{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00016224942604265536,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6224942604265538e-05,
      "grad_norm": 1.4677215814590454,
      "learning_rate": 2e-05,
      "loss": 1.7133,
      "step": 1
    },
    {
      "epoch": 1.6224942604265538e-05,
      "eval_loss": 1.9538787603378296,
      "eval_runtime": 5683.1071,
      "eval_samples_per_second": 2.283,
      "eval_steps_per_second": 2.283,
      "step": 1
    },
    {
      "epoch": 3.2449885208531077e-05,
      "grad_norm": 1.3518354892730713,
      "learning_rate": 4e-05,
      "loss": 1.955,
      "step": 2
    },
    {
      "epoch": 4.867482781279661e-05,
      "grad_norm": 1.5147732496261597,
      "learning_rate": 6e-05,
      "loss": 1.7071,
      "step": 3
    },
    {
      "epoch": 4.867482781279661e-05,
      "eval_loss": 1.9528447389602661,
      "eval_runtime": 5328.2489,
      "eval_samples_per_second": 2.435,
      "eval_steps_per_second": 2.435,
      "step": 3
    },
    {
      "epoch": 6.489977041706215e-05,
      "grad_norm": 1.2925186157226562,
      "learning_rate": 8e-05,
      "loss": 1.7569,
      "step": 4
    },
    {
      "epoch": 8.112471302132768e-05,
      "grad_norm": 1.0739161968231201,
      "learning_rate": 0.0001,
      "loss": 1.5754,
      "step": 5
    },
    {
      "epoch": 9.734965562559322e-05,
      "grad_norm": 1.2039471864700317,
      "learning_rate": 0.00012,
      "loss": 1.3445,
      "step": 6
    },
    {
      "epoch": 9.734965562559322e-05,
      "eval_loss": 1.9351859092712402,
      "eval_runtime": 5317.1839,
      "eval_samples_per_second": 2.44,
      "eval_steps_per_second": 2.44,
      "step": 6
    },
    {
      "epoch": 0.00011357459822985876,
      "grad_norm": 1.8413569927215576,
      "learning_rate": 0.00014,
      "loss": 1.3185,
      "step": 7
    },
    {
      "epoch": 0.0001297995408341243,
      "grad_norm": 1.9093056917190552,
      "learning_rate": 0.00016,
      "loss": 1.7758,
      "step": 8
    },
    {
      "epoch": 0.00014602448343838985,
      "grad_norm": 1.4453094005584717,
      "learning_rate": 0.00018,
      "loss": 1.6346,
      "step": 9
    },
    {
      "epoch": 0.00014602448343838985,
      "eval_loss": 1.8292412757873535,
      "eval_runtime": 5327.3696,
      "eval_samples_per_second": 2.436,
      "eval_steps_per_second": 2.436,
      "step": 9
    },
    {
      "epoch": 0.00016224942604265536,
      "grad_norm": 1.4990195035934448,
      "learning_rate": 0.0002,
      "loss": 1.5415,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3485272092180480.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}