{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011927836588638736,
  "eval_steps": 2,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005963918294319368,
      "grad_norm": 1.6181567907333374,
      "learning_rate": 2e-05,
      "loss": 0.9239,
      "step": 1
    },
    {
      "epoch": 0.0005963918294319368,
      "eval_loss": 0.9878367781639099,
      "eval_runtime": 163.2398,
      "eval_samples_per_second": 4.325,
      "eval_steps_per_second": 2.162,
      "step": 1
    },
    {
      "epoch": 0.0011927836588638736,
      "grad_norm": 1.3211941719055176,
      "learning_rate": 4e-05,
      "loss": 0.8277,
      "step": 2
    },
    {
      "epoch": 0.0011927836588638736,
      "eval_loss": 0.9849085211753845,
      "eval_runtime": 164.233,
      "eval_samples_per_second": 4.299,
      "eval_steps_per_second": 2.149,
      "step": 2
    },
    {
      "epoch": 0.0017891754882958103,
      "grad_norm": 1.601605772972107,
      "learning_rate": 6e-05,
      "loss": 0.8999,
      "step": 3
    },
    {
      "epoch": 0.0023855673177277472,
      "grad_norm": 1.8614158630371094,
      "learning_rate": 8e-05,
      "loss": 1.0458,
      "step": 4
    },
    {
      "epoch": 0.0023855673177277472,
      "eval_loss": 0.9355581998825073,
      "eval_runtime": 164.3033,
      "eval_samples_per_second": 4.297,
      "eval_steps_per_second": 2.148,
      "step": 4
    },
    {
      "epoch": 0.002981959147159684,
      "grad_norm": 1.9287219047546387,
      "learning_rate": 0.0001,
      "loss": 0.8825,
      "step": 5
    },
    {
      "epoch": 0.0035783509765916206,
      "grad_norm": 1.8925817012786865,
      "learning_rate": 0.00012,
      "loss": 0.8816,
      "step": 6
    },
    {
      "epoch": 0.0035783509765916206,
      "eval_loss": 0.7097150087356567,
      "eval_runtime": 164.4009,
      "eval_samples_per_second": 4.294,
      "eval_steps_per_second": 2.147,
      "step": 6
    },
    {
      "epoch": 0.004174742806023557,
      "grad_norm": 1.8584522008895874,
      "learning_rate": 0.00014,
      "loss": 0.8515,
      "step": 7
    },
    {
      "epoch": 0.0047711346354554944,
      "grad_norm": 1.426723599433899,
      "learning_rate": 0.00016,
      "loss": 0.5865,
      "step": 8
    },
    {
      "epoch": 0.0047711346354554944,
      "eval_loss": 0.4429967999458313,
      "eval_runtime": 164.4169,
      "eval_samples_per_second": 4.294,
      "eval_steps_per_second": 2.147,
      "step": 8
    },
    {
      "epoch": 0.005367526464887431,
      "grad_norm": 1.0089243650436401,
      "learning_rate": 0.00018,
      "loss": 0.4271,
      "step": 9
    },
    {
      "epoch": 0.005963918294319368,
      "grad_norm": 0.9701283574104309,
      "learning_rate": 0.0002,
      "loss": 0.3907,
      "step": 10
    },
    {
      "epoch": 0.005963918294319368,
      "eval_loss": 0.32635578513145447,
      "eval_runtime": 164.2476,
      "eval_samples_per_second": 4.298,
      "eval_steps_per_second": 2.149,
      "step": 10
    },
    {
      "epoch": 0.006560310123751305,
      "grad_norm": 1.138580083847046,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.5474,
      "step": 11
    },
    {
      "epoch": 0.007156701953183241,
      "grad_norm": 0.8171162605285645,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.2495,
      "step": 12
    },
    {
      "epoch": 0.007156701953183241,
      "eval_loss": 0.24059152603149414,
      "eval_runtime": 164.1937,
      "eval_samples_per_second": 4.3,
      "eval_steps_per_second": 2.15,
      "step": 12
    },
    {
      "epoch": 0.007753093782615178,
      "grad_norm": 0.9625129103660583,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.1852,
      "step": 13
    },
    {
      "epoch": 0.008349485612047115,
      "grad_norm": 1.333743929862976,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.2489,
      "step": 14
    },
    {
      "epoch": 0.008349485612047115,
      "eval_loss": 0.19883611798286438,
      "eval_runtime": 164.7477,
      "eval_samples_per_second": 4.285,
      "eval_steps_per_second": 2.143,
      "step": 14
    },
    {
      "epoch": 0.008945877441479051,
      "grad_norm": 1.2359386682510376,
      "learning_rate": 0.0001,
      "loss": 0.2844,
      "step": 15
    },
    {
      "epoch": 0.009542269270910989,
      "grad_norm": 1.2958358526229858,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.2865,
      "step": 16
    },
    {
      "epoch": 0.009542269270910989,
      "eval_loss": 0.17618103325366974,
      "eval_runtime": 164.6292,
      "eval_samples_per_second": 4.288,
      "eval_steps_per_second": 2.144,
      "step": 16
    },
    {
      "epoch": 0.010138661100342925,
      "grad_norm": 1.5453649759292603,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.1897,
      "step": 17
    },
    {
      "epoch": 0.010735052929774861,
      "grad_norm": 1.1022392511367798,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0626,
      "step": 18
    },
    {
      "epoch": 0.010735052929774861,
      "eval_loss": 0.15503820776939392,
      "eval_runtime": 164.3594,
      "eval_samples_per_second": 4.295,
      "eval_steps_per_second": 2.148,
      "step": 18
    },
    {
      "epoch": 0.0113314447592068,
      "grad_norm": 0.8071819543838501,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.149,
      "step": 19
    },
    {
      "epoch": 0.011927836588638736,
      "grad_norm": 0.8944453597068787,
      "learning_rate": 0.0,
      "loss": 0.1737,
      "step": 20
    },
    {
      "epoch": 0.011927836588638736,
      "eval_loss": 0.15017978847026825,
      "eval_runtime": 164.4532,
      "eval_samples_per_second": 4.293,
      "eval_steps_per_second": 2.147,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "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": 1.31825833869312e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}