last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00019196928491441368,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.1329920546045965e-05,
      "grad_norm": 0.01398987602442503,
      "learning_rate": 2e-05,
      "loss": 11.9347,
      "step": 1
    },
    {
      "epoch": 2.1329920546045965e-05,
      "eval_loss": 11.931791305541992,
      "eval_runtime": 121.0916,
      "eval_samples_per_second": 163.017,
      "eval_steps_per_second": 81.509,
      "step": 1
    },
    {
      "epoch": 4.265984109209193e-05,
      "grad_norm": 0.015205233357846737,
      "learning_rate": 4e-05,
      "loss": 11.9296,
      "step": 2
    },
    {
      "epoch": 6.39897616381379e-05,
      "grad_norm": 0.022257650271058083,
      "learning_rate": 6e-05,
      "loss": 11.9326,
      "step": 3
    },
    {
      "epoch": 6.39897616381379e-05,
      "eval_loss": 11.931781768798828,
      "eval_runtime": 121.305,
      "eval_samples_per_second": 162.73,
      "eval_steps_per_second": 81.365,
      "step": 3
    },
    {
      "epoch": 8.531968218418386e-05,
      "grad_norm": 0.01359029021114111,
      "learning_rate": 8e-05,
      "loss": 11.9345,
      "step": 4
    },
    {
      "epoch": 0.00010664960273022984,
      "grad_norm": 0.01420881599187851,
      "learning_rate": 0.0001,
      "loss": 11.9364,
      "step": 5
    },
    {
      "epoch": 0.0001279795232762758,
      "grad_norm": 0.011488054879009724,
      "learning_rate": 0.00012,
      "loss": 11.9313,
      "step": 6
    },
    {
      "epoch": 0.0001279795232762758,
      "eval_loss": 11.931743621826172,
      "eval_runtime": 121.6631,
      "eval_samples_per_second": 162.251,
      "eval_steps_per_second": 81.126,
      "step": 6
    },
    {
      "epoch": 0.00014930944382232175,
      "grad_norm": 0.01305566169321537,
      "learning_rate": 0.00014,
      "loss": 11.9362,
      "step": 7
    },
    {
      "epoch": 0.00017063936436836772,
      "grad_norm": 0.013313014060258865,
      "learning_rate": 0.00016,
      "loss": 11.9296,
      "step": 8
    },
    {
      "epoch": 0.00019196928491441368,
      "grad_norm": 0.012543230317533016,
      "learning_rate": 0.00018,
      "loss": 11.9292,
      "step": 9
    },
    {
      "epoch": 0.00019196928491441368,
      "eval_loss": 11.931682586669922,
      "eval_runtime": 121.6197,
      "eval_samples_per_second": 162.309,
      "eval_steps_per_second": 81.155,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2126905344.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}