trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 24.8895814604259,
      "learning_rate": 1e-05,
      "loss": 0.9347,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 10.507921581694449,
      "learning_rate": 9.330127018922195e-06,
      "loss": 1.0402,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.750956118106842,
      "eval_runtime": 13.4777,
      "eval_samples_per_second": 19.514,
      "eval_steps_per_second": 0.371,
      "step": 5
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.2842066334321927,
      "learning_rate": 6.913417161825449e-06,
      "loss": 0.691,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5700622200965881,
      "eval_runtime": 13.3794,
      "eval_samples_per_second": 19.657,
      "eval_steps_per_second": 0.374,
      "step": 10
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.0707933492232007,
      "learning_rate": 3.705904774487396e-06,
      "loss": 0.5239,
      "step": 15
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.426382839679718,
      "eval_runtime": 13.3851,
      "eval_samples_per_second": 19.649,
      "eval_steps_per_second": 0.374,
      "step": 15
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.1454642852295103,
      "learning_rate": 1.0332332985438248e-06,
      "loss": 0.3917,
      "step": 20
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.33590540289878845,
      "eval_runtime": 13.3827,
      "eval_samples_per_second": 19.652,
      "eval_steps_per_second": 0.374,
      "step": 20
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.732790702100083,
      "learning_rate": 0.0,
      "loss": 0.3221,
      "step": 25
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.31167706847190857,
      "eval_runtime": 13.3175,
      "eval_samples_per_second": 19.749,
      "eval_steps_per_second": 0.375,
      "step": 25
    },
    {
      "epoch": 5.0,
      "step": 25,
      "total_flos": 10468982784000.0,
      "train_loss": 0.5895810270309448,
      "train_runtime": 388.4587,
      "train_samples_per_second": 3.385,
      "train_steps_per_second": 0.064
    }
  ],
  "logging_steps": 5,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 10468982784000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}