{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9900497512437811,
  "eval_steps": 35,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028429282160625444,
      "grad_norm": 5.805906295776367,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 10.5536,
      "step": 5
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 7.361557960510254,
      "learning_rate": 2.857142857142857e-05,
      "loss": 10.4859,
      "step": 10
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 9.014820098876953,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 9.3188,
      "step": 15
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 10.094988822937012,
      "learning_rate": 5.714285714285714e-05,
      "loss": 6.6553,
      "step": 20
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 15.287639617919922,
      "learning_rate": 7.142857142857143e-05,
      "loss": 3.4581,
      "step": 25
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 1.3499271869659424,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.5521,
      "step": 30
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 1.5600136518478394,
      "learning_rate": 0.0001,
      "loss": 0.3823,
      "step": 35
    },
    {
      "epoch": 0.19900497512437812,
      "eval_loss": 0.35117578506469727,
      "eval_runtime": 230.9383,
      "eval_samples_per_second": 10.825,
      "eval_steps_per_second": 10.825,
      "step": 35
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 3.365349531173706,
      "learning_rate": 9.993784606094612e-05,
      "loss": 0.363,
      "step": 40
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 1.3274873495101929,
      "learning_rate": 9.975153876827008e-05,
      "loss": 0.3428,
      "step": 45
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 1.2516767978668213,
      "learning_rate": 9.944154131125642e-05,
      "loss": 0.349,
      "step": 50
    },
    {
      "epoch": 0.31272210376687987,
      "grad_norm": 1.22030770778656,
      "learning_rate": 9.900862439242719e-05,
      "loss": 0.3336,
      "step": 55
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 1.0675277709960938,
      "learning_rate": 9.84538643114539e-05,
      "loss": 0.3486,
      "step": 60
    },
    {
      "epoch": 0.3695806680881308,
      "grad_norm": 1.42255699634552,
      "learning_rate": 9.777864028930705e-05,
      "loss": 0.2993,
      "step": 65
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 2.10113787651062,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.3257,
      "step": 70
    },
    {
      "epoch": 0.39800995024875624,
      "eval_loss": 0.2916417121887207,
      "eval_runtime": 231.0131,
      "eval_samples_per_second": 10.822,
      "eval_steps_per_second": 10.822,
      "step": 70
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 1.51693594455719,
      "learning_rate": 9.607381059352038e-05,
      "loss": 0.3209,
      "step": 75
    },
    {
      "epoch": 0.4548685145700071,
      "grad_norm": 1.0357732772827148,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.2859,
      "step": 80
    },
    {
      "epoch": 0.48329779673063256,
      "grad_norm": 0.8819968104362488,
      "learning_rate": 9.391107866851143e-05,
      "loss": 0.3123,
      "step": 85
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 0.9069387316703796,
      "learning_rate": 9.266454408160779e-05,
      "loss": 0.273,
      "step": 90
    },
    {
      "epoch": 0.5401563610518835,
      "grad_norm": 0.9045886993408203,
      "learning_rate": 9.131193871579975e-05,
      "loss": 0.2927,
      "step": 95
    },
    {
      "epoch": 0.5685856432125089,
      "grad_norm": 1.3000465631484985,
      "learning_rate": 8.985662536114613e-05,
      "loss": 0.2767,
      "step": 100
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.7296444177627563,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2834,
      "step": 105
    },
    {
      "epoch": 0.5970149253731343,
      "eval_loss": 0.28583231568336487,
      "eval_runtime": 230.4985,
      "eval_samples_per_second": 10.846,
      "eval_steps_per_second": 10.846,
      "step": 105
    },
    {
      "epoch": 0.6254442075337597,
      "grad_norm": 0.6089270710945129,
      "learning_rate": 8.665259359149132e-05,
      "loss": 0.2764,
      "step": 110
    },
    {
      "epoch": 0.6538734896943852,
      "grad_norm": 0.8748773336410522,
      "learning_rate": 8.491184090430364e-05,
      "loss": 0.2816,
      "step": 115
    },
    {
      "epoch": 0.6823027718550106,
      "grad_norm": 0.7506688833236694,
      "learning_rate": 8.308429187984297e-05,
      "loss": 0.2766,
      "step": 120
    },
    {
      "epoch": 0.7107320540156361,
      "grad_norm": 0.6250064373016357,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.2746,
      "step": 125
    },
    {
