trainer_state.json

{
  "best_global_step": 1850,
  "best_metric": 0.30451855063438416,
  "best_model_checkpoint": "checkpoints/lora_top10/checkpoint-1850",
  "epoch": 0.39864246080913646,
  "eval_steps": 925,
  "global_step": 1850,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04956095458708183,
      "grad_norm": 0.934660017490387,
      "learning_rate": 0.00024998556318640624,
      "loss": 0.6914,
      "step": 230
    },
    {
      "epoch": 0.09912190917416366,
      "grad_norm": 0.4911360442638397,
      "learning_rate": 0.00024944056289455033,
      "loss": 0.3825,
      "step": 460
    },
    {
      "epoch": 0.14868286376124548,
      "grad_norm": 0.4823257625102997,
      "learning_rate": 0.0002481105375159093,
      "loss": 0.3522,
      "step": 690
    },
    {
      "epoch": 0.19824381834832733,
      "grad_norm": 0.44280752539634705,
      "learning_rate": 0.0002460038774278972,
      "loss": 0.3361,
      "step": 920
    },
    {
      "epoch": 0.19932123040456823,
      "eval_loss": 0.3328564167022705,
      "eval_runtime": 444.8042,
      "eval_samples_per_second": 3.372,
      "eval_steps_per_second": 0.843,
      "step": 925
    },
    {
      "epoch": 0.24780477293540915,
      "grad_norm": 0.3403889536857605,
      "learning_rate": 0.00024313387235678932,
      "loss": 0.3233,
      "step": 1150
    },
    {
      "epoch": 0.29736572752249096,
      "grad_norm": 0.368375301361084,
      "learning_rate": 0.00023951862754036037,
      "loss": 0.317,
      "step": 1380
    },
    {
      "epoch": 0.3469266821095728,
      "grad_norm": 0.31689661741256714,
      "learning_rate": 0.00023518094951218544,
      "loss": 0.3072,
      "step": 1610
    },
    {
      "epoch": 0.39648763669665466,
      "grad_norm": 0.27953606843948364,
      "learning_rate": 0.00023014820222812683,
      "loss": 0.3016,
      "step": 1840
    },
    {
      "epoch": 0.39864246080913646,
      "eval_loss": 0.30451855063438416,
      "eval_runtime": 458.3568,
      "eval_samples_per_second": 3.273,
      "eval_steps_per_second": 0.818,
      "step": 1850
    }
  ],
  "logging_steps": 230,
  "max_steps": 9280,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 925,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.390942703157248e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}