checkpoint-10/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8e-05,
      "grad_norm": 0.2126462459564209,
      "learning_rate": 0.0,
      "loss": 0.7797,
      "step": 1
    },
    {
      "epoch": 0.00016,
      "grad_norm": 0.22393645346164703,
      "learning_rate": 4e-05,
      "loss": 0.8394,
      "step": 2
    },
    {
      "epoch": 0.00024,
      "grad_norm": 0.2677486538887024,
      "learning_rate": 8e-05,
      "loss": 1.0813,
      "step": 3
    },
    {
      "epoch": 0.00032,
      "grad_norm": 0.22248658537864685,
      "learning_rate": 0.00012,
      "loss": 0.8929,
      "step": 4
    },
    {
      "epoch": 0.0004,
      "grad_norm": 0.21182884275913239,
      "learning_rate": 0.00016,
      "loss": 0.7681,
      "step": 5
    },
    {
      "epoch": 0.00048,
      "grad_norm": 0.22956359386444092,
      "learning_rate": 0.0002,
      "loss": 0.9418,
      "step": 6
    },
    {
      "epoch": 0.00056,
      "grad_norm": 0.15817037224769592,
      "learning_rate": 0.00019636363636363636,
      "loss": 0.622,
      "step": 7
    },
    {
      "epoch": 0.00064,
      "grad_norm": 0.21448425948619843,
      "learning_rate": 0.00019272727272727274,
      "loss": 1.0023,
      "step": 8
    },
    {
      "epoch": 0.00072,
      "grad_norm": 0.13674581050872803,
      "learning_rate": 0.0001890909090909091,
      "loss": 0.8601,
      "step": 9
    },
    {
      "epoch": 0.0008,
      "grad_norm": 0.17133376002311707,
      "learning_rate": 0.00018545454545454545,
      "loss": 0.7606,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 939165480419328.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}