last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00031196381219778506,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.119638121977851e-05,
      "grad_norm": 0.23111587762832642,
      "learning_rate": 2e-05,
      "loss": 8.5193,
      "step": 1
    },
    {
      "epoch": 3.119638121977851e-05,
      "eval_loss": 2.0701801776885986,
      "eval_runtime": 1109.5498,
      "eval_samples_per_second": 12.164,
      "eval_steps_per_second": 6.083,
      "step": 1
    },
    {
      "epoch": 6.239276243955701e-05,
      "grad_norm": 0.28426310420036316,
      "learning_rate": 4e-05,
      "loss": 7.712,
      "step": 2
    },
    {
      "epoch": 9.358914365933551e-05,
      "grad_norm": 0.3509170711040497,
      "learning_rate": 6e-05,
      "loss": 7.9013,
      "step": 3
    },
    {
      "epoch": 9.358914365933551e-05,
      "eval_loss": 2.0701029300689697,
      "eval_runtime": 1109.0501,
      "eval_samples_per_second": 12.17,
      "eval_steps_per_second": 6.085,
      "step": 3
    },
    {
      "epoch": 0.00012478552487911403,
      "grad_norm": 0.2368977963924408,
      "learning_rate": 8e-05,
      "loss": 7.9581,
      "step": 4
    },
    {
      "epoch": 0.00015598190609889253,
      "grad_norm": 0.2663523256778717,
      "learning_rate": 0.0001,
      "loss": 8.0291,
      "step": 5
    },
    {
      "epoch": 0.00018717828731867103,
      "grad_norm": 0.3481164872646332,
      "learning_rate": 0.00012,
      "loss": 8.4042,
      "step": 6
    },
    {
      "epoch": 0.00018717828731867103,
      "eval_loss": 2.069063663482666,
      "eval_runtime": 1110.048,
      "eval_samples_per_second": 12.159,
      "eval_steps_per_second": 6.08,
      "step": 6
    },
    {
      "epoch": 0.00021837466853844953,
      "grad_norm": 0.28629568219184875,
      "learning_rate": 0.00014,
      "loss": 8.3721,
      "step": 7
    },
    {
      "epoch": 0.00024957104975822806,
      "grad_norm": 0.3808829188346863,
      "learning_rate": 0.00016,
      "loss": 8.4298,
      "step": 8
    },
    {
      "epoch": 0.00028076743097800656,
      "grad_norm": 0.3027486503124237,
      "learning_rate": 0.00018,
      "loss": 7.6258,
      "step": 9
    },
    {
      "epoch": 0.00028076743097800656,
      "eval_loss": 2.063856601715088,
      "eval_runtime": 1109.5521,
      "eval_samples_per_second": 12.164,
      "eval_steps_per_second": 6.083,
      "step": 9
    },
    {
      "epoch": 0.00031196381219778506,
      "grad_norm": 0.3592076301574707,
      "learning_rate": 0.0002,
      "loss": 7.9813,
      "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": 6174137395445760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}