{
  "best_metric": 1.9303518533706665,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.008514261387824606,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034057045551298427,
      "grad_norm": 2.36114239692688,
      "learning_rate": 2e-05,
      "loss": 1.0057,
      "step": 1
    },
    {
      "epoch": 0.00034057045551298427,
      "eval_loss": 1.9671335220336914,
      "eval_runtime": 375.106,
      "eval_samples_per_second": 3.298,
      "eval_steps_per_second": 1.65,
      "step": 1
    },
    {
      "epoch": 0.0006811409110259685,
      "grad_norm": 2.3865537643432617,
      "learning_rate": 4e-05,
      "loss": 0.9927,
      "step": 2
    },
    {
      "epoch": 0.0010217113665389529,
      "grad_norm": 2.001999616622925,
      "learning_rate": 6e-05,
      "loss": 1.0757,
      "step": 3
    },
    {
      "epoch": 0.001362281822051937,
      "grad_norm": 2.0456292629241943,
      "learning_rate": 8e-05,
      "loss": 1.041,
      "step": 4
    },
    {
      "epoch": 0.0017028522775649213,
      "grad_norm": 1.9042091369628906,
      "learning_rate": 0.0001,
      "loss": 0.8738,
      "step": 5
    },
    {
      "epoch": 0.0017028522775649213,
      "eval_loss": 1.9631969928741455,
      "eval_runtime": 371.2469,
      "eval_samples_per_second": 3.332,
      "eval_steps_per_second": 1.667,
      "step": 5
    },
    {
      "epoch": 0.0020434227330779057,
      "grad_norm": 2.3928301334381104,
      "learning_rate": 0.00012,
      "loss": 1.0461,
      "step": 6
    },
    {
      "epoch": 0.00238399318859089,
      "grad_norm": 2.3232131004333496,
      "learning_rate": 0.00014,
      "loss": 1.0432,
      "step": 7
    },
    {
      "epoch": 0.002724563644103874,
      "grad_norm": 2.0950968265533447,
      "learning_rate": 0.00016,
      "loss": 1.0164,
      "step": 8
    },
    {
      "epoch": 0.0030651340996168583,
      "grad_norm": 2.052090883255005,
      "learning_rate": 0.00018,
      "loss": 1.0253,
      "step": 9
    },
    {
      "epoch": 0.0034057045551298426,
      "grad_norm": 2.2930943965911865,
      "learning_rate": 0.0002,
      "loss": 1.022,
      "step": 10
    },
    {
      "epoch": 0.0034057045551298426,
      "eval_loss": 1.9730497598648071,
      "eval_runtime": 369.7618,
      "eval_samples_per_second": 3.345,
      "eval_steps_per_second": 1.674,
      "step": 10
    },
    {
      "epoch": 0.0037462750106428268,
      "grad_norm": 1.7902344465255737,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.9363,
      "step": 11
    },
    {
      "epoch": 0.004086845466155811,
      "grad_norm": 4.487222194671631,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.8989,
      "step": 12
    },
    {
      "epoch": 0.004427415921668796,
      "grad_norm": 3.1565561294555664,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.2051,
      "step": 13
    },
    {
      "epoch": 0.00476798637718178,
      "grad_norm": 3.1876792907714844,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.0949,
      "step": 14
    },
    {
      "epoch": 0.005108556832694764,
      "grad_norm": 4.557372570037842,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.9383,
      "step": 15
    },
    {
      "epoch": 0.005108556832694764,
      "eval_loss": 1.9593802690505981,
      "eval_runtime": 363.5952,
      "eval_samples_per_second": 3.402,
      "eval_steps_per_second": 1.702,
      "step": 15
    },
    {
      "epoch": 0.005449127288207748,
      "grad_norm": 3.520530939102173,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.0281,
      "step": 16
    },
    {
      "epoch": 0.0057896977437207325,
      "grad_norm": 3.064483165740967,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.0693,
      "step": 17
    },
    {
      "epoch": 0.006130268199233717,
      "grad_norm": 4.370338439941406,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.0305,
      "step": 18
    },
    {
      "epoch": 0.006470838654746701,
      "grad_norm": 3.855978488922119,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.0917,
      "step": 19
    },
    {
      "epoch": 0.006811409110259685,
      "grad_norm": 4.2285380363464355,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.9723,
      "step": 20
    },
    {
      "epoch": 0.006811409110259685,
      "eval_loss": 1.9303518533706665,
      "eval_runtime": 365.1536,
      "eval_samples_per_second": 3.388,
      "eval_steps_per_second": 1.695,
      "step": 20
    },
    {
      "epoch": 0.007151979565772669,
      "grad_norm": 4.142763614654541,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.8279,
      "step": 21
    },
    {
      "epoch": 0.0074925500212856535,
      "grad_norm": 26.084022521972656,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.8288,
      "step": 22
    },
    {
      "epoch": 0.007833120476798638,
      "grad_norm": 5.616507530212402,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.9997,
      "step": 23
    },
    {
      "epoch": 0.008173690932311623,
      "grad_norm": 4.470533847808838,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.9749,
      "step": 24
    },
    {
      "epoch": 0.008514261387824606,
      "grad_norm": 3.6379683017730713,
      "learning_rate": 0.0,
      "loss": 0.953,
      "step": 25
    },
    {
      "epoch": 0.008514261387824606,
      "eval_loss": 1.9331988096237183,
      "eval_runtime": 357.497,
      "eval_samples_per_second": 3.46,
      "eval_steps_per_second": 1.731,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3187382000025600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}