{
  "best_metric": 1.5803078413009644,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.012642225031605562,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012642225031605564,
      "grad_norm": 1.9378573894500732,
      "learning_rate": 2e-05,
      "loss": 8.6874,
      "step": 1
    },
    {
      "epoch": 0.0012642225031605564,
      "eval_loss": 2.1115481853485107,
      "eval_runtime": 49.5266,
      "eval_samples_per_second": 6.744,
      "eval_steps_per_second": 3.372,
      "step": 1
    },
    {
      "epoch": 0.0025284450063211127,
      "grad_norm": 2.0282223224639893,
      "learning_rate": 4e-05,
      "loss": 8.3938,
      "step": 2
    },
    {
      "epoch": 0.0037926675094816687,
      "grad_norm": 1.9364533424377441,
      "learning_rate": 6e-05,
      "loss": 9.1156,
      "step": 3
    },
    {
      "epoch": 0.0050568900126422255,
      "grad_norm": 2.017167329788208,
      "learning_rate": 8e-05,
      "loss": 8.4278,
      "step": 4
    },
    {
      "epoch": 0.006321112515802781,
      "grad_norm": 2.3764736652374268,
      "learning_rate": 0.0001,
      "loss": 7.7881,
      "step": 5
    },
    {
      "epoch": 0.006321112515802781,
      "eval_loss": 2.0647788047790527,
      "eval_runtime": 49.568,
      "eval_samples_per_second": 6.738,
      "eval_steps_per_second": 3.369,
      "step": 5
    },
    {
      "epoch": 0.007585335018963337,
      "grad_norm": 2.7689037322998047,
      "learning_rate": 0.00012,
      "loss": 7.601,
      "step": 6
    },
    {
      "epoch": 0.008849557522123894,
      "grad_norm": 3.710773468017578,
      "learning_rate": 0.00014,
      "loss": 7.6337,
      "step": 7
    },
    {
      "epoch": 0.010113780025284451,
      "grad_norm": 4.302574157714844,
      "learning_rate": 0.00016,
      "loss": 7.6958,
      "step": 8
    },
    {
      "epoch": 0.011378002528445006,
      "grad_norm": 5.66724967956543,
      "learning_rate": 0.00018,
      "loss": 8.0003,
      "step": 9
    },
    {
      "epoch": 0.012642225031605562,
      "grad_norm": 4.579207897186279,
      "learning_rate": 0.0002,
      "loss": 6.8932,
      "step": 10
    },
    {
      "epoch": 0.012642225031605562,
      "eval_loss": 1.5803078413009644,
      "eval_runtime": 49.5724,
      "eval_samples_per_second": 6.738,
      "eval_steps_per_second": 3.369,
      "step": 10
    }
  ],
  "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3482301549772800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}