expC/gsm8k/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.8,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.4214686155319214,
      "learning_rate": 1e-05,
      "loss": 17.7087,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4086034297943115,
      "learning_rate": 1e-05,
      "loss": 17.5413,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.4138821363449097,
      "learning_rate": 1e-05,
      "loss": 17.7531,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.3965802192687988,
      "learning_rate": 1e-05,
      "loss": 17.5294,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4018938541412354,
      "learning_rate": 1e-05,
      "loss": 17.7374,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.1549352407455444,
      "learning_rate": 1e-05,
      "loss": 17.7056,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.2719894647598267,
      "learning_rate": 1e-05,
      "loss": 17.7976,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.3657876253128052,
      "learning_rate": 1e-05,
      "loss": 18.0324,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.3647119998931885,
      "learning_rate": 1e-05,
      "loss": 18.1207,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.3407888412475586,
      "learning_rate": 1e-05,
      "loss": 18.559,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.1251682043075562,
      "learning_rate": 1e-05,
      "loss": 18.7872,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.277592420578003,
      "learning_rate": 1e-05,
      "loss": 18.9959,
      "step": 600
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}