last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.017057569296375266,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005685856432125089,
      "eval_loss": 1.1807148456573486,
      "eval_runtime": 151.889,
      "eval_samples_per_second": 4.879,
      "eval_steps_per_second": 2.443,
      "step": 1
    },
    {
      "epoch": 0.0017057569296375266,
      "grad_norm": 2.177881956100464,
      "learning_rate": 3e-05,
      "loss": 1.1351,
      "step": 3
    },
    {
      "epoch": 0.003411513859275053,
      "grad_norm": 2.4825961589813232,
      "learning_rate": 6e-05,
      "loss": 1.059,
      "step": 6
    },
    {
      "epoch": 0.004548685145700071,
      "eval_loss": 1.007865071296692,
      "eval_runtime": 152.549,
      "eval_samples_per_second": 4.857,
      "eval_steps_per_second": 2.432,
      "step": 8
    },
    {
      "epoch": 0.00511727078891258,
      "grad_norm": 1.4245496988296509,
      "learning_rate": 9e-05,
      "loss": 0.9503,
      "step": 9
    },
    {
      "epoch": 0.006823027718550106,
      "grad_norm": 1.2302700281143188,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9584,
      "step": 12
    },
    {
      "epoch": 0.008528784648187633,
      "grad_norm": 1.1729754209518433,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8833,
      "step": 15
    },
    {
      "epoch": 0.009097370291400142,
      "eval_loss": 0.8791064023971558,
      "eval_runtime": 152.5481,
      "eval_samples_per_second": 4.857,
      "eval_steps_per_second": 2.432,
      "step": 16
    },
    {
      "epoch": 0.01023454157782516,
      "grad_norm": 0.9204723238945007,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8179,
      "step": 18
    },
    {
      "epoch": 0.011940298507462687,
      "grad_norm": 1.1938751935958862,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.8799,
      "step": 21
    },
    {
      "epoch": 0.013646055437100213,
      "grad_norm": 0.857722818851471,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8658,
      "step": 24
    },
    {
      "epoch": 0.013646055437100213,
      "eval_loss": 0.8418713212013245,
      "eval_runtime": 152.5492,
      "eval_samples_per_second": 4.857,
      "eval_steps_per_second": 2.432,
      "step": 24
    },
    {
      "epoch": 0.01535181236673774,
      "grad_norm": 0.9830237627029419,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.8299,
      "step": 27
    },
    {
      "epoch": 0.017057569296375266,
      "grad_norm": 1.1891757249832153,
      "learning_rate": 0.0,
      "loss": 0.8234,
      "step": 30
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7434351163670528e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}