{
  "best_metric": 1.3194454908370972,
  "best_model_checkpoint": "saves/Llama-3.2-3B-Instruct/Phi-3.5-mini-instruct-24-9-29\\checkpoint-100",
  "epoch": 0.16016016016016016,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016016016016016017,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2106,
      "step": 10
    },
    {
      "epoch": 0.0032032032032032033,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4712,
      "step": 20
    },
    {
      "epoch": 0.004804804804804805,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2974,
      "step": 30
    },
    {
      "epoch": 0.006406406406406407,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.304,
      "step": 40
    },
    {
      "epoch": 0.008008008008008008,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2863,
      "step": 50
    },
    {
      "epoch": 0.00960960960960961,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.5074,
      "step": 60
    },
    {
      "epoch": 0.01121121121121121,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3915,
      "step": 70
    },
    {
      "epoch": 0.012812812812812813,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3476,
      "step": 80
    },
    {
      "epoch": 0.014414414414414415,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3663,
      "step": 90
    },
    {
      "epoch": 0.016016016016016016,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.428,
      "step": 100
    },
    {
      "epoch": 0.016016016016016016,
      "eval_loss": 1.3194454908370972,
      "eval_runtime": 12.8069,
      "eval_samples_per_second": 7.808,
      "eval_steps_per_second": 3.904,
      "step": 100
    },
    {
      "epoch": 0.01761761761761762,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2343,
      "step": 110
    },
    {
      "epoch": 0.01921921921921922,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.343,
      "step": 120
    },
    {
      "epoch": 0.02082082082082082,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3258,
      "step": 130
    },
    {
      "epoch": 0.02242242242242242,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3007,
      "step": 140
    },
    {
      "epoch": 0.024024024024024024,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.35,
      "step": 150
    },
    {
      "epoch": 0.025625625625625627,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2401,
      "step": 160
    },
    {
      "epoch": 0.027227227227227226,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2047,
      "step": 170
    },
    {
      "epoch": 0.02882882882882883,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3125,
      "step": 180
    },
    {
      "epoch": 0.03043043043043043,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.283,
      "step": 190
    },
    {
      "epoch": 0.03203203203203203,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2653,
      "step": 200
    },
    {
      "epoch": 0.03203203203203203,
      "eval_loss": 1.3194454908370972,
      "eval_runtime": 12.8038,
      "eval_samples_per_second": 7.81,
      "eval_steps_per_second": 3.905,
      "step": 200
    },
    {
      "epoch": 0.033633633633633635,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3293,
      "step": 210
    },
    {
      "epoch": 0.03523523523523524,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.5406,
      "step": 220
    },
    {
      "epoch": 0.036836836836836834,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2827,
      "step": 230
    },
    {
      "epoch": 0.03843843843843844,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2914,
      "step": 240
    },
    {
      "epoch": 0.04004004004004004,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3335,
      "step": 250
    },
    {
      "epoch": 0.04164164164164164,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4173,
      "step": 260
    },
    {
      "epoch": 0.043243243243243246,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2077,
      "step": 270
    },
    {
      "epoch": 0.04484484484484484,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2665,
      "step": 280
    },
    {
      "epoch": 0.046446446446446445,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3744,
      "step": 290
    },
    {
      "epoch": 0.04804804804804805,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3084,
      "step": 300
    },
    {
      "epoch": 0.04804804804804805,
      "eval_loss": 1.3194454908370972,
      "eval_runtime": 12.9051,
      "eval_samples_per_second": 7.749,
      "eval_steps_per_second": 3.874,
      "step": 300
    },
    {
      "epoch": 0.04964964964964965,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3119,
      "step": 310
    },
    {
      "epoch": 0.051251251251251254,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.1759,
      "step": 320
    },
    {
      "epoch": 0.05285285285285285,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4001,
      "step": 330
    },
    {
      "epoch": 0.05445445445445445,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3775,
      "step": 340
    },
    {
      "epoch": 0.056056056056056056,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2751,
      "step": 350
    },
    {
      "epoch": 0.05765765765765766,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3655,
      "step": 360
    },
    {
      "epoch": 0.05925925925925926,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3717,
      "step": 370
    },
    {
      "epoch": 0.06086086086086086,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.22,
      "step": 380
    },
    {
      "epoch": 0.06246246246246246,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3391,
      "step": 390
    },
    {
      "epoch": 0.06406406406406406,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3234,
      "step": 400
    },
    {
      "epoch": 0.06406406406406406,
      "eval_loss": 1.3194454908370972,
      "eval_runtime": 12.7832,
      "eval_samples_per_second": 7.823,
      "eval_steps_per_second": 3.911,
      "step": 400
    },
    {
      "epoch": 0.06566566566566566,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.1899,
      "step": 410
    },
    {
      "epoch": 0.06726726726726727,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4017,
      "step": 420
    },
    {
      "epoch": 0.06886886886886887,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4969,
      "step": 430
    },
    {
      "epoch": 0.07047047047047048,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2447,
      "step": 440
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3669,
      "step": 450
    },
    {
      "epoch": 0.07367367367367367,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.5245,
      "step": 460
    },
    {
      "epoch": 0.07527527527527528,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4036,
      "step": 470
    },
    {
      "epoch": 0.07687687687687687,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4029,
      "step": 480
    },
    {
      "epoch": 0.07847847847847848,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.5582,
      "step": 490
    },
    {
      "epoch": 0.08008008008008008,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4091,
      "step": 500
    },
    {
      "epoch": 0.08008008008008008,
      "eval_loss": 1.3194454908370972,
      "eval_runtime": 12.8939,
      "eval_samples_per_second": 7.756,
      "eval_steps_per_second": 3.878,
      "step": 500
    },
    {
      "epoch": 0.08168168168168168,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2554,
