{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 96,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03125,
      "grad_norm": 5.212899684906006,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.5701,
      "step": 1
    },
    {
      "epoch": 0.0625,
      "grad_norm": 5.509668827056885,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.6002,
      "step": 2
    },
    {
      "epoch": 0.09375,
      "grad_norm": 5.713456630706787,
      "learning_rate": 3e-06,
      "loss": 0.578,
      "step": 3
    },
    {
      "epoch": 0.125,
      "grad_norm": 4.650047779083252,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.5471,
      "step": 4
    },
    {
      "epoch": 0.15625,
      "grad_norm": 4.2114577293396,
      "learning_rate": 5e-06,
      "loss": 0.6588,
      "step": 5
    },
    {
      "epoch": 0.1875,
      "grad_norm": 3.0272881984710693,
      "learning_rate": 6e-06,
      "loss": 0.5074,
      "step": 6
    },
    {
      "epoch": 0.21875,
      "grad_norm": 2.395081043243408,
      "learning_rate": 7e-06,
      "loss": 0.484,
      "step": 7
    },
    {
      "epoch": 0.25,
      "grad_norm": 5.17173957824707,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6328,
      "step": 8
    },
    {
      "epoch": 0.28125,
      "grad_norm": 2.2946617603302,
      "learning_rate": 9e-06,
      "loss": 0.47,
      "step": 9
    },
    {
      "epoch": 0.3125,
      "grad_norm": 3.2116971015930176,
      "learning_rate": 1e-05,
      "loss": 0.4675,
      "step": 10
    },
    {
      "epoch": 0.34375,
      "grad_norm": 7.591786861419678,
      "learning_rate": 9.996664241851197e-06,
      "loss": 0.6794,
      "step": 11
    },
    {
      "epoch": 0.375,
      "grad_norm": 2.43316912651062,
      "learning_rate": 9.986661418317759e-06,
      "loss": 0.4242,
      "step": 12
    },
    {
      "epoch": 0.40625,
      "grad_norm": 2.3921120166778564,
      "learning_rate": 9.970004876199731e-06,
      "loss": 0.4481,
      "step": 13
    },
    {
      "epoch": 0.4375,
      "grad_norm": 6.6794328689575195,
      "learning_rate": 9.946716840375552e-06,
      "loss": 0.5388,
      "step": 14
    },
    {
      "epoch": 0.46875,
      "grad_norm": 1.9656387567520142,
      "learning_rate": 9.91682838414733e-06,
      "loss": 0.4292,
      "step": 15
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.9465067386627197,
      "learning_rate": 9.880379387779637e-06,
      "loss": 0.3977,
      "step": 16
    },
    {
      "epoch": 0.53125,
      "grad_norm": 1.9357396364212036,
      "learning_rate": 9.837418485287126e-06,
      "loss": 0.418,
      "step": 17
    },
    {
      "epoch": 0.5625,
      "grad_norm": 1.4802380800247192,
      "learning_rate": 9.78800299954203e-06,
      "loss": 0.382,
      "step": 18
    },
    {
      "epoch": 0.59375,
      "grad_norm": 1.3597159385681152,
      "learning_rate": 9.732198865788047e-06,
      "loss": 0.3844,
      "step": 19
    },
    {
      "epoch": 0.625,
      "grad_norm": 1.699665904045105,
      "learning_rate": 9.670080543662742e-06,
      "loss": 0.3707,
      "step": 20
    },
    {
      "epoch": 0.65625,
      "grad_norm": 2.6564078330993652,
      "learning_rate": 9.601730917845798e-06,
      "loss": 0.5049,
      "step": 21
    },
    {
      "epoch": 0.6875,
      "grad_norm": 1.8858695030212402,
      "learning_rate": 9.527241187465735e-06,
      "loss": 0.3874,
      "step": 22
    },
    {
      "epoch": 0.71875,
      "grad_norm": 1.5440151691436768,
      "learning_rate": 9.446710744412595e-06,
      "loss": 0.3295,
      "step": 23
    },
    {
      "epoch": 0.75,
      "grad_norm": 2.438760280609131,
      "learning_rate": 9.36024704071904e-06,
      "loss": 0.3313,
      "step": 24
    },
    {
      "epoch": 0.78125,
      "grad_norm": 1.462939739227295,
      "learning_rate": 9.267965445186733e-06,
      "loss": 0.3649,
      "step": 25
