checkpoints/checkpoint-10/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00010767507967955896,
  "eval_steps": 10,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0767507967955897e-05,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 1.4467,
      "step": 1
    },
    {
      "epoch": 2.1535015935911793e-05,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 1.6789,
      "step": 2
    },
    {
      "epoch": 3.2302523903867686e-05,
      "grad_norm": 78.11644744873047,
      "learning_rate": 4.389877161664096e-05,
      "loss": 1.9166,
      "step": 3
    },
    {
      "epoch": 4.3070031871823586e-05,
      "grad_norm": 18.779193878173828,
      "learning_rate": 4.070288237343632e-05,
      "loss": 1.1499,
      "step": 4
    },
    {
      "epoch": 5.383753983977948e-05,
      "grad_norm": Infinity,
      "learning_rate": 4.070288237343632e-05,
      "loss": 3.5213,
      "step": 5
    },
    {
      "epoch": 6.460504780773537e-05,
      "grad_norm": 38.93891525268555,
      "learning_rate": 3.572516817658065e-05,
      "loss": 1.7919,
      "step": 6
    },
    {
      "epoch": 7.537255577569128e-05,
      "grad_norm": 63.632408142089844,
      "learning_rate": 2.945288237343632e-05,
      "loss": 2.5181,
      "step": 7
    },
    {
      "epoch": 8.614006374364717e-05,
      "grad_norm": Infinity,
      "learning_rate": 2.945288237343632e-05,
      "loss": 2.1183,
      "step": 8
    },
    {
      "epoch": 9.690757171160307e-05,
      "grad_norm": 54.854434967041016,
      "learning_rate": 2.25e-05,
      "loss": 1.8283,
      "step": 9
    },
    {
      "epoch": 0.00010767507967955896,
      "grad_norm": 49.24325180053711,
      "learning_rate": 1.5547117626563687e-05,
      "loss": 1.4226,
      "step": 10
    },
    {
      "epoch": 0.00010767507967955896,
      "eval_loss": 1.4747177362442017,
      "eval_runtime": 99.0186,
      "eval_samples_per_second": 8.332,
      "eval_steps_per_second": 1.05,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1844410287390720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}