trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09022104155180191,
  "eval_steps": 500,
  "global_step": 4500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010024560172422436,
      "grad_norm": 0.857642412185669,
      "learning_rate": 2.9699260180042907e-05,
      "loss": 0.0968,
      "step": 500
    },
    {
      "epoch": 0.02004912034484487,
      "grad_norm": 0.6691309809684753,
      "learning_rate": 2.939852036008581e-05,
      "loss": 0.0902,
      "step": 1000
    },
    {
      "epoch": 0.030073680517267304,
      "grad_norm": 1.1712273359298706,
      "learning_rate": 2.909778054012872e-05,
      "loss": 0.0901,
      "step": 1500
    },
    {
      "epoch": 0.04009824068968974,
      "grad_norm": 0.9760019779205322,
      "learning_rate": 2.879704072017162e-05,
      "loss": 0.0881,
      "step": 2000
    },
    {
      "epoch": 0.050122800862112175,
      "grad_norm": 1.1272913217544556,
      "learning_rate": 2.8496300900214528e-05,
      "loss": 0.0888,
      "step": 2500
    },
    {
      "epoch": 0.06014736103453461,
      "grad_norm": 0.6894537806510925,
      "learning_rate": 2.8195561080257434e-05,
      "loss": 0.0872,
      "step": 3000
    },
    {
      "epoch": 0.07017192120695705,
      "grad_norm": 2.6526694297790527,
      "learning_rate": 2.789482126030034e-05,
      "loss": 0.0884,
      "step": 3500
    },
    {
      "epoch": 0.08019648137937949,
      "grad_norm": 1.0844719409942627,
      "learning_rate": 2.7594081440343246e-05,
      "loss": 0.0875,
      "step": 4000
    },
    {
      "epoch": 0.09022104155180191,
      "grad_norm": 0.9350685477256775,
      "learning_rate": 2.7293341620386152e-05,
      "loss": 0.087,
      "step": 4500
    }
  ],
  "logging_steps": 500,
  "max_steps": 49877,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}