    },
    {
      "epoch": 0.8125,
      "grad_norm": 3.8231046199798584,
      "learning_rate": 9.16998908944939e-06,
      "loss": 0.4084,
      "step": 26
    },
    {
      "epoch": 0.84375,
      "grad_norm": 1.501857876777649,
      "learning_rate": 9.066448703677828e-06,
      "loss": 0.3463,
      "step": 27
    },
    {
      "epoch": 0.875,
      "grad_norm": 4.742476463317871,
      "learning_rate": 8.957482442146271e-06,
      "loss": 0.4789,
      "step": 28
    },
    {
      "epoch": 0.90625,
      "grad_norm": 2.2912559509277344,
      "learning_rate": 8.843235698892661e-06,
      "loss": 0.4739,
      "step": 29
    },
    {
      "epoch": 0.9375,
      "grad_norm": 1.3147192001342773,
      "learning_rate": 8.72386091371891e-06,
      "loss": 0.3864,
      "step": 30
    },
    {
      "epoch": 0.96875,
      "grad_norm": 1.2147444486618042,
      "learning_rate": 8.599517368789981e-06,
      "loss": 0.3181,
      "step": 31
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.0684988498687744,
      "learning_rate": 8.470370976103171e-06,
      "loss": 0.2821,
      "step": 32
    },
    {
      "epoch": 1.03125,
      "grad_norm": 2.0786163806915283,
      "learning_rate": 8.336594056111197e-06,
      "loss": 0.288,
      "step": 33
    },
    {
      "epoch": 1.0625,
      "grad_norm": 1.4894177913665771,
      "learning_rate": 8.198365107794457e-06,
      "loss": 0.275,
      "step": 34
    },
    {
      "epoch": 1.09375,
      "grad_norm": 1.039533019065857,
      "learning_rate": 8.055868570489247e-06,
      "loss": 0.2725,
      "step": 35
    },
    {
      "epoch": 1.125,
      "grad_norm": 1.105832815170288,
      "learning_rate": 7.909294577789765e-06,
      "loss": 0.2298,
      "step": 36
    },
    {
      "epoch": 1.15625,
      "grad_norm": 0.9874384999275208,
      "learning_rate": 7.75883870385223e-06,
      "loss": 0.2389,
      "step": 37
    },
    {
      "epoch": 1.1875,
      "grad_norm": 1.0676255226135254,
      "learning_rate": 7.604701702439652e-06,
      "loss": 0.2394,
      "step": 38
    },
    {
      "epoch": 1.21875,
      "grad_norm": 1.0422248840332031,
      "learning_rate": 7.447089239055428e-06,
      "loss": 0.2535,
      "step": 39
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.4323464632034302,
      "learning_rate": 7.286211616523193e-06,
      "loss": 0.2704,
      "step": 40
    },
    {
      "epoch": 1.28125,
      "grad_norm": 1.0653886795043945,
      "learning_rate": 7.122283494379076e-06,
      "loss": 0.2416,
      "step": 41
    },
    {
      "epoch": 1.3125,
      "grad_norm": 3.6688082218170166,
      "learning_rate": 6.95552360245078e-06,
      "loss": 0.2793,
      "step": 42
    },
    {
      "epoch": 1.34375,
      "grad_norm": 2.467761993408203,
      "learning_rate": 6.786154449005664e-06,
      "loss": 0.2504,
      "step": 43
    },
    {
      "epoch": 1.375,
      "grad_norm": 1.1717958450317383,
      "learning_rate": 6.614402023857231e-06,
      "loss": 0.2549,
      "step": 44
    },
    {
      "epoch": 1.40625,
      "grad_norm": 2.00671648979187,
      "learning_rate": 6.440495496826189e-06,
      "loss": 0.2179,
      "step": 45
    },
    {
      "epoch": 1.4375,
      "grad_norm": 1.0691853761672974,
      "learning_rate": 6.264666911958404e-06,
      "loss": 0.1993,
      "step": 46
    },
    {
      "epoch": 1.46875,
      "grad_norm": 2.143359661102295,
      "learning_rate": 6.087150877907786e-06,
      "loss": 0.2553,
      "step": 47
    },
    {
      "epoch": 1.5,
      "grad_norm": 3.1730265617370605,
      "learning_rate": 5.908184254897183e-06,
      "loss": 0.2949,
      "step": 48
    },
    {
      "epoch": 1.53125,
      "grad_norm": 1.2100728750228882,
      "learning_rate": 5.728005838675026e-06,
      "loss": 0.2204,
      "step": 49
    },
    {
      "epoch": 1.5625,
      "grad_norm": 1.1710706949234009,
