last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009212290139896894,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.3621256768966393e-05,
      "eval_loss": 2.5973010063171387,
      "eval_runtime": 1087.6377,
      "eval_samples_per_second": 16.39,
      "eval_steps_per_second": 8.195,
      "step": 1
    },
    {
      "epoch": 0.00011810628384483197,
      "grad_norm": 1.0713368654251099,
      "learning_rate": 5e-05,
      "loss": 2.5569,
      "step": 5
    },
    {
      "epoch": 0.00023621256768966393,
      "grad_norm": 1.5047534704208374,
      "learning_rate": 0.0001,
      "loss": 2.5144,
      "step": 10
    },
    {
      "epoch": 0.00023621256768966393,
      "eval_loss": 2.4695518016815186,
      "eval_runtime": 1090.9228,
      "eval_samples_per_second": 16.34,
      "eval_steps_per_second": 8.17,
      "step": 10
    },
    {
      "epoch": 0.0003543188515344959,
      "grad_norm": 1.2811824083328247,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.4537,
      "step": 15
    },
    {
      "epoch": 0.00047242513537932787,
      "grad_norm": 1.3264565467834473,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.1594,
      "step": 20
    },
    {
      "epoch": 0.00047242513537932787,
      "eval_loss": 2.0356850624084473,
      "eval_runtime": 1094.5602,
      "eval_samples_per_second": 16.286,
      "eval_steps_per_second": 8.143,
      "step": 20
    },
    {
      "epoch": 0.0005905314192241598,
      "grad_norm": 1.7341872453689575,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.0475,
      "step": 25
    },
    {
      "epoch": 0.0007086377030689918,
      "grad_norm": 1.5635089874267578,
      "learning_rate": 5e-05,
      "loss": 1.9059,
      "step": 30
    },
    {
      "epoch": 0.0007086377030689918,
      "eval_loss": 1.9371638298034668,
      "eval_runtime": 1091.4736,
      "eval_samples_per_second": 16.332,
      "eval_steps_per_second": 8.166,
      "step": 30
    },
    {
      "epoch": 0.0008267439869138238,
      "grad_norm": 1.4265427589416504,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.9827,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6109362554142720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}