{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.27114967462039047,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027114967462039045,
      "grad_norm": 0.00136566162109375,
      "learning_rate": 0.00019800000000000002,
      "loss": 0.9637,
      "step": 50
    },
    {
      "epoch": 0.005422993492407809,
      "grad_norm": 0.01171875,
      "learning_rate": 0.000196,
      "loss": 0.8921,
      "step": 100
    },
    {
      "epoch": 0.008134490238611713,
      "grad_norm": 13.9375,
      "learning_rate": 0.000194,
      "loss": 0.4537,
      "step": 150
    },
    {
      "epoch": 0.010845986984815618,
      "grad_norm": 0.00579833984375,
      "learning_rate": 0.000192,
      "loss": 0.4135,
      "step": 200
    },
    {
      "epoch": 0.013557483731019523,
      "grad_norm": 57.0,
      "learning_rate": 0.00019,
      "loss": 0.251,
      "step": 250
    },
    {
      "epoch": 0.016268980477223426,
      "grad_norm": 159.0,
      "learning_rate": 0.000188,
      "loss": 0.4018,
      "step": 300
    },
    {
      "epoch": 0.01898047722342733,
      "grad_norm": 0.0012359619140625,
      "learning_rate": 0.00018600000000000002,
      "loss": 0.1588,
      "step": 350
    },
    {
      "epoch": 0.021691973969631236,
      "grad_norm": 0.011962890625,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.5163,
      "step": 400
    },
    {
      "epoch": 0.02440347071583514,
      "grad_norm": 0.06591796875,
      "learning_rate": 0.000182,
      "loss": 0.4493,
      "step": 450
    },
    {
      "epoch": 0.027114967462039046,
      "grad_norm": 14.125,
      "learning_rate": 0.00018,
      "loss": 0.3355,
      "step": 500
    },
    {
      "epoch": 0.02982646420824295,
      "grad_norm": 0.0113525390625,
      "learning_rate": 0.00017800000000000002,
      "loss": 0.2711,
      "step": 550
    },
    {
      "epoch": 0.03253796095444685,
      "grad_norm": 0.0224609375,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.3634,
      "step": 600
    },
    {
      "epoch": 0.03524945770065076,
      "grad_norm": 0.1396484375,
      "learning_rate": 0.000174,
      "loss": 0.4355,
      "step": 650
    },
    {
      "epoch": 0.03796095444685466,
      "grad_norm": 22.375,
      "learning_rate": 0.000172,
      "loss": 0.2781,
      "step": 700
    },
    {
      "epoch": 0.04067245119305857,
      "grad_norm": 0.034423828125,
      "learning_rate": 0.00017,
      "loss": 0.3848,
      "step": 750
    },
    {
      "epoch": 0.04338394793926247,
      "grad_norm": 0.0286865234375,
      "learning_rate": 0.000168,
      "loss": 0.2264,
      "step": 800
    },
    {
      "epoch": 0.04609544468546638,
      "grad_norm": 2.171875,
      "learning_rate": 0.000166,
      "loss": 0.4542,
      "step": 850
    },
    {
      "epoch": 0.04880694143167028,
      "grad_norm": 0.0380859375,
      "learning_rate": 0.000164,
      "loss": 0.1554,
      "step": 900
    },
    {
      "epoch": 0.05151843817787419,
      "grad_norm": 0.0264892578125,
      "learning_rate": 0.000162,
      "loss": 0.2198,
      "step": 950
    },
    {
      "epoch": 0.05422993492407809,
      "grad_norm": 0.0673828125,
      "learning_rate": 0.00016,
      "loss": 0.3759,
      "step": 1000
    },
    {
      "epoch": 0.056941431670282,
      "grad_norm": 0.0091552734375,
      "learning_rate": 0.00015800000000000002,
      "loss": 0.2689,
      "step": 1050
    },
    {
      "epoch": 0.0596529284164859,
      "grad_norm": 0.01031494140625,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.2071,
      "step": 1100
    },
    {
      "epoch": 0.06236442516268981,
      "grad_norm": 0.09912109375,
      "learning_rate": 0.000154,
      "loss": 0.1407,
      "step": 1150
    },
    {
      "epoch": 0.0650759219088937,
      "grad_norm": 0.08447265625,
      "learning_rate": 0.000152,
      "loss": 0.3599,
      "step": 1200
    },
    {
      "epoch": 0.06778741865509762,
