last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25252525252525254,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016835016835016834,
      "eval_loss": 0.1869848221540451,
      "eval_runtime": 6.0667,
      "eval_samples_per_second": 20.604,
      "eval_steps_per_second": 10.384,
      "step": 1
    },
    {
      "epoch": 0.016835016835016835,
      "grad_norm": 0.0014907927252352238,
      "learning_rate": 0.0002,
      "loss": 0.0694,
      "step": 10
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 0.0010236403904855251,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 0.00038739299634471536,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 8.558121771784499e-05,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.08417508417508418,
      "grad_norm": 8.605782932136208e-05,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.08417508417508418,
      "eval_loss": 8.993897040454613e-07,
      "eval_runtime": 5.0388,
      "eval_samples_per_second": 24.808,
      "eval_steps_per_second": 12.503,
      "step": 50
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 3.201066283509135e-05,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.11784511784511785,
      "grad_norm": 2.310053605469875e-05,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 1.7268168448936194e-05,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 1.6050498743425123e-05,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 1.2347415577096399e-05,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.16835016835016836,
      "eval_loss": 2.861329164716153e-07,
      "eval_runtime": 5.086,
      "eval_samples_per_second": 24.577,
      "eval_steps_per_second": 12.387,
      "step": 100
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.0527721315156668e-05,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 9.965347999241203e-06,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.21885521885521886,
      "grad_norm": 9.623281584936194e-06,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 8.889406672096811e-06,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 8.956275451055262e-06,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.25252525252525254,
      "eval_loss": 1.7172290256439737e-07,
      "eval_runtime": 5.0926,
      "eval_samples_per_second": 24.545,
      "eval_steps_per_second": 12.371,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.59919424667648e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}