trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9846153846153847,
  "eval_steps": 500,
  "global_step": 48,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 2e-05,
      "loss": 1.628,
      "step": 2
    },
    {
      "epoch": 0.08,
      "learning_rate": 2e-05,
      "loss": 1.7785,
      "step": 4
    },
    {
      "epoch": 0.12,
      "learning_rate": 2e-05,
      "loss": 1.7989,
      "step": 6
    },
    {
      "epoch": 0.16,
      "learning_rate": 2e-05,
      "loss": 1.9499,
      "step": 8
    },
    {
      "epoch": 0.21,
      "learning_rate": 2e-05,
      "loss": 2.083,
      "step": 10
    },
    {
      "epoch": 0.25,
      "learning_rate": 2e-05,
      "loss": 2.2934,
      "step": 12
    },
    {
      "epoch": 0.29,
      "learning_rate": 2e-05,
      "loss": 1.6058,
      "step": 14
    },
    {
      "epoch": 0.33,
      "learning_rate": 2e-05,
      "loss": 1.5273,
      "step": 16
    },
    {
      "epoch": 0.37,
      "learning_rate": 2e-05,
      "loss": 1.8161,
      "step": 18
    },
    {
      "epoch": 0.41,
      "learning_rate": 2e-05,
      "loss": 1.6572,
      "step": 20
    },
    {
      "epoch": 0.45,
      "learning_rate": 2e-05,
      "loss": 1.9493,
      "step": 22
    },
    {
      "epoch": 0.49,
      "learning_rate": 2e-05,
      "loss": 2.0149,
      "step": 24
    },
    {
      "epoch": 0.53,
      "learning_rate": 2e-05,
      "loss": 1.5307,
      "step": 26
    },
    {
      "epoch": 0.57,
      "learning_rate": 2e-05,
      "loss": 1.7295,
      "step": 28
    },
    {
      "epoch": 0.62,
      "learning_rate": 2e-05,
      "loss": 1.8937,
      "step": 30
    },
    {
      "epoch": 0.66,
      "learning_rate": 2e-05,
      "loss": 1.7242,
      "step": 32
    },
    {
      "epoch": 0.7,
      "learning_rate": 2e-05,
      "loss": 1.7415,
      "step": 34
    },
    {
      "epoch": 0.74,
      "learning_rate": 2e-05,
      "loss": 2.0247,
      "step": 36
    },
    {
      "epoch": 0.78,
      "learning_rate": 2e-05,
      "loss": 1.6039,
      "step": 38
    },
    {
      "epoch": 0.82,
      "learning_rate": 2e-05,
      "loss": 1.7683,
      "step": 40
    },
    {
      "epoch": 0.86,
      "learning_rate": 2e-05,
      "loss": 1.8772,
      "step": 42
    },
    {
      "epoch": 0.9,
      "learning_rate": 2e-05,
      "loss": 1.911,
      "step": 44
    },
    {
      "epoch": 0.94,
      "learning_rate": 2e-05,
      "loss": 1.7922,
      "step": 46
    },
    {
      "epoch": 0.98,
      "learning_rate": 2e-05,
      "loss": 1.908,
      "step": 48
    }
  ],
  "logging_steps": 2,
  "max_steps": 48,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 1.6455943600201728e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}