checkpoint-204288/trainer_state.json

{
  "best_metric": 0.002683098893612623,
  "best_model_checkpoint": "wsd_embedding/checkpoint-204288",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 204288,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.013213178142905235,
      "learning_rate": 9.800046992481203e-05,
      "loss": 0.0078,
      "step": 25536
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.004399613011628389,
      "eval_runtime": 113.9442,
      "eval_samples_per_second": 94.362,
      "eval_steps_per_second": 11.795,
      "step": 25536
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.008942891843616962,
      "learning_rate": 9.600117481203008e-05,
      "loss": 0.0056,
      "step": 51072
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.0036812573671340942,
      "eval_runtime": 113.8113,
      "eval_samples_per_second": 94.472,
      "eval_steps_per_second": 11.809,
      "step": 51072
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.019620591774582863,
      "learning_rate": 9.400180137844612e-05,
      "loss": 0.0049,
      "step": 76608
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.003332871478050947,
      "eval_runtime": 113.7743,
      "eval_samples_per_second": 94.503,
      "eval_steps_per_second": 11.813,
      "step": 76608
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.009495776146650314,
      "learning_rate": 9.200250626566417e-05,
      "loss": 0.0045,
      "step": 102144
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.0030836393125355244,
      "eval_runtime": 113.745,
      "eval_samples_per_second": 94.527,
      "eval_steps_per_second": 11.816,
      "step": 102144
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.007638801820576191,
      "learning_rate": 9.00031328320802e-05,
      "loss": 0.0043,
      "step": 127680
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.002948065521195531,
      "eval_runtime": 113.6579,
      "eval_samples_per_second": 94.6,
      "eval_steps_per_second": 11.825,
      "step": 127680
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.010788742452859879,
      "learning_rate": 8.800407268170426e-05,
      "loss": 0.0041,
      "step": 153216
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.0028368972707539797,
      "eval_runtime": 114.0546,
      "eval_samples_per_second": 94.271,
      "eval_steps_per_second": 11.784,
      "step": 153216
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.017284151166677475,
      "learning_rate": 8.600477756892231e-05,
      "loss": 0.0039,
      "step": 178752
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.0027765275444835424,
      "eval_runtime": 113.8381,
      "eval_samples_per_second": 94.45,
      "eval_steps_per_second": 11.806,
      "step": 178752
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.008209532126784325,
      "learning_rate": 8.400540413533835e-05,
      "loss": 0.0038,
      "step": 204288
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.002683098893612623,
      "eval_runtime": 113.811,
      "eval_samples_per_second": 94.472,
      "eval_steps_per_second": 11.809,
      "step": 204288
    }
  ],
  "logging_steps": 500,
  "max_steps": 1276800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.164557305754419e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}