{
  "best_metric": 1.4588630199432373,
  "best_model_checkpoint": "/kaggle/working/mistral-finance/checkpoint-562",
  "epoch": 1.9982222222222221,
  "eval_steps": 500,
  "global_step": 1124,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 2.05849027633667,
      "learning_rate": 0.00014705882352941178,
      "loss": 1.6696,
      "step": 25
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 1.0702296495437622,
      "learning_rate": 0.00019989368862054812,
      "loss": 1.357,
      "step": 50
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 1.1396949291229248,
      "learning_rate": 0.00019930260467930706,
      "loss": 1.3491,
      "step": 75
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 1.0242853164672852,
      "learning_rate": 0.00019819617404036628,
      "loss": 1.3763,
      "step": 100
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.0257024765014648,
      "learning_rate": 0.00019658013870191258,
      "loss": 1.3871,
      "step": 125
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 1.249104619026184,
      "learning_rate": 0.00019446288533696144,
      "loss": 1.3785,
      "step": 150
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 1.0635004043579102,
      "learning_rate": 0.00019185540176938065,
      "loss": 1.3311,
      "step": 175
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.0092597007751465,
      "learning_rate": 0.0001887712199508264,
      "loss": 1.3478,
      "step": 200
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.1924484968185425,
      "learning_rate": 0.00018522634573452313,
      "loss": 1.335,
      "step": 225
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.0947246551513672,
      "learning_rate": 0.0001812391758103364,
      "loss": 1.3503,
      "step": 250
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 1.3176860809326172,
      "learning_rate": 0.00017683040223221826,
      "loss": 1.3804,
      "step": 275
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.9309181571006775,
      "learning_rate": 0.00017202290503349436,
      "loss": 1.3684,
      "step": 300
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 1.0398943424224854,
      "learning_rate": 0.00016684163348728364,
      "loss": 1.3663,
      "step": 325
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 1.141608715057373,
      "learning_rate": 0.00016131347662826792,
      "loss": 1.3751,
      "step": 350
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.158071517944336,
      "learning_rate": 0.00015546712370776005,
      "loss": 1.4016,
      "step": 375
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 1.0812592506408691,
      "learning_rate": 0.00014933291530626046,
      "loss": 1.3253,
      "step": 400
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 0.9800846576690674,
      "learning_rate": 0.0001429426858761777,
      "loss": 1.3642,
      "step": 425
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9113844037055969,
      "learning_rate": 0.0001363295985318628,
      "loss": 1.3555,
      "step": 450
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 1.076130986213684,
      "learning_rate": 0.0001295279729443406,
      "loss": 1.3169,
      "step": 475
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.120133876800537,
      "learning_rate": 0.0001225731072339054,
      "loss": 1.4286,
      "step": 500
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.982066810131073,
      "learning_rate": 0.00011550109478489894,
      "loss": 1.3114,
      "step": 525
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 1.1076117753982544,
      "learning_rate": 0.00010834863693333805,
      "loss": 1.2723,
      "step": 550
    },
    {
      "epoch": 0.9991111111111111,
      "eval_loss": 1.4588630199432373,
      "eval_runtime": 398.985,
      "eval_samples_per_second": 2.506,
      "eval_steps_per_second": 0.313,
      "step": 562
    },
    {
      "epoch": 1.0222222222222221,
      "grad_norm": 1.101711392402649,
      "learning_rate": 0.00010115285249948073,
      "loss": 1.2287,
      "step": 575
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 1.0834338665008545,
      "learning_rate": 9.395108515379082e-05,
      "loss": 1.0606,
      "step": 600
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 1.438604474067688,
      "learning_rate": 8.678070961600693e-05,
      "loss": 1.0234,
      "step": 625
    },
    {
      "epoch": 1.1555555555555554,
      "grad_norm": 1.3387609720230103,
      "learning_rate": 7.967893769307608e-05,
      "loss": 1.018,
      "step": 650
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.1515276432037354,
      "learning_rate": 7.268262516254934e-05,
      "loss": 1.0172,
      "step": 675
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 1.1627109050750732,
      "learning_rate": 6.582808050364864e-05,
      "loss": 1.02,
      "step": 700
    },
    {
      "epoch": 1.2888888888888888,
      "grad_norm": 1.106823205947876,
      "learning_rate": 5.915087646862562e-05,
      "loss": 0.9891,
      "step": 725
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.2206761837005615,
      "learning_rate": 5.26856654722928e-05,
      "loss": 1.0186,
      "step": 750
    },
    {
      "epoch": 1.3777777777777778,
      "grad_norm": 1.2441461086273193,
      "learning_rate": 4.646599975779281e-05,
      "loss": 1.0631,
      "step": 775
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 1.3241393566131592,
      "learning_rate": 4.0524157271883634e-05,
      "loss": 1.0262,
      "step": 800
    },
    {
      "epoch": 1.4666666666666668,
      "grad_norm": 1.316847324371338,
      "learning_rate": 3.4890974153388076e-05,
      "loss": 1.0161,
      "step": 825
    },
    {
      "epoch": 1.511111111111111,
      "grad_norm": 1.2122712135314941,
      "learning_rate": 2.959568470413572e-05,
      "loss": 0.9915,
      "step": 850
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 1.1466624736785889,
      "learning_rate": 2.4665769672892947e-05,
      "loss": 1.0087,
      "step": 875
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.1826366186141968,
      "learning_rate": 2.012681363963621e-05,
      "loss": 1.0173,
      "step": 900
    },
    {
      "epoch": 1.6444444444444444,
      "grad_norm": 1.1746392250061035,
      "learning_rate": 1.600237224029565e-05,
      "loss": 0.9612,
      "step": 925
    },
    {
      "epoch": 1.6888888888888889,
      "grad_norm": 1.2078734636306763,
      "learning_rate": 1.2313849921027277e-05,
      "loss": 0.9795,
      "step": 950
    },
    {
      "epoch": 1.7333333333333334,
      "grad_norm": 1.3540568351745605,
      "learning_rate": 9.08038885642729e-06,
      "loss": 1.0277,
      "step": 975
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 1.383931279182434,
      "learning_rate": 6.318769608165332e-06,
      "loss": 1.0562,
      "step": 1000
    },
    {
      "epoch": 1.8222222222222222,
      "grad_norm": 1.3799922466278076,
      "learning_rate": 4.043324039584728e-06,
      "loss": 0.9885,
      "step": 1025
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 1.371010184288025,
      "learning_rate": 2.2658609382127384e-06,
      "loss": 0.9994,
      "step": 1050
    },
    {
      "epoch": 1.911111111111111,
      "grad_norm": 1.4156333208084106,
      "learning_rate": 9.95604732175215e-07,
      "loss": 1.0306,
      "step": 1075
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 1.3464016914367676,
      "learning_rate": 2.391476185563235e-07,
      "loss": 1.0242,
      "step": 1100
    },
    {
      "epoch": 1.9982222222222221,
      "eval_loss": 1.506870150566101,
      "eval_runtime": 399.1436,
      "eval_samples_per_second": 2.505,
      "eval_steps_per_second": 0.313,
      "step": 1124
    }
  ],
  "logging_steps": 25,
  "max_steps": 1124,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 1.4561037719927194e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}