checkpoint-52/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 52,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1927710843373494,
      "grad_norm": 95.26730346679688,
      "learning_rate": 0.0004180909090909091,
      "loss": 22.4465,
      "mean_token_accuracy": 0.08969678990542888,
      "num_tokens": 1310720.0,
      "step": 10
    },
    {
      "epoch": 0.3855421686746988,
      "grad_norm": 0.0,
      "learning_rate": 0.0005103526968014265,
      "loss": 0.8012,
      "mean_token_accuracy": 0.13804710581898688,
      "num_tokens": 2621440.0,
      "step": 20
    },
    {
      "epoch": 0.5783132530120482,
      "grad_norm": 0.0,
      "learning_rate": 0.0005077286477833616,
      "loss": 452.9577,
      "mean_token_accuracy": 0.05160275483503938,
      "num_tokens": 3932160.0,
      "step": 30
    },
    {
      "epoch": 0.7710843373493976,
      "grad_norm": 0.0,
      "learning_rate": 0.0005031081504278389,
      "loss": 470.5136,
      "mean_token_accuracy": 0.03822226445190609,
      "num_tokens": 5242880.0,
      "step": 40
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 26.303752899169922,
      "learning_rate": 0.0004965277770447238,
      "loss": 167.1384,
      "mean_token_accuracy": 0.057517293840646744,
      "num_tokens": 6553600.0,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_loss": NaN,
      "eval_mean_token_accuracy": 0.13677339731378757,
      "eval_num_tokens": 6713344.0,
      "eval_runtime": 8.9806,
      "eval_samples_per_second": 41.089,
      "eval_steps_per_second": 5.233,
      "step": 52
    }
  ],
  "logging_steps": 10,
  "max_steps": 364,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.950418957829407e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}