last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002158288908553299,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.316577817106598e-05,
      "eval_loss": 2.0471103191375732,
      "eval_runtime": 952.5392,
      "eval_samples_per_second": 10.241,
      "eval_steps_per_second": 5.121,
      "step": 1
    },
    {
      "epoch": 0.00012949733451319794,
      "grad_norm": 8.12905216217041,
      "learning_rate": 6e-05,
      "loss": 8.1991,
      "step": 3
    },
    {
      "epoch": 0.0002589946690263959,
      "grad_norm": 8.616674423217773,
      "learning_rate": 0.00012,
      "loss": 7.7102,
      "step": 6
    },
    {
      "epoch": 0.0003884920035395938,
      "grad_norm": 6.983860492706299,
      "learning_rate": 0.00018,
      "loss": 7.6783,
      "step": 9
    },
    {
      "epoch": 0.0005179893380527918,
      "grad_norm": 8.666030883789062,
      "learning_rate": 0.00019876883405951377,
      "loss": 7.3833,
      "step": 12
    },
    {
      "epoch": 0.0005611551162238577,
      "eval_loss": 1.7469043731689453,
      "eval_runtime": 956.4149,
      "eval_samples_per_second": 10.2,
      "eval_steps_per_second": 5.1,
      "step": 13
    },
    {
      "epoch": 0.0006474866725659897,
      "grad_norm": 4.685945510864258,
      "learning_rate": 0.0001923879532511287,
      "loss": 7.0577,
      "step": 15
    },
    {
      "epoch": 0.0007769840070791876,
      "grad_norm": 5.418538570404053,
      "learning_rate": 0.00018090169943749476,
      "loss": 6.7296,
      "step": 18
    },
    {
      "epoch": 0.0009064813415923856,
      "grad_norm": 3.6164493560791016,
      "learning_rate": 0.00016494480483301836,
      "loss": 6.2438,
      "step": 21
    },
    {
      "epoch": 0.0010359786761055835,
      "grad_norm": 4.651533603668213,
      "learning_rate": 0.00014539904997395468,
      "loss": 6.3792,
      "step": 24
    },
    {
      "epoch": 0.0011223102324477154,
      "eval_loss": 1.5663001537322998,
      "eval_runtime": 956.4981,
      "eval_samples_per_second": 10.199,
      "eval_steps_per_second": 5.1,
      "step": 26
    },
    {
      "epoch": 0.0011654760106187814,
      "grad_norm": 3.52091383934021,
      "learning_rate": 0.00012334453638559057,
      "loss": 6.5441,
      "step": 27
    },
    {
      "epoch": 0.0012949733451319795,
      "grad_norm": 4.742680549621582,
      "learning_rate": 0.0001,
      "loss": 6.3389,
      "step": 30
    },
    {
      "epoch": 0.0014244706796451773,
      "grad_norm": 3.460523843765259,
      "learning_rate": 7.66554636144095e-05,
      "loss": 6.5699,
      "step": 33
    },
    {
      "epoch": 0.0015539680141583752,
      "grad_norm": 2.5011720657348633,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 6.2508,
      "step": 36
    },
    {
      "epoch": 0.0016834653486715733,
      "grad_norm": 3.5199382305145264,
      "learning_rate": 3.5055195166981645e-05,
      "loss": 6.1756,
      "step": 39
    },
    {
      "epoch": 0.0016834653486715733,
      "eval_loss": 1.5250167846679688,
      "eval_runtime": 956.8088,
      "eval_samples_per_second": 10.195,
      "eval_steps_per_second": 5.098,
      "step": 39
    },
    {
      "epoch": 0.0018129626831847711,
      "grad_norm": 3.094237804412842,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 6.1102,
      "step": 42
    },
    {
      "epoch": 0.001942460017697969,
      "grad_norm": 3.035853862762451,
      "learning_rate": 7.612046748871327e-06,
      "loss": 6.36,
      "step": 45
    },
    {
      "epoch": 0.002071957352211167,
      "grad_norm": 2.3664188385009766,
      "learning_rate": 1.231165940486234e-06,
      "loss": 6.046,
      "step": 48
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.63366161088512e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}