last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00014775031673974152,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.4775031673974151e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 1.4775031673974151e-05,
      "eval_loss": NaN,
      "eval_runtime": 480.2526,
      "eval_samples_per_second": 59.34,
      "eval_steps_per_second": 29.67,
      "step": 1
    },
    {
      "epoch": 2.9550063347948303e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 4.432509502192245e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 4.432509502192245e-05,
      "eval_loss": NaN,
      "eval_runtime": 484.0028,
      "eval_samples_per_second": 58.88,
      "eval_steps_per_second": 29.44,
      "step": 3
    },
    {
      "epoch": 5.9100126695896606e-05,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 7.387515836987076e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 8.86501900438449e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 8.86501900438449e-05,
      "eval_loss": NaN,
      "eval_runtime": 487.2274,
      "eval_samples_per_second": 58.49,
      "eval_steps_per_second": 29.245,
      "step": 6
    },
    {
      "epoch": 0.00010342522171781905,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00011820025339179321,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00013297528506576737,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00013297528506576737,
      "eval_loss": NaN,
      "eval_runtime": 482.7792,
      "eval_samples_per_second": 59.029,
      "eval_steps_per_second": 29.515,
      "step": 9
    },
    {
      "epoch": 0.00014775031673974152,
      "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": 89038163804160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}