checkpoint-423/trainer_state.json

{
  "best_metric": 1.0,
  "best_model_checkpoint": "/kaggle/working/new_downloads/checkpoint-397",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 423,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06297229219143577,
      "grad_norm": 1.4191151857376099,
      "learning_rate": 6.25e-05,
      "loss": 4.3195,
      "step": 25
    },
    {
      "epoch": 0.12594458438287154,
      "grad_norm": 1.5384018421173096,
      "learning_rate": 0.000125,
      "loss": 4.2512,
      "step": 50
    },
    {
      "epoch": 0.1889168765743073,
      "grad_norm": 1.5718939304351807,
      "learning_rate": 0.00018749999999999998,
      "loss": 4.2373,
      "step": 75
    },
    {
      "epoch": 0.2518891687657431,
      "grad_norm": 1.4780595302581787,
      "learning_rate": 0.00025,
      "loss": 4.2214,
      "step": 100
    },
    {
      "epoch": 0.3148614609571788,
      "grad_norm": 1.543885588645935,
      "learning_rate": 0.00029980818414322247,
      "loss": 4.2333,
      "step": 125
    },
    {
      "epoch": 0.3778337531486146,
      "grad_norm": 1.5833216905593872,
      "learning_rate": 0.000298849104859335,
      "loss": 4.2375,
      "step": 150
    },
    {
      "epoch": 0.44080604534005036,
      "grad_norm": 1.8211495876312256,
      "learning_rate": 0.00029789002557544756,
      "loss": 4.2227,
      "step": 175
    },
    {
      "epoch": 0.5037783375314862,
      "grad_norm": 1.5552014112472534,
      "learning_rate": 0.0002969309462915601,
      "loss": 4.2426,
      "step": 200
    },
    {
      "epoch": 0.5667506297229219,
      "grad_norm": 1.5943366289138794,
      "learning_rate": 0.0002959718670076726,
      "loss": 4.2254,
      "step": 225
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 1.9039855003356934,
      "learning_rate": 0.0002950127877237851,
      "loss": 4.2428,
      "step": 250
    },
    {
      "epoch": 0.6926952141057935,
      "grad_norm": 1.624612808227539,
      "learning_rate": 0.0002940537084398977,
      "loss": 4.2183,
      "step": 275
    },
    {
      "epoch": 0.7556675062972292,
      "grad_norm": 1.5801411867141724,
      "learning_rate": 0.0002930946291560102,
      "loss": 4.2032,
      "step": 300
    },
    {
      "epoch": 0.818639798488665,
      "grad_norm": 1.6559851169586182,
      "learning_rate": 0.0002921355498721227,
      "loss": 4.1869,
      "step": 325
    },
    {
      "epoch": 0.8816120906801007,
      "grad_norm": 1.6399421691894531,
      "learning_rate": 0.00029117647058823524,
      "loss": 4.2117,
      "step": 350
    },
    {
      "epoch": 0.9445843828715366,
      "grad_norm": 1.6710602045059204,
      "learning_rate": 0.0002902173913043478,
      "loss": 4.2257,
      "step": 375
    },
    {
      "epoch": 1.0,
      "eval_cer": 1.0,
      "eval_loss": 4.691751956939697,
      "eval_runtime": 1056.28,
      "eval_samples_per_second": 2.082,
      "eval_steps_per_second": 0.017,
      "eval_wer": 1.0,
      "step": 397
    },
    {
      "epoch": 2.8368794326241136,
      "grad_norm": 1.1363143920898438,
      "learning_rate": 0.00026209386281588447,
      "loss": 3.967,
      "step": 400
    },
    {
      "epoch": 3.0,
      "eval_cer": 1.0,
      "eval_loss": 4.709719657897949,
      "eval_runtime": 540.9535,
      "eval_samples_per_second": 4.065,
      "eval_steps_per_second": 0.017,
      "eval_wer": 1.0,
      "step": 423
    }
  ],
  "logging_steps": 25,
  "max_steps": 2820,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.8935455694848e+18,
  "train_batch_size": 360,
  "trial_name": null,
  "trial_params": null
}