last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018424689083371717,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018424689083371719,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.0599,
      "step": 1
    },
    {
      "epoch": 0.0018424689083371719,
      "eval_loss": 10.444669723510742,
      "eval_runtime": 20.8715,
      "eval_samples_per_second": 21.896,
      "eval_steps_per_second": 5.51,
      "step": 1
    },
    {
      "epoch": 0.0036849378166743437,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.0419,
      "step": 2
    },
    {
      "epoch": 0.0055274067250115156,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 11.0173,
      "step": 3
    },
    {
      "epoch": 0.0055274067250115156,
      "eval_loss": 10.444669723510742,
      "eval_runtime": 20.1507,
      "eval_samples_per_second": 22.679,
      "eval_steps_per_second": 5.707,
      "step": 3
    },
    {
      "epoch": 0.007369875633348687,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.8688,
      "step": 4
    },
    {
      "epoch": 0.009212344541685858,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.5447,
      "step": 5
    },
    {
      "epoch": 0.011054813450023031,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.5789,
      "step": 6
    },
    {
      "epoch": 0.011054813450023031,
      "eval_loss": 10.444669723510742,
      "eval_runtime": 20.1457,
      "eval_samples_per_second": 22.685,
      "eval_steps_per_second": 5.708,
      "step": 6
    },
    {
      "epoch": 0.012897282358360202,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 11.4302,
      "step": 7
    },
    {
      "epoch": 0.014739751266697375,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.3072,
      "step": 8
    },
    {
      "epoch": 0.016582220175034548,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 11.2267,
      "step": 9
    },
    {
      "epoch": 0.016582220175034548,
      "eval_loss": 10.444669723510742,
      "eval_runtime": 20.1372,
      "eval_samples_per_second": 22.694,
      "eval_steps_per_second": 5.711,
      "step": 9
    },
    {
      "epoch": 0.018424689083371717,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.4356,
      "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": 1.47552863256576e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}