{
  "best_metric": 1.1743316650390625,
  "best_model_checkpoint": "/gscratch/stf/seunguk/dipika/olmo-code-sft/train/result_outputs/13b_py23_mix_10k_normal/allenai_OLMo-2-1124-13B-Instruct/r64_lr1.5e-05/checkpoint-429",
  "epoch": 2.9861224489795917,
  "eval_steps": 39,
  "global_step": 459,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006530612244897959,
      "grad_norm": 7.480628490447998,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 15.3347,
      "step": 1
    },
    {
      "epoch": 0.0653061224489796,
      "grad_norm": 7.086081504821777,
      "learning_rate": 3e-06,
      "loss": 16.3175,
      "step": 10
    },
    {
      "epoch": 0.1306122448979592,
      "grad_norm": 6.222248077392578,
      "learning_rate": 6e-06,
      "loss": 16.0446,
      "step": 20
    },
    {
      "epoch": 0.19591836734693877,
      "grad_norm": 5.059980392456055,
      "learning_rate": 9e-06,
      "loss": 14.2873,
      "step": 30
    },
    {
      "epoch": 0.2546938775510204,
      "eval_loss": 1.4279829263687134,
      "eval_runtime": 10.3422,
      "eval_samples_per_second": 9.669,
      "eval_steps_per_second": 1.257,
      "step": 39
    },
    {
      "epoch": 0.2612244897959184,
      "grad_norm": 2.272027015686035,
      "learning_rate": 1.2e-05,
      "loss": 12.1039,
      "step": 40
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 1.4014880657196045,
      "learning_rate": 1.5e-05,
      "loss": 10.8603,
      "step": 50
    },
    {
      "epoch": 0.39183673469387753,
      "grad_norm": 1.2100738286972046,
      "learning_rate": 1.4977885819099278e-05,
      "loss": 10.3019,
      "step": 60
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.9245325922966003,
      "learning_rate": 1.4911673686262952e-05,
      "loss": 10.208,
      "step": 70
    },
    {
      "epoch": 0.5093877551020408,
      "eval_loss": 1.2185193300247192,
      "eval_runtime": 10.2655,
      "eval_samples_per_second": 9.741,
      "eval_steps_per_second": 1.266,
      "step": 78
    },
    {
      "epoch": 0.5224489795918368,
      "grad_norm": 1.0301765203475952,
      "learning_rate": 1.4801754062046587e-05,
      "loss": 9.9344,
      "step": 80
    },
    {
      "epoch": 0.5877551020408164,
      "grad_norm": 0.9953351020812988,
      "learning_rate": 1.4648775155104705e-05,
      "loss": 9.8284,
      "step": 90
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 0.9446775913238525,
      "learning_rate": 1.4453639099629869e-05,
      "loss": 9.8364,
      "step": 100
    },
    {
      "epoch": 0.7183673469387755,
      "grad_norm": 0.8912749290466309,
      "learning_rate": 1.4217496635363684e-05,
      "loss": 9.8114,
      "step": 110
    },
    {
      "epoch": 0.7640816326530612,
      "eval_loss": 1.1940735578536987,
      "eval_runtime": 10.2644,
      "eval_samples_per_second": 9.742,
      "eval_steps_per_second": 1.267,
      "step": 117
    },
    {
      "epoch": 0.7836734693877551,
      "grad_norm": 0.8845490217208862,
      "learning_rate": 1.3941740321552318e-05,
      "loss": 9.7705,
      "step": 120
    },
    {
      "epoch": 0.8489795918367347,
      "grad_norm": 0.9408980011940002,
      "learning_rate": 1.3627996324864611e-05,
      "loss": 9.6758,
      "step": 130
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 1.036733865737915,
      "learning_rate": 1.3278114829700362e-05,
      "loss": 9.7541,
      "step": 140
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 1.0284887552261353,
      "learning_rate": 1.2894159127440344e-05,
      "loss": 9.4729,
      "step": 150
    },
