last-checkpoint/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005254860746190226,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005254860746190226,
      "grad_norm": 0.4879109859466553,
      "learning_rate": 0.0,
      "loss": 0.2021,
      "step": 1
    },
    {
      "epoch": 0.0005254860746190226,
      "eval_loss": 0.2006789743900299,
      "eval_runtime": 17.8493,
      "eval_samples_per_second": 44.932,
      "eval_steps_per_second": 22.466,
      "step": 1
    },
    {
      "epoch": 0.0010509721492380452,
      "grad_norm": 0.5094596743583679,
      "learning_rate": 2e-05,
      "loss": 0.1743,
      "step": 2
    },
    {
      "epoch": 0.0015764582238570678,
      "grad_norm": 0.5767768621444702,
      "learning_rate": 4e-05,
      "loss": 0.1865,
      "step": 3
    },
    {
      "epoch": 0.0015764582238570678,
      "eval_loss": 0.19553354382514954,
      "eval_runtime": 17.8733,
      "eval_samples_per_second": 44.871,
      "eval_steps_per_second": 22.436,
      "step": 3
    },
    {
      "epoch": 0.0021019442984760903,
      "grad_norm": 0.49973180890083313,
      "learning_rate": 6e-05,
      "loss": 0.1795,
      "step": 4
    },
    {
      "epoch": 0.002627430373095113,
      "grad_norm": 0.44989892840385437,
      "learning_rate": 8e-05,
      "loss": 0.1553,
      "step": 5
    },
    {
      "epoch": 0.0031529164477141357,
      "grad_norm": 0.48157909512519836,
      "learning_rate": 0.0001,
      "loss": 0.1703,
      "step": 6
    },
    {
      "epoch": 0.0031529164477141357,
      "eval_loss": 0.12358408421278,
      "eval_runtime": 20.3291,
      "eval_samples_per_second": 39.451,
      "eval_steps_per_second": 19.725,
      "step": 6
    },
    {
      "epoch": 0.0036784025223331584,
      "grad_norm": 0.4450327455997467,
      "learning_rate": 0.00012,
      "loss": 0.1192,
      "step": 7
    },
    {
      "epoch": 0.004203888596952181,
      "grad_norm": 0.39254745841026306,
      "learning_rate": 0.00014,
      "loss": 0.0797,
      "step": 8
    },
    {
      "epoch": 0.004729374671571204,
      "grad_norm": 0.3380250632762909,
      "learning_rate": 0.00016,
      "loss": 0.0549,
      "step": 9
    },
    {
      "epoch": 0.004729374671571204,
      "eval_loss": 0.03407502919435501,
      "eval_runtime": 20.178,
      "eval_samples_per_second": 39.746,
      "eval_steps_per_second": 19.873,
      "step": 9
    },
    {
      "epoch": 0.005254860746190226,
      "grad_norm": 0.4398048520088196,
      "learning_rate": 0.00018,
      "loss": 0.0441,
      "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": 324298258513920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}