checkpoint-150/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24,
  "eval_steps": 1000.0,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 0.05375732481479645,
      "learning_rate": 0.0001,
      "loss": 4.9168,
      "step": 10
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.06290680170059204,
      "learning_rate": 0.0001,
      "loss": 4.7727,
      "step": 20
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.18232201039791107,
      "learning_rate": 0.0001,
      "loss": 4.6199,
      "step": 30
    },
    {
      "epoch": 0.064,
      "grad_norm": 4.475333213806152,
      "learning_rate": 0.0001,
      "loss": 4.2628,
      "step": 40
    },
    {
      "epoch": 0.08,
      "grad_norm": 5.602807998657227,
      "learning_rate": 0.0001,
      "loss": 2.2105,
      "step": 50
    },
    {
      "epoch": 0.096,
      "grad_norm": 4.922974586486816,
      "learning_rate": 0.0001,
      "loss": 1.4091,
      "step": 60
    },
    {
      "epoch": 0.112,
      "grad_norm": 7.1347479820251465,
      "learning_rate": 0.0001,
      "loss": 0.85,
      "step": 70
    },
    {
      "epoch": 0.128,
      "grad_norm": 3.1461501121520996,
      "learning_rate": 0.0001,
      "loss": 0.6901,
      "step": 80
    },
    {
      "epoch": 0.144,
      "grad_norm": 1.2969322204589844,
      "learning_rate": 0.0001,
      "loss": 0.5742,
      "step": 90
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.384674549102783,
      "learning_rate": 0.0001,
      "loss": 0.781,
      "step": 100
    },
    {
      "epoch": 0.176,
      "grad_norm": 1.1518051624298096,
      "learning_rate": 0.0001,
      "loss": 0.6573,
      "step": 110
    },
    {
      "epoch": 0.192,
      "grad_norm": 1.042501449584961,
      "learning_rate": 0.0001,
      "loss": 0.7151,
      "step": 120
    },
    {
      "epoch": 0.208,
      "grad_norm": 2.2350070476531982,
      "learning_rate": 0.0001,
      "loss": 0.6271,
      "step": 130
    },
    {
      "epoch": 0.224,
      "grad_norm": 29.857282638549805,
      "learning_rate": 0.0001,
      "loss": 1.2141,
      "step": 140
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.7340813875198364,
      "learning_rate": 0.0001,
      "loss": 0.8102,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.484662633791488e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}