,
      "loss": 6.5843,
      "step": 25
    },
    {
      "epoch": 0.06443298969072164,
      "eval_loss": 7.125263214111328,
      "eval_runtime": 26.0926,
      "eval_samples_per_second": 100.182,
      "eval_steps_per_second": 12.532,
      "step": 25
    },
    {
      "epoch": 0.06701030927835051,
      "grad_norm": 2.849268674850464,
      "learning_rate": 5e-05,
      "loss": 7.2586,
      "step": 26
    },
    {
      "epoch": 0.06958762886597938,
      "grad_norm": 1.6071581840515137,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 7.837,
      "step": 27
    },
    {
      "epoch": 0.07216494845360824,
      "grad_norm": 1.3252266645431519,
      "learning_rate": 4.347369038899744e-05,
      "loss": 7.5216,
      "step": 28
    },
    {
      "epoch": 0.07474226804123711,
      "grad_norm": 1.1092205047607422,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 7.42,
      "step": 29
    },
    {
      "epoch": 0.07731958762886598,
      "grad_norm": 0.9314132928848267,
      "learning_rate": 3.705904774487396e-05,
      "loss": 7.3253,
      "step": 30
    },
    {
      "epoch": 0.07989690721649484,
      "grad_norm": 0.9957264065742493,
      "learning_rate": 3.392802673484193e-05,
      "loss": 7.4278,
      "step": 31
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 1.0452556610107422,
      "learning_rate": 3.086582838174551e-05,
      "loss": 6.961,
      "step": 32
    },
    {
      "epoch": 0.08505154639175258,
      "grad_norm": 0.9974004626274109,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 7.1028,
      "step": 33
    },
    {
      "epoch": 0.08762886597938144,
      "grad_norm": 0.866974949836731,
      "learning_rate": 2.500000000000001e-05,
      "loss": 6.855,
      "step": 34
    },
    {
      "epoch": 0.09020618556701031,
      "grad_norm": 0.9052703976631165,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 6.8511,
      "step": 35
    },
    {
      "epoch": 0.09278350515463918,
      "grad_norm": 0.9637014269828796,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 6.7397,
      "step": 36
    },
    {
      "epoch": 0.09536082474226804,
      "grad_norm": 1.1197189092636108,
      "learning_rate": 1.703270924499656e-05,
      "loss": 6.6541,
      "step": 37
    },
    {
      "epoch": 0.0979381443298969,
      "grad_norm": 1.420501708984375,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 7.7482,
      "step": 38
    },
    {
      "epoch": 0.10051546391752578,
      "grad_norm": 1.498699426651001,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 7.6799,
      "step": 39
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 1.1142817735671997,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 7.5234,
      "step": 40
    },
    {
      "epoch": 0.1056701030927835,
      "grad_norm": 1.0226730108261108,
      "learning_rate": 8.426519384872733e-06,
      "loss": 7.4547,
      "step": 41
    },
    {
      "epoch": 0.10824742268041238,
      "grad_norm": 0.8474833965301514,
      "learning_rate": 6.698729810778065e-06,
      "loss": 7.4219,
      "step": 42
    },
    {
      "epoch": 0.11082474226804123,
      "grad_norm": 0.9374727010726929,
      "learning_rate": 5.156362923365588e-06,
      "loss": 7.2288,
      "step": 43
    },
    {
      "epoch": 0.1134020618556701,
      "grad_norm": 0.9378708004951477,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 7.1749,
      "step": 44
    },
    {
      "epoch": 0.11597938144329897,
      "grad_norm": 0.847159743309021,
      "learning_rate": 2.653493525244721e-06,
      "loss": 7.0036,
      "step": 45
    },
    {
      "epoch": 0.11855670103092783,
      "grad_norm": 0.8835762143135071,
      "learning_rate": 1.70370868554659e-06,
      "loss": 6.9541,
      "step": 46
    },
    {
      "epoch": 0.1211340206185567,
      "grad_norm": 0.8930884003639221,
      "learning_rate": 9.607359798384785e-07,
      "loss": 6.8733,
      "step": 47
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.8807015419006348,
      "learning_rate": 4.277569313094809e-07,
      "loss": 6.6641,
      "step": 48
    },
    {
      "epoch": 0.12628865979381443,
      "grad_norm": 0.9850261807441711,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 6.8159,
      "step": 49
    },
    {
      "epoch": 0.12886597938144329,
      "grad_norm": 1.192939281463623,
      "learning_rate": 0.0,
      "loss": 6.6461,
      "step": 50
    },
    {
      "epoch": 0.12886597938144329,
      "eval_loss": 7.067266941070557,
      "eval_runtime": 25.9801,
      "eval_samples_per_second": 100.616,
      "eval_steps_per_second": 12.587,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 239916767772672.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}