{
  "best_metric": 9.125,
  "best_model_checkpoint": "model_bloomz_7b_hu_v2/checkpoint-36000",
  "epoch": 1.75,
  "eval_steps": 6000,
  "global_step": 42000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "learning_rate": 1.95e-05,
      "loss": 9.1897,
      "step": 6000
    },
    {
      "epoch": 0.25,
      "eval_loss": 9.1484375,
      "eval_runtime": 6192.9248,
      "eval_samples_per_second": 0.969,
      "eval_steps_per_second": 0.969,
      "step": 6000
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.9e-05,
      "loss": 9.1324,
      "step": 12000
    },
    {
      "epoch": 0.5,
      "eval_loss": 9.1328125,
      "eval_runtime": 4300.0934,
      "eval_samples_per_second": 1.395,
      "eval_steps_per_second": 1.395,
      "step": 12000
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.8500000000000002e-05,
      "loss": 9.1315,
      "step": 18000
    },
    {
      "epoch": 0.75,
      "eval_loss": 9.1328125,
      "eval_runtime": 6523.4477,
      "eval_samples_per_second": 0.92,
      "eval_steps_per_second": 0.92,
      "step": 18000
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.8e-05,
      "loss": 9.085,
      "step": 24000
    },
    {
      "epoch": 1.0,
      "eval_loss": 9.1328125,
      "eval_runtime": 6525.6719,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.919,
      "step": 24000
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 9.1184,
      "step": 30000
    },
    {
      "epoch": 1.25,
      "eval_loss": 9.1328125,
      "eval_runtime": 6539.0051,
      "eval_samples_per_second": 0.918,
      "eval_steps_per_second": 0.918,
      "step": 30000
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.7e-05,
      "loss": 9.1195,
      "step": 36000
    },
    {
      "epoch": 1.5,
      "eval_loss": 9.125,
      "eval_runtime": 6552.0304,
      "eval_samples_per_second": 0.916,
      "eval_steps_per_second": 0.916,
      "step": 36000
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.65e-05,
      "loss": 9.14,
      "step": 42000
    },
    {
      "epoch": 1.75,
      "eval_loss": 9.125,
      "eval_runtime": 6560.9944,
      "eval_samples_per_second": 0.914,
      "eval_steps_per_second": 0.914,
      "step": 42000
    }
  ],
  "logging_steps": 6000,
  "max_steps": 240000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 6000,
  "total_flos": 3.117948352856064e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}