{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1960,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 1.4080712099870045,
      "las": 70.92972501091226,
      "step": 196,
      "uas": 80.57616761239633
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.741866283946567,
      "las": 73.1121780881711,
      "step": 392,
      "uas": 82.58402444347446
    },
    {
      "epoch": 2.5510204081632653,
      "grad_norm": 2.2205545902252197,
      "learning_rate": 0.00014897959183673472,
      "loss": 0.6053,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.9176928202311199,
      "las": 75.07638585770407,
      "step": 588,
      "uas": 83.45700567437801
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.9914132754007976,
      "las": 73.02487996508074,
      "step": 784,
      "uas": 82.45307725883893
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.1381421354081898,
      "las": 73.72326494980358,
      "step": 980,
      "uas": 82.49672632038411
    },
    {
      "epoch": 5.1020408163265305,
      "grad_norm": 1.395138144493103,
      "learning_rate": 9.79591836734694e-05,
      "loss": 0.1184,
      "step": 1000
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.532452874713474,
      "las": 73.41772151898735,
      "step": 1176,
      "uas": 81.79834133566129
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.5041761729452343,
      "las": 74.81449148843299,
      "step": 1372,
      "uas": 83.41335661283283
    },
    {
      "epoch": 7.653061224489796,
      "grad_norm": 1.2384448051452637,
      "learning_rate": 4.6938775510204086e-05,
      "loss": 0.042,
      "step": 1500
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.593573318587409,
      "las": 74.2470536883457,
      "step": 1568,
      "uas": 82.58402444347446
    },
    {
      "epoch": 9.0,
      "eval_loss": 2.78382584783766,
      "las": 74.50894805761676,
      "step": 1764,
      "uas": 82.97686599738105
    },
    {
      "epoch": 10.0,
      "eval_loss": 3.0200728840298123,
      "las": 74.81449148843299,
      "step": 1960,
      "uas": 83.19511130510693
    },
    {
      "epoch": 10.0,
      "step": 1960,
      "total_flos": 4.315289190137856e+16,
      "train_loss": 0.19818094482227247,
      "train_runtime": 2176.467,
      "train_samples_per_second": 115.269,
      "train_steps_per_second": 0.901
    }
  ],
  "logging_steps": 500,
  "max_steps": 1960,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.315289190137856e+16,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}