trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.3929121725731894,
  "eval_steps": 500,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7704160246533128,
      "grad_norm": 9.17220401763916,
      "learning_rate": 1.7452491011813045e-05,
      "loss": 0.6268,
      "step": 500
    },
    {
      "epoch": 1.5408320493066254,
      "grad_norm": 1.130704641342163,
      "learning_rate": 1.4884437596302003e-05,
      "loss": 0.2416,
      "step": 1000
    },
    {
      "epoch": 2.3112480739599386,
      "grad_norm": 10.34769058227539,
      "learning_rate": 1.2321520287621984e-05,
      "loss": 0.21,
      "step": 1500
    },
    {
      "epoch": 3.0816640986132513,
      "grad_norm": 8.762519836425781,
      "learning_rate": 9.753466872110941e-06,
      "loss": 0.1846,
      "step": 2000
    },
    {
      "epoch": 3.852080123266564,
      "grad_norm": 3.5205228328704834,
      "learning_rate": 7.185413456599898e-06,
      "loss": 0.154,
      "step": 2500
    },
    {
      "epoch": 4.622496147919877,
      "grad_norm": 4.912118434906006,
      "learning_rate": 4.617360041088855e-06,
      "loss": 0.1376,
      "step": 3000
    },
    {
      "epoch": 5.3929121725731894,
      "grad_norm": 6.772336483001709,
      "learning_rate": 2.0493066255778122e-06,
      "loss": 0.1164,
      "step": 3500
    }
  ],
  "logging_steps": 500,
  "max_steps": 3894,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 2.9468968108425216e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}