{
  "best_metric": 0.4023851752281189,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 2.435820895522388,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04776119402985075,
      "grad_norm": 0.29309335350990295,
      "learning_rate": 5e-05,
      "loss": 0.551,
      "step": 1
    },
    {
      "epoch": 0.04776119402985075,
      "eval_loss": 0.5565004348754883,
      "eval_runtime": 1.6321,
      "eval_samples_per_second": 86.392,
      "eval_steps_per_second": 11.029,
      "step": 1
    },
    {
      "epoch": 0.0955223880597015,
      "grad_norm": 0.34882017970085144,
      "learning_rate": 0.0001,
      "loss": 0.5825,
      "step": 2
    },
    {
      "epoch": 0.14328358208955225,
      "grad_norm": 0.33288702368736267,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.5791,
      "step": 3
    },
    {
      "epoch": 0.191044776119403,
      "grad_norm": 0.36883237957954407,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.538,
      "step": 4
    },
    {
      "epoch": 0.23880597014925373,
      "grad_norm": 0.3539741337299347,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.5281,
      "step": 5
    },
    {
      "epoch": 0.2865671641791045,
      "grad_norm": 0.23581592738628387,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.5197,
      "step": 6
    },
    {
      "epoch": 0.33432835820895523,
      "grad_norm": 0.28109219670295715,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.5066,
      "step": 7
    },
    {
      "epoch": 0.382089552238806,
      "grad_norm": 0.29403433203697205,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.4929,
      "step": 8
    },
    {
      "epoch": 0.4298507462686567,
      "grad_norm": 0.2939996123313904,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.5313,
      "step": 9
    },
    {
      "epoch": 0.47761194029850745,
      "grad_norm": 0.363861083984375,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.4514,
      "step": 10
    },
    {
      "epoch": 0.5253731343283582,
      "grad_norm": 0.19598151743412018,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.4927,
      "step": 11
    },
    {
      "epoch": 0.573134328358209,
      "grad_norm": 0.20769856870174408,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.5076,
      "step": 12
    },
    {
      "epoch": 0.6208955223880597,
      "grad_norm": 0.2053491175174713,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.4653,
      "step": 13
    },
    {
      "epoch": 0.6686567164179105,
      "grad_norm": 0.22446739673614502,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.4791,
      "step": 14
    },
    {
      "epoch": 0.7164179104477612,
      "grad_norm": 0.2886030972003937,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.4275,
      "step": 15
    },
    {
      "epoch": 0.764179104477612,
      "grad_norm": 0.1693258434534073,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.4891,
      "step": 16
    },
    {
      "epoch": 0.8119402985074626,
      "grad_norm": 0.18894262611865997,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.4471,
      "step": 17
    },
    {
      "epoch": 0.8597014925373134,
      "grad_norm": 0.2001345455646515,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4717,
      "step": 18
    },
    {
      "epoch": 0.9074626865671642,
      "grad_norm": 0.25183868408203125,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.458,
      "step": 19
    },
    {
      "epoch": 0.9552238805970149,
      "grad_norm": 0.29334449768066406,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.3965,
      "step": 20
    },
    {
      "epoch": 1.026865671641791,
      "grad_norm": 0.28625965118408203,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.796,
      "step": 21
    },
    {
      "epoch": 1.0746268656716418,
      "grad_norm": 0.16455918550491333,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.4404,
      "step": 22
    },
    {
      "epoch": 1.1223880597014926,
      "grad_norm": 0.1942681223154068,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.4026,
      "step": 23
    },
    {
      "epoch": 1.1701492537313434,
      "grad_norm": 0.21410231292247772,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.413,
      "step": 24
    },
    {
      "epoch": 1.217910447761194,
      "grad_norm": 0.25955915451049805,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.4206,
      "step": 25
    },
    {
      "epoch": 1.217910447761194,
      "eval_loss": 0.4251263737678528,
      "eval_runtime": 1.6332,
      "eval_samples_per_second": 86.336,
      "eval_steps_per_second": 11.022,
      "step": 25
    },
    {
      "epoch": 1.2656716417910447,
      "grad_norm": 0.18197745084762573,
      "learning_rate": 5e-05,
      "loss": 0.378,
      "step": 26
    },
    {
      "epoch": 1.3134328358208955,
      "grad_norm": 0.1775834709405899,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.4182,
      "step": 27
    },
    {
      "epoch": 1.3611940298507463,
      "grad_norm": 0.19821526110172272,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.4157,
      "step": 28
    },
    {
      "epoch": 1.408955223880597,
      "grad_norm": 0.21566687524318695,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.3821,
      "step": 29
    },
    {
      "epoch": 1.4567164179104477,
      "grad_norm": 0.2709551453590393,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.3742,
      "step": 30
    },
    {
      "epoch": 1.5044776119402985,
      "grad_norm": 0.1894427090883255,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.372,
      "step": 31
    },
    {
      "epoch": 1.5522388059701493,
      "grad_norm": 0.19189490377902985,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.4192,
      "step": 32
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.22904697060585022,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.4083,
      "step": 33
    },
    {
      "epoch": 1.6477611940298509,
      "grad_norm": 0.24419617652893066,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.4,
      "step": 34
    },
    {
      "epoch": 1.6955223880597015,
      "grad_norm": 0.250863641500473,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.3735,
      "step": 35
    },
    {
      "epoch": 1.7432835820895523,
      "grad_norm": 0.22108954191207886,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.3983,
      "step": 36
    },
    {
      "epoch": 1.7910447761194028,
      "grad_norm": 0.1873919814825058,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.3949,
      "step": 37
    },
    {
      "epoch": 1.8388059701492536,
      "grad_norm": 0.2162359058856964,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.4166,
      "step": 38
    },
    {
      "epoch": 1.8865671641791044,
      "grad_norm": 0.2337595373392105,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.377,
      "step": 39
    },
    {
      "epoch": 1.9343283582089552,
      "grad_norm": 0.2757619619369507,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.3678,
      "step": 40
    },
    {
      "epoch": 2.005970149253731,
      "grad_norm": 0.30736440420150757,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.5346,
      "step": 41
    },
    {
      "epoch": 2.053731343283582,
      "grad_norm": 0.17773054540157318,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.3897,
      "step": 42
    },
    {
      "epoch": 2.1014925373134328,
      "grad_norm": 0.18972079455852509,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.3795,
      "step": 43
    },
    {
      "epoch": 2.1492537313432836,
      "grad_norm": 0.21727779507637024,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.3802,
      "step": 44
    },
    {
      "epoch": 2.1970149253731344,
      "grad_norm": 0.25702959299087524,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.3841,
      "step": 45
    },
    {
      "epoch": 2.244776119402985,
      "grad_norm": 0.26603198051452637,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.3291,
      "step": 46
    },
    {
      "epoch": 2.292537313432836,
      "grad_norm": 0.1831669956445694,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.4069,
      "step": 47
    },
    {
      "epoch": 2.3402985074626868,
      "grad_norm": 0.20122045278549194,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.3851,
      "step": 48
    },
    {
      "epoch": 2.388059701492537,
      "grad_norm": 0.2129780352115631,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.3787,
      "step": 49
    },
    {
      "epoch": 2.435820895522388,
      "grad_norm": 0.2397255003452301,
      "learning_rate": 0.0,
      "loss": 0.3508,
      "step": 50
    },
    {
      "epoch": 2.435820895522388,
      "eval_loss": 0.4023851752281189,
      "eval_runtime": 1.632,
      "eval_samples_per_second": 86.399,
      "eval_steps_per_second": 11.03,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.059536353886208e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}