trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06650732619765146,
  "eval_steps": 10,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.25e-06,
      "loss": 1.6498,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.5e-06,
      "loss": 1.6432,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 1.523,
      "step": 3
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-06,
      "loss": 1.3035,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.25e-06,
      "loss": 1.1292,
      "step": 5
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.0208,
      "step": 6
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.750000000000001e-06,
      "loss": 0.9857,
      "step": 7
    },
    {
      "epoch": 0.05,
      "learning_rate": 1e-05,
      "loss": 0.9697,
      "step": 8
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.998776383426217e-06,
      "loss": 0.9408,
      "step": 9
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.995106132599869e-06,
      "loss": 0.9246,
      "step": 10
    },
    {
      "epoch": 0.07,
      "eval_loss": 1.008070707321167,
      "eval_runtime": 45.3586,
      "eval_samples_per_second": 17.152,
      "eval_steps_per_second": 1.08,
      "step": 10
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 12822618701824.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}