{
  "best_metric": 0.12750904262065887,
  "best_model_checkpoint": "miner_id_24/checkpoint-700",
  "epoch": 0.11748909029875797,
  "eval_steps": 100,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016784155756965425,
      "eval_loss": 3.459160089492798,
      "eval_runtime": 1050.456,
      "eval_samples_per_second": 9.553,
      "eval_steps_per_second": 2.388,
      "step": 1
    },
    {
      "epoch": 0.008392077878482713,
      "grad_norm": 20.790891647338867,
      "learning_rate": 0.000106,
      "loss": 7.2986,
      "step": 50
    },
    {
      "epoch": 0.016784155756965426,
      "grad_norm": 34.94457244873047,
      "learning_rate": 0.000212,
      "loss": 2.7683,
      "step": 100
    },
    {
      "epoch": 0.016784155756965426,
      "eval_loss": 0.37283119559288025,
      "eval_runtime": 1051.8636,
      "eval_samples_per_second": 9.54,
      "eval_steps_per_second": 2.385,
      "step": 100
    },
    {
      "epoch": 0.025176233635448138,
      "grad_norm": 149.3499298095703,
      "learning_rate": 0.00020838813758664124,
      "loss": 3.2576,
      "step": 150
    },
    {
      "epoch": 0.03356831151393085,
      "grad_norm": 244.96925354003906,
      "learning_rate": 0.00019779869280115052,
      "loss": 4.1013,
      "step": 200
    },
    {
      "epoch": 0.03356831151393085,
      "eval_loss": 0.33724460005760193,
      "eval_runtime": 1051.4899,
      "eval_samples_per_second": 9.544,
      "eval_steps_per_second": 2.386,
      "step": 200
    },
    {
      "epoch": 0.04196038939241356,
      "grad_norm": 17.12479591369629,
      "learning_rate": 0.00018095331880577404,
      "loss": 2.4161,
      "step": 250
    },
    {
      "epoch": 0.050352467270896276,
      "grad_norm": 9.897245407104492,
      "learning_rate": 0.00015900000000000002,
      "loss": 2.0184,
      "step": 300
    },
    {
      "epoch": 0.050352467270896276,
      "eval_loss": 0.2701140344142914,
      "eval_runtime": 1050.2948,
      "eval_samples_per_second": 9.554,
      "eval_steps_per_second": 2.389,
      "step": 300
    },
    {
      "epoch": 0.058744545149378984,
      "grad_norm": 29.458805084228516,
      "learning_rate": 0.0001334348187808672,
      "loss": 1.7644,
      "step": 350
    },
    {
      "epoch": 0.0671366230278617,
      "grad_norm": 7.331902503967285,
      "learning_rate": 0.000106,
      "loss": 1.7493,
      "step": 400
    },
    {
      "epoch": 0.0671366230278617,
      "eval_loss": 0.19820711016654968,
      "eval_runtime": 1049.7804,
      "eval_samples_per_second": 9.559,
      "eval_steps_per_second": 2.39,
      "step": 400
    },
    {
      "epoch": 0.0755287009063444,
      "grad_norm": 9.694393157958984,
      "learning_rate": 7.856518121913279e-05,
      "loss": 1.5108,
      "step": 450
    },
    {
      "epoch": 0.08392077878482712,
      "grad_norm": 8.91313648223877,
      "learning_rate": 5.300000000000002e-05,
      "loss": 1.3887,
      "step": 500
    },
    {
      "epoch": 0.08392077878482712,
      "eval_loss": 0.15681935846805573,
      "eval_runtime": 1050.1313,
      "eval_samples_per_second": 9.556,
      "eval_steps_per_second": 2.389,
      "step": 500
    },
    {
      "epoch": 0.09231285666330984,
      "grad_norm": 5.003987789154053,
      "learning_rate": 3.104668119422597e-05,
      "loss": 1.1952,
      "step": 550
    },
    {
      "epoch": 0.10070493454179255,
      "grad_norm": 5.510656833648682,
      "learning_rate": 1.4201307198849497e-05,
      "loss": 1.0865,
      "step": 600
    },
    {
      "epoch": 0.10070493454179255,
      "eval_loss": 0.1338842660188675,
      "eval_runtime": 1050.1035,
      "eval_samples_per_second": 9.556,
      "eval_steps_per_second": 2.389,
      "step": 600
    },
    {
      "epoch": 0.10909701242027527,
      "grad_norm": 3.9216854572296143,
      "learning_rate": 3.6118624133587706e-06,
      "loss": 1.0772,
      "step": 650
    },
    {
      "epoch": 0.11748909029875797,
      "grad_norm": 11.056459426879883,
      "learning_rate": 0.0,
      "loss": 1.0085,
      "step": 700
    },
    {
      "epoch": 0.11748909029875797,
      "eval_loss": 0.12750904262065887,
      "eval_runtime": 1050.7509,
      "eval_samples_per_second": 9.55,
      "eval_steps_per_second": 2.388,
      "step": 700
    }
  ],
  "logging_steps": 50,
  "max_steps": 700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 1.0027718547980943e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}