checkpoint-18/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 10.875,
      "learning_rate": 0.0,
      "loss": 2.6157,
      "step": 1
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 9.8125,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.4889,
      "step": 2
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 7.78125,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.3111,
      "step": 3
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 6.9375,
      "learning_rate": 5e-05,
      "loss": 2.1313,
      "step": 4
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 6.3125,
      "learning_rate": 4.9974091841168195e-05,
      "loss": 2.0006,
      "step": 5
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.828125,
      "learning_rate": 4.9896421063288286e-05,
      "loss": 1.9674,
      "step": 6
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 3.296875,
      "learning_rate": 4.976714865090827e-05,
      "loss": 1.8848,
      "step": 7
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.140625,
      "learning_rate": 4.958654254084355e-05,
      "loss": 1.8648,
      "step": 8
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.21875,
      "learning_rate": 4.9354977066836986e-05,
      "loss": 1.8344,
      "step": 9
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 2.21875,
      "learning_rate": 4.907293218369499e-05,
      "loss": 1.7973,
      "step": 10
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 1.984375,
      "learning_rate": 4.874099247250798e-05,
      "loss": 1.7639,
      "step": 11
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.890625,
      "learning_rate": 4.835984592901678e-05,
      "loss": 1.7202,
      "step": 12
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 1.953125,
      "learning_rate": 4.793028253763633e-05,
      "loss": 1.8029,
      "step": 13
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 2.015625,
      "learning_rate": 4.74531926340924e-05,
      "loss": 1.7007,
      "step": 14
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 2.0,
      "learning_rate": 4.6929565060064864e-05,
      "loss": 1.7268,
      "step": 15
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.9375,
      "learning_rate": 4.6360485113662216e-05,
      "loss": 1.7007,
      "step": 16
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 1.9609375,
      "learning_rate": 4.574713229997563e-05,
      "loss": 1.679,
      "step": 17
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.4375,
      "learning_rate": 4.509077788637446e-05,
      "loss": 1.6594,
      "step": 18
    }
  ],
  "logging_steps": 1,
  "max_steps": 72,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 18,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.413174968451072e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}