last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017139429257005741,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001713942925700574,
      "grad_norm": 0.7288455367088318,
      "learning_rate": 2e-05,
      "loss": 5.2217,
      "step": 1
    },
    {
      "epoch": 0.0001713942925700574,
      "eval_loss": 1.2500425577163696,
      "eval_runtime": 160.3308,
      "eval_samples_per_second": 15.325,
      "eval_steps_per_second": 7.665,
      "step": 1
    },
    {
      "epoch": 0.0003427885851401148,
      "grad_norm": 0.5146114826202393,
      "learning_rate": 4e-05,
      "loss": 5.07,
      "step": 2
    },
    {
      "epoch": 0.0005141828777101723,
      "grad_norm": 0.7018376588821411,
      "learning_rate": 6e-05,
      "loss": 4.7617,
      "step": 3
    },
    {
      "epoch": 0.0005141828777101723,
      "eval_loss": 1.2494888305664062,
      "eval_runtime": 160.2774,
      "eval_samples_per_second": 15.33,
      "eval_steps_per_second": 7.668,
      "step": 3
    },
    {
      "epoch": 0.0006855771702802296,
      "grad_norm": 0.5810421109199524,
      "learning_rate": 8e-05,
      "loss": 4.1974,
      "step": 4
    },
    {
      "epoch": 0.0008569714628502871,
      "grad_norm": 0.9707323312759399,
      "learning_rate": 0.0001,
      "loss": 4.4864,
      "step": 5
    },
    {
      "epoch": 0.0010283657554203446,
      "grad_norm": 0.7004103660583496,
      "learning_rate": 0.00012,
      "loss": 4.6663,
      "step": 6
    },
    {
      "epoch": 0.0010283657554203446,
      "eval_loss": 1.245200514793396,
      "eval_runtime": 160.4134,
      "eval_samples_per_second": 15.317,
      "eval_steps_per_second": 7.661,
      "step": 6
    },
    {
      "epoch": 0.0011997600479904018,
      "grad_norm": 0.6433274149894714,
      "learning_rate": 0.00014,
      "loss": 4.9182,
      "step": 7
    },
    {
      "epoch": 0.0013711543405604593,
      "grad_norm": 0.6342811584472656,
      "learning_rate": 0.00016,
      "loss": 4.8562,
      "step": 8
    },
    {
      "epoch": 0.0015425486331305167,
      "grad_norm": 0.8066439032554626,
      "learning_rate": 0.00018,
      "loss": 4.2763,
      "step": 9
    },
    {
      "epoch": 0.0015425486331305167,
      "eval_loss": 1.21627676486969,
      "eval_runtime": 160.4101,
      "eval_samples_per_second": 15.317,
      "eval_steps_per_second": 7.662,
      "step": 9
    },
    {
      "epoch": 0.0017139429257005741,
      "grad_norm": 1.0727403163909912,
      "learning_rate": 0.0002,
      "loss": 5.0417,
      "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": 4246709207040000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}