last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.027629079606285616,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027629079606285617,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 2399.0908,
      "step": 1
    },
    {
      "epoch": 0.0027629079606285617,
      "eval_loss": NaN,
      "eval_runtime": 124.2939,
      "eval_samples_per_second": 4.908,
      "eval_steps_per_second": 2.454,
      "step": 1
    },
    {
      "epoch": 0.005525815921257123,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.008288723881885684,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.008288723881885684,
      "eval_loss": NaN,
      "eval_runtime": 14.6094,
      "eval_samples_per_second": 41.754,
      "eval_steps_per_second": 20.877,
      "step": 3
    },
    {
      "epoch": 0.011051631842514247,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.013814539803142808,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.016577447763771368,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.016577447763771368,
      "eval_loss": NaN,
      "eval_runtime": 14.6303,
      "eval_samples_per_second": 41.694,
      "eval_steps_per_second": 20.847,
      "step": 6
    },
    {
      "epoch": 0.019340355724399932,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.022103263685028494,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.024866171645657055,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.024866171645657055,
      "eval_loss": NaN,
      "eval_runtime": 14.6107,
      "eval_samples_per_second": 41.75,
      "eval_steps_per_second": 20.875,
      "step": 9
    },
    {
      "epoch": 0.027629079606285616,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "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": 7166496664977408.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}