last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00023621256768966393,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.3621256768966393e-05,
      "grad_norm": 0.9869203567504883,
      "learning_rate": 2e-05,
      "loss": 2.5605,
      "step": 1
    },
    {
      "epoch": 2.3621256768966393e-05,
      "eval_loss": 2.5971951484680176,
      "eval_runtime": 925.9517,
      "eval_samples_per_second": 19.252,
      "eval_steps_per_second": 9.626,
      "step": 1
    },
    {
      "epoch": 4.7242513537932786e-05,
      "grad_norm": 1.456836223602295,
      "learning_rate": 4e-05,
      "loss": 2.3873,
      "step": 2
    },
    {
      "epoch": 7.086377030689917e-05,
      "grad_norm": 0.9866998195648193,
      "learning_rate": 6e-05,
      "loss": 2.5667,
      "step": 3
    },
    {
      "epoch": 7.086377030689917e-05,
      "eval_loss": 2.592090129852295,
      "eval_runtime": 925.5105,
      "eval_samples_per_second": 19.261,
      "eval_steps_per_second": 9.63,
      "step": 3
    },
    {
      "epoch": 9.448502707586557e-05,
      "grad_norm": 1.2852237224578857,
      "learning_rate": 8e-05,
      "loss": 2.7288,
      "step": 4
    },
    {
      "epoch": 0.00011810628384483197,
      "grad_norm": 1.0875444412231445,
      "learning_rate": 0.0001,
      "loss": 2.5297,
      "step": 5
    },
    {
      "epoch": 0.00014172754061379835,
      "grad_norm": 1.081312656402588,
      "learning_rate": 0.00012,
      "loss": 2.3429,
      "step": 6
    },
    {
      "epoch": 0.00014172754061379835,
      "eval_loss": 2.5326483249664307,
      "eval_runtime": 926.1561,
      "eval_samples_per_second": 19.247,
      "eval_steps_per_second": 9.624,
      "step": 6
    },
    {
      "epoch": 0.00016534879738276475,
      "grad_norm": 1.1779303550720215,
      "learning_rate": 0.00014,
      "loss": 2.4194,
      "step": 7
    },
    {
      "epoch": 0.00018897005415173114,
      "grad_norm": 1.2905443906784058,
      "learning_rate": 0.00016,
      "loss": 2.3349,
      "step": 8
    },
    {
      "epoch": 0.00021259131092069754,
      "grad_norm": 1.367085337638855,
      "learning_rate": 0.00018,
      "loss": 2.6235,
      "step": 9
    },
    {
      "epoch": 0.00021259131092069754,
      "eval_loss": 2.3391339778900146,
      "eval_runtime": 926.1708,
      "eval_samples_per_second": 19.247,
      "eval_steps_per_second": 9.623,
      "step": 9
    },
    {
      "epoch": 0.00023621256768966393,
      "grad_norm": 1.6501195430755615,
      "learning_rate": 0.0002,
      "loss": 2.39,
      "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": 1517090030223360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}