last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006747638326585695,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.747638326585695e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 6.747638326585695e-05,
      "eval_loss": NaN,
      "eval_runtime": 254.5032,
      "eval_samples_per_second": 24.518,
      "eval_steps_per_second": 12.259,
      "step": 1
    },
    {
      "epoch": 0.0001349527665317139,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 1.4803,
      "step": 2
    },
    {
      "epoch": 0.00020242914979757084,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00020242914979757084,
      "eval_loss": NaN,
      "eval_runtime": 253.2462,
      "eval_samples_per_second": 24.64,
      "eval_steps_per_second": 12.32,
      "step": 3
    },
    {
      "epoch": 0.0002699055330634278,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00033738191632928474,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0004048582995951417,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0004048582995951417,
      "eval_loss": NaN,
      "eval_runtime": 253.2964,
      "eval_samples_per_second": 24.635,
      "eval_steps_per_second": 12.318,
      "step": 6
    },
    {
      "epoch": 0.00047233468286099863,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0005398110661268556,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0006072874493927126,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0006072874493927126,
      "eval_loss": NaN,
      "eval_runtime": 253.6018,
      "eval_samples_per_second": 24.606,
      "eval_steps_per_second": 12.303,
      "step": 9
    },
    {
      "epoch": 0.0006747638326585695,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2320944718675968.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}