last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00033987016959521465,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.3987016959521466e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 3.3987016959521466e-05,
      "eval_loss": NaN,
      "eval_runtime": 201.1813,
      "eval_samples_per_second": 61.581,
      "eval_steps_per_second": 30.793,
      "step": 1
    },
    {
      "epoch": 6.797403391904293e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00010196105087856439,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00010196105087856439,
      "eval_loss": NaN,
      "eval_runtime": 200.8035,
      "eval_samples_per_second": 61.697,
      "eval_steps_per_second": 30.851,
      "step": 3
    },
    {
      "epoch": 0.00013594806783808586,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00016993508479760732,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00020392210175712878,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00020392210175712878,
      "eval_loss": NaN,
      "eval_runtime": 203.4236,
      "eval_samples_per_second": 60.902,
      "eval_steps_per_second": 30.454,
      "step": 6
    },
    {
      "epoch": 0.00023790911871665024,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00027189613567617173,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 1.0951,
      "step": 8
    },
    {
      "epoch": 0.00030588315263569316,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 2.1132,
      "step": 9
    },
    {
      "epoch": 0.00030588315263569316,
      "eval_loss": NaN,
      "eval_runtime": 202.5542,
      "eval_samples_per_second": 61.164,
      "eval_steps_per_second": 30.584,
      "step": 9
    },
    {
      "epoch": 0.00033987016959521465,
      "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": 354804635271168.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}