{
  "best_metric": 11.130102157592773,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.03690036900369004,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036900369003690036,
      "grad_norm": 1.791113018989563,
      "learning_rate": 2e-05,
      "loss": 44.5973,
      "step": 1
    },
    {
      "epoch": 0.0036900369003690036,
      "eval_loss": 11.170838356018066,
      "eval_runtime": 1.9984,
      "eval_samples_per_second": 57.545,
      "eval_steps_per_second": 29.023,
      "step": 1
    },
    {
      "epoch": 0.007380073800738007,
      "grad_norm": 2.3068079948425293,
      "learning_rate": 4e-05,
      "loss": 44.6951,
      "step": 2
    },
    {
      "epoch": 0.01107011070110701,
      "grad_norm": 2.204294443130493,
      "learning_rate": 6e-05,
      "loss": 44.6784,
      "step": 3
    },
    {
      "epoch": 0.014760147601476014,
      "grad_norm": 2.4943387508392334,
      "learning_rate": 8e-05,
      "loss": 44.5942,
      "step": 4
    },
    {
      "epoch": 0.01845018450184502,
      "grad_norm": 2.697859287261963,
      "learning_rate": 0.0001,
      "loss": 44.7435,
      "step": 5
    },
    {
      "epoch": 0.01845018450184502,
      "eval_loss": 11.16266918182373,
      "eval_runtime": 0.897,
      "eval_samples_per_second": 128.199,
      "eval_steps_per_second": 64.657,
      "step": 5
    },
    {
      "epoch": 0.02214022140221402,
      "grad_norm": 2.368184804916382,
      "learning_rate": 0.00012,
      "loss": 44.6444,
      "step": 6
    },
    {
      "epoch": 0.025830258302583026,
      "grad_norm": 2.20993709564209,
      "learning_rate": 0.00014,
      "loss": 44.5774,
      "step": 7
    },
    {
      "epoch": 0.02952029520295203,
      "grad_norm": 2.647223949432373,
      "learning_rate": 0.00016,
      "loss": 44.6219,
      "step": 8
    },
    {
      "epoch": 0.033210332103321034,
      "grad_norm": 2.0904574394226074,
      "learning_rate": 0.00018,
      "loss": 44.5955,
      "step": 9
    },
    {
      "epoch": 0.03690036900369004,
      "grad_norm": 2.8271727561950684,
      "learning_rate": 0.0002,
      "loss": 44.5294,
      "step": 10
    },
    {
      "epoch": 0.03690036900369004,
      "eval_loss": 11.130102157592773,
      "eval_runtime": 0.895,
      "eval_samples_per_second": 128.492,
      "eval_steps_per_second": 64.805,
      "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": 192896040960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}