      "epoch": 0.7391613361762616,
      "grad_norm": 0.687236487865448,
      "learning_rate": 7.91871836117395e-05,
      "loss": 0.2691,
      "step": 130
    },
    {
      "epoch": 0.767590618336887,
      "grad_norm": 1.2124730348587036,
      "learning_rate": 7.712731319328798e-05,
      "loss": 0.2977,
      "step": 135
    },
    {
      "epoch": 0.7960199004975125,
      "grad_norm": 0.7678080797195435,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2809,
      "step": 140
    },
    {
      "epoch": 0.7960199004975125,
      "eval_loss": 0.2728855609893799,
      "eval_runtime": 230.8787,
      "eval_samples_per_second": 10.828,
      "eval_steps_per_second": 10.828,
      "step": 140
    },
    {
      "epoch": 0.8244491826581379,
      "grad_norm": 1.257142424583435,
      "learning_rate": 7.281053286765815e-05,
      "loss": 0.2658,
      "step": 145
    },
    {
      "epoch": 0.8528784648187633,
      "grad_norm": 0.8419828414916992,
      "learning_rate": 7.056435515653059e-05,
      "loss": 0.289,
      "step": 150
    },
    {
      "epoch": 0.8813077469793887,
      "grad_norm": 0.6198025345802307,
      "learning_rate": 6.826705121831976e-05,
      "loss": 0.2941,
      "step": 155
    },
    {
      "epoch": 0.9097370291400142,
      "grad_norm": 0.5303702354431152,
      "learning_rate": 6.592433251258423e-05,
      "loss": 0.2752,
      "step": 160
    },
    {
      "epoch": 0.9381663113006397,
      "grad_norm": 1.7567023038864136,
      "learning_rate": 6.354202340715026e-05,
      "loss": 0.2569,
      "step": 165
    },
    {
      "epoch": 0.9665955934612651,
      "grad_norm": 0.6840919852256775,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.2587,
      "step": 170
    },
    {
      "epoch": 0.9950248756218906,
      "grad_norm": 0.5812920928001404,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2826,
      "step": 175
    },
    {
      "epoch": 0.9950248756218906,
      "eval_loss": 0.2588258981704712,
      "eval_runtime": 231.051,
      "eval_samples_per_second": 10.82,
      "eval_steps_per_second": 10.82,
      "step": 175
    },
    {
      "epoch": 1.023454157782516,
      "grad_norm": 0.5891302824020386,
      "learning_rate": 5.621718523237427e-05,
      "loss": 0.2676,
      "step": 180
    },
    {
      "epoch": 1.0518834399431414,
      "grad_norm": 0.7072641253471375,
      "learning_rate": 5.373650467932122e-05,
      "loss": 0.2378,
      "step": 185
    },
    {
      "epoch": 1.080312722103767,
      "grad_norm": 1.350577712059021,
      "learning_rate": 5.124653458690365e-05,
      "loss": 0.2682,
      "step": 190
    },
    {
      "epoch": 1.1087420042643923,
      "grad_norm": 0.8520832657814026,
      "learning_rate": 4.875346541309637e-05,
      "loss": 0.2454,
      "step": 195
    },
    {
      "epoch": 1.1371712864250179,
      "grad_norm": 0.7263408303260803,
      "learning_rate": 4.626349532067879e-05,
      "loss": 0.2622,
      "step": 200
    },
    {
      "epoch": 1.1656005685856432,
      "grad_norm": 1.0578335523605347,
      "learning_rate": 4.378281476762576e-05,
      "loss": 0.258,
      "step": 205
    },
    {
      "epoch": 1.1940298507462686,
      "grad_norm": 0.5315471291542053,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2476,
      "step": 210
    },
    {
      "epoch": 1.1940298507462686,
      "eval_loss": 0.2553260922431946,
      "eval_runtime": 230.8625,
      "eval_samples_per_second": 10.829,
      "eval_steps_per_second": 10.829,
      "step": 210
    },
    {
      "epoch": 1.2224591329068941,
      "grad_norm": 0.5915615558624268,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.2368,
      "step": 215
    },
    {
      "epoch": 1.2508884150675195,
      "grad_norm": 0.7240003943443298,
      "learning_rate": 3.6457976592849754e-05,
      "loss": 0.2334,
      "step": 220
    },
    {
      "epoch": 1.279317697228145,
      "grad_norm": 1.510029673576355,
      "learning_rate": 3.4075667487415785e-05,
      "loss": 0.2636,
      "step": 225
    },
    {
      "epoch": 1.3077469793887704,
      "grad_norm": 0.8403149247169495,
      "learning_rate": 3.173294878168025e-05,
      "loss": 0.2528,
      "step": 230
    },
    {
      "epoch": 1.336176261549396,
      "grad_norm": 0.5781741142272949,
      "learning_rate": 2.9435644843469436e-05,
      "loss": 0.2489,
      "step": 235
    },
    {
      "epoch": 1.3646055437100213,
      "grad_norm": 0.6707499027252197,
      "learning_rate": 2.718946713234185e-05,
      "loss": 0.2485,
      "step": 240
    },
    {
      "epoch": 1.3930348258706466,
      "grad_norm": 1.0248913764953613,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2694,
      "step": 245
    },
    {
      "epoch": 1.3930348258706466,
      "eval_loss": 0.2521698772907257,
