last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004005607850991388,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004005607850991388,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0004005607850991388,
      "eval_loss": NaN,
      "eval_runtime": 32.9745,
      "eval_samples_per_second": 31.903,
      "eval_steps_per_second": 15.952,
      "step": 1
    },
    {
      "epoch": 0.0008011215701982776,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0012016823552974164,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0012016823552974164,
      "eval_loss": NaN,
      "eval_runtime": 31.5338,
      "eval_samples_per_second": 33.361,
      "eval_steps_per_second": 16.681,
      "step": 3
    },
    {
      "epoch": 0.0016022431403965552,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.002002803925495694,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.002403364710594833,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.002403364710594833,
      "eval_loss": NaN,
      "eval_runtime": 31.7247,
      "eval_samples_per_second": 33.16,
      "eval_steps_per_second": 16.58,
      "step": 6
    },
    {
      "epoch": 0.0028039254956939716,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0032044862807931104,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0036050470658922492,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0036050470658922492,
      "eval_loss": NaN,
      "eval_runtime": 31.6078,
      "eval_samples_per_second": 33.283,
      "eval_steps_per_second": 16.641,
      "step": 9
    },
    {
      "epoch": 0.004005607850991388,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1752671799214080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}