checkpoint-100/trainer_state.json

{
  "best_metric": 1.173593521118164,
  "best_model_checkpoint": "/kaggle/working/checkpoint-90",
  "epoch": 11.11111111111111,
  "eval_steps": 10,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.022457197308540344,
      "learning_rate": 0.0001925925925925926,
      "loss": 2.0406,
      "step": 10
    },
    {
      "epoch": 1.1111111111111112,
      "eval_loss": 1.729261875152588,
      "eval_runtime": 34.8953,
      "eval_samples_per_second": 1.032,
      "eval_steps_per_second": 0.143,
      "step": 10
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.018787898123264313,
      "learning_rate": 0.0001851851851851852,
      "loss": 1.6016,
      "step": 20
    },
    {
      "epoch": 2.2222222222222223,
      "eval_loss": 1.5362553596496582,
      "eval_runtime": 34.8752,
      "eval_samples_per_second": 1.032,
      "eval_steps_per_second": 0.143,
      "step": 20
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.021070128306746483,
      "learning_rate": 0.00017777777777777779,
      "loss": 1.3937,
      "step": 30
    },
    {
      "epoch": 3.3333333333333335,
      "eval_loss": 1.4144253730773926,
      "eval_runtime": 34.9429,
      "eval_samples_per_second": 1.03,
      "eval_steps_per_second": 0.143,
      "step": 30
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.037991978228092194,
      "learning_rate": 0.00017037037037037037,
      "loss": 1.2721,
      "step": 40
    },
    {
      "epoch": 4.444444444444445,
      "eval_loss": 1.3360365629196167,
      "eval_runtime": 34.8947,
      "eval_samples_per_second": 1.032,
      "eval_steps_per_second": 0.143,
      "step": 40
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 0.029117526486516,
      "learning_rate": 0.00016296296296296295,
      "loss": 1.1384,
      "step": 50
    },
    {
      "epoch": 5.555555555555555,
      "eval_loss": 1.2785382270812988,
      "eval_runtime": 34.8447,
      "eval_samples_per_second": 1.033,
      "eval_steps_per_second": 0.143,
      "step": 50
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.0317281112074852,
      "learning_rate": 0.00015555555555555556,
      "loss": 1.0023,
      "step": 60
    },
    {
      "epoch": 6.666666666666667,
      "eval_loss": 1.2417998313903809,
      "eval_runtime": 34.8141,
      "eval_samples_per_second": 1.034,
      "eval_steps_per_second": 0.144,
      "step": 60
    },
    {
      "epoch": 7.777777777777778,
      "grad_norm": 0.034914035350084305,
      "learning_rate": 0.00014814814814814815,
      "loss": 0.9166,
      "step": 70
    },
    {
      "epoch": 7.777777777777778,
      "eval_loss": 1.2166908979415894,
      "eval_runtime": 34.8956,
      "eval_samples_per_second": 1.032,
      "eval_steps_per_second": 0.143,
      "step": 70
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 0.04872061312198639,
      "learning_rate": 0.00014074074074074076,
      "loss": 0.7726,
      "step": 80
    },
    {
      "epoch": 8.88888888888889,
      "eval_loss": 1.19890296459198,
      "eval_runtime": 34.8433,
      "eval_samples_per_second": 1.033,
      "eval_steps_per_second": 0.143,
      "step": 80
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.04901803284883499,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.676,
      "step": 90
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.173593521118164,
      "eval_runtime": 34.7999,
      "eval_samples_per_second": 1.034,
      "eval_steps_per_second": 0.144,
      "step": 90
    },
    {
      "epoch": 11.11111111111111,
      "grad_norm": 0.055481575429439545,
      "learning_rate": 0.00012592592592592592,
      "loss": 0.56,
      "step": 100
    },
    {
      "epoch": 11.11111111111111,
      "eval_loss": 1.2059063911437988,
      "eval_runtime": 34.8432,
      "eval_samples_per_second": 1.033,
      "eval_steps_per_second": 0.143,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 270,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6718311886422016e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}