last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017592212513927168,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.8640708379757225e-05,
      "eval_loss": NaN,
      "eval_runtime": 558.8024,
      "eval_samples_per_second": 12.851,
      "eval_steps_per_second": 6.426,
      "step": 1
    },
    {
      "epoch": 0.00017592212513927168,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00035184425027854336,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0004691256670380578,
      "eval_loss": NaN,
      "eval_runtime": 558.3664,
      "eval_samples_per_second": 12.861,
      "eval_steps_per_second": 6.431,
      "step": 8
    },
    {
      "epoch": 0.000527766375417815,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0007036885005570867,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0008796106256963584,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0009382513340761156,
      "eval_loss": NaN,
      "eval_runtime": 558.4893,
      "eval_samples_per_second": 12.858,
      "eval_steps_per_second": 6.43,
      "step": 16
    },
    {
      "epoch": 0.00105553275083563,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0012314548759749019,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0014073770011141734,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0014073770011141734,
      "eval_loss": NaN,
      "eval_runtime": 558.4669,
      "eval_samples_per_second": 12.858,
      "eval_steps_per_second": 6.43,
      "step": 24
    },
    {
      "epoch": 0.0015832991262534452,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0017592212513927168,
      "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": 9801879068344320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}