{
  "best_metric": 1.8985799551010132,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.05847953216374269,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0023391812865497076,
      "grad_norm": 4.100360870361328,
      "learning_rate": 2e-05,
      "loss": 14.7526,
      "step": 1
    },
    {
      "epoch": 0.0023391812865497076,
      "eval_loss": 3.5069966316223145,
      "eval_runtime": 52.5964,
      "eval_samples_per_second": 3.422,
      "eval_steps_per_second": 1.711,
      "step": 1
    },
    {
      "epoch": 0.004678362573099415,
      "grad_norm": 2.771986484527588,
      "learning_rate": 4e-05,
      "loss": 14.2356,
      "step": 2
    },
    {
      "epoch": 0.007017543859649123,
      "grad_norm": 9.985754013061523,
      "learning_rate": 6e-05,
      "loss": 15.9264,
      "step": 3
    },
    {
      "epoch": 0.00935672514619883,
      "grad_norm": 1.9136978387832642,
      "learning_rate": 8e-05,
      "loss": 13.1933,
      "step": 4
    },
    {
      "epoch": 0.011695906432748537,
      "grad_norm": 2.744441509246826,
      "learning_rate": 0.0001,
      "loss": 15.7586,
      "step": 5
    },
    {
      "epoch": 0.011695906432748537,
      "eval_loss": 3.49050235748291,
      "eval_runtime": 52.8953,
      "eval_samples_per_second": 3.403,
      "eval_steps_per_second": 1.701,
      "step": 5
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 1.951014757156372,
      "learning_rate": 0.00012,
      "loss": 11.1923,
      "step": 6
    },
    {
      "epoch": 0.016374269005847954,
      "grad_norm": 2.661343812942505,
      "learning_rate": 0.00014,
      "loss": 12.659,
      "step": 7
    },
    {
      "epoch": 0.01871345029239766,
      "grad_norm": 3.7844579219818115,
      "learning_rate": 0.00016,
      "loss": 14.3566,
      "step": 8
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 3.7590487003326416,
      "learning_rate": 0.00018,
      "loss": 12.6791,
      "step": 9
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 3.8777852058410645,
      "learning_rate": 0.0002,
      "loss": 9.9197,
      "step": 10
    },
    {
      "epoch": 0.023391812865497075,
      "eval_loss": 2.8525774478912354,
      "eval_runtime": 52.5716,
      "eval_samples_per_second": 3.424,
      "eval_steps_per_second": 1.712,
      "step": 10
    },
    {
      "epoch": 0.025730994152046785,
      "grad_norm": 4.353909015655518,
      "learning_rate": 0.00019781476007338058,
      "loss": 10.8984,
      "step": 11
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 3.5024590492248535,
      "learning_rate": 0.0001913545457642601,
      "loss": 11.0107,
      "step": 12
    },
    {
      "epoch": 0.0304093567251462,
      "grad_norm": 7.128164768218994,
      "learning_rate": 0.00018090169943749476,
      "loss": 11.8648,
      "step": 13
    },
    {
      "epoch": 0.03274853801169591,
      "grad_norm": 7.6712141036987305,
      "learning_rate": 0.00016691306063588583,
      "loss": 8.9836,
      "step": 14
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 12.34415340423584,
      "learning_rate": 0.00015000000000000001,
      "loss": 14.5467,
      "step": 15
    },
    {
      "epoch": 0.03508771929824561,
      "eval_loss": 2.3073062896728516,
      "eval_runtime": 52.5708,
      "eval_samples_per_second": 3.424,
      "eval_steps_per_second": 1.712,
      "step": 15
    },
    {
      "epoch": 0.03742690058479532,
      "grad_norm": 8.823278427124023,
      "learning_rate": 0.00013090169943749476,
      "loss": 8.7913,
      "step": 16
    },
    {
      "epoch": 0.03976608187134503,
      "grad_norm": 9.27376937866211,
      "learning_rate": 0.00011045284632676536,
      "loss": 10.8245,
      "step": 17
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 9.13545036315918,
      "learning_rate": 8.954715367323468e-05,
      "loss": 8.807,
      "step": 18
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 6.375463962554932,
      "learning_rate": 6.909830056250527e-05,
      "loss": 7.6188,
      "step": 19
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 7.590856075286865,
      "learning_rate": 5.000000000000002e-05,
      "loss": 7.2438,
      "step": 20
    },
    {
      "epoch": 0.04678362573099415,
      "eval_loss": 1.9674196243286133,
      "eval_runtime": 52.4841,
      "eval_samples_per_second": 3.43,
      "eval_steps_per_second": 1.715,
      "step": 20
    },
    {
      "epoch": 0.04912280701754386,
      "grad_norm": 9.282962799072266,
      "learning_rate": 3.308693936411421e-05,
      "loss": 9.5229,
      "step": 21
    },
    {
      "epoch": 0.05146198830409357,
      "grad_norm": 11.135098457336426,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 7.772,
      "step": 22
    },
    {
      "epoch": 0.05380116959064327,
      "grad_norm": 8.167407989501953,
      "learning_rate": 8.645454235739903e-06,
      "loss": 7.4072,
      "step": 23
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": 8.186439514160156,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 8.0662,
      "step": 24
    },
    {
      "epoch": 0.05847953216374269,
      "grad_norm": 5.752795219421387,
      "learning_rate": 0.0,
      "loss": 6.7849,
      "step": 25
    },
    {
      "epoch": 0.05847953216374269,
      "eval_loss": 1.8985799551010132,
      "eval_runtime": 52.6292,
      "eval_samples_per_second": 3.42,
      "eval_steps_per_second": 1.71,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 1.54353434886144e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}