trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16039296275875897,
  "eval_steps": 500,
  "global_step": 8000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010024560172422436,
      "grad_norm": 0.7648569941520691,
      "learning_rate": 2.9699260180042907e-05,
      "loss": 0.0563,
      "step": 500
    },
    {
      "epoch": 0.02004912034484487,
      "grad_norm": 0.5078855752944946,
      "learning_rate": 2.939852036008581e-05,
      "loss": 0.051,
      "step": 1000
    },
    {
      "epoch": 0.030073680517267304,
      "grad_norm": 0.6789458394050598,
      "learning_rate": 2.909778054012872e-05,
      "loss": 0.0481,
      "step": 1500
    },
    {
      "epoch": 0.04009824068968974,
      "grad_norm": 0.561828076839447,
      "learning_rate": 2.879704072017162e-05,
      "loss": 0.0475,
      "step": 2000
    },
    {
      "epoch": 0.050122800862112175,
      "grad_norm": 0.7291754484176636,
      "learning_rate": 2.8496300900214528e-05,
      "loss": 0.0461,
      "step": 2500
    },
    {
      "epoch": 0.06014736103453461,
      "grad_norm": 0.5085094571113586,
      "learning_rate": 2.8195561080257434e-05,
      "loss": 0.0447,
      "step": 3000
    },
    {
      "epoch": 0.07017192120695705,
      "grad_norm": 0.5000583529472351,
      "learning_rate": 2.789482126030034e-05,
      "loss": 0.0438,
      "step": 3500
    },
    {
      "epoch": 0.08019648137937949,
      "grad_norm": 0.36143258213996887,
      "learning_rate": 2.7594081440343246e-05,
      "loss": 0.0427,
      "step": 4000
    },
    {
      "epoch": 0.09022104155180191,
      "grad_norm": 0.6115249991416931,
      "learning_rate": 2.7293341620386152e-05,
      "loss": 0.0422,
      "step": 4500
    },
    {
      "epoch": 0.10024560172422435,
      "grad_norm": 0.28902167081832886,
      "learning_rate": 2.6992601800429055e-05,
      "loss": 0.0418,
      "step": 5000
    },
    {
      "epoch": 0.11027016189664679,
      "grad_norm": 0.3481534421443939,
      "learning_rate": 2.669186198047196e-05,
      "loss": 0.0413,
      "step": 5500
    },
    {
      "epoch": 0.12029472206906922,
      "grad_norm": 0.4140373468399048,
      "learning_rate": 2.6391122160514867e-05,
      "loss": 0.0403,
      "step": 6000
    },
    {
      "epoch": 0.13031928224149164,
      "grad_norm": 0.3342398703098297,
      "learning_rate": 2.6090382340557773e-05,
      "loss": 0.0395,
      "step": 6500
    },
    {
      "epoch": 0.1403438424139141,
      "grad_norm": 0.32196730375289917,
      "learning_rate": 2.578964252060068e-05,
      "loss": 0.039,
      "step": 7000
    },
    {
      "epoch": 0.15036840258633652,
      "grad_norm": 0.3885316252708435,
      "learning_rate": 2.548890270064358e-05,
      "loss": 0.0381,
      "step": 7500
    },
    {
      "epoch": 0.16039296275875897,
      "grad_norm": 0.37349772453308105,
      "learning_rate": 2.518816288068649e-05,
      "loss": 0.0378,
      "step": 8000
    }
  ],
  "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
}