last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02702702702702703,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002702702702702703,
      "grad_norm": 0.2378644198179245,
      "learning_rate": 2e-05,
      "loss": 2.4235,
      "step": 1
    },
    {
      "epoch": 0.002702702702702703,
      "eval_loss": 2.200819492340088,
      "eval_runtime": 23.968,
      "eval_samples_per_second": 3.254,
      "eval_steps_per_second": 3.254,
      "step": 1
    },
    {
      "epoch": 0.005405405405405406,
      "grad_norm": 0.2817547917366028,
      "learning_rate": 4e-05,
      "loss": 2.2166,
      "step": 2
    },
    {
      "epoch": 0.008108108108108109,
      "grad_norm": 0.22646959125995636,
      "learning_rate": 6e-05,
      "loss": 2.6545,
      "step": 3
    },
    {
      "epoch": 0.008108108108108109,
      "eval_loss": 2.1994752883911133,
      "eval_runtime": 23.8826,
      "eval_samples_per_second": 3.266,
      "eval_steps_per_second": 3.266,
      "step": 3
    },
    {
      "epoch": 0.010810810810810811,
      "grad_norm": 0.25837552547454834,
      "learning_rate": 8e-05,
      "loss": 2.625,
      "step": 4
    },
    {
      "epoch": 0.013513513513513514,
      "grad_norm": 0.3031831681728363,
      "learning_rate": 0.0001,
      "loss": 2.0932,
      "step": 5
    },
    {
      "epoch": 0.016216216216216217,
      "grad_norm": 0.24016548693180084,
      "learning_rate": 0.00012,
      "loss": 2.3491,
      "step": 6
    },
    {
      "epoch": 0.016216216216216217,
      "eval_loss": 2.193232774734497,
      "eval_runtime": 23.9312,
      "eval_samples_per_second": 3.259,
      "eval_steps_per_second": 3.259,
      "step": 6
    },
    {
      "epoch": 0.01891891891891892,
      "grad_norm": 0.24453988671302795,
      "learning_rate": 0.00014,
      "loss": 2.0364,
      "step": 7
    },
    {
      "epoch": 0.021621621621621623,
      "grad_norm": 0.3633563816547394,
      "learning_rate": 0.00016,
      "loss": 2.0773,
      "step": 8
    },
    {
      "epoch": 0.024324324324324326,
      "grad_norm": 0.29696428775787354,
      "learning_rate": 0.00018,
      "loss": 2.3294,
      "step": 9
    },
    {
      "epoch": 0.024324324324324326,
      "eval_loss": 2.1837782859802246,
      "eval_runtime": 24.0965,
      "eval_samples_per_second": 3.237,
      "eval_steps_per_second": 3.237,
      "step": 9
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 0.26503047347068787,
      "learning_rate": 0.0002,
      "loss": 2.1022,
      "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": 3467932965273600.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}