trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001779061865097297,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.895309325486485e-05,
      "grad_norm": 0.1897999793291092,
      "learning_rate": 2.5e-05,
      "loss": 2.3044,
      "step": 25
    },
    {
      "epoch": 0.0001779061865097297,
      "grad_norm": 0.23376008868217468,
      "learning_rate": 2.5e-05,
      "loss": 2.3592,
      "step": 50
    },
    {
      "epoch": 0.0002668592797645945,
      "grad_norm": 0.13603591918945312,
      "learning_rate": 2.5e-05,
      "loss": 2.084,
      "step": 75
    },
    {
      "epoch": 0.0003558123730194594,
      "grad_norm": 0.34403547644615173,
      "learning_rate": 2.5e-05,
      "loss": 2.076,
      "step": 100
    },
    {
      "epoch": 0.00044476546627432423,
      "grad_norm": 0.1530287265777588,
      "learning_rate": 2.5e-05,
      "loss": 1.7806,
      "step": 125
    },
    {
      "epoch": 0.000533718559529189,
      "grad_norm": 0.344722718000412,
      "learning_rate": 2.5e-05,
      "loss": 1.5749,
      "step": 150
    },
    {
      "epoch": 0.0006226716527840539,
      "grad_norm": 0.38181471824645996,
      "learning_rate": 2.5e-05,
      "loss": 1.5243,
      "step": 175
    },
    {
      "epoch": 0.0007116247460389188,
      "grad_norm": 0.25272616744041443,
      "learning_rate": 2.5e-05,
      "loss": 1.4728,
      "step": 200
    },
    {
      "epoch": 0.0008005778392937836,
      "grad_norm": 0.6237773299217224,
      "learning_rate": 2.5e-05,
      "loss": 1.3028,
      "step": 225
    },
    {
      "epoch": 0.0008895309325486485,
      "grad_norm": 0.5120233297348022,
      "learning_rate": 2.5e-05,
      "loss": 1.0721,
      "step": 250
    },
    {
      "epoch": 0.0009784840258035134,
      "grad_norm": 0.6732835173606873,
      "learning_rate": 2.5e-05,
      "loss": 0.8071,
      "step": 275
    },
    {
      "epoch": 0.001067437119058378,
      "grad_norm": 0.5018543004989624,
      "learning_rate": 2.5e-05,
      "loss": 0.8138,
      "step": 300
    },
    {
      "epoch": 0.001156390212313243,
      "grad_norm": 0.24052944779396057,
      "learning_rate": 2.5e-05,
      "loss": 0.702,
      "step": 325
    },
    {
      "epoch": 0.0012453433055681078,
      "grad_norm": 0.2696482837200165,
      "learning_rate": 2.5e-05,
      "loss": 0.6689,
      "step": 350
    },
    {
      "epoch": 0.0013342963988229727,
      "grad_norm": 0.21222035586833954,
      "learning_rate": 2.5e-05,
      "loss": 0.7498,
      "step": 375
    },
    {
      "epoch": 0.0014232494920778376,
      "grad_norm": 0.27624765038490295,
      "learning_rate": 2.5e-05,
      "loss": 0.6544,
      "step": 400
    },
    {
      "epoch": 0.0015122025853327023,
      "grad_norm": 0.8518249988555908,
      "learning_rate": 2.5e-05,
      "loss": 0.6908,
      "step": 425
    },
    {
      "epoch": 0.0016011556785875672,
      "grad_norm": 0.588943600654602,
      "learning_rate": 2.5e-05,
      "loss": 0.7507,
      "step": 450
    },
    {
      "epoch": 0.001690108771842432,
      "grad_norm": 0.4197629690170288,
      "learning_rate": 2.5e-05,
      "loss": 0.8013,
      "step": 475
    },
    {
      "epoch": 0.001779061865097297,
      "grad_norm": 0.48924073576927185,
      "learning_rate": 2.5e-05,
      "loss": 0.6292,
      "step": 500
    }
  ],
  "logging_steps": 25,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.087597314048e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}