last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0012396566151176124,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012396566151176124,
      "grad_norm": 1.4749228954315186,
      "learning_rate": 2e-05,
      "loss": 2.3448,
      "step": 1
    },
    {
      "epoch": 0.0002479313230235225,
      "grad_norm": 1.1061748266220093,
      "learning_rate": 4e-05,
      "loss": 2.3491,
      "step": 2
    },
    {
      "epoch": 0.00037189698453528373,
      "grad_norm": 1.2379366159439087,
      "learning_rate": 6e-05,
      "loss": 2.327,
      "step": 3
    },
    {
      "epoch": 0.00037189698453528373,
      "eval_loss": 2.8299930095672607,
      "eval_runtime": 231.6956,
      "eval_samples_per_second": 14.661,
      "eval_steps_per_second": 7.333,
      "step": 3
    },
    {
      "epoch": 0.000495862646047045,
      "grad_norm": 1.9947458505630493,
      "learning_rate": 8e-05,
      "loss": 3.0068,
      "step": 4
    },
    {
      "epoch": 0.0006198283075588062,
      "grad_norm": 1.231313705444336,
      "learning_rate": 0.0001,
      "loss": 2.5538,
      "step": 5
    },
    {
      "epoch": 0.0007437939690705675,
      "grad_norm": 1.4085564613342285,
      "learning_rate": 0.00012,
      "loss": 2.4,
      "step": 6
    },
    {
      "epoch": 0.0007437939690705675,
      "eval_loss": 2.711785078048706,
      "eval_runtime": 234.2588,
      "eval_samples_per_second": 14.501,
      "eval_steps_per_second": 7.253,
      "step": 6
    },
    {
      "epoch": 0.0008677596305823287,
      "grad_norm": 1.1774617433547974,
      "learning_rate": 0.00014,
      "loss": 2.1749,
      "step": 7
    },
    {
      "epoch": 0.00099172529209409,
      "grad_norm": 1.5084151029586792,
      "learning_rate": 0.00016,
      "loss": 2.7707,
      "step": 8
    },
    {
      "epoch": 0.001115690953605851,
      "grad_norm": 1.7904571294784546,
      "learning_rate": 0.00018,
      "loss": 2.8662,
      "step": 9
    },
    {
      "epoch": 0.001115690953605851,
      "eval_loss": 2.3707175254821777,
      "eval_runtime": 237.4543,
      "eval_samples_per_second": 14.306,
      "eval_steps_per_second": 7.155,
      "step": 9
    },
    {
      "epoch": 0.0012396566151176124,
      "grad_norm": 1.475090503692627,
      "learning_rate": 0.0002,
      "loss": 2.0393,
      "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": 397265366679552.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}