trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 7.872949600219727,
      "learning_rate": 4e-05,
      "loss": 0.7355,
      "step": 4
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 14.582996368408203,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 1.5402,
      "step": 8
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 3.2852540016174316,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 0.8569,
      "step": 12
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.19074285030365,
      "learning_rate": 4.123620120825459e-05,
      "loss": 0.6691,
      "step": 16
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.3106497526168823,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.6102,
      "step": 20
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.5743669867515564,
      "learning_rate": 2.6961477393196126e-05,
      "loss": 0.5809,
      "step": 24
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.40740063786506653,
      "learning_rate": 1.9163865903602374e-05,
      "loss": 0.5609,
      "step": 28
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.33093440532684326,
      "learning_rate": 1.1937535882101281e-05,
      "loss": 0.5423,
      "step": 32
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.26830199360847473,
      "learning_rate": 5.989850859999227e-06,
      "loss": 0.5396,
      "step": 36
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.22767265141010284,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.5399,
      "step": 40
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.19699975848197937,
      "learning_rate": 7.706665667180091e-08,
      "loss": 0.5329,
      "step": 44
    },
    {
      "epoch": 1.0,
      "step": 45,
      "total_flos": 5.3119016276852736e+17,
      "train_loss": 0.0,
      "train_runtime": 10.4657,
      "train_samples_per_second": 275.186,
      "train_steps_per_second": 4.3
    }
  ],
  "logging_steps": 4,
  "max_steps": 45,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 4,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.3119016276852736e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}