last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.029563932002956393,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009854644000985464,
      "eval_loss": NaN,
      "eval_runtime": 14.7216,
      "eval_samples_per_second": 29.073,
      "eval_steps_per_second": 14.536,
      "step": 1
    },
    {
      "epoch": 0.0029563932002956393,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.004927322000492732,
      "eval_loss": NaN,
      "eval_runtime": 14.3322,
      "eval_samples_per_second": 29.863,
      "eval_steps_per_second": 14.931,
      "step": 5
    },
    {
      "epoch": 0.005912786400591279,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.008869179600886918,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.009854644000985464,
      "eval_loss": NaN,
      "eval_runtime": 14.3587,
      "eval_samples_per_second": 29.808,
      "eval_steps_per_second": 14.904,
      "step": 10
    },
    {
      "epoch": 0.011825572801182557,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.014781966001478197,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.014781966001478197,
      "eval_loss": NaN,
      "eval_runtime": 14.3545,
      "eval_samples_per_second": 29.817,
      "eval_steps_per_second": 14.908,
      "step": 15
    },
    {
      "epoch": 0.017738359201773836,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.01970928800197093,
      "eval_loss": NaN,
      "eval_runtime": 14.3472,
      "eval_samples_per_second": 29.832,
      "eval_steps_per_second": 14.916,
      "step": 20
    },
    {
      "epoch": 0.020694752402069475,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.023651145602365115,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.02463661000246366,
      "eval_loss": NaN,
      "eval_runtime": 14.3312,
      "eval_samples_per_second": 29.865,
      "eval_steps_per_second": 14.932,
      "step": 25
    },
    {
      "epoch": 0.026607538802660754,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.029563932002956393,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.029563932002956393,
      "eval_loss": NaN,
      "eval_runtime": 14.3343,
      "eval_samples_per_second": 29.859,
      "eval_steps_per_second": 14.929,
      "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": 1013841985536000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}