trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.34285714285714286,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022857142857142857,
      "grad_norm": 1.0595301389694214,
      "learning_rate": 0.002,
      "loss": 3.6082,
      "step": 10
    },
    {
      "epoch": 0.045714285714285714,
      "grad_norm": 0.2752091884613037,
      "learning_rate": 0.002,
      "loss": 1.5529,
      "step": 20
    },
    {
      "epoch": 0.06857142857142857,
      "grad_norm": 0.17800529301166534,
      "learning_rate": 0.002,
      "loss": 1.0928,
      "step": 30
    },
    {
      "epoch": 0.09142857142857143,
      "grad_norm": 0.21639685332775116,
      "learning_rate": 0.002,
      "loss": 0.99,
      "step": 40
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.2555713951587677,
      "learning_rate": 0.002,
      "loss": 0.884,
      "step": 50
    },
    {
      "epoch": 0.13714285714285715,
      "grad_norm": 0.1835678517818451,
      "learning_rate": 0.002,
      "loss": 1.2252,
      "step": 60
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.23407411575317383,
      "learning_rate": 0.002,
      "loss": 1.0325,
      "step": 70
    },
    {
      "epoch": 0.18285714285714286,
      "grad_norm": 0.20827867090702057,
      "learning_rate": 0.002,
      "loss": 0.9401,
      "step": 80
    },
    {
      "epoch": 0.2057142857142857,
      "grad_norm": 0.20146110653877258,
      "learning_rate": 0.002,
      "loss": 0.8852,
      "step": 90
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.2659783661365509,
      "learning_rate": 0.002,
      "loss": 0.8176,
      "step": 100
    },
    {
      "epoch": 0.25142857142857145,
      "grad_norm": 0.20099078118801117,
      "learning_rate": 0.002,
      "loss": 1.1806,
      "step": 110
    },
    {
      "epoch": 0.2742857142857143,
      "grad_norm": 0.18531735241413116,
      "learning_rate": 0.002,
      "loss": 0.9712,
      "step": 120
    },
    {
      "epoch": 0.29714285714285715,
      "grad_norm": 0.19588737189769745,
      "learning_rate": 0.002,
      "loss": 0.918,
      "step": 130
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.19109125435352325,
      "learning_rate": 0.002,
      "loss": 0.7857,
      "step": 140
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.2857687771320343,
      "learning_rate": 0.002,
      "loss": 0.7828,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.524734837978624e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}