last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04678362573099415,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004678362573099415,
      "eval_loss": 10.380034446716309,
      "eval_runtime": 0.3461,
      "eval_samples_per_second": 260.048,
      "eval_steps_per_second": 130.024,
      "step": 1
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 0.031849831342697144,
      "learning_rate": 6e-05,
      "loss": 10.379,
      "step": 3
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 0.03441135212779045,
      "learning_rate": 0.00012,
      "loss": 10.38,
      "step": 6
    },
    {
      "epoch": 0.03742690058479532,
      "eval_loss": 10.379748344421387,
      "eval_runtime": 0.3416,
      "eval_samples_per_second": 263.439,
      "eval_steps_per_second": 131.719,
      "step": 8
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.023490067571401596,
      "learning_rate": 0.00018,
      "loss": 10.3785,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 261512232960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}