last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04287245444801715,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004287245444801715,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 15.9631,
      "step": 1
    },
    {
      "epoch": 0.004287245444801715,
      "eval_loss": 16.551647186279297,
      "eval_runtime": 0.5073,
      "eval_samples_per_second": 98.556,
      "eval_steps_per_second": 98.556,
      "step": 1
    },
    {
      "epoch": 0.00857449088960343,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 16.1876,
      "step": 2
    },
    {
      "epoch": 0.012861736334405145,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 16.0269,
      "step": 3
    },
    {
      "epoch": 0.012861736334405145,
      "eval_loss": 16.551647186279297,
      "eval_runtime": 0.492,
      "eval_samples_per_second": 101.631,
      "eval_steps_per_second": 101.631,
      "step": 3
    },
    {
      "epoch": 0.01714898177920686,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 17.5816,
      "step": 4
    },
    {
      "epoch": 0.021436227224008574,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 16.6133,
      "step": 5
    },
    {
      "epoch": 0.02572347266881029,
      "grad_norm": 18.79177474975586,
      "learning_rate": 2e-05,
      "loss": 17.427,
      "step": 6
    },
    {
      "epoch": 0.02572347266881029,
      "eval_loss": 16.551647186279297,
      "eval_runtime": 0.4925,
      "eval_samples_per_second": 101.517,
      "eval_steps_per_second": 101.517,
      "step": 6
    },
    {
      "epoch": 0.030010718113612004,
      "grad_norm": 17.39157485961914,
      "learning_rate": 4e-05,
      "loss": 17.1975,
      "step": 7
    },
    {
      "epoch": 0.03429796355841372,
      "grad_norm": 18.5988826751709,
      "learning_rate": 6e-05,
      "loss": 16.2112,
      "step": 8
    },
    {
      "epoch": 0.03858520900321544,
      "grad_norm": 19.167139053344727,
      "learning_rate": 8e-05,
      "loss": 17.2223,
      "step": 9
    },
    {
      "epoch": 0.03858520900321544,
      "eval_loss": 16.201391220092773,
      "eval_runtime": 0.4652,
      "eval_samples_per_second": 107.473,
      "eval_steps_per_second": 107.473,
      "step": 9
    },
    {
      "epoch": 0.04287245444801715,
      "grad_norm": 17.39168930053711,
      "learning_rate": 0.0001,
      "loss": 15.691,
      "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": 43272886026240.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}