trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 83,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12048192771084337,
      "grad_norm": 0.34623724837906805,
      "learning_rate": 1.999098966204682e-05,
      "loss": 3.1281,
      "mean_token_accuracy": 0.4044489324092865,
      "step": 10
    },
    {
      "epoch": 0.24096385542168675,
      "grad_norm": 0.3168403307775846,
      "learning_rate": 1.8929258581495688e-05,
      "loss": 3.1223,
      "mean_token_accuracy": 0.40491955280303954,
      "step": 20
    },
    {
      "epoch": 0.3614457831325301,
      "grad_norm": 0.30659730967389204,
      "learning_rate": 1.6282199972956425e-05,
      "loss": 3.1207,
      "mean_token_accuracy": 0.4047501623630524,
      "step": 30
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 0.3018085567056833,
      "learning_rate": 1.2519780613851254e-05,
      "loss": 3.116,
      "mean_token_accuracy": 0.40474292188882827,
      "step": 40
    },
    {
      "epoch": 0.6024096385542169,
      "grad_norm": 0.2912488543840164,
      "learning_rate": 8.309991796781512e-06,
      "loss": 3.1406,
      "mean_token_accuracy": 0.4022863879799843,
      "step": 50
    },
    {
      "epoch": 0.7228915662650602,
      "grad_norm": 0.3004434522468456,
      "learning_rate": 4.400252138624047e-06,
      "loss": 3.1273,
      "mean_token_accuracy": 0.4048710376024246,
      "step": 60
    },
    {
      "epoch": 0.8433734939759037,
      "grad_norm": 0.29104893141806826,
      "learning_rate": 1.4847086226668871e-06,
      "loss": 3.0992,
      "mean_token_accuracy": 0.4070223793387413,
      "step": 70
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 0.2993999885820785,
      "learning_rate": 8.099564741123167e-08,
      "loss": 3.1293,
      "mean_token_accuracy": 0.40418306440114976,
      "step": 80
    },
    {
      "epoch": 1.0,
      "mean_token_accuracy": 0.40785687665144604,
      "step": 83,
      "total_flos": 5452245613150208.0,
      "train_loss": 3.1222703313253013,
      "train_runtime": 348.715,
      "train_samples_per_second": 7.605,
      "train_steps_per_second": 0.238
    }
  ],
  "logging_steps": 10,
  "max_steps": 83,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5452245613150208.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}