      "learning_rate": 5.546856041889374e-06,
      "loss": 0.2082,
      "step": 50
    },
    {
      "epoch": 1.59375,
      "grad_norm": 1.1728243827819824,
      "learning_rate": 5.364976573304538e-06,
      "loss": 0.2052,
      "step": 51
    },
    {
      "epoch": 1.625,
      "grad_norm": 1.1219596862792969,
      "learning_rate": 5.182610115288296e-06,
      "loss": 0.2308,
      "step": 52
    },
    {
      "epoch": 1.65625,
      "grad_norm": 1.3272408246994019,
      "learning_rate": 5e-06,
      "loss": 0.2448,
      "step": 53
    },
    {
      "epoch": 1.6875,
      "grad_norm": 1.3118982315063477,
      "learning_rate": 4.817389884711706e-06,
      "loss": 0.2229,
      "step": 54
    },
    {
      "epoch": 1.71875,
      "grad_norm": 1.0828900337219238,
      "learning_rate": 4.635023426695462e-06,
      "loss": 0.216,
      "step": 55
    },
    {
      "epoch": 1.75,
      "grad_norm": 1.1662155389785767,
      "learning_rate": 4.4531439581106295e-06,
      "loss": 0.1926,
      "step": 56
    },
    {
      "epoch": 1.78125,
      "grad_norm": 1.1041769981384277,
      "learning_rate": 4.271994161324977e-06,
      "loss": 0.2045,
      "step": 57
    },
    {
      "epoch": 1.8125,
      "grad_norm": 1.1366336345672607,
      "learning_rate": 4.091815745102818e-06,
      "loss": 0.2125,
      "step": 58
    },
    {
      "epoch": 1.84375,
      "grad_norm": 1.0897059440612793,
      "learning_rate": 3.912849122092216e-06,
      "loss": 0.2282,
      "step": 59
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.9965717196464539,
      "learning_rate": 3.7353330880415963e-06,
      "loss": 0.2317,
      "step": 60
    },
    {
      "epoch": 1.90625,
      "grad_norm": 1.1308876276016235,
      "learning_rate": 3.5595045031738123e-06,
      "loss": 0.2459,
      "step": 61
    },
    {
      "epoch": 1.9375,
      "grad_norm": 1.449512243270874,
      "learning_rate": 3.3855979761427705e-06,
      "loss": 0.2836,
      "step": 62
    },
    {
      "epoch": 1.96875,
      "grad_norm": 1.0659527778625488,
      "learning_rate": 3.2138455509943365e-06,
      "loss": 0.2508,
      "step": 63
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.1291404962539673,
      "learning_rate": 3.044476397549221e-06,
      "loss": 0.1681,
      "step": 64
    },
    {
      "epoch": 2.03125,
      "grad_norm": 0.9167552590370178,
      "learning_rate": 2.8777165056209256e-06,
      "loss": 0.1305,
      "step": 65
    },
    {
      "epoch": 2.0625,
      "grad_norm": 0.9367494583129883,
      "learning_rate": 2.7137883834768076e-06,
      "loss": 0.1462,
      "step": 66
    },
    {
      "epoch": 2.09375,
      "grad_norm": 0.7913087010383606,
      "learning_rate": 2.5529107609445737e-06,
      "loss": 0.1384,
      "step": 67
    },
    {
      "epoch": 2.125,
      "grad_norm": 0.8486475944519043,
      "learning_rate": 2.3952982975603494e-06,
      "loss": 0.1262,
      "step": 68
    },
    {
      "epoch": 2.15625,
      "grad_norm": 0.8827183246612549,
      "learning_rate": 2.2411612961477704e-06,
      "loss": 0.1297,
      "step": 69
    },
    {
      "epoch": 2.1875,
      "grad_norm": 0.9331244230270386,
      "learning_rate": 2.0907054222102367e-06,
      "loss": 0.127,
      "step": 70
    },
    {
      "epoch": 2.21875,
      "grad_norm": 0.8335605263710022,
      "learning_rate": 1.944131429510754e-06,
      "loss": 0.131,
      "step": 71
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.7966263890266418,
      "learning_rate": 1.8016348922055448e-06,
      "loss": 0.1119,
      "step": 72
    },
    {
      "epoch": 2.28125,
      "grad_norm": 0.9054017066955566,
      "learning_rate": 1.6634059438888034e-06,
      "loss": 0.1131,
      "step": 73
    },
    {
      "epoch": 2.3125,
      "grad_norm": 1.0144445896148682,
      "learning_rate": 1.5296290238968303e-06,
      "loss": 0.1147,
      "step": 74
    },