    {
      "epoch": 1.0130612244897959,
      "eval_loss": 1.1869996786117554,
      "eval_runtime": 10.2878,
      "eval_samples_per_second": 9.72,
      "eval_steps_per_second": 1.264,
      "step": 156
    },
    {
      "epoch": 1.0391836734693878,
      "grad_norm": 0.9137061238288879,
      "learning_rate": 1.2478393448979922e-05,
      "loss": 8.7202,
      "step": 160
    },
    {
      "epoch": 1.1044897959183673,
      "grad_norm": 1.0339038372039795,
      "learning_rate": 1.2033269612299312e-05,
      "loss": 9.5115,
      "step": 170
    },
    {
      "epoch": 1.169795918367347,
      "grad_norm": 1.0830352306365967,
      "learning_rate": 1.1561412563811198e-05,
      "loss": 9.5251,
      "step": 180
    },
    {
      "epoch": 1.2351020408163265,
      "grad_norm": 1.210103988647461,
      "learning_rate": 1.1065604898750127e-05,
      "loss": 9.6413,
      "step": 190
    },
    {
      "epoch": 1.2677551020408164,
      "eval_loss": 1.1819005012512207,
      "eval_runtime": 10.2481,
      "eval_samples_per_second": 9.758,
      "eval_steps_per_second": 1.269,
      "step": 195
    },
    {
      "epoch": 1.3004081632653062,
      "grad_norm": 1.1372894048690796,
      "learning_rate": 1.0548770451888665e-05,
      "loss": 9.3296,
      "step": 200
    },
    {
      "epoch": 1.3657142857142857,
      "grad_norm": 1.081299901008606,
      "learning_rate": 1.0013957055347779e-05,
      "loss": 9.5166,
      "step": 210
    },
    {
      "epoch": 1.4310204081632654,
      "grad_norm": 1.2336442470550537,
      "learning_rate": 9.464318565180596e-06,
      "loss": 9.5273,
      "step": 220
    },
    {
      "epoch": 1.4963265306122449,
      "grad_norm": 1.3089706897735596,
      "learning_rate": 8.903096262720867e-06,
      "loss": 9.6093,
      "step": 230
    },
    {
      "epoch": 1.5224489795918368,
      "eval_loss": 1.1787770986557007,
      "eval_runtime": 10.2953,
      "eval_samples_per_second": 9.713,
      "eval_steps_per_second": 1.263,
      "step": 234
    },
    {
      "epoch": 1.5616326530612246,
      "grad_norm": 1.2751823663711548,
      "learning_rate": 8.333599740374487e-06,
      "loss": 9.5248,
      "step": 240
    },
    {
      "epoch": 1.626938775510204,
      "grad_norm": 1.049634575843811,
      "learning_rate": 7.75918738457279e-06,
      "loss": 9.3375,
      "step": 250
    },
    {
      "epoch": 1.6922448979591835,
      "grad_norm": 1.1573090553283691,
      "learning_rate": 7.183246570981859e-06,
      "loss": 9.488,
      "step": 260
    },
    {
      "epoch": 1.7575510204081632,
      "grad_norm": 1.1605769395828247,
      "learning_rate": 6.609173688758989e-06,
      "loss": 9.456,
      "step": 270
    },
    {
      "epoch": 1.7771428571428571,
      "eval_loss": 1.1771632432937622,
      "eval_runtime": 10.3065,
      "eval_samples_per_second": 9.703,
      "eval_steps_per_second": 1.261,
      "step": 273
    },
    {
      "epoch": 1.822857142857143,
      "grad_norm": 1.0704485177993774,
      "learning_rate": 6.0403541116555636e-06,
      "loss": 9.6155,
      "step": 280
    },
    {
      "epoch": 1.8881632653061224,
      "grad_norm": 1.5852781534194946,
      "learning_rate": 5.480142234079027e-06,
      "loss": 9.4657,
      "step": 290
    },
    {
      "epoch": 1.953469387755102,
      "grad_norm": 1.571425437927246,
      "learning_rate": 4.9318416898436404e-06,
      "loss": 9.5001,
      "step": 300
    },
    {
      "epoch": 2.013061224489796,
      "grad_norm": 1.1965842247009277,
      "learning_rate": 4.398685870262254e-06,
      "loss": 8.5998,