      "grad_norm": 0.023193359375,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.3034,
      "step": 1250
    },
    {
      "epoch": 0.07049891540130152,
      "grad_norm": 0.103515625,
      "learning_rate": 0.000148,
      "loss": 0.2354,
      "step": 1300
    },
    {
      "epoch": 0.07321041214750543,
      "grad_norm": 0.03759765625,
      "learning_rate": 0.000146,
      "loss": 0.2458,
      "step": 1350
    },
    {
      "epoch": 0.07592190889370933,
      "grad_norm": 0.0137939453125,
      "learning_rate": 0.000144,
      "loss": 0.2756,
      "step": 1400
    },
    {
      "epoch": 0.07863340563991324,
      "grad_norm": 0.0126953125,
      "learning_rate": 0.000142,
      "loss": 0.1256,
      "step": 1450
    },
    {
      "epoch": 0.08134490238611713,
      "grad_norm": 0.236328125,
      "learning_rate": 0.00014,
      "loss": 0.3264,
      "step": 1500
    },
    {
      "epoch": 0.08405639913232105,
      "grad_norm": 0.01416015625,
      "learning_rate": 0.000138,
      "loss": 0.0995,
      "step": 1550
    },
    {
      "epoch": 0.08676789587852494,
      "grad_norm": 0.1005859375,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.3766,
      "step": 1600
    },
    {
      "epoch": 0.08947939262472886,
      "grad_norm": 0.02490234375,
      "learning_rate": 0.000134,
      "loss": 0.3071,
      "step": 1650
    },
    {
      "epoch": 0.09219088937093275,
      "grad_norm": 0.0224609375,
      "learning_rate": 0.000132,
      "loss": 0.2511,
      "step": 1700
    },
    {
      "epoch": 0.09490238611713665,
      "grad_norm": 3.65625,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.1508,
      "step": 1750
    },
    {
      "epoch": 0.09761388286334056,
      "grad_norm": 0.0133056640625,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.2386,
      "step": 1800
    },
    {
      "epoch": 0.10032537960954446,
      "grad_norm": 13.75,
      "learning_rate": 0.000126,
      "loss": 0.2268,
      "step": 1850
    },
    {
      "epoch": 0.10303687635574837,
      "grad_norm": 0.0244140625,
      "learning_rate": 0.000124,
      "loss": 0.1943,
      "step": 1900
    },
    {
      "epoch": 0.10574837310195227,
      "grad_norm": 0.011962890625,
      "learning_rate": 0.000122,
      "loss": 0.2053,
      "step": 1950
    },
    {
      "epoch": 0.10845986984815618,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00012,
      "loss": 0.1648,
      "step": 2000
    },
    {
      "epoch": 0.11117136659436008,
      "grad_norm": 0.0181884765625,
      "learning_rate": 0.000118,
      "loss": 0.1398,
      "step": 2050
    },
    {
      "epoch": 0.113882863340564,
      "grad_norm": 0.083984375,
      "learning_rate": 0.000116,
      "loss": 0.1745,
      "step": 2100
    },
    {
      "epoch": 0.11659436008676789,
      "grad_norm": 0.053955078125,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.1719,
      "step": 2150
    },
    {
      "epoch": 0.1193058568329718,
      "grad_norm": 0.0390625,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.1191,
      "step": 2200
    },
    {
      "epoch": 0.1220173535791757,
      "grad_norm": 0.00799560546875,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.0768,
      "step": 2250
    },
    {
      "epoch": 0.12472885032537961,
      "grad_norm": 0.007720947265625,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.1663,
      "step": 2300
    },
    {
      "epoch": 0.12744034707158353,
      "grad_norm": 0.0289306640625,
      "learning_rate": 0.00010600000000000002,
      "loss": 0.1374,
      "step": 2350
    },
    {
      "epoch": 0.1301518438177874,
      "grad_norm": 0.28125,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.3337,
      "step": 2400
    },
    {
      "epoch": 0.13286334056399132,
      "grad_norm": 0.01708984375,
      "learning_rate": 0.00010200000000000001,
      "loss": 0.3759,
      "step": 2450
    },
    {
      "epoch": 0.13557483731019523,
      "grad_norm": 0.01611328125,
      "learning_rate": 0.0001,
