ptoro's picture
Upload folder using huggingface_hub
ba371da verified
raw
history blame
58.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9444444444444446,
"eval_steps": 27,
"global_step": 324,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.009259259259259259,
"grad_norm": 3.136354684829712,
"learning_rate": 3.0000000000000004e-08,
"loss": 7.126,
"step": 1
},
{
"epoch": 0.009259259259259259,
"eval_loss": 5.272334098815918,
"eval_runtime": 10.9491,
"eval_samples_per_second": 9.59,
"eval_steps_per_second": 9.59,
"step": 1
},
{
"epoch": 0.018518518518518517,
"grad_norm": 1.6424509286880493,
"learning_rate": 6.000000000000001e-08,
"loss": 6.2434,
"step": 2
},
{
"epoch": 0.027777777777777776,
"grad_norm": 1.3273869752883911,
"learning_rate": 9e-08,
"loss": 5.851,
"step": 3
},
{
"epoch": 0.037037037037037035,
"grad_norm": 1.9482982158660889,
"learning_rate": 1.2000000000000002e-07,
"loss": 7.0582,
"step": 4
},
{
"epoch": 0.046296296296296294,
"grad_norm": 2.214090347290039,
"learning_rate": 1.5000000000000002e-07,
"loss": 6.2122,
"step": 5
},
{
"epoch": 0.05555555555555555,
"grad_norm": 1.6521217823028564,
"learning_rate": 1.8e-07,
"loss": 6.0318,
"step": 6
},
{
"epoch": 0.06481481481481481,
"grad_norm": 1.2911734580993652,
"learning_rate": 2.1000000000000003e-07,
"loss": 6.1264,
"step": 7
},
{
"epoch": 0.07407407407407407,
"grad_norm": 1.2651853561401367,
"learning_rate": 2.4000000000000003e-07,
"loss": 5.6821,
"step": 8
},
{
"epoch": 0.08333333333333333,
"grad_norm": 1.2058266401290894,
"learning_rate": 2.7e-07,
"loss": 5.7295,
"step": 9
},
{
"epoch": 0.09259259259259259,
"grad_norm": 2.896589994430542,
"learning_rate": 3.0000000000000004e-07,
"loss": 7.4781,
"step": 10
},
{
"epoch": 0.10185185185185185,
"grad_norm": 1.313854694366455,
"learning_rate": 3.3e-07,
"loss": 6.1254,
"step": 11
},
{
"epoch": 0.1111111111111111,
"grad_norm": 2.281994104385376,
"learning_rate": 3.6e-07,
"loss": 6.683,
"step": 12
},
{
"epoch": 0.12037037037037036,
"grad_norm": 1.2343209981918335,
"learning_rate": 3.9e-07,
"loss": 6.2304,
"step": 13
},
{
"epoch": 0.12962962962962962,
"grad_norm": 1.3297009468078613,
"learning_rate": 4.2000000000000006e-07,
"loss": 6.2013,
"step": 14
},
{
"epoch": 0.1388888888888889,
"grad_norm": 1.9952207803726196,
"learning_rate": 4.5e-07,
"loss": 6.9842,
"step": 15
},
{
"epoch": 0.14814814814814814,
"grad_norm": 1.3968197107315063,
"learning_rate": 4.800000000000001e-07,
"loss": 6.2524,
"step": 16
},
{
"epoch": 0.1574074074074074,
"grad_norm": 4.7724127769470215,
"learning_rate": 5.100000000000001e-07,
"loss": 8.551,
"step": 17
},
{
"epoch": 0.16666666666666666,
"grad_norm": 0.9988604187965393,
"learning_rate": 5.4e-07,
"loss": 5.5391,
"step": 18
},
{
"epoch": 0.17592592592592593,
"grad_norm": 1.2599544525146484,
"learning_rate": 5.7e-07,
"loss": 6.4559,
"step": 19
},
{
"epoch": 0.18518518518518517,
"grad_norm": 1.984928846359253,
"learning_rate": 6.000000000000001e-07,
"loss": 6.954,
"step": 20
},
{
"epoch": 0.19444444444444445,
