trainer_state.json

{
  "best_metric": 0.34165722131729126,
  "best_model_checkpoint": "camembert-model/checkpoint-1600",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.880101905419033,
      "eval_f1": 0.0,
      "eval_loss": 0.6244299411773682,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.7459,
      "eval_samples_per_second": 456.492,
      "eval_steps_per_second": 28.638,
      "step": 160
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.949524972135237,
      "eval_f1": 0.0,
      "eval_loss": 0.5487059354782104,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.7233,
      "eval_samples_per_second": 462.498,
      "eval_steps_per_second": 29.015,
      "step": 320
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9524972135236983,
      "eval_f1": 0.0,
      "eval_loss": 0.4897811710834503,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.7082,
      "eval_samples_per_second": 466.564,
      "eval_steps_per_second": 29.27,
      "step": 480
    },
    {
      "epoch": 3.125,
      "grad_norm": 1.9320571422576904,
      "learning_rate": 1.375e-05,
      "loss": 0.5894,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9527625922190966,
      "eval_f1": 0.0,
      "eval_loss": 0.44394731521606445,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.7198,
      "eval_samples_per_second": 463.435,
      "eval_steps_per_second": 29.074,
      "step": 640
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9527625922190966,
      "eval_f1": 0.0,
      "eval_loss": 0.40905287861824036,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.7243,
      "eval_samples_per_second": 462.226,
      "eval_steps_per_second": 28.998,
      "step": 800
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9527625922190966,
      "eval_f1": 0.0,
      "eval_loss": 0.38293978571891785,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 4.7777,
      "eval_samples_per_second": 166.818,
      "eval_steps_per_second": 10.465,
      "step": 960
    },
    {
      "epoch": 6.25,
      "grad_norm": 1.3343875408172607,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.4292,
      "step": 1000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9527625922190966,
      "eval_f1": 0.0,
      "eval_loss": 0.36409473419189453,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.7395,
      "eval_samples_per_second": 458.191,
      "eval_steps_per_second": 28.745,
      "step": 1120
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9527625922190966,
      "eval_f1": 0.0,
      "eval_loss": 0.35134562849998474,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.7277,
      "eval_samples_per_second": 461.316,
      "eval_steps_per_second": 28.941,
      "step": 1280
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9527625922190966,
      "eval_f1": 0.0,
      "eval_loss": 0.34404492378234863,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.696,
      "eval_samples_per_second": 469.941,
      "eval_steps_per_second": 29.482,
      "step": 1440
    },
    {
      "epoch": 9.375,
      "grad_norm": 1.457685112953186,
      "learning_rate": 1.25e-06,
      "loss": 0.3631,
      "step": 1500
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9527625922190966,
      "eval_f1": 0.0,
      "eval_loss": 0.34165722131729126,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.8323,
      "eval_samples_per_second": 434.963,
      "eval_steps_per_second": 27.288,
      "step": 1600
    }
  ],
  "logging_steps": 500,
  "max_steps": 1600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 884828390782752.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}