      "step": 310
    },
    {
      "epoch": 2.0261224489795917,
      "eval_loss": 1.1757442951202393,
      "eval_runtime": 10.261,
      "eval_samples_per_second": 9.746,
      "eval_steps_per_second": 1.267,
      "step": 312
    },
    {
      "epoch": 2.0783673469387756,
      "grad_norm": 1.2646270990371704,
      "learning_rate": 3.883818856466194e-06,
      "loss": 9.2906,
      "step": 320
    },
    {
      "epoch": 2.143673469387755,
      "grad_norm": 1.1598410606384277,
      "learning_rate": 3.390276878397574e-06,
      "loss": 9.339,
      "step": 330
    },
    {
      "epoch": 2.2089795918367345,
      "grad_norm": 1.4158833026885986,
      "learning_rate": 2.9209704098124204e-06,
      "loss": 9.5879,
      "step": 340
    },
    {
      "epoch": 2.2742857142857145,
      "grad_norm": 1.4064640998840332,
      "learning_rate": 2.47866700488251e-06,
      "loss": 9.1889,
      "step": 350
    },
    {
      "epoch": 2.280816326530612,
      "eval_loss": 1.1747936010360718,
      "eval_runtime": 10.2783,
      "eval_samples_per_second": 9.729,
      "eval_steps_per_second": 1.265,
      "step": 351
    },
    {
      "epoch": 2.339591836734694,
      "grad_norm": 1.3816022872924805,
      "learning_rate": 2.0659749776104147e-06,
      "loss": 9.1374,
      "step": 360
    },
    {
      "epoch": 2.4048979591836734,
      "grad_norm": 1.2557651996612549,
      "learning_rate": 1.6853280203020998e-06,
      "loss": 9.4392,
      "step": 370
    },
    {
      "epoch": 2.470204081632653,
      "grad_norm": 1.3306424617767334,
      "learning_rate": 1.3389708518037574e-06,
      "loss": 9.3487,
      "step": 380
    },
    {
      "epoch": 2.535510204081633,
      "grad_norm": 1.1443352699279785,
      "learning_rate": 1.0289459801368406e-06,
      "loss": 9.4177,
      "step": 390
    },
    {
      "epoch": 2.535510204081633,
      "eval_loss": 1.1745020151138306,
      "eval_runtime": 10.2669,
      "eval_samples_per_second": 9.74,
      "eval_steps_per_second": 1.266,
      "step": 390
    },
    {
      "epoch": 2.6008163265306123,
      "grad_norm": 1.2281705141067505,
      "learning_rate": 7.570816575935527e-07,
      "loss": 9.3764,
      "step": 400
    },
    {
      "epoch": 2.666122448979592,
      "grad_norm": 1.2790119647979736,
      "learning_rate": 5.249810993230036e-07,
      "loss": 9.4371,
      "step": 410
    },
    {
      "epoch": 2.7314285714285713,
      "grad_norm": 1.3635507822036743,
      "learning_rate": 3.3401302898726395e-07,
      "loss": 9.4412,
      "step": 420
    },
    {
      "epoch": 2.790204081632653,
      "eval_loss": 1.1743316650390625,
      "eval_runtime": 10.2825,
      "eval_samples_per_second": 9.725,
      "eval_steps_per_second": 1.264,
      "step": 429
    },
    {
      "epoch": 2.796734693877551,
      "grad_norm": 1.5212961435317993,
      "learning_rate": 1.853036072406436e-07,
      "loss": 9.2948,
      "step": 430
    },
    {
      "epoch": 2.8620408163265307,
      "grad_norm": 1.4816234111785889,
      "learning_rate": 7.972979063091468e-08,
      "loss": 9.5499,
      "step": 440
    },
    {
      "epoch": 2.92734693877551,
      "grad_norm": 1.343505620956421,
      "learning_rate": 1.7914160085782116e-08,
      "loss": 9.3699,
      "step": 450
    }
  ],
  "logging_steps": 10,
  "max_steps": 459,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 39,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 10,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.675106681184322e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}