"grad_norm": 1.2283947467803955,
"learning_rate": 6.3e-07,
"loss": 6.1821,
"step": 21
},
{
"epoch": 0.2037037037037037,
"grad_norm": 2.2317938804626465,
"learning_rate": 6.6e-07,
"loss": 6.9164,
"step": 22
},
{
"epoch": 0.21296296296296297,
"grad_norm": 1.5473928451538086,
"learning_rate": 6.900000000000001e-07,
"loss": 6.5494,
"step": 23
},
{
"epoch": 0.2222222222222222,
"grad_norm": 1.508975625038147,
"learning_rate": 7.2e-07,
"loss": 6.4025,
"step": 24
},
{
"epoch": 0.23148148148148148,
"grad_norm": 2.4396748542785645,
"learning_rate": 7.5e-07,
"loss": 7.2659,
"step": 25
},
{
"epoch": 0.24074074074074073,
"grad_norm": 1.1266586780548096,
"learning_rate": 7.8e-07,
"loss": 6.0911,
"step": 26
},
{
"epoch": 0.25,
"grad_norm": 1.515765905380249,
"learning_rate": 8.100000000000001e-07,
"loss": 6.503,
"step": 27
},
{
"epoch": 0.25,
"eval_loss": 5.270267963409424,
"eval_runtime": 10.4888,
"eval_samples_per_second": 10.011,
"eval_steps_per_second": 10.011,
"step": 27
},
{
"epoch": 0.25925925925925924,
"grad_norm": 1.2845295667648315,
"learning_rate": 8.400000000000001e-07,
"loss": 6.3435,
"step": 28
},
{
"epoch": 0.26851851851851855,
"grad_norm": 1.528168797492981,
"learning_rate": 8.699999999999999e-07,
"loss": 6.8436,
"step": 29
},
{
"epoch": 0.2777777777777778,
"grad_norm": 1.555953860282898,
"learning_rate": 9e-07,
"loss": 6.404,
"step": 30
},
{
"epoch": 0.28703703703703703,
"grad_norm": 1.293718934059143,
"learning_rate": 9.3e-07,
"loss": 6.0386,
"step": 31
},
{
"epoch": 0.2962962962962963,
"grad_norm": 1.0446598529815674,
"learning_rate": 9.600000000000001e-07,
"loss": 5.677,
"step": 32
},
{
"epoch": 0.3055555555555556,
"grad_norm": 1.3030468225479126,
"learning_rate": 9.9e-07,
"loss": 5.8789,
"step": 33
},
{
"epoch": 0.3148148148148148,
"grad_norm": 1.108596682548523,
"learning_rate": 1.0200000000000002e-06,
"loss": 5.8663,
"step": 34
},
{
"epoch": 0.32407407407407407,
"grad_norm": 1.833085536956787,
"learning_rate": 1.05e-06,
"loss": 5.7367,
"step": 35
},
{
"epoch": 0.3333333333333333,
"grad_norm": 1.561715006828308,
"learning_rate": 1.08e-06,
"loss": 6.2266,
"step": 36
},
{
"epoch": 0.3425925925925926,
"grad_norm": 1.6098933219909668,
"learning_rate": 1.11e-06,
"loss": 6.3335,
"step": 37
},
{
"epoch": 0.35185185185185186,
"grad_norm": 1.6193208694458008,
"learning_rate": 1.14e-06,
"loss": 6.3869,
"step": 38
},
{
"epoch": 0.3611111111111111,
"grad_norm": 1.5229904651641846,
"learning_rate": 1.17e-06,
"loss": 6.0453,
"step": 39
},
{
"epoch": 0.37037037037037035,
"grad_norm": 1.511690616607666,
"learning_rate": 1.2000000000000002e-06,
"loss": 6.7203,
"step": 40
},
{
"epoch": 0.37962962962962965,
"grad_norm": 0.9691258668899536,
"learning_rate": 1.2299999999999999e-06,
"loss": 5.8176,
"step": 41
},
{
"epoch": 0.3888888888888889,
"grad_norm": 1.1707255840301514,
"learning_rate": 1.26e-06,
"loss": 6.2779,
"step": 42
},
{
"epoch": 0.39814814814814814,
"grad_norm": 1.1281574964523315,
"learning_rate": 1.29e-06,
"loss": 5.8402,
"step": 43
