checkpoint-10/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.032,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032,
      "grad_norm": 0.48788756132125854,
      "learning_rate": 1e-05,
      "loss": 2.1278,
      "step": 1
    },
    {
      "epoch": 0.0064,
      "grad_norm": 0.5204982161521912,
      "learning_rate": 8.888888888888888e-06,
      "loss": 1.9334,
      "step": 2
    },
    {
      "epoch": 0.0096,
      "grad_norm": 0.4236851930618286,
      "learning_rate": 7.77777777777778e-06,
      "loss": 1.9925,
      "step": 3
    },
    {
      "epoch": 0.0128,
      "grad_norm": 0.43057286739349365,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.9375,
      "step": 4
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.4727758765220642,
      "learning_rate": 5.555555555555557e-06,
      "loss": 2.0073,
      "step": 5
    },
    {
      "epoch": 0.016,
      "eval_loss": 1.959301233291626,
      "eval_runtime": 3474.2308,
      "eval_samples_per_second": 0.288,
      "eval_steps_per_second": 0.144,
      "step": 5
    },
    {
      "epoch": 0.0192,
      "grad_norm": 0.5164967775344849,
      "learning_rate": 4.444444444444444e-06,
      "loss": 2.047,
      "step": 6
    },
    {
      "epoch": 0.0224,
      "grad_norm": 0.5229511260986328,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.9692,
      "step": 7
    },
    {
      "epoch": 0.0256,
      "grad_norm": 0.5437039136886597,
      "learning_rate": 2.222222222222222e-06,
      "loss": 2.0288,
      "step": 8
    },
    {
      "epoch": 0.0288,
      "grad_norm": 0.566317081451416,
      "learning_rate": 1.111111111111111e-06,
      "loss": 1.8071,
      "step": 9
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.6055211424827576,
      "learning_rate": 0.0,
      "loss": 1.8889,
      "step": 10
    },
    {
      "epoch": 0.032,
      "eval_loss": 1.9509223699569702,
      "eval_runtime": 3416.6549,
      "eval_samples_per_second": 0.293,
      "eval_steps_per_second": 0.146,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.663173528190976e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}