checkpoint-24/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 0.049072265625,
      "learning_rate": 0.0002,
      "loss": 1.2558,
      "step": 1
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.046630859375,
      "learning_rate": 0.0002,
      "loss": 1.276,
      "step": 2
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.046875,
      "learning_rate": 0.0002,
      "loss": 1.2758,
      "step": 3
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.054443359375,
      "learning_rate": 0.0002,
      "loss": 1.2889,
      "step": 4
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.058349609375,
      "learning_rate": 0.0002,
      "loss": 1.3781,
      "step": 5
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.042724609375,
      "learning_rate": 0.0002,
      "loss": 1.2866,
      "step": 6
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.041748046875,
      "learning_rate": 0.0002,
      "loss": 1.1998,
      "step": 7
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.044677734375,
      "learning_rate": 0.0002,
      "loss": 1.2973,
      "step": 8
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.044921875,
      "learning_rate": 0.0002,
      "loss": 1.2811,
      "step": 9
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.039794921875,
      "learning_rate": 0.0002,
      "loss": 1.2072,
      "step": 10
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.040283203125,
      "learning_rate": 0.0002,
      "loss": 1.2256,
      "step": 11
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.0380859375,
      "learning_rate": 0.0002,
      "loss": 1.3164,
      "step": 12
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.0380859375,
      "learning_rate": 0.0002,
      "loss": 1.2636,
      "step": 13
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.039794921875,
      "learning_rate": 0.0002,
      "loss": 1.2758,
      "step": 14
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.0400390625,
      "learning_rate": 0.0002,
      "loss": 1.097,
      "step": 15
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.04248046875,
      "learning_rate": 0.0002,
      "loss": 1.1723,
      "step": 16
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.0419921875,
      "learning_rate": 0.0002,
      "loss": 1.2034,
      "step": 17
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.043212890625,
      "learning_rate": 0.0002,
      "loss": 1.1135,
      "step": 18
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.044921875,
      "learning_rate": 0.0002,
      "loss": 1.2245,
      "step": 19
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.04541015625,
      "learning_rate": 0.0002,
      "loss": 1.1489,
      "step": 20
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.042724609375,
      "learning_rate": 0.0002,
      "loss": 1.193,
      "step": 21
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.040771484375,
      "learning_rate": 0.0002,
      "loss": 1.2408,
      "step": 22
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.046142578125,
      "learning_rate": 0.0002,
      "loss": 1.1367,
      "step": 23
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.0419921875,
      "learning_rate": 0.0002,
      "loss": 1.0999,
      "step": 24
    }
  ],
  "logging_steps": 1,
  "max_steps": 24,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 8,
  "total_flos": 4961451135467520.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}