last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12361178174794785,
  "eval_steps": 8,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00772573635924674,
      "grad_norm": 0.0652494952082634,
      "learning_rate": 1e-05,
      "loss": 11.9262,
      "step": 1
    },
    {
      "epoch": 0.00772573635924674,
      "eval_loss": 11.928458213806152,
      "eval_runtime": 16.6092,
      "eval_samples_per_second": 13.185,
      "eval_steps_per_second": 6.623,
      "step": 1
    },
    {
      "epoch": 0.01545147271849348,
      "grad_norm": 0.07395407557487488,
      "learning_rate": 2e-05,
      "loss": 11.9359,
      "step": 2
    },
    {
      "epoch": 0.02317720907774022,
      "grad_norm": 0.06961611658334732,
      "learning_rate": 3e-05,
      "loss": 11.9329,
      "step": 3
    },
    {
      "epoch": 0.03090294543698696,
      "grad_norm": 0.06199463829398155,
      "learning_rate": 4e-05,
      "loss": 11.9383,
      "step": 4
    },
    {
      "epoch": 0.0386286817962337,
      "grad_norm": 0.07943562418222427,
      "learning_rate": 5e-05,
      "loss": 11.9162,
      "step": 5
    },
    {
      "epoch": 0.04635441815548044,
      "grad_norm": 0.06378127634525299,
      "learning_rate": 6e-05,
      "loss": 11.9223,
      "step": 6
    },
    {
      "epoch": 0.05408015451472718,
      "grad_norm": 0.07464384287595749,
      "learning_rate": 7e-05,
      "loss": 11.9215,
      "step": 7
    },
    {
      "epoch": 0.06180589087397392,
      "grad_norm": 0.0745854601264,
      "learning_rate": 8e-05,
      "loss": 11.9247,
      "step": 8
    },
    {
      "epoch": 0.06180589087397392,
      "eval_loss": 11.92805004119873,
      "eval_runtime": 1.0766,
      "eval_samples_per_second": 203.416,
      "eval_steps_per_second": 102.172,
      "step": 8
    },
    {
      "epoch": 0.06953162723322066,
      "grad_norm": 0.09723018854856491,
      "learning_rate": 9e-05,
      "loss": 11.9271,
      "step": 9
    },
    {
      "epoch": 0.0772573635924674,
      "grad_norm": 0.06599853187799454,
      "learning_rate": 0.0001,
      "loss": 11.9294,
      "step": 10
    },
    {
      "epoch": 0.08498309995171414,
      "grad_norm": 0.08143449574708939,
      "learning_rate": 9.938441702975689e-05,
      "loss": 11.9204,
      "step": 11
    },
    {
      "epoch": 0.09270883631096088,
      "grad_norm": 0.06527712196111679,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.9218,
      "step": 12
    },
    {
      "epoch": 0.10043457267020763,
      "grad_norm": 0.04510502144694328,
      "learning_rate": 9.45503262094184e-05,
      "loss": 11.932,
      "step": 13
    },
    {
      "epoch": 0.10816030902945437,
      "grad_norm": 0.0751844048500061,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.9265,
      "step": 14
    },
    {
      "epoch": 0.1158860453887011,
      "grad_norm": 0.05361689627170563,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9278,
      "step": 15
    },
    {
      "epoch": 0.12361178174794785,
      "grad_norm": 0.09501861780881882,
      "learning_rate": 7.938926261462366e-05,
      "loss": 11.9095,
      "step": 16
    },
    {
      "epoch": 0.12361178174794785,
      "eval_loss": 11.927022933959961,
      "eval_runtime": 1.0762,
      "eval_samples_per_second": 203.491,
      "eval_steps_per_second": 102.21,
      "step": 16
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 8,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 95932121088.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}