trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 200,
  "global_step": 1610,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2484472049689441,
      "grad_norm": 0.00017012437456287444,
      "learning_rate": 9.096774193548388e-06,
      "loss": 0.1254,
      "step": 200
    },
    {
      "epoch": 0.2484472049689441,
      "eval_loss": 4.401431083679199,
      "eval_runtime": 482.0342,
      "eval_samples_per_second": 23.735,
      "eval_steps_per_second": 0.187,
      "eval_wer": 2.0,
      "step": 200
    },
    {
      "epoch": 0.4968944099378882,
      "grad_norm": 8.738960605114698e-05,
      "learning_rate": 7.806451612903227e-06,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 0.4968944099378882,
      "eval_loss": 4.486298561096191,
      "eval_runtime": 479.7958,
      "eval_samples_per_second": 23.846,
      "eval_steps_per_second": 0.188,
      "eval_wer": 2.0,
      "step": 400
    },
    {
      "epoch": 0.7453416149068323,
      "grad_norm": 5.72737590118777e-05,
      "learning_rate": 6.516129032258065e-06,
      "loss": 0.0,
      "step": 600
    },
    {
      "epoch": 0.7453416149068323,
      "eval_loss": 4.560394763946533,
      "eval_runtime": 481.9341,
      "eval_samples_per_second": 23.74,
      "eval_steps_per_second": 0.187,
      "eval_wer": 2.0,
      "step": 600
    },
    {
      "epoch": 0.9937888198757764,
      "grad_norm": 4.319087747717276e-05,
      "learning_rate": 5.2258064516129035e-06,
      "loss": 0.0,
      "step": 800
    },
    {
      "epoch": 0.9937888198757764,
      "eval_loss": 4.643311023712158,
      "eval_runtime": 486.0191,
      "eval_samples_per_second": 23.54,
      "eval_steps_per_second": 0.185,
      "eval_wer": 2.0,
      "step": 800
    },
    {
      "epoch": 1.2422360248447206,
      "grad_norm": 3.755719444598071e-05,
      "learning_rate": 3.935483870967742e-06,
      "loss": 0.0,
      "step": 1000
    },
    {
      "epoch": 1.2422360248447206,
      "eval_loss": 4.694763660430908,
      "eval_runtime": 502.8422,
      "eval_samples_per_second": 22.753,
      "eval_steps_per_second": 0.179,
      "eval_wer": 2.0,
      "step": 1000
    },
    {
      "epoch": 1.4906832298136645,
      "grad_norm": 3.350584302097559e-05,
      "learning_rate": 2.645161290322581e-06,
      "loss": 0.0,
      "step": 1200
    },
    {
      "epoch": 1.4906832298136645,
      "eval_loss": 4.719086170196533,
      "eval_runtime": 485.7343,
      "eval_samples_per_second": 23.554,
      "eval_steps_per_second": 0.185,
      "eval_wer": 2.0,
      "step": 1200
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 3.120445762760937e-05,
      "learning_rate": 1.3548387096774195e-06,
      "loss": 0.0,
      "step": 1400
    },
    {
      "epoch": 1.7391304347826086,
      "eval_loss": 4.765808582305908,
      "eval_runtime": 479.5669,
      "eval_samples_per_second": 23.857,
      "eval_steps_per_second": 0.188,
      "eval_wer": 2.0,
      "step": 1400
    },
    {
      "epoch": 1.9875776397515528,
      "grad_norm": 3.0503017114824615e-05,
      "learning_rate": 6.451612903225807e-08,
      "loss": 0.0,
      "step": 1600
    },
    {
      "epoch": 1.9875776397515528,
      "eval_loss": 4.749756336212158,
      "eval_runtime": 486.8107,
      "eval_samples_per_second": 23.502,
      "eval_steps_per_second": 0.185,
      "eval_wer": 2.0,
      "step": 1600
    },
    {
      "epoch": 2.0,
      "step": 1610,
      "total_flos": 3.5135633858236934e+20,
      "train_loss": 1.8667458151082107e-07,
      "train_runtime": 3820.4641,
      "train_samples_per_second": 53.88,
      "train_steps_per_second": 0.421
    }
  ],
  "logging_steps": 200,
  "max_steps": 1610,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.5135633858236934e+20,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}