last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10204081632653061,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01020408163265306,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.01020408163265306,
      "eval_loss": NaN,
      "eval_runtime": 197.0891,
      "eval_samples_per_second": 0.837,
      "eval_steps_per_second": 0.421,
      "step": 1
    },
    {
      "epoch": 0.02040816326530612,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.030612244897959183,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.030612244897959183,
      "eval_loss": NaN,
      "eval_runtime": 1.7655,
      "eval_samples_per_second": 93.455,
      "eval_steps_per_second": 47.011,
      "step": 3
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.05102040816326531,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.061224489795918366,
      "eval_loss": NaN,
      "eval_runtime": 1.7742,
      "eval_samples_per_second": 93.001,
      "eval_steps_per_second": 46.782,
      "step": 6
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.09183673469387756,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.09183673469387756,
      "eval_loss": NaN,
      "eval_runtime": 1.7738,
      "eval_samples_per_second": 93.023,
      "eval_steps_per_second": 46.793,
      "step": 9
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "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": 1329622859907072.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}