checkpoint-250/trainer_state.json

{
  "best_metric": 2.9989981651306152,
  "best_model_checkpoint": "./whisper-LoRA-small-ha/checkpoint-250",
  "epoch": 1.5923566878980893,
  "eval_steps": 250,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1592356687898089,
      "grad_norm": 10.639625549316406,
      "learning_rate": 1.3800000000000002e-05,
      "loss": 5.8923,
      "step": 25
    },
    {
      "epoch": 0.3184713375796178,
      "grad_norm": 3.0570621490478516,
      "learning_rate": 2.88e-05,
      "loss": 5.1217,
      "step": 50
    },
    {
      "epoch": 0.47770700636942676,
      "grad_norm": 1.420814037322998,
      "learning_rate": 3e-05,
      "loss": 4.1046,
      "step": 75
    },
    {
      "epoch": 0.6369426751592356,
      "grad_norm": 1.6677359342575073,
      "learning_rate": 3e-05,
      "loss": 3.5633,
      "step": 100
    },
    {
      "epoch": 0.7961783439490446,
      "grad_norm": 1.1571909189224243,
      "learning_rate": 3e-05,
      "loss": 3.2634,
      "step": 125
    },
    {
      "epoch": 0.9554140127388535,
      "grad_norm": 1.4416701793670654,
      "learning_rate": 3e-05,
      "loss": 3.2152,
      "step": 150
    },
    {
      "epoch": 1.1146496815286624,
      "grad_norm": 1.3764861822128296,
      "learning_rate": 3e-05,
      "loss": 3.1248,
      "step": 175
    },
    {
      "epoch": 1.2738853503184713,
      "grad_norm": 1.537541389465332,
      "learning_rate": 3e-05,
      "loss": 3.0425,
      "step": 200
    },
    {
      "epoch": 1.4331210191082802,
      "grad_norm": 1.239444613456726,
      "learning_rate": 3e-05,
      "loss": 3.0277,
      "step": 225
    },
    {
      "epoch": 1.5923566878980893,
      "grad_norm": 1.4676295518875122,
      "learning_rate": 3e-05,
      "loss": 3.0616,
      "step": 250
    },
    {
      "epoch": 1.5923566878980893,
      "eval_loss": 2.9989981651306152,
      "eval_runtime": 130.5989,
      "eval_samples_per_second": 5.054,
      "eval_steps_per_second": 0.636,
      "step": 250
    }
  ],
  "logging_steps": 25,
  "max_steps": 3140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.17355119280128e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}