checkpoint-100/trainer_state.json

{
  "best_global_step": 100,
  "best_metric": 0.8038855791091919,
  "best_model_checkpoint": "./tinyllama-custom-quotes-fine-tuned/checkpoint-100",
  "epoch": 0.25,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025,
      "grad_norm": 0.7440543174743652,
      "learning_rate": 0.00015000000000000001,
      "loss": 2.9746,
      "step": 10
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.447368860244751,
      "learning_rate": 0.0001998394219742627,
      "loss": 1.4501,
      "step": 20
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.5628308653831482,
      "learning_rate": 0.00019905415858090036,
      "loss": 1.0079,
      "step": 30
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.5305753946304321,
      "learning_rate": 0.0001976198547939518,
      "loss": 0.8519,
      "step": 40
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.7008503079414368,
      "learning_rate": 0.0001955459087155033,
      "loss": 0.798,
      "step": 50
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.3367324471473694,
      "learning_rate": 0.00019284590962639176,
      "loss": 0.9812,
      "step": 60
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.41013872623443604,
      "learning_rate": 0.00018953754894408616,
      "loss": 0.7821,
      "step": 70
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.3676799237728119,
      "learning_rate": 0.00018564250430181387,
      "loss": 0.8898,
      "step": 80
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.621743381023407,
      "learning_rate": 0.00018118629750849105,
      "loss": 0.8397,
      "step": 90
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.37409332394599915,
      "learning_rate": 0.00017619812732015664,
      "loss": 0.5815,
      "step": 100
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.8038855791091919,
      "eval_runtime": 48.3297,
      "eval_samples_per_second": 4.138,
      "eval_steps_per_second": 0.517,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 333304351948800.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}