    {
      "epoch": 2.34375,
      "grad_norm": 0.9999849796295166,
      "learning_rate": 1.4004826312100218e-06,
      "loss": 0.1219,
      "step": 75
    },
    {
      "epoch": 2.375,
      "grad_norm": 1.117247462272644,
      "learning_rate": 1.2761390862810907e-06,
      "loss": 0.1178,
      "step": 76
    },
    {
      "epoch": 2.40625,
      "grad_norm": 1.0464344024658203,
      "learning_rate": 1.1567643011073393e-06,
      "loss": 0.1102,
      "step": 77
    },
    {
      "epoch": 2.4375,
      "grad_norm": 1.0447325706481934,
      "learning_rate": 1.04251755785373e-06,
      "loss": 0.1077,
      "step": 78
    },
    {
      "epoch": 2.46875,
      "grad_norm": 1.0977072715759277,
      "learning_rate": 9.335512963221732e-07,
      "loss": 0.1045,
      "step": 79
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.6026099920272827,
      "learning_rate": 8.30010910550611e-07,
      "loss": 0.1298,
      "step": 80
    },
    {
      "epoch": 2.53125,
      "grad_norm": 0.9658783674240112,
      "learning_rate": 7.320345548132679e-07,
      "loss": 0.1336,
      "step": 81
    },
    {
      "epoch": 2.5625,
      "grad_norm": 1.047508716583252,
      "learning_rate": 6.397529592809615e-07,
      "loss": 0.1017,
      "step": 82
    },
    {
      "epoch": 2.59375,
      "grad_norm": 1.0574610233306885,
      "learning_rate": 5.532892555874059e-07,
      "loss": 0.1058,
      "step": 83
    },
    {
      "epoch": 2.625,
      "grad_norm": 1.155909776687622,
      "learning_rate": 4.727588125342669e-07,
      "loss": 0.1174,
      "step": 84
    },
    {
      "epoch": 2.65625,
      "grad_norm": 1.0230557918548584,
      "learning_rate": 3.9826908215420344e-07,
      "loss": 0.1076,
      "step": 85
    },
    {
      "epoch": 2.6875,
      "grad_norm": 0.9394001960754395,
      "learning_rate": 3.299194563372604e-07,
      "loss": 0.1411,
      "step": 86
    },
    {
      "epoch": 2.71875,
      "grad_norm": 0.9740204811096191,
      "learning_rate": 2.67801134211953e-07,
      "loss": 0.1101,
      "step": 87
    },
    {
      "epoch": 2.75,
      "grad_norm": 1.1990844011306763,
      "learning_rate": 2.1199700045797077e-07,
      "loss": 0.1397,
      "step": 88
    },
    {
      "epoch": 2.78125,
      "grad_norm": 0.9166547060012817,
      "learning_rate": 1.6258151471287397e-07,
      "loss": 0.1053,
      "step": 89
    },
    {
      "epoch": 2.8125,
      "grad_norm": 1.7290699481964111,
      "learning_rate": 1.196206122203647e-07,
      "loss": 0.1197,
      "step": 90
    },
    {
      "epoch": 2.84375,
      "grad_norm": 0.9263373017311096,
      "learning_rate": 8.317161585266964e-08,
      "loss": 0.1004,
      "step": 91
    },
    {
      "epoch": 2.875,
      "grad_norm": 0.9613826870918274,
      "learning_rate": 5.3283159624448745e-08,
      "loss": 0.1161,
      "step": 92
    },
    {
      "epoch": 2.90625,
      "grad_norm": 0.9571884870529175,
      "learning_rate": 2.9995123800270476e-08,
      "loss": 0.1109,
      "step": 93
    },
    {
      "epoch": 2.9375,
      "grad_norm": 0.9712323546409607,
      "learning_rate": 1.333858168224178e-08,
      "loss": 0.109,
      "step": 94
    },
    {
      "epoch": 2.96875,
      "grad_norm": 0.9421584606170654,
      "learning_rate": 3.3357581488030476e-09,
      "loss": 0.1002,
      "step": 95
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7927206158638,
      "learning_rate": 0.0,
      "loss": 0.0853,
      "step": 96
    },
    {
      "epoch": 3.0,
      "step": 96,
      "total_flos": 5914053476352.0,
      "train_loss": 0.2707547560178985,
      "train_runtime": 421.6069,
      "train_samples_per_second": 7.116,
      "train_steps_per_second": 0.228
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 96,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5914053476352.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}