{
  "best_metric": 1.1766549348831177,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.025162507863283706,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000838750262109457,
      "eval_loss": 1.7440450191497803,
      "eval_runtime": 63.2129,
      "eval_samples_per_second": 7.941,
      "eval_steps_per_second": 3.971,
      "step": 1
    },
    {
      "epoch": 0.0025162507863283707,
      "grad_norm": 0.9366751313209534,
      "learning_rate": 6e-05,
      "loss": 1.702,
      "step": 3
    },
    {
      "epoch": 0.004193751310547285,
      "eval_loss": 1.6217440366744995,
      "eval_runtime": 64.2917,
      "eval_samples_per_second": 7.808,
      "eval_steps_per_second": 3.904,
      "step": 5
    },
    {
      "epoch": 0.0050325015726567415,
      "grad_norm": 1.183415412902832,
      "learning_rate": 9.96057350657239e-05,
      "loss": 1.6848,
      "step": 6
    },
    {
      "epoch": 0.007548752358985112,
      "grad_norm": 0.7446143627166748,
      "learning_rate": 9.381533400219318e-05,
      "loss": 1.5654,
      "step": 9
    },
    {
      "epoch": 0.00838750262109457,
      "eval_loss": 1.3832272291183472,
      "eval_runtime": 64.5116,
      "eval_samples_per_second": 7.782,
      "eval_steps_per_second": 3.891,
      "step": 10
    },
    {
      "epoch": 0.010065003145313483,
      "grad_norm": 0.8925324082374573,
      "learning_rate": 8.18711994874345e-05,
      "loss": 1.4887,
      "step": 12
    },
    {
      "epoch": 0.012581253931641853,
      "grad_norm": 0.8682627081871033,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.3685,
      "step": 15
    },
    {
      "epoch": 0.012581253931641853,
      "eval_loss": 1.285154104232788,
      "eval_runtime": 64.5467,
      "eval_samples_per_second": 7.777,
      "eval_steps_per_second": 3.889,
      "step": 15
    },
    {
      "epoch": 0.015097504717970224,
      "grad_norm": 0.957084059715271,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 1.2482,
      "step": 18
    },
    {
      "epoch": 0.01677500524218914,
      "eval_loss": 1.220939040184021,
      "eval_runtime": 64.5366,
      "eval_samples_per_second": 7.779,
      "eval_steps_per_second": 3.889,
      "step": 20
    },
    {
      "epoch": 0.017613755504298594,
      "grad_norm": 1.0577512979507446,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 1.3029,
      "step": 21
    },
    {
      "epoch": 0.020130006290626966,
      "grad_norm": 1.3813283443450928,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 1.1785,
      "step": 24
    },
    {
      "epoch": 0.020968756552736424,
      "eval_loss": 1.1839109659194946,
      "eval_runtime": 64.5305,
      "eval_samples_per_second": 7.779,
      "eval_steps_per_second": 3.89,
      "step": 25
    },
    {
      "epoch": 0.022646257076955337,
      "grad_norm": 1.0368940830230713,
      "learning_rate": 3.511175705587433e-06,
      "loss": 1.1967,
      "step": 27
    },
    {
      "epoch": 0.025162507863283706,
      "grad_norm": 1.231654167175293,
      "learning_rate": 0.0,
      "loss": 1.2565,
      "step": 30
    },
    {
      "epoch": 0.025162507863283706,
      "eval_loss": 1.1766549348831177,
      "eval_runtime": 64.5307,
      "eval_samples_per_second": 7.779,
      "eval_steps_per_second": 3.89,
      "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": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}