last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0664819944598338,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00221606648199446,
      "eval_loss": NaN,
      "eval_runtime": 42.8078,
      "eval_samples_per_second": 4.438,
      "eval_steps_per_second": 2.219,
      "step": 1
    },
    {
      "epoch": 0.006648199445983379,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.013296398891966758,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.01772853185595568,
      "eval_loss": NaN,
      "eval_runtime": 42.8172,
      "eval_samples_per_second": 4.437,
      "eval_steps_per_second": 2.219,
      "step": 8
    },
    {
      "epoch": 0.019944598337950138,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.026592797783933517,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0332409972299169,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.03545706371191136,
      "eval_loss": NaN,
      "eval_runtime": 42.8887,
      "eval_samples_per_second": 4.43,
      "eval_steps_per_second": 2.215,
      "step": 16
    },
    {
      "epoch": 0.039889196675900275,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.04653739612188366,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.05318559556786703,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.05318559556786703,
      "eval_loss": NaN,
      "eval_runtime": 42.8825,
      "eval_samples_per_second": 4.431,
      "eval_steps_per_second": 2.215,
      "step": 24
    },
    {
      "epoch": 0.059833795013850416,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0664819944598338,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.109390911963136e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}