trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1258,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0794912559618442,
      "grad_norm": 0.07843409478664398,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.4022,
      "step": 100
    },
    {
      "epoch": 0.1589825119236884,
      "grad_norm": 0.17949211597442627,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.3835,
      "step": 200
    },
    {
      "epoch": 0.2384737678855326,
      "grad_norm": 0.40208756923675537,
      "learning_rate": 2e-05,
      "loss": 2.3114,
      "step": 300
    },
    {
      "epoch": 0.3179650238473768,
      "grad_norm": 0.48176440596580505,
      "learning_rate": 1.946710303471214e-05,
      "loss": 2.2008,
      "step": 400
    },
    {
      "epoch": 0.397456279809221,
      "grad_norm": 0.6267661452293396,
      "learning_rate": 1.7925207973971163e-05,
      "loss": 2.0805,
      "step": 500
    },
    {
      "epoch": 0.4769475357710652,
      "grad_norm": 0.7604636549949646,
      "learning_rate": 1.5538649057509307e-05,
      "loss": 2.0478,
      "step": 600
    },
    {
      "epoch": 0.5564387917329093,
      "grad_norm": 0.7635889649391174,
      "learning_rate": 1.2561784286139214e-05,
      "loss": 1.9975,
      "step": 700
    },
    {
      "epoch": 0.6359300476947536,
      "grad_norm": 0.8927960991859436,
      "learning_rate": 9.311886100407975e-06,
      "loss": 1.9719,
      "step": 800
    },
    {
      "epoch": 0.7154213036565977,
      "grad_norm": 1.0471729040145874,
      "learning_rate": 6.13532667644974e-06,
      "loss": 1.9603,
      "step": 900
    },
    {
      "epoch": 0.794912559618442,
      "grad_norm": 0.8145257830619812,
      "learning_rate": 3.3706617896812775e-06,
      "loss": 1.9426,
      "step": 1000
    },
    {
      "epoch": 0.8744038155802861,
      "grad_norm": 0.9433038234710693,
      "learning_rate": 1.312547745741959e-06,
      "loss": 1.9316,
      "step": 1100
    },
    {
      "epoch": 0.9538950715421304,
      "grad_norm": 1.0557024478912354,
      "learning_rate": 1.8033709027809655e-07,
      "loss": 1.9277,
      "step": 1200
    },
    {
      "epoch": 1.0,
      "step": 1258,
      "total_flos": 2.2852829872128e+16,
      "train_loss": 2.0900387422837587,
      "train_runtime": 392.7068,
      "train_samples_per_second": 6.404,
      "train_steps_per_second": 3.203
    }
  ],
  "logging_steps": 100,
  "max_steps": 1258,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2852829872128e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}