last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06842105263157895,
  "eval_steps": 13,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017543859649122807,
      "eval_loss": 2.627302885055542,
      "eval_runtime": 4.6289,
      "eval_samples_per_second": 51.848,
      "eval_steps_per_second": 25.924,
      "step": 1
    },
    {
      "epoch": 0.008771929824561403,
      "grad_norm": 2.6059508323669434,
      "learning_rate": 5e-05,
      "loss": 2.7507,
      "step": 5
    },
    {
      "epoch": 0.017543859649122806,
      "grad_norm": 1.4112547636032104,
      "learning_rate": 0.0001,
      "loss": 2.5653,
      "step": 10
    },
    {
      "epoch": 0.02280701754385965,
      "eval_loss": 2.263962745666504,
      "eval_runtime": 4.5485,
      "eval_samples_per_second": 52.765,
      "eval_steps_per_second": 26.382,
      "step": 13
    },
    {
      "epoch": 0.02631578947368421,
      "grad_norm": 1.3983335494995117,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.4368,
      "step": 15
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 2.202619791030884,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.0027,
      "step": 20
    },
    {
      "epoch": 0.043859649122807015,
      "grad_norm": 2.056281805038452,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.7852,
      "step": 25
    },
    {
      "epoch": 0.0456140350877193,
      "eval_loss": 1.7858082056045532,
      "eval_runtime": 4.6364,
      "eval_samples_per_second": 51.764,
      "eval_steps_per_second": 25.882,
      "step": 26
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 2.750361919403076,
      "learning_rate": 5e-05,
      "loss": 1.8224,
      "step": 30
    },
    {
      "epoch": 0.06140350877192982,
      "grad_norm": 1.9289882183074951,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.8185,
      "step": 35
    },
    {
      "epoch": 0.06842105263157895,
      "eval_loss": 1.6389496326446533,
      "eval_runtime": 4.6174,
      "eval_samples_per_second": 51.977,
      "eval_steps_per_second": 25.989,
      "step": 39
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 997588715175936.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}