checkpoint-60/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 54.002506256103516,
      "learning_rate": 0.00019,
      "loss": 1.1516,
      "step": 10
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 94.82562255859375,
      "learning_rate": 0.0001788888888888889,
      "loss": 0.7908,
      "step": 20
    },
    {
      "epoch": 0.5,
      "grad_norm": 59.41981506347656,
      "learning_rate": 0.0001677777777777778,
      "loss": 0.9385,
      "step": 30
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 52.318058013916016,
      "learning_rate": 0.00015666666666666666,
      "loss": 0.7055,
      "step": 40
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 23.831907272338867,
      "learning_rate": 0.00014555555555555556,
      "loss": 0.5176,
      "step": 50
    },
    {
      "epoch": 1.0,
      "grad_norm": 16.34128761291504,
      "learning_rate": 0.00013444444444444447,
      "loss": 0.3808,
      "step": 60
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.37904611229896545,
      "eval_runtime": 112.1148,
      "eval_samples_per_second": 1.07,
      "eval_steps_per_second": 0.268,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 5975284415201280.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}