last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008988764044943821,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009987515605493133,
      "grad_norm": 0.29484567046165466,
      "learning_rate": 2e-05,
      "loss": 0.9667,
      "step": 1
    },
    {
      "epoch": 0.0019975031210986267,
      "grad_norm": 0.4613470137119293,
      "learning_rate": 4e-05,
      "loss": 1.3396,
      "step": 2
    },
    {
      "epoch": 0.00299625468164794,
      "grad_norm": 0.32433879375457764,
      "learning_rate": 6e-05,
      "loss": 0.9502,
      "step": 3
    },
    {
      "epoch": 0.00299625468164794,
      "eval_loss": 1.0558395385742188,
      "eval_runtime": 24.2386,
      "eval_samples_per_second": 17.41,
      "eval_steps_per_second": 8.705,
      "step": 3
    },
    {
      "epoch": 0.003995006242197253,
      "grad_norm": 0.3317357003688812,
      "learning_rate": 8e-05,
      "loss": 0.9,
      "step": 4
    },
    {
      "epoch": 0.004993757802746567,
      "grad_norm": 0.3528467118740082,
      "learning_rate": 0.0001,
      "loss": 0.9682,
      "step": 5
    },
    {
      "epoch": 0.00599250936329588,
      "grad_norm": 0.45743900537490845,
      "learning_rate": 0.00012,
      "loss": 1.1032,
      "step": 6
    },
    {
      "epoch": 0.00599250936329588,
      "eval_loss": 1.039202094078064,
      "eval_runtime": 22.8981,
      "eval_samples_per_second": 18.429,
      "eval_steps_per_second": 9.215,
      "step": 6
    },
    {
      "epoch": 0.006991260923845194,
      "grad_norm": 0.3344796895980835,
      "learning_rate": 0.00014,
      "loss": 0.9604,
      "step": 7
    },
    {
      "epoch": 0.007990012484394507,
      "grad_norm": 0.36716145277023315,
      "learning_rate": 0.00016,
      "loss": 0.9254,
      "step": 8
    },
    {
      "epoch": 0.008988764044943821,
      "grad_norm": 0.5545617341995239,
      "learning_rate": 0.00018,
      "loss": 0.9992,
      "step": 9
    },
    {
      "epoch": 0.008988764044943821,
      "eval_loss": 0.9399694800376892,
      "eval_runtime": 22.0251,
      "eval_samples_per_second": 19.16,
      "eval_steps_per_second": 9.58,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 738043798487040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}