last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015789058182679404,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015789058182679404,
      "grad_norm": 0.3037138879299164,
      "learning_rate": 2e-05,
      "loss": 1.0644,
      "step": 1
    },
    {
      "epoch": 0.0003157811636535881,
      "grad_norm": 0.2807854413986206,
      "learning_rate": 4e-05,
      "loss": 0.9028,
      "step": 2
    },
    {
      "epoch": 0.0004736717454803821,
      "grad_norm": 0.29301321506500244,
      "learning_rate": 6e-05,
      "loss": 1.0961,
      "step": 3
    },
    {
      "epoch": 0.0004736717454803821,
      "eval_loss": 1.0998167991638184,
      "eval_runtime": 95.5547,
      "eval_samples_per_second": 27.911,
      "eval_steps_per_second": 13.961,
      "step": 3
    },
    {
      "epoch": 0.0006315623273071762,
      "grad_norm": 0.21612311899662018,
      "learning_rate": 8e-05,
      "loss": 1.0022,
      "step": 4
    },
    {
      "epoch": 0.0007894529091339702,
      "grad_norm": 0.3548424541950226,
      "learning_rate": 0.0001,
      "loss": 1.4068,
      "step": 5
    },
    {
      "epoch": 0.0009473434909607642,
      "grad_norm": 0.2541038393974304,
      "learning_rate": 0.00012,
      "loss": 1.0515,
      "step": 6
    },
    {
      "epoch": 0.0009473434909607642,
      "eval_loss": 1.0915995836257935,
      "eval_runtime": 99.2772,
      "eval_samples_per_second": 26.864,
      "eval_steps_per_second": 13.437,
      "step": 6
    },
    {
      "epoch": 0.0011052340727875582,
      "grad_norm": 0.26632893085479736,
      "learning_rate": 0.00014,
      "loss": 0.9681,
      "step": 7
    },
    {
      "epoch": 0.0012631246546143523,
      "grad_norm": 0.28235024213790894,
      "learning_rate": 0.00016,
      "loss": 1.0387,
      "step": 8
    },
    {
      "epoch": 0.0014210152364411463,
      "grad_norm": 0.45062515139579773,
      "learning_rate": 0.00018,
      "loss": 1.215,
      "step": 9
    },
    {
      "epoch": 0.0014210152364411463,
      "eval_loss": 1.0538045167922974,
      "eval_runtime": 92.7417,
      "eval_samples_per_second": 28.757,
      "eval_steps_per_second": 14.384,
      "step": 9
    },
    {
      "epoch": 0.0015789058182679404,
      "grad_norm": 0.32025063037872314,
      "learning_rate": 0.0002,
      "loss": 0.9243,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 390082766831616.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}