last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008103125780769932,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7010419269233105e-05,
      "eval_loss": NaN,
      "eval_runtime": 4943.6388,
      "eval_samples_per_second": 3.153,
      "eval_steps_per_second": 1.577,
      "step": 1
    },
    {
      "epoch": 8.103125780769932e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00016206251561539864,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00021608335415386484,
      "eval_loss": NaN,
      "eval_runtime": 4949.2821,
      "eval_samples_per_second": 3.15,
      "eval_steps_per_second": 1.575,
      "step": 8
    },
    {
      "epoch": 0.00024309377342309797,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0003241250312307973,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0004051562890384966,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0004321667083077297,
      "eval_loss": NaN,
      "eval_runtime": 4954.3455,
      "eval_samples_per_second": 3.147,
      "eval_steps_per_second": 1.573,
      "step": 16
    },
    {
      "epoch": 0.00048618754684619594,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0005672188046538952,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0006482500624615946,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0006482500624615946,
      "eval_loss": NaN,
      "eval_runtime": 4950.1234,
      "eval_samples_per_second": 3.149,
      "eval_steps_per_second": 1.575,
      "step": 24
    },
    {
      "epoch": 0.0007292813202692939,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0008103125780769932,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "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": 3.34003062177792e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}