{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010862480990658266,
  "eval_steps": 9,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00043449923962633063,
      "grad_norm": 0.7322242259979248,
      "learning_rate": 1e-05,
      "loss": 4.6281,
      "step": 1
    },
    {
      "epoch": 0.00043449923962633063,
      "eval_loss": 2.2681100368499756,
      "eval_runtime": 936.1826,
      "eval_samples_per_second": 2.071,
      "eval_steps_per_second": 0.26,
      "step": 1
    },
    {
      "epoch": 0.0008689984792526613,
      "grad_norm": 0.7169781923294067,
      "learning_rate": 2e-05,
      "loss": 4.5781,
      "step": 2
    },
    {
      "epoch": 0.001303497718878992,
      "grad_norm": 0.6220166683197021,
      "learning_rate": 3e-05,
      "loss": 4.5088,
      "step": 3
    },
    {
      "epoch": 0.0017379969585053225,
      "grad_norm": 0.6577661037445068,
      "learning_rate": 4e-05,
      "loss": 4.5698,
      "step": 4
    },
    {
      "epoch": 0.0021724961981316533,
      "grad_norm": 0.6816755533218384,
      "learning_rate": 5e-05,
      "loss": 4.5211,
      "step": 5
    },
    {
      "epoch": 0.002606995437757984,
      "grad_norm": 0.7988889217376709,
      "learning_rate": 6e-05,
      "loss": 4.4963,
      "step": 6
    },
    {
      "epoch": 0.0030414946773843145,
      "grad_norm": 0.9024376273155212,
      "learning_rate": 7e-05,
      "loss": 4.5237,
      "step": 7
    },
    {
      "epoch": 0.003475993917010645,
      "grad_norm": 1.0115993022918701,
      "learning_rate": 8e-05,
      "loss": 4.321,
      "step": 8
    },
    {
      "epoch": 0.003910493156636976,
      "grad_norm": 1.0931627750396729,
      "learning_rate": 9e-05,
      "loss": 4.1351,
      "step": 9
    },
    {
      "epoch": 0.003910493156636976,
      "eval_loss": 1.9916020631790161,
      "eval_runtime": 939.5626,
      "eval_samples_per_second": 2.064,
      "eval_steps_per_second": 0.259,
      "step": 9
    },
    {
      "epoch": 0.004344992396263307,
      "grad_norm": 1.3642878532409668,
      "learning_rate": 0.0001,
      "loss": 3.9607,
      "step": 10
    },
    {
      "epoch": 0.004779491635889637,
      "grad_norm": 1.5105156898498535,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.7648,
      "step": 11
    },
    {
      "epoch": 0.005213990875515968,
      "grad_norm": 1.1561989784240723,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.3213,
      "step": 12
    },
    {
      "epoch": 0.005648490115142298,
      "grad_norm": 1.2711970806121826,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.1605,
      "step": 13
    },
    {
      "epoch": 0.006082989354768629,
      "grad_norm": 1.2520768642425537,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.7325,
      "step": 14
    },
    {
      "epoch": 0.00651748859439496,
      "grad_norm": 1.3953733444213867,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.4149,
      "step": 15
    },
    {
      "epoch": 0.00695198783402129,
      "grad_norm": 1.2582489252090454,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.3447,
      "step": 16
    },
    {
      "epoch": 0.007386487073647621,
      "grad_norm": 1.0818967819213867,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.0851,
      "step": 17
    },
    {
      "epoch": 0.007820986313273952,
      "grad_norm": 1.0467973947525024,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.9362,
      "step": 18
    },
    {
      "epoch": 0.007820986313273952,
      "eval_loss": 0.9285404086112976,
      "eval_runtime": 938.7411,
      "eval_samples_per_second": 2.066,
      "eval_steps_per_second": 0.259,
      "step": 18
    },
    {
      "epoch": 0.008255485552900283,
      "grad_norm": 1.0093339681625366,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.9558,
      "step": 19
    },
    {
      "epoch": 0.008689984792526613,
      "grad_norm": 0.9407274723052979,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.7688,
      "step": 20
    },
    {
      "epoch": 0.009124484032152944,
      "grad_norm": 0.89859539270401,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.6283,
      "step": 21
    },
    {
      "epoch": 0.009558983271779274,
      "grad_norm": 1.0678013563156128,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.2764,
      "step": 22
    },
    {
      "epoch": 0.009993482511405605,
      "grad_norm": 0.9045027494430542,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.4258,
      "step": 23
    },
    {
      "epoch": 0.010427981751031936,
      "grad_norm": 0.9049425721168518,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.3559,
      "step": 24
    },
    {
      "epoch": 0.010862480990658266,
      "grad_norm": 0.9243524074554443,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.1685,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.03043846422528e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}