trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0028310967668874923,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028310967668874923,
      "grad_norm": 2836.33096180012,
      "learning_rate": 1.6985939416816083e-08,
      "loss": 31.7647,
      "step": 10
    },
    {
      "epoch": 0.0005662193533774985,
      "grad_norm": 2885.3911544972293,
      "learning_rate": 3.585920543550062e-08,
      "loss": 32.3929,
      "step": 20
    },
    {
      "epoch": 0.0008493290300662477,
      "grad_norm": 2873.9526888921782,
      "learning_rate": 5.473247145418515e-08,
      "loss": 34.8664,
      "step": 30
    },
    {
      "epoch": 0.001132438706754997,
      "grad_norm": 2790.5502303854028,
      "learning_rate": 7.360573747286969e-08,
      "loss": 33.9609,
      "step": 40
    },
    {
      "epoch": 0.0014155483834437461,
      "grad_norm": 2679.2455640686744,
      "learning_rate": 9.247900349155422e-08,
      "loss": 33.3976,
      "step": 50
    },
    {
      "epoch": 0.0016986580601324954,
      "grad_norm": 2527.487761845231,
      "learning_rate": 1.1135226951023875e-07,
      "loss": 30.1905,
      "step": 60
    },
    {
      "epoch": 0.0019817677368212444,
      "grad_norm": 2168.6914860160564,
      "learning_rate": 1.302255355289233e-07,
      "loss": 26.9287,
      "step": 70
    },
    {
      "epoch": 0.002264877413509994,
      "grad_norm": 2046.4600106893272,
      "learning_rate": 1.4909880154760783e-07,
      "loss": 22.5402,
      "step": 80
    },
    {
      "epoch": 0.002547987090198743,
      "grad_norm": 1834.565702441259,
      "learning_rate": 1.6797206756629234e-07,
      "loss": 21.2989,
      "step": 90
    },
    {
      "epoch": 0.0028310967668874923,
      "grad_norm": 632.4488826895641,
      "learning_rate": 1.868453335849769e-07,
      "loss": 14.9413,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 353220,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1021942005760.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}