last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00011498184724086685,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1498184724086685e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 5.8587,
      "step": 1
    },
    {
      "epoch": 1.1498184724086685e-05,
      "eval_loss": NaN,
      "eval_runtime": 5207.2072,
      "eval_samples_per_second": 7.033,
      "eval_steps_per_second": 3.516,
      "step": 1
    },
    {
      "epoch": 2.299636944817337e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 3.4494554172260055e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 3.4494554172260055e-05,
      "eval_loss": NaN,
      "eval_runtime": 5203.4858,
      "eval_samples_per_second": 7.038,
      "eval_steps_per_second": 3.519,
      "step": 3
    },
    {
      "epoch": 4.599273889634674e-05,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 5.7490923620433424e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 6.898910834452011e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 6.898910834452011e-05,
      "eval_loss": NaN,
      "eval_runtime": 5242.9839,
      "eval_samples_per_second": 6.985,
      "eval_steps_per_second": 3.492,
      "step": 6
    },
    {
      "epoch": 8.04872930686068e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 9.198547779269348e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00010348366251678016,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00010348366251678016,
      "eval_loss": NaN,
      "eval_runtime": 5239.5403,
      "eval_samples_per_second": 6.989,
      "eval_steps_per_second": 3.495,
      "step": 9
    },
    {
      "epoch": 0.00011498184724086685,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "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": 3093178981810176.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}