      "step": 510
    },
    {
      "epoch": 0.08328328328328329,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3238,
      "step": 520
    },
    {
      "epoch": 0.08488488488488488,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2115,
      "step": 530
    },
    {
      "epoch": 0.08648648648648649,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3589,
      "step": 540
    },
    {
      "epoch": 0.08808808808808809,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3267,
      "step": 550
    },
    {
      "epoch": 0.08968968968968968,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2068,
      "step": 560
    },
    {
      "epoch": 0.0912912912912913,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4504,
      "step": 570
    },
    {
      "epoch": 0.09289289289289289,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3775,
      "step": 580
    },
    {
      "epoch": 0.0944944944944945,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3212,
      "step": 590
    },
    {
      "epoch": 0.0960960960960961,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2878,
      "step": 600
    },
    {
      "epoch": 0.0960960960960961,
      "eval_loss": 1.3194454908370972,
      "eval_runtime": 12.7841,
      "eval_samples_per_second": 7.822,
      "eval_steps_per_second": 3.911,
      "step": 600
    },
    {
      "epoch": 0.09769769769769769,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4902,
      "step": 610
    },
    {
      "epoch": 0.0992992992992993,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.203,
      "step": 620
    },
    {
      "epoch": 0.1009009009009009,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2783,
      "step": 630
    },
    {
      "epoch": 0.10250250250250251,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2326,
      "step": 640
    },
    {
      "epoch": 0.1041041041041041,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3132,
      "step": 650
    },
    {
      "epoch": 0.1057057057057057,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2495,
      "step": 660
    },
    {
      "epoch": 0.10730730730730731,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.329,
      "step": 670
    },
    {
      "epoch": 0.1089089089089089,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3178,
      "step": 680
    },
    {
      "epoch": 0.11051051051051052,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3798,
      "step": 690
    },
    {
      "epoch": 0.11211211211211211,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2933,
      "step": 700
    },
    {
      "epoch": 0.11211211211211211,
      "eval_loss": 1.3194454908370972,
      "eval_runtime": 12.8596,
      "eval_samples_per_second": 7.776,
      "eval_steps_per_second": 3.888,
      "step": 700
    },
    {
      "epoch": 0.11371371371371371,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2721,
      "step": 710
    },
    {
      "epoch": 0.11531531531531532,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3859,
      "step": 720
    },
    {
      "epoch": 0.11691691691691691,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2536,
      "step": 730
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3625,
      "step": 740
    },
    {
      "epoch": 0.12012012012012012,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3386,
      "step": 750
    },
    {
      "epoch": 0.12172172172172172,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4023,
      "step": 760
    },
    {
      "epoch": 0.12332332332332333,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2977,
      "step": 770
    },
    {
      "epoch": 0.12492492492492492,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4091,
      "step": 780
    },
    {
      "epoch": 0.12652652652652652,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2513,
      "step": 790
    },
    {
      "epoch": 0.12812812812812813,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3246,
      "step": 800
    },
    {
      "epoch": 0.12812812812812813,
      "eval_loss": 1.3194454908370972,
      "eval_runtime": 12.7102,
      "eval_samples_per_second": 7.868,
      "eval_steps_per_second": 3.934,
      "step": 800
    },
    {
      "epoch": 0.12972972972972974,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3271,
      "step": 810
    },
    {
      "epoch": 0.13133133133133132,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3497,
      "step": 820
    },
    {
      "epoch": 0.13293293293293293,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2833,
      "step": 830
    },
    {
      "epoch": 0.13453453453453454,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3491,
      "step": 840
    },
    {
      "epoch": 0.13613613613613615,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2592,
      "step": 850
    },
    {
      "epoch": 0.13773773773773773,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3241,
      "step": 860
    },
    {
      "epoch": 0.13933933933933934,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3809,
      "step": 870
    },
    {
      "epoch": 0.14094094094094095,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.294,
      "step": 880
    },
    {
      "epoch": 0.14254254254254253,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3025,
      "step": 890
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2911,
      "step": 900
    },
    {
      "epoch": 0.14414414414414414,
      "eval_loss": 1.3194454908370972,
      "eval_runtime": 12.7786,
      "eval_samples_per_second": 7.826,
      "eval_steps_per_second": 3.913,
      "step": 900
    },
    {
      "epoch": 0.14574574574574575,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3149,
      "step": 910
    },
    {
      "epoch": 0.14734734734734733,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2697,
      "step": 920
    },
    {
      "epoch": 0.14894894894894894,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3088,
      "step": 930
    },
    {
      "epoch": 0.15055055055055055,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3579,
      "step": 940
    },
    {
      "epoch": 0.15215215215215216,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4073,
      "step": 950
    },
    {
      "epoch": 0.15375375375375375,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2242,
      "step": 960
    },
    {
      "epoch": 0.15535535535535536,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.3585,
      "step": 970
    },
    {
      "epoch": 0.15695695695695697,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2407,
      "step": 980
    },
    {
      "epoch": 0.15855855855855855,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2609,
      "step": 990
    },
    {
      "epoch": 0.16016016016016016,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.4227,
      "step": 1000
    },
    {
      "epoch": 0.16016016016016016,
      "eval_loss": 1.3194454908370972,
      "eval_runtime": 12.8395,
      "eval_samples_per_second": 7.788,
      "eval_steps_per_second": 3.894,
      "step": 1000
    },
    {
      "epoch": 0.16016016016016016,
      "step": 1000,
      "total_flos": 2.9103944129622835e+17,
      "train_loss": 1.3281120185852051,
      "train_runtime": 3519.7932,
      "train_samples_per_second": 4.546,
      "train_steps_per_second": 0.284
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.9103944129622835e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}