trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.437636761487965,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02188183807439825,
      "grad_norm": 7.38808464543784,
      "learning_rate": 6.666666666666666e-07,
      "loss": 1.957,
      "step": 10
    },
    {
      "epoch": 0.0437636761487965,
      "grad_norm": 6.694792139315802,
      "learning_rate": 1.3333333333333332e-06,
      "loss": 1.8366,
      "step": 20
    },
    {
      "epoch": 0.06564551422319474,
      "grad_norm": 2.753054563296277,
      "learning_rate": 2e-06,
      "loss": 1.6834,
      "step": 30
    },
    {
      "epoch": 0.087527352297593,
      "grad_norm": 3.0196829311173383,
      "learning_rate": 1.997294683476273e-06,
      "loss": 1.5792,
      "step": 40
    },
    {
      "epoch": 0.10940919037199125,
      "grad_norm": 2.043213920847318,
      "learning_rate": 1.9891933713800795e-06,
      "loss": 1.5421,
      "step": 50
    },
    {
      "epoch": 0.13129102844638948,
      "grad_norm": 1.9290165973717828,
      "learning_rate": 1.975739896938375e-06,
      "loss": 1.4976,
      "step": 60
    },
    {
      "epoch": 0.15317286652078774,
      "grad_norm": 1.8958297962498376,
      "learning_rate": 1.9570070519645765e-06,
      "loss": 1.4696,
      "step": 70
    },
    {
      "epoch": 0.175054704595186,
      "grad_norm": 3.538308772432866,
      "learning_rate": 1.9330961930087725e-06,
      "loss": 1.4409,
      "step": 80
    },
    {
      "epoch": 0.19693654266958424,
      "grad_norm": 2.1951202653523803,
      "learning_rate": 1.9041366929546216e-06,
      "loss": 1.4601,
      "step": 90
    },
    {
      "epoch": 0.2188183807439825,
      "grad_norm": 2.1497845944555514,
      "learning_rate": 1.8702852410301553e-06,
      "loss": 1.4162,
      "step": 100
    },
    {
      "epoch": 0.24070021881838075,
      "grad_norm": 1.8478185733675352,
      "learning_rate": 1.8317249950198596e-06,
      "loss": 1.4207,
      "step": 110
    },
    {
      "epoch": 0.26258205689277897,
      "grad_norm": 2.0111628068672567,
      "learning_rate": 1.7886645902651164e-06,
      "loss": 1.3857,
      "step": 120
    },
    {
      "epoch": 0.2844638949671772,
      "grad_norm": 4.441684060204544,
      "learning_rate": 1.7413370108149287e-06,
      "loss": 1.3821,
      "step": 130
    },
    {
      "epoch": 0.3063457330415755,
      "grad_norm": 1.9878264739514673,
      "learning_rate": 1.6899983288347247e-06,
      "loss": 1.3559,
      "step": 140
    },
    {
      "epoch": 0.3282275711159737,
      "grad_norm": 2.0597952266115915,
      "learning_rate": 1.63492631909384e-06,
      "loss": 1.3683,
      "step": 150
    },
    {
      "epoch": 0.350109409190372,
      "grad_norm": 1.8085416648968597,
      "learning_rate": 1.5764189560281674e-06,
      "loss": 1.3484,
      "step": 160
    },
    {
      "epoch": 0.37199124726477023,
      "grad_norm": 1.9540811212682783,
      "learning_rate": 1.5147928015098307e-06,
      "loss": 1.3377,
      "step": 170
    },
    {
      "epoch": 0.3938730853391685,
      "grad_norm": 1.896162081853637,
      "learning_rate": 1.4503812920470533e-06,
      "loss": 1.3267,
      "step": 180
    },
    {
      "epoch": 0.41575492341356673,
      "grad_norm": 1.824280170852011,
      "learning_rate": 1.3835329346815714e-06,
      "loss": 1.3259,
      "step": 190
    },
    {
      "epoch": 0.437636761487965,
      "grad_norm": 1.8853200942482258,
      "learning_rate": 1.3146094213449146e-06,
      "loss": 1.3293,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 457,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 32614907904000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}