trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13050993949870354,
  "eval_steps": 30,
  "global_step": 151,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02592912705272256,
      "grad_norm": 5.810948371887207,
      "learning_rate": 1e-05,
      "loss": 1.0753,
      "step": 30
    },
    {
      "epoch": 0.02592912705272256,
      "eval_loss": 1.035988450050354,
      "eval_runtime": 2794.7093,
      "eval_samples_per_second": 6.622,
      "eval_steps_per_second": 0.414,
      "eval_wer": 0.7042336108830772,
      "step": 30
    },
    {
      "epoch": 0.05185825410544512,
      "grad_norm": 5.501910209655762,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.9233,
      "step": 60
    },
    {
      "epoch": 0.05185825410544512,
      "eval_loss": 0.944149374961853,
      "eval_runtime": 2608.5893,
      "eval_samples_per_second": 7.095,
      "eval_steps_per_second": 0.444,
      "eval_wer": 0.6614362221961612,
      "step": 60
    },
    {
      "epoch": 0.07778738115816768,
      "grad_norm": 6.307258605957031,
      "learning_rate": 5e-06,
      "loss": 0.8769,
      "step": 90
    },
    {
      "epoch": 0.07778738115816768,
      "eval_loss": 0.893798828125,
      "eval_runtime": 2594.5747,
      "eval_samples_per_second": 7.133,
      "eval_steps_per_second": 0.446,
      "eval_wer": 0.6292326335952465,
      "step": 90
    },
    {
      "epoch": 0.10371650821089023,
      "grad_norm": 5.156771659851074,
      "learning_rate": 2.5e-06,
      "loss": 0.8629,
      "step": 120
    },
    {
      "epoch": 0.10371650821089023,
      "eval_loss": 0.865983784198761,
      "eval_runtime": 2583.4969,
      "eval_samples_per_second": 7.164,
      "eval_steps_per_second": 0.448,
      "eval_wer": 0.6228607169383527,
      "step": 120
    },
    {
      "epoch": 0.12964563526361278,
      "grad_norm": 5.835461139678955,
      "learning_rate": 0.0,
      "loss": 0.8423,
      "step": 150
    },
    {
      "epoch": 0.12964563526361278,
      "eval_loss": 0.8570162057876587,
      "eval_runtime": 2583.4519,
      "eval_samples_per_second": 7.164,
      "eval_steps_per_second": 0.448,
      "eval_wer": 0.6128141980376061,
      "step": 150
    },
    {
      "epoch": 0.13050993949870354,
      "step": 151,
      "total_flos": 4.7898502889472e+17,
      "train_loss": 0.005337685938702514,
      "train_runtime": 31.1769,
      "train_samples_per_second": 615.841,
      "train_steps_per_second": 4.811
    }
  ],
  "logging_steps": 30,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.7898502889472e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}