last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0032680628557422587,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010893542852474196,
      "eval_loss": NaN,
      "eval_runtime": 237.3388,
      "eval_samples_per_second": 16.289,
      "eval_steps_per_second": 8.144,
      "step": 1
    },
    {
      "epoch": 0.0003268062855742259,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0005446771426237097,
      "eval_loss": NaN,
      "eval_runtime": 237.3222,
      "eval_samples_per_second": 16.29,
      "eval_steps_per_second": 8.145,
      "step": 5
    },
    {
      "epoch": 0.0006536125711484518,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0009804188567226777,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0010893542852474195,
      "eval_loss": NaN,
      "eval_runtime": 237.3799,
      "eval_samples_per_second": 16.286,
      "eval_steps_per_second": 8.143,
      "step": 10
    },
    {
      "epoch": 0.0013072251422969036,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0016340314278711294,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0016340314278711294,
      "eval_loss": NaN,
      "eval_runtime": 237.3995,
      "eval_samples_per_second": 16.285,
      "eval_steps_per_second": 8.142,
      "step": 15
    },
    {
      "epoch": 0.0019608377134453553,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.002178708570494839,
      "eval_loss": NaN,
      "eval_runtime": 237.3389,
      "eval_samples_per_second": 16.289,
      "eval_steps_per_second": 8.144,
      "step": 20
    },
    {
      "epoch": 0.0022876439990195813,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0026144502845938072,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.002723385713118549,
      "eval_loss": NaN,
      "eval_runtime": 237.3766,
      "eval_samples_per_second": 16.286,
      "eval_steps_per_second": 8.143,
      "step": 25
    },
    {
      "epoch": 0.0029412565701680327,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0032680628557422587,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0032680628557422587,
      "eval_loss": NaN,
      "eval_runtime": 237.4031,
      "eval_samples_per_second": 16.285,
      "eval_steps_per_second": 8.142,
      "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": 1.08314109149184e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}