last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3287019130641754,
  "global_step": 11048,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.9900826118433453e-05,
      "loss": 2.5088,
      "step": 500
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9801652236866898e-05,
      "loss": 2.4955,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.970247835530035e-05,
      "loss": 2.5035,
      "step": 1500
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.96033044737338e-05,
      "loss": 2.4969,
      "step": 2000
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9504130592167246e-05,
      "loss": 2.4963,
      "step": 2500
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9404956710600698e-05,
      "loss": 2.5023,
      "step": 3000
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.930578282903415e-05,
      "loss": 2.5007,
      "step": 3500
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9206608947467594e-05,
      "loss": 2.4953,
      "step": 4000
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9107435065901046e-05,
      "loss": 2.499,
      "step": 4500
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9008261184334497e-05,
      "loss": 2.4919,
      "step": 5000
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.8909087302767945e-05,
      "loss": 2.4988,
      "step": 5500
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8809913421201393e-05,
      "loss": 2.5076,
      "step": 6000
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.8710739539634845e-05,
      "loss": 2.4915,
      "step": 6500
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.8611565658068293e-05,
      "loss": 2.4823,
      "step": 7000
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.851239177650174e-05,
      "loss": 2.4859,
      "step": 7500
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.8413217894935193e-05,
      "loss": 2.4951,
      "step": 8000
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.831404401336864e-05,
      "loss": 2.4816,
      "step": 8500
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.821487013180209e-05,
      "loss": 2.485,
      "step": 9000
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.811569625023554e-05,
      "loss": 2.4889,
      "step": 9500
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.801652236866899e-05,
      "loss": 2.4812,
      "step": 10000
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.7917348487102437e-05,
      "loss": 2.4774,
      "step": 10500
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.781817460553589e-05,
      "loss": 2.4796,
      "step": 11000
    }
  ],
  "max_steps": 100833,
  "num_train_epochs": 3,
  "total_flos": 2.972249387945165e+16,
  "trial_name": null,
  "trial_params": null
}