{
  "best_metric": 9.236889839172363,
  "best_model_checkpoint": "miner_id_besimray/checkpoint-5",
  "epoch": 0.004074979625101874,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00020374898125509371,
      "grad_norm": 6342301433462784.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 9.0297,
      "step": 1
    },
    {
      "epoch": 0.00020374898125509371,
      "eval_loss": 9.31723690032959,
      "eval_runtime": 839.5639,
      "eval_samples_per_second": 3.077,
      "eval_steps_per_second": 0.308,
      "step": 1
    },
    {
      "epoch": 0.00040749796251018743,
      "grad_norm": Infinity,
      "learning_rate": 4.000000000000001e-06,
      "loss": 10.6943,
      "step": 2
    },
    {
      "epoch": 0.0006112469437652812,
      "grad_norm": 1.1465935952866705e+19,
      "learning_rate": 6e-06,
      "loss": 7.7524,
      "step": 3
    },
    {
      "epoch": 0.0008149959250203749,
      "grad_norm": Infinity,
      "learning_rate": 8.000000000000001e-06,
      "loss": 10.3849,
      "step": 4
    },
    {
      "epoch": 0.0010187449062754685,
      "grad_norm": 1.5911073997232538e+18,
      "learning_rate": 1e-05,
      "loss": 9.734,
      "step": 5
    },
    {
      "epoch": 0.0010187449062754685,
      "eval_loss": 9.236889839172363,
      "eval_runtime": 842.6603,
      "eval_samples_per_second": 3.065,
      "eval_steps_per_second": 0.307,
      "step": 5
    },
    {
      "epoch": 0.0012224938875305623,
      "grad_norm": 7954734698725376.0,
      "learning_rate": 1.2e-05,
      "loss": 8.1799,
      "step": 6
    },
    {
      "epoch": 0.0014262428687856561,
      "grad_norm": Infinity,
      "learning_rate": 1.4e-05,
      "loss": 9.2379,
      "step": 7
    },
    {
      "epoch": 0.0016299918500407497,
      "grad_norm": Infinity,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 11.4264,
      "step": 8
    },
    {
      "epoch": 0.0018337408312958435,
      "grad_norm": 9.681396420271145e+17,
      "learning_rate": 1.8e-05,
      "loss": 8.77,
      "step": 9
    },
    {
      "epoch": 0.002037489812550937,
      "grad_norm": 2.2846267641246515e+17,
      "learning_rate": 2e-05,
      "loss": 10.016,
      "step": 10
    },
    {
      "epoch": 0.002037489812550937,
      "eval_loss": 9.262293815612793,
      "eval_runtime": 843.2301,
      "eval_samples_per_second": 3.063,
      "eval_steps_per_second": 0.307,
      "step": 10
    },
    {
      "epoch": 0.002241238793806031,
      "grad_norm": Infinity,
      "learning_rate": 1.9999999505531342e-05,
      "loss": 9.4106,
      "step": 11
    },
    {
      "epoch": 0.0024449877750611247,
      "grad_norm": 4.027428285574021e+17,
      "learning_rate": 1.9999998022125415e-05,
      "loss": 9.2865,
      "step": 12
    },
    {
      "epoch": 0.0026487367563162185,
      "grad_norm": Infinity,
      "learning_rate": 1.9999995549782365e-05,
      "loss": 10.231,
      "step": 13
    },
    {
      "epoch": 0.0028524857375713123,
      "grad_norm": Infinity,
      "learning_rate": 1.9999992088502437e-05,
      "loss": 9.015,
      "step": 14
    },
    {
      "epoch": 0.003056234718826406,
      "grad_norm": Infinity,
      "learning_rate": 1.9999987638285976e-05,
      "loss": 8.0792,
      "step": 15
    },
    {
      "epoch": 0.003056234718826406,
      "eval_loss": 9.262674331665039,
      "eval_runtime": 842.767,
      "eval_samples_per_second": 3.065,
      "eval_steps_per_second": 0.307,
      "step": 15
    },
    {
      "epoch": 0.0032599837000814994,
      "grad_norm": 1.3874351302323995e+19,
      "learning_rate": 1.9999982199133416e-05,
      "loss": 8.5286,
      "step": 16
    },
    {
      "epoch": 0.0034637326813365932,
      "grad_norm": 9.607972408157798e+18,
      "learning_rate": 1.9999975771045303e-05,
      "loss": 7.7833,
      "step": 17
    },
    {
      "epoch": 0.003667481662591687,
      "grad_norm": Infinity,
      "learning_rate": 1.9999968354022266e-05,
      "loss": 10.4327,
      "step": 18
    },
    {
      "epoch": 0.003871230643846781,
      "grad_norm": Infinity,
      "learning_rate": 1.999995994806504e-05,
      "loss": 8.3376,
      "step": 19
    },
    {
      "epoch": 0.004074979625101874,
      "grad_norm": Infinity,
      "learning_rate": 1.999995055317446e-05,
      "loss": 9.8773,
      "step": 20
    },
    {
      "epoch": 0.004074979625101874,
      "eval_loss": 9.251687049865723,
      "eval_runtime": 841.2776,
      "eval_samples_per_second": 3.07,
      "eval_steps_per_second": 0.308,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 5,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.83706639663104e+16,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}