checkpoint-500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016286485799813031,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003257297159962606,
      "grad_norm": 2.2308592796325684,
      "learning_rate": 4.99853416853153e-05,
      "loss": 1.4483,
      "step": 100
    },
    {
      "epoch": 0.0006514594319925212,
      "grad_norm": 2.3997225761413574,
      "learning_rate": 4.996905466899897e-05,
      "loss": 1.3276,
      "step": 200
    },
    {
      "epoch": 0.0009771891479887819,
      "grad_norm": 1.4687339067459106,
      "learning_rate": 4.995276765268264e-05,
      "loss": 1.3394,
      "step": 300
    },
    {
      "epoch": 0.0013029188639850425,
      "grad_norm": 0.6583470702171326,
      "learning_rate": 4.993648063636631e-05,
      "loss": 1.3245,
      "step": 400
    },
    {
      "epoch": 0.0016286485799813031,
      "grad_norm": 1.6252340078353882,
      "learning_rate": 4.992019362004997e-05,
      "loss": 1.3249,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 307003,
  "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": 7429806882816000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}