last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03461205653302567,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011537352177675222,
      "eval_loss": NaN,
      "eval_runtime": 55.4978,
      "eval_samples_per_second": 6.577,
      "eval_steps_per_second": 3.297,
      "step": 1
    },
    {
      "epoch": 0.003461205653302567,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.005768676088837612,
      "eval_loss": NaN,
      "eval_runtime": 54.9702,
      "eval_samples_per_second": 6.64,
      "eval_steps_per_second": 3.329,
      "step": 5
    },
    {
      "epoch": 0.006922411306605134,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.010383616959907702,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.011537352177675224,
      "eval_loss": NaN,
      "eval_runtime": 55.0456,
      "eval_samples_per_second": 6.631,
      "eval_steps_per_second": 3.325,
      "step": 10
    },
    {
      "epoch": 0.013844822613210269,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.017306028266512834,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.017306028266512834,
      "eval_loss": NaN,
      "eval_runtime": 55.1032,
      "eval_samples_per_second": 6.624,
      "eval_steps_per_second": 3.321,
      "step": 15
    },
    {
      "epoch": 0.020767233919815404,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.02307470435535045,
      "eval_loss": NaN,
      "eval_runtime": 55.1075,
      "eval_samples_per_second": 6.623,
      "eval_steps_per_second": 3.321,
      "step": 20
    },
    {
      "epoch": 0.02422843957311797,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.027689645226420537,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.02884338044418806,
      "eval_loss": NaN,
      "eval_runtime": 55.1273,
      "eval_samples_per_second": 6.621,
      "eval_steps_per_second": 3.32,
      "step": 25
    },
    {
      "epoch": 0.031150850879723104,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.03461205653302567,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.03461205653302567,
      "eval_loss": NaN,
      "eval_runtime": 55.1328,
      "eval_samples_per_second": 6.62,
      "eval_steps_per_second": 3.319,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.160746713369805e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}