{
  "best_global_step": 4000,
  "best_metric": 2.714773265402766,
  "best_model_checkpoint": "./SALAMA_NEW/checkpoint-4000",
  "epoch": 3.0,
  "eval_steps": 2000,
  "global_step": 5007,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2995805871779509,
      "grad_norm": 8.785015106201172,
      "learning_rate": 9.186875891583453e-06,
      "loss": 0.1615,
      "step": 500
    },
    {
      "epoch": 0.5991611743559018,
      "grad_norm": 4.029974460601807,
      "learning_rate": 8.167923374770737e-06,
      "loss": 0.1535,
      "step": 1000
    },
    {
      "epoch": 0.8987417615338527,
      "grad_norm": 3.3210387229919434,
      "learning_rate": 7.14897085795802e-06,
      "loss": 0.1406,
      "step": 1500
    },
    {
      "epoch": 1.1983223487118035,
      "grad_norm": 2.3362109661102295,
      "learning_rate": 6.130018341145303e-06,
      "loss": 0.0821,
      "step": 2000
    },
    {
      "epoch": 1.1983223487118035,
      "eval_loss": 0.0653982162475586,
      "eval_runtime": 4767.7684,
      "eval_samples_per_second": 2.8,
      "eval_steps_per_second": 0.35,
      "eval_wer": 5.400969970117083,
      "step": 2000
    },
    {
      "epoch": 1.4979029358897544,
      "grad_norm": 2.6497209072113037,
      "learning_rate": 5.111065824332586e-06,
      "loss": 0.054,
      "step": 2500
    },
    {
      "epoch": 1.7974835230677053,
      "grad_norm": 1.7399611473083496,
      "learning_rate": 4.09211330751987e-06,
      "loss": 0.0537,
      "step": 3000
    },
    {
      "epoch": 2.097064110245656,
      "grad_norm": 1.538604497909546,
      "learning_rate": 3.073160790707153e-06,
      "loss": 0.0408,
      "step": 3500
    },
    {
      "epoch": 2.396644697423607,
      "grad_norm": 1.3203742504119873,
      "learning_rate": 2.0542082738944367e-06,
      "loss": 0.0168,
      "step": 4000
    },
    {
      "epoch": 2.396644697423607,
      "eval_loss": 0.037878651171922684,
      "eval_runtime": 4800.6459,
      "eval_samples_per_second": 2.781,
      "eval_steps_per_second": 0.348,
      "eval_wer": 2.714773265402766,
      "step": 4000
    },
    {
      "epoch": 2.696225284601558,
      "grad_norm": 1.2901939153671265,
      "learning_rate": 1.03525575708172e-06,
      "loss": 0.0163,
      "step": 4500
    },
    {
      "epoch": 2.995805871779509,
      "grad_norm": 1.3657872676849365,
      "learning_rate": 1.6303240269003464e-08,
      "loss": 0.0157,
      "step": 5000
    }
  ],
  "logging_steps": 500,
  "max_steps": 5007,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.6231381131264e+19,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}