trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.719640179910045,
  "eval_steps": 10.0,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01199400299850075,
      "grad_norm": 0.1552346225216276,
      "learning_rate": 4.998209387040829e-06,
      "loss": 0.919921875,
      "memory(GiB)": 21.25,
      "step": 1,
      "token_acc": 0.7323325635103927,
      "train_speed(iter/s)": 0.004341
    },
    {
      "epoch": 0.1199400299850075,
      "grad_norm": 0.12043793788509607,
      "learning_rate": 4.823045180793914e-06,
      "loss": 1.0885823567708333,
      "memory(GiB)": 21.25,
      "step": 10,
      "token_acc": 0.6962809017011649,
      "train_speed(iter/s)": 0.004719
    },
    {
      "epoch": 0.239880059970015,
      "grad_norm": 0.13374119375123103,
      "learning_rate": 4.317231129607859e-06,
      "loss": 1.054248046875,
      "memory(GiB)": 21.25,
      "step": 20,
      "token_acc": 0.7000147372169994,
      "train_speed(iter/s)": 0.004742
    },
    {
      "epoch": 0.3598200899550225,
      "grad_norm": 0.12281991001428441,
      "learning_rate": 3.55416283362546e-06,
      "loss": 1.061480712890625,
      "memory(GiB)": 21.25,
      "step": 30,
      "token_acc": 0.6975865397876155,
      "train_speed(iter/s)": 0.004746
    },
    {
      "epoch": 0.47976011994003,
      "grad_norm": 0.127887157838879,
      "learning_rate": 2.6418631827326857e-06,
      "loss": 1.0652984619140624,
      "memory(GiB)": 21.25,
      "step": 40,
      "token_acc": 0.699011663875183,
      "train_speed(iter/s)": 0.004756
    },
    {
      "epoch": 0.5997001499250375,
      "grad_norm": 0.12489181910395658,
      "learning_rate": 1.7094808327579401e-06,
      "loss": 1.0861114501953124,
      "memory(GiB)": 21.25,
      "step": 50,
      "token_acc": 0.6962444893765123,
      "train_speed(iter/s)": 0.004759
    },
    {
      "epoch": 0.719640179910045,
      "grad_norm": 0.1422097243980343,
      "learning_rate": 8.890074238378074e-07,
      "loss": 1.1186553955078125,
      "memory(GiB)": 21.25,
      "step": 60,
      "token_acc": 0.6851036117116058,
      "train_speed(iter/s)": 0.004754
    }
  ],
  "logging_steps": 10,
  "max_steps": 83,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8932162626123203e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}