{
  "best_metric": 1.8694967031478882,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.000519545743837971,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.73181914612657e-05,
      "eval_loss": 2.635225772857666,
      "eval_runtime": 2550.4874,
      "eval_samples_per_second": 9.533,
      "eval_steps_per_second": 4.767,
      "step": 1
    },
    {
      "epoch": 5.19545743837971e-05,
      "grad_norm": 2.8524539470672607,
      "learning_rate": 6e-05,
      "loss": 12.0173,
      "step": 3
    },
    {
      "epoch": 8.65909573063285e-05,
      "eval_loss": 2.526580333709717,
      "eval_runtime": 2559.2871,
      "eval_samples_per_second": 9.5,
      "eval_steps_per_second": 4.75,
      "step": 5
    },
    {
      "epoch": 0.0001039091487675942,
      "grad_norm": 3.086183547973633,
      "learning_rate": 0.00012,
      "loss": 9.8823,
      "step": 6
    },
    {
      "epoch": 0.0001558637231513913,
      "grad_norm": 2.5752129554748535,
      "learning_rate": 0.00018,
      "loss": 8.6885,
      "step": 9
    },
    {
      "epoch": 0.000173181914612657,
      "eval_loss": 2.164038896560669,
      "eval_runtime": 2559.0584,
      "eval_samples_per_second": 9.501,
      "eval_steps_per_second": 4.751,
      "step": 10
    },
    {
      "epoch": 0.0002078182975351884,
      "grad_norm": 3.4389102458953857,
      "learning_rate": 0.00019510565162951537,
      "loss": 8.7216,
      "step": 12
    },
    {
      "epoch": 0.0002597728719189855,
      "grad_norm": 197.77755737304688,
      "learning_rate": 0.00017071067811865476,
      "loss": 7.3942,
      "step": 15
    },
    {
      "epoch": 0.0002597728719189855,
      "eval_loss": 1.9867361783981323,
      "eval_runtime": 2559.4363,
      "eval_samples_per_second": 9.499,
      "eval_steps_per_second": 4.75,
      "step": 15
    },
    {
      "epoch": 0.0003117274463027826,
      "grad_norm": 11.952207565307617,
      "learning_rate": 0.00013090169943749476,
      "loss": 7.8135,
      "step": 18
    },
    {
      "epoch": 0.000346363829225314,
      "eval_loss": 1.964493989944458,
      "eval_runtime": 2558.5543,
      "eval_samples_per_second": 9.503,
      "eval_steps_per_second": 4.752,
      "step": 20
    },
    {
      "epoch": 0.0003636820206865797,
      "grad_norm": 3.959014654159546,
      "learning_rate": 8.435655349597689e-05,
      "loss": 8.1898,
      "step": 21
    },
    {
      "epoch": 0.0004156365950703768,
      "grad_norm": 4.150637626647949,
      "learning_rate": 4.12214747707527e-05,
      "loss": 6.6662,
      "step": 24
    },
    {
      "epoch": 0.0004329547865316425,
      "eval_loss": 1.8823362588882446,
      "eval_runtime": 2557.8667,
      "eval_samples_per_second": 9.505,
      "eval_steps_per_second": 4.753,
      "step": 25
    },
    {
      "epoch": 0.0004675911694541739,
      "grad_norm": 4.115035533905029,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 8.1748,
      "step": 27
    },
    {
      "epoch": 0.000519545743837971,
      "grad_norm": 2.4167399406433105,
      "learning_rate": 0.0,
      "loss": 6.8152,
      "step": 30
    },
    {
      "epoch": 0.000519545743837971,
      "eval_loss": 1.8694967031478882,
      "eval_runtime": 2557.4188,
      "eval_samples_per_second": 9.507,
      "eval_steps_per_second": 4.754,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": 9894476656128000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}