Monolingual-FR/SpanBased-DeBERTa/checkpoint-6972/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 6972,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1434308663224326,
      "grad_norm": 0.007672377396374941,
      "learning_rate": 1.8568559954102125e-05,
      "loss": 0.009684596061706543,
      "step": 500
    },
    {
      "epoch": 0.2868617326448652,
      "grad_norm": 0.012297257781028748,
      "learning_rate": 1.7134251290877798e-05,
      "loss": 0.004615603446960449,
      "step": 1000
    },
    {
      "epoch": 0.43029259896729777,
      "grad_norm": 0.011442928574979305,
      "learning_rate": 1.5699942627653474e-05,
      "loss": 0.002997920036315918,
      "step": 1500
    },
    {
      "epoch": 0.5737234652897304,
      "grad_norm": 0.013272660784423351,
      "learning_rate": 1.4265633964429147e-05,
      "loss": 0.0017894148826599122,
      "step": 2000
    },
    {
      "epoch": 0.7171543316121629,
      "grad_norm": 0.014016266912221909,
      "learning_rate": 1.283132530120482e-05,
      "loss": 0.0011281795501708984,
      "step": 2500
    },
    {
      "epoch": 0.8605851979345955,
      "grad_norm": 0.010322137735784054,
      "learning_rate": 1.1397016637980494e-05,
      "loss": 0.0008115814924240112,
      "step": 3000
    },
    {
      "epoch": 1.0040160642570282,
      "grad_norm": 0.01365757267922163,
      "learning_rate": 9.962707974756169e-06,
      "loss": 0.0006433913707733155,
      "step": 3500
    },
    {
      "epoch": 1.1474469305794608,
      "grad_norm": 0.009805912151932716,
      "learning_rate": 8.528399311531842e-06,
      "loss": 0.000557729184627533,
      "step": 4000
    },
    {
      "epoch": 1.2908777969018934,
      "grad_norm": 0.008765346370637417,
      "learning_rate": 7.0940906483075165e-06,
      "loss": 0.000488772600889206,
      "step": 4500
    },
    {
      "epoch": 1.4343086632243258,
      "grad_norm": 0.00846004392951727,
      "learning_rate": 5.65978198508319e-06,
      "loss": 0.00042926350235939024,
      "step": 5000
    },
    {
      "epoch": 1.5777395295467584,
      "grad_norm": 0.005864540580660105,
      "learning_rate": 4.225473321858865e-06,
      "loss": 0.00040997520089149477,
      "step": 5500
    },
    {
      "epoch": 1.721170395869191,
      "grad_norm": 0.004622944165021181,
      "learning_rate": 2.791164658634538e-06,
      "loss": 0.00037252518534660337,
      "step": 6000
    },
    {
      "epoch": 1.8646012621916235,
      "grad_norm": 0.01336298044770956,
      "learning_rate": 1.3568559954102124e-06,
      "loss": 0.0003555941879749298,
      "step": 6500
    }
  ],
  "logging_steps": 500,
  "max_steps": 6972,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6188296941634716.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}