      "eval_runtime": 230.6792,
      "eval_samples_per_second": 10.838,
      "eval_steps_per_second": 10.838,
      "step": 245
    },
    {
      "epoch": 1.4214641080312722,
      "grad_norm": 0.7928401231765747,
      "learning_rate": 2.2872686806712035e-05,
      "loss": 0.2506,
      "step": 250
    },
    {
      "epoch": 1.4498933901918978,
      "grad_norm": 0.7061648368835449,
      "learning_rate": 2.0812816388260518e-05,
      "loss": 0.2397,
      "step": 255
    },
    {
      "epoch": 1.4783226723525231,
      "grad_norm": 0.673512876033783,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.2138,
      "step": 260
    },
    {
      "epoch": 1.5067519545131485,
      "grad_norm": 0.6658352613449097,
      "learning_rate": 1.691570812015704e-05,
      "loss": 0.2417,
      "step": 265
    },
    {
      "epoch": 1.535181236673774,
      "grad_norm": 0.7412824034690857,
      "learning_rate": 1.5088159095696363e-05,
      "loss": 0.2568,
      "step": 270
    },
    {
      "epoch": 1.5636105188343994,
      "grad_norm": 1.0643491744995117,
      "learning_rate": 1.3347406408508695e-05,
      "loss": 0.2246,
      "step": 275
    },
    {
      "epoch": 1.5920398009950247,
      "grad_norm": 0.8839688301086426,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.249,
      "step": 280
    },
    {
      "epoch": 1.5920398009950247,
      "eval_loss": 0.253582626581192,
      "eval_runtime": 230.7977,
      "eval_samples_per_second": 10.832,
      "eval_steps_per_second": 10.832,
      "step": 280
    },
    {
      "epoch": 1.6204690831556503,
      "grad_norm": 1.12769615650177,
      "learning_rate": 1.0143374638853891e-05,
      "loss": 0.2577,
      "step": 285
    },
    {
      "epoch": 1.6488983653162759,
      "grad_norm": 0.8129110336303711,
      "learning_rate": 8.688061284200266e-06,
      "loss": 0.238,
      "step": 290
    },
    {
      "epoch": 1.6773276474769012,
      "grad_norm": 0.6995929479598999,
      "learning_rate": 7.33545591839222e-06,
      "loss": 0.2255,
      "step": 295
    },
    {
      "epoch": 1.7057569296375266,
      "grad_norm": 0.9470205903053284,
      "learning_rate": 6.088921331488568e-06,
      "loss": 0.251,
      "step": 300
    },
    {
      "epoch": 1.7341862117981521,
      "grad_norm": 0.8157157897949219,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.2634,
      "step": 305
    },
    {
      "epoch": 1.7626154939587777,
      "grad_norm": 0.7747371196746826,
      "learning_rate": 3.9261894064796135e-06,
      "loss": 0.2154,
      "step": 310
    },
    {
      "epoch": 1.7910447761194028,
      "grad_norm": 0.8623983263969421,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2255,
      "step": 315
    },
    {
      "epoch": 1.7910447761194028,
      "eval_loss": 0.25022172927856445,
      "eval_runtime": 231.0404,
      "eval_samples_per_second": 10.821,
      "eval_steps_per_second": 10.821,
      "step": 315
    },
    {
      "epoch": 1.8194740582800284,
      "grad_norm": 0.7183609008789062,
      "learning_rate": 2.221359710692961e-06,
      "loss": 0.2207,
      "step": 320
    },
    {
      "epoch": 1.847903340440654,
      "grad_norm": 0.7335498929023743,
      "learning_rate": 1.5461356885461075e-06,
      "loss": 0.2431,
      "step": 325
    },
    {
      "epoch": 1.8763326226012793,
      "grad_norm": 1.230342149734497,
      "learning_rate": 9.913756075728087e-07,
      "loss": 0.2442,
      "step": 330
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.5340166687965393,
      "learning_rate": 5.584586887435739e-07,
      "loss": 0.2535,
      "step": 335
    },
    {
      "epoch": 1.9331911869225302,
      "grad_norm": 0.69173264503479,
      "learning_rate": 2.4846123172992954e-07,
      "loss": 0.2384,
      "step": 340
    },
    {
      "epoch": 1.9616204690831558,
      "grad_norm": 0.7743846774101257,
      "learning_rate": 6.215393905388278e-08,
      "loss": 0.2436,
      "step": 345
    },
    {
      "epoch": 1.9900497512437811,
      "grad_norm": 0.7788644433021545,
      "learning_rate": 0.0,
      "loss": 0.2451,
      "step": 350
    },
    {
      "epoch": 1.9900497512437811,
      "eval_loss": 0.2479189932346344,
      "eval_runtime": 231.34,
      "eval_samples_per_second": 10.807,
      "eval_steps_per_second": 10.807,
      "step": 350
    },
    {
      "epoch": 1.9900497512437811,
      "step": 350,
      "total_flos": 9.569357529321308e+17,
      "train_loss": 0.8324783420562745,
      "train_runtime": 16271.8867,
      "train_samples_per_second": 2.766,
      "train_steps_per_second": 0.022
    }
  ],
  "logging_steps": 5,
  "max_steps": 350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 35,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.569357529321308e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}