{
  "best_metric": 1.4709290266036987,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0011969119671248179,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.9897065570827266e-05,
      "eval_loss": 2.117204189300537,
      "eval_runtime": 2251.1802,
      "eval_samples_per_second": 4.688,
      "eval_steps_per_second": 2.344,
      "step": 1
    },
    {
      "epoch": 0.0001196911967124818,
      "grad_norm": 1.0353018045425415,
      "learning_rate": 0.00012,
      "loss": 1.8489,
      "step": 3
    },
    {
      "epoch": 0.00019948532785413634,
      "eval_loss": 1.8039857149124146,
      "eval_runtime": 2284.5934,
      "eval_samples_per_second": 4.62,
      "eval_steps_per_second": 2.31,
      "step": 5
    },
    {
      "epoch": 0.0002393823934249636,
      "grad_norm": 0.9052342772483826,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.7178,
      "step": 6
    },
    {
      "epoch": 0.0003590735901374454,
      "grad_norm": 0.7083010673522949,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.5257,
      "step": 9
    },
    {
      "epoch": 0.0003989706557082727,
      "eval_loss": 1.5616681575775146,
      "eval_runtime": 2281.4959,
      "eval_samples_per_second": 4.626,
      "eval_steps_per_second": 2.313,
      "step": 10
    },
    {
      "epoch": 0.0004787647868499272,
      "grad_norm": 0.612604558467865,
      "learning_rate": 0.000163742398974869,
      "loss": 1.5036,
      "step": 12
    },
    {
      "epoch": 0.0005984559835624089,
      "grad_norm": 0.6625750660896301,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.5145,
      "step": 15
    },
    {
      "epoch": 0.0005984559835624089,
      "eval_loss": 1.4995189905166626,
      "eval_runtime": 2282.0838,
      "eval_samples_per_second": 4.625,
      "eval_steps_per_second": 2.312,
      "step": 15
    },
    {
      "epoch": 0.0007181471802748908,
      "grad_norm": 0.6003637909889221,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.4118,
      "step": 18
    },
    {
      "epoch": 0.0007979413114165454,
      "eval_loss": 1.4814709424972534,
      "eval_runtime": 2279.4137,
      "eval_samples_per_second": 4.63,
      "eval_steps_per_second": 2.315,
      "step": 20
    },
    {
      "epoch": 0.0008378383769873726,
      "grad_norm": 0.5599179863929749,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.4394,
      "step": 21
    },
    {
      "epoch": 0.0009575295736998544,
      "grad_norm": 0.5533298254013062,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.3392,
      "step": 24
    },
    {
      "epoch": 0.0009974266392706816,
      "eval_loss": 1.47230863571167,
      "eval_runtime": 2280.0193,
      "eval_samples_per_second": 4.629,
      "eval_steps_per_second": 2.314,
      "step": 25
    },
    {
      "epoch": 0.0010772207704123362,
      "grad_norm": 0.5216392874717712,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.4882,
      "step": 27
    },
    {
      "epoch": 0.0011969119671248179,
      "grad_norm": 0.5612313747406006,
      "learning_rate": 0.0,
      "loss": 1.4671,
      "step": 30
    },
    {
      "epoch": 0.0011969119671248179,
      "eval_loss": 1.4709290266036987,
      "eval_runtime": 2282.1443,
      "eval_samples_per_second": 4.625,
      "eval_steps_per_second": 2.312,
      "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": 1.1221045163851776e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}