{
  "best_metric": 4.222692012786865,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.03836317135549872,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012787723785166241,
      "eval_loss": 6.751004695892334,
      "eval_runtime": 77.0361,
      "eval_samples_per_second": 4.284,
      "eval_steps_per_second": 2.142,
      "step": 1
    },
    {
      "epoch": 0.0038363171355498722,
      "grad_norm": 14.386683464050293,
      "learning_rate": 6e-05,
      "loss": 26.345,
      "step": 3
    },
    {
      "epoch": 0.00639386189258312,
      "eval_loss": 6.65928840637207,
      "eval_runtime": 77.7571,
      "eval_samples_per_second": 4.244,
      "eval_steps_per_second": 2.122,
      "step": 5
    },
    {
      "epoch": 0.0076726342710997444,
      "grad_norm": 24.970596313476562,
      "learning_rate": 0.00012,
      "loss": 28.8655,
      "step": 6
    },
    {
      "epoch": 0.011508951406649617,
      "grad_norm": 39.15000534057617,
      "learning_rate": 0.00018,
      "loss": 26.8247,
      "step": 9
    },
    {
      "epoch": 0.01278772378516624,
      "eval_loss": 5.828286170959473,
      "eval_runtime": 77.2128,
      "eval_samples_per_second": 4.274,
      "eval_steps_per_second": 2.137,
      "step": 10
    },
    {
      "epoch": 0.015345268542199489,
      "grad_norm": 52.72223663330078,
      "learning_rate": 0.00019510565162951537,
      "loss": 22.6195,
      "step": 12
    },
    {
      "epoch": 0.01918158567774936,
      "grad_norm": 11.487237930297852,
      "learning_rate": 0.00017071067811865476,
      "loss": 22.1898,
      "step": 15
    },
    {
      "epoch": 0.01918158567774936,
      "eval_loss": 5.105317115783691,
      "eval_runtime": 77.2505,
      "eval_samples_per_second": 4.272,
      "eval_steps_per_second": 2.136,
      "step": 15
    },
    {
      "epoch": 0.023017902813299233,
      "grad_norm": 12.449233055114746,
      "learning_rate": 0.00013090169943749476,
      "loss": 19.154,
      "step": 18
    },
    {
      "epoch": 0.02557544757033248,
      "eval_loss": 4.558893203735352,
      "eval_runtime": 77.2495,
      "eval_samples_per_second": 4.272,
      "eval_steps_per_second": 2.136,
      "step": 20
    },
    {
      "epoch": 0.026854219948849106,
      "grad_norm": 10.153334617614746,
      "learning_rate": 8.435655349597689e-05,
      "loss": 18.4833,
      "step": 21
    },
    {
      "epoch": 0.030690537084398978,
      "grad_norm": 14.909246444702148,
      "learning_rate": 4.12214747707527e-05,
      "loss": 16.9899,
      "step": 24
    },
    {
      "epoch": 0.0319693094629156,
      "eval_loss": 4.26448392868042,
      "eval_runtime": 77.2033,
      "eval_samples_per_second": 4.274,
      "eval_steps_per_second": 2.137,
      "step": 25
    },
    {
      "epoch": 0.034526854219948847,
      "grad_norm": 14.013001441955566,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 18.0847,
      "step": 27
    },
    {
      "epoch": 0.03836317135549872,
      "grad_norm": 13.466968536376953,
      "learning_rate": 0.0,
      "loss": 17.8296,
      "step": 30
    },
    {
      "epoch": 0.03836317135549872,
      "eval_loss": 4.222692012786865,
      "eval_runtime": 77.3336,
      "eval_samples_per_second": 4.267,
      "eval_steps_per_second": 2.134,
      "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": 2.042527481856e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}