      "loss": 0.237,
      "step": 2500
    },
    {
      "epoch": 0.13828633405639915,
      "grad_norm": 42.75,
      "learning_rate": 9.8e-05,
      "loss": 0.2289,
      "step": 2550
    },
    {
      "epoch": 0.14099783080260303,
      "grad_norm": 19.0,
      "learning_rate": 9.6e-05,
      "loss": 0.39,
      "step": 2600
    },
    {
      "epoch": 0.14370932754880694,
      "grad_norm": 0.045166015625,
      "learning_rate": 9.4e-05,
      "loss": 0.2849,
      "step": 2650
    },
    {
      "epoch": 0.14642082429501085,
      "grad_norm": 0.05224609375,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.281,
      "step": 2700
    },
    {
      "epoch": 0.14913232104121474,
      "grad_norm": 0.0303955078125,
      "learning_rate": 9e-05,
      "loss": 0.107,
      "step": 2750
    },
    {
      "epoch": 0.15184381778741865,
      "grad_norm": 0.0220947265625,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.3079,
      "step": 2800
    },
    {
      "epoch": 0.15455531453362256,
      "grad_norm": 1.6953125,
      "learning_rate": 8.6e-05,
      "loss": 0.1839,
      "step": 2850
    },
    {
      "epoch": 0.15726681127982647,
      "grad_norm": 1.03125,
      "learning_rate": 8.4e-05,
      "loss": 0.2098,
      "step": 2900
    },
    {
      "epoch": 0.15997830802603036,
      "grad_norm": 0.2080078125,
      "learning_rate": 8.2e-05,
      "loss": 0.2058,
      "step": 2950
    },
    {
      "epoch": 0.16268980477223427,
      "grad_norm": 0.0152587890625,
      "learning_rate": 8e-05,
      "loss": 0.2558,
      "step": 3000
    },
    {
      "epoch": 0.16540130151843818,
      "grad_norm": 0.01025390625,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.2058,
      "step": 3050
    },
    {
      "epoch": 0.1681127982646421,
      "grad_norm": 0.01904296875,
      "learning_rate": 7.6e-05,
      "loss": 0.1929,
      "step": 3100
    },
    {
      "epoch": 0.17082429501084598,
      "grad_norm": 0.00732421875,
      "learning_rate": 7.4e-05,
      "loss": 0.1941,
      "step": 3150
    },
    {
      "epoch": 0.1735357917570499,
      "grad_norm": 60.75,
      "learning_rate": 7.2e-05,
      "loss": 0.2042,
      "step": 3200
    },
    {
      "epoch": 0.1762472885032538,
      "grad_norm": 0.028076171875,
      "learning_rate": 7e-05,
      "loss": 0.2161,
      "step": 3250
    },
    {
      "epoch": 0.1789587852494577,
      "grad_norm": 1.5,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.1245,
      "step": 3300
    },
    {
      "epoch": 0.1816702819956616,
      "grad_norm": 74.0,
      "learning_rate": 6.6e-05,
      "loss": 0.1341,
      "step": 3350
    },
    {
      "epoch": 0.1843817787418655,
      "grad_norm": 0.0230712890625,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.1216,
      "step": 3400
    },
    {
      "epoch": 0.18709327548806942,
      "grad_norm": 0.27734375,
      "learning_rate": 6.2e-05,
      "loss": 0.1534,
      "step": 3450
    },
    {
      "epoch": 0.1898047722342733,
      "grad_norm": 1.421875,
      "learning_rate": 6e-05,
      "loss": 0.1427,
      "step": 3500
    },
    {
      "epoch": 0.19251626898047722,
      "grad_norm": 0.006134033203125,
      "learning_rate": 5.8e-05,
      "loss": 0.1307,
      "step": 3550
    },
    {
      "epoch": 0.19522776572668113,
      "grad_norm": 0.12060546875,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.2316,
      "step": 3600
    },
    {
      "epoch": 0.19793926247288504,
      "grad_norm": 0.0264892578125,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.0439,
      "step": 3650
    },
    {
      "epoch": 0.20065075921908893,
      "grad_norm": 0.054931640625,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.2922,
      "step": 3700
    },
    {
      "epoch": 0.20336225596529284,
      "grad_norm": 0.015380859375,
      "learning_rate": 5e-05,
      "loss": 0.3503,
      "step": 3750
    },
    {
      "epoch": 0.20607375271149675,
