last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009290658243136526,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.290658243136526e-05,
      "grad_norm": 51.71630096435547,
      "learning_rate": 2e-05,
      "loss": 13.9523,
      "step": 1
    },
    {
      "epoch": 9.290658243136526e-05,
      "eval_loss": 3.434204339981079,
      "eval_runtime": 50.6887,
      "eval_samples_per_second": 89.409,
      "eval_steps_per_second": 44.704,
      "step": 1
    },
    {
      "epoch": 0.00018581316486273051,
      "grad_norm": 57.94331359863281,
      "learning_rate": 4e-05,
      "loss": 13.85,
      "step": 2
    },
    {
      "epoch": 0.00027871974729409577,
      "grad_norm": 57.31100082397461,
      "learning_rate": 6e-05,
      "loss": 13.4466,
      "step": 3
    },
    {
      "epoch": 0.00027871974729409577,
      "eval_loss": 3.4339802265167236,
      "eval_runtime": 48.1321,
      "eval_samples_per_second": 94.158,
      "eval_steps_per_second": 47.079,
      "step": 3
    },
    {
      "epoch": 0.00037162632972546103,
      "grad_norm": 62.255516052246094,
      "learning_rate": 8e-05,
      "loss": 13.6484,
      "step": 4
    },
    {
      "epoch": 0.0004645329121568263,
      "grad_norm": 68.01496887207031,
      "learning_rate": 0.0001,
      "loss": 15.8262,
      "step": 5
    },
    {
      "epoch": 0.0005574394945881915,
      "grad_norm": 42.891239166259766,
      "learning_rate": 0.00012,
      "loss": 13.0994,
      "step": 6
    },
    {
      "epoch": 0.0005574394945881915,
      "eval_loss": 3.4298434257507324,
      "eval_runtime": 47.8312,
      "eval_samples_per_second": 94.75,
      "eval_steps_per_second": 47.375,
      "step": 6
    },
    {
      "epoch": 0.0006503460770195569,
      "grad_norm": 61.19314956665039,
      "learning_rate": 0.00014,
      "loss": 13.2718,
      "step": 7
    },
    {
      "epoch": 0.0007432526594509221,
      "grad_norm": 49.314762115478516,
      "learning_rate": 0.00016,
      "loss": 13.1002,
      "step": 8
    },
    {
      "epoch": 0.0008361592418822874,
      "grad_norm": 53.37507247924805,
      "learning_rate": 0.00018,
      "loss": 13.5421,
      "step": 9
    },
    {
      "epoch": 0.0008361592418822874,
      "eval_loss": 3.413646936416626,
      "eval_runtime": 48.3954,
      "eval_samples_per_second": 93.645,
      "eval_steps_per_second": 46.823,
      "step": 9
    },
    {
      "epoch": 0.0009290658243136526,
      "grad_norm": 61.506229400634766,
      "learning_rate": 0.0002,
      "loss": 14.7379,
      "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": 92114994069504.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}