{
  "best_metric": 2.6111176013946533,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0049063701038515005,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016354567012838336,
      "eval_loss": 4.267529487609863,
      "eval_runtime": 507.3022,
      "eval_samples_per_second": 5.076,
      "eval_steps_per_second": 2.539,
      "step": 1
    },
    {
      "epoch": 0.00049063701038515,
      "grad_norm": 1.061664342880249,
      "learning_rate": 3e-05,
      "loss": 3.8929,
      "step": 3
    },
    {
      "epoch": 0.0008177283506419167,
      "eval_loss": 4.160350322723389,
      "eval_runtime": 510.5273,
      "eval_samples_per_second": 5.044,
      "eval_steps_per_second": 2.523,
      "step": 5
    },
    {
      "epoch": 0.0009812740207703,
      "grad_norm": 1.6031444072723389,
      "learning_rate": 6e-05,
      "loss": 4.122,
      "step": 6
    },
    {
      "epoch": 0.0014719110311554502,
      "grad_norm": 1.1639562845230103,
      "learning_rate": 9e-05,
      "loss": 3.4398,
      "step": 9
    },
    {
      "epoch": 0.0016354567012838335,
      "eval_loss": 3.4370737075805664,
      "eval_runtime": 510.509,
      "eval_samples_per_second": 5.044,
      "eval_steps_per_second": 2.523,
      "step": 10
    },
    {
      "epoch": 0.0019625480415406,
      "grad_norm": 1.746925711631775,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.4661,
      "step": 12
    },
    {
      "epoch": 0.0024531850519257502,
      "grad_norm": 1.3604792356491089,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.7556,
      "step": 15
    },
    {
      "epoch": 0.0024531850519257502,
      "eval_loss": 2.8416481018066406,
      "eval_runtime": 510.5806,
      "eval_samples_per_second": 5.043,
      "eval_steps_per_second": 2.523,
      "step": 15
    },
    {
      "epoch": 0.0029438220623109004,
      "grad_norm": 1.0310943126678467,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.6629,
      "step": 18
    },
    {
      "epoch": 0.003270913402567667,
      "eval_loss": 2.66746187210083,
      "eval_runtime": 510.8032,
      "eval_samples_per_second": 5.041,
      "eval_steps_per_second": 2.522,
      "step": 20
    },
    {
      "epoch": 0.0034344590726960505,
      "grad_norm": 1.4085278511047363,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 2.2877,
      "step": 21
    },
    {
      "epoch": 0.0039250960830812,
      "grad_norm": 1.4254778623580933,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.4096,
      "step": 24
    },
    {
      "epoch": 0.004088641753209584,
      "eval_loss": 2.6312296390533447,
      "eval_runtime": 510.5738,
      "eval_samples_per_second": 5.043,
      "eval_steps_per_second": 2.523,
      "step": 25
    },
    {
      "epoch": 0.004415733093466351,
      "grad_norm": 1.1322522163391113,
      "learning_rate": 5.449673790581611e-06,
      "loss": 2.4184,
      "step": 27
    },
    {
      "epoch": 0.0049063701038515005,
      "grad_norm": 2.1908793449401855,
      "learning_rate": 0.0,
      "loss": 2.9997,
      "step": 30
    },
    {
      "epoch": 0.0049063701038515005,
      "eval_loss": 2.6111176013946533,
      "eval_runtime": 510.3088,
      "eval_samples_per_second": 5.046,
      "eval_steps_per_second": 2.524,
      "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": 1.9043369091072e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}