{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 126,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.5622067451477051,
      "learning_rate": 4.922693215572695e-05,
      "loss": 2.359,
      "num_input_tokens_seen": 81920,
      "step": 10
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.5337382555007935,
      "learning_rate": 4.6955539334255716e-05,
      "loss": 2.3166,
      "num_input_tokens_seen": 163840,
      "step": 20
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.6496122479438782,
      "learning_rate": 4.332629679574566e-05,
      "loss": 2.2205,
      "num_input_tokens_seen": 245760,
      "step": 30
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.6310074329376221,
      "learning_rate": 3.856365659664399e-05,
      "loss": 2.159,
      "num_input_tokens_seen": 327680,
      "step": 40
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 1.2455250024795532,
      "learning_rate": 3.2962166256292113e-05,
      "loss": 2.0625,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 2.0558948516845703,
      "learning_rate": 2.686825233966061e-05,
      "loss": 2.0294,
      "num_input_tokens_seen": 491520,
      "step": 60
    },
    {
      "epoch": 3.888888888888889,
      "grad_norm": 1.1326656341552734,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 1.9556,
      "num_input_tokens_seen": 573440,
      "step": 70
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 1.0931998491287231,
      "learning_rate": 1.4717822421734718e-05,
      "loss": 1.8462,
      "num_input_tokens_seen": 655360,
      "step": 80
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.1948561668395996,
      "learning_rate": 9.412754953531663e-06,
      "loss": 1.8544,
      "num_input_tokens_seen": 737280,
      "step": 90
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 1.3811908960342407,
      "learning_rate": 5.071687319426946e-06,
      "loss": 1.7957,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 6.111111111111111,
      "grad_norm": 1.2763166427612305,
      "learning_rate": 1.9630947032398067e-06,
      "loss": 1.7244,
      "num_input_tokens_seen": 901120,
      "step": 110
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 1.3015738725662231,
      "learning_rate": 2.7922934437178695e-07,
      "loss": 1.7368,
      "num_input_tokens_seen": 983040,
      "step": 120
    },
    {
      "epoch": 7.0,
      "num_input_tokens_seen": 1032192,
      "step": 126,
      "total_flos": 4.69986584863703e+16,
      "train_loss": 1.9939293407258534,
      "train_runtime": 612.6473,
      "train_samples_per_second": 0.206,
      "train_steps_per_second": 0.206
    }
  ],
  "logging_steps": 10,
  "max_steps": 126,
  "num_input_tokens_seen": 1032192,
  "num_train_epochs": 7,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.69986584863703e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}