      "grad_norm": 0.294921875,
      "learning_rate": 4.8e-05,
      "loss": 0.1714,
      "step": 3800
    },
    {
      "epoch": 0.20878524945770066,
      "grad_norm": 0.146484375,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.0389,
      "step": 3850
    },
    {
      "epoch": 0.21149674620390455,
      "grad_norm": 0.021240234375,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.1058,
      "step": 3900
    },
    {
      "epoch": 0.21420824295010846,
      "grad_norm": 0.0252685546875,
      "learning_rate": 4.2e-05,
      "loss": 0.1039,
      "step": 3950
    },
    {
      "epoch": 0.21691973969631237,
      "grad_norm": 0.0751953125,
      "learning_rate": 4e-05,
      "loss": 0.1852,
      "step": 4000
    },
    {
      "epoch": 0.21963123644251628,
      "grad_norm": 0.00927734375,
      "learning_rate": 3.8e-05,
      "loss": 0.0974,
      "step": 4050
    },
    {
      "epoch": 0.22234273318872017,
      "grad_norm": 60.75,
      "learning_rate": 3.6e-05,
      "loss": 0.1371,
      "step": 4100
    },
    {
      "epoch": 0.22505422993492408,
      "grad_norm": 0.16796875,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.2533,
      "step": 4150
    },
    {
      "epoch": 0.227765726681128,
      "grad_norm": 0.011474609375,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.2726,
      "step": 4200
    },
    {
      "epoch": 0.2304772234273319,
      "grad_norm": 0.2041015625,
      "learning_rate": 3e-05,
      "loss": 0.1344,
      "step": 4250
    },
    {
      "epoch": 0.23318872017353579,
      "grad_norm": 0.031982421875,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.1649,
      "step": 4300
    },
    {
      "epoch": 0.2359002169197397,
      "grad_norm": 64.0,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.0462,
      "step": 4350
    },
    {
      "epoch": 0.2386117136659436,
      "grad_norm": 0.01348876953125,
      "learning_rate": 2.4e-05,
      "loss": 0.2292,
      "step": 4400
    },
    {
      "epoch": 0.2413232104121475,
      "grad_norm": 0.0084228515625,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.1774,
      "step": 4450
    },
    {
      "epoch": 0.2440347071583514,
      "grad_norm": 0.03125,
      "learning_rate": 2e-05,
      "loss": 0.1743,
      "step": 4500
    },
    {
      "epoch": 0.24674620390455532,
      "grad_norm": 0.01007080078125,
      "learning_rate": 1.8e-05,
      "loss": 0.3265,
      "step": 4550
    },
    {
      "epoch": 0.24945770065075923,
      "grad_norm": 0.0157470703125,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0298,
      "step": 4600
    },
    {
      "epoch": 0.25216919739696314,
      "grad_norm": 0.005828857421875,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.0788,
      "step": 4650
    },
    {
      "epoch": 0.25488069414316705,
      "grad_norm": 0.0400390625,
      "learning_rate": 1.2e-05,
      "loss": 0.1261,
      "step": 4700
    },
    {
      "epoch": 0.2575921908893709,
      "grad_norm": 0.0108642578125,
      "learning_rate": 1e-05,
      "loss": 0.1364,
      "step": 4750
    },
    {
      "epoch": 0.2603036876355748,
      "grad_norm": 0.0079345703125,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.1416,
      "step": 4800
    },
    {
      "epoch": 0.26301518438177873,
      "grad_norm": 0.00830078125,
      "learning_rate": 6e-06,
      "loss": 0.1362,
      "step": 4850
    },
    {
      "epoch": 0.26572668112798264,
      "grad_norm": 0.06298828125,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.112,
      "step": 4900
    },
    {
      "epoch": 0.26843817787418656,
      "grad_norm": 0.0185546875,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.2715,
      "step": 4950
    },
    {
      "epoch": 0.27114967462039047,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.0,
      "loss": 0.2406,
      "step": 5000
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.387481970192384e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}