},
{
"epoch": 0.4074074074074074,
"grad_norm": 3.945136308670044,
"learning_rate": 1.32e-06,
"loss": 7.5325,
"step": 44
},
{
"epoch": 0.4166666666666667,
"grad_norm": 1.8681273460388184,
"learning_rate": 1.35e-06,
"loss": 6.3374,
"step": 45
},
{
"epoch": 0.42592592592592593,
"grad_norm": 1.300478458404541,
"learning_rate": 1.3800000000000001e-06,
"loss": 5.9715,
"step": 46
},
{
"epoch": 0.4351851851851852,
"grad_norm": 1.2660181522369385,
"learning_rate": 1.41e-06,
"loss": 6.0421,
"step": 47
},
{
"epoch": 0.4444444444444444,
"grad_norm": 1.817872405052185,
"learning_rate": 1.44e-06,
"loss": 7.0875,
"step": 48
},
{
"epoch": 0.4537037037037037,
"grad_norm": 1.6538351774215698,
"learning_rate": 1.4700000000000001e-06,
"loss": 6.1825,
"step": 49
},
{
"epoch": 0.46296296296296297,
"grad_norm": 1.5821293592453003,
"learning_rate": 1.5e-06,
"loss": 6.0065,
"step": 50
},
{
"epoch": 0.4722222222222222,
"grad_norm": 1.5061155557632446,
"learning_rate": 1.53e-06,
"loss": 5.8156,
"step": 51
},
{
"epoch": 0.48148148148148145,
"grad_norm": 1.495235562324524,
"learning_rate": 1.56e-06,
"loss": 5.792,
"step": 52
},
{
"epoch": 0.49074074074074076,
"grad_norm": 1.2974352836608887,
"learning_rate": 1.59e-06,
"loss": 6.3621,
"step": 53
},
{
"epoch": 0.5,
"grad_norm": 1.2943974733352661,
"learning_rate": 1.6200000000000002e-06,
"loss": 5.9853,
"step": 54
},
{
"epoch": 0.5,
"eval_loss": 5.2575860023498535,
"eval_runtime": 10.6855,
"eval_samples_per_second": 9.826,
"eval_steps_per_second": 9.826,
"step": 54
},
{
"epoch": 0.5092592592592593,
"grad_norm": 1.0820438861846924,
"learning_rate": 1.65e-06,
"loss": 5.7026,
"step": 55
},
{
"epoch": 0.5185185185185185,
"grad_norm": 1.9304187297821045,
"learning_rate": 1.6800000000000002e-06,
"loss": 6.5805,
"step": 56
},
{
"epoch": 0.5277777777777778,
"grad_norm": 1.238295555114746,
"learning_rate": 1.71e-06,
"loss": 5.9397,
"step": 57
},
{
"epoch": 0.5370370370370371,
"grad_norm": 1.7372101545333862,
"learning_rate": 1.7399999999999999e-06,
"loss": 5.8761,
"step": 58
},
{
"epoch": 0.5462962962962963,
"grad_norm": 1.6708195209503174,
"learning_rate": 1.77e-06,
"loss": 6.0646,
"step": 59
},
{
"epoch": 0.5555555555555556,
"grad_norm": 1.5075998306274414,
"learning_rate": 1.8e-06,
"loss": 6.276,
"step": 60
},
{
"epoch": 0.5648148148148148,
"grad_norm": 1.4556330442428589,
"learning_rate": 1.83e-06,
"loss": 6.4906,
"step": 61
},
{
"epoch": 0.5740740740740741,
"grad_norm": 1.2507421970367432,
"learning_rate": 1.86e-06,
"loss": 6.2285,
"step": 62
},
{
"epoch": 0.5833333333333334,
"grad_norm": 1.1143450736999512,
"learning_rate": 1.8900000000000001e-06,
"loss": 5.7344,
"step": 63
},
{
"epoch": 0.5925925925925926,
"grad_norm": 2.05438232421875,
"learning_rate": 1.9200000000000003e-06,
"loss": 6.85,
"step": 64
},
{
"epoch": 0.6018518518518519,
"grad_norm": 1.104891300201416,
"learning_rate": 1.95e-06,
"loss": 6.1067,
"step": 65
},
{
"epoch": 0.6111111111111112,
"grad_norm": 1.34933602809906,
"learning_rate": 1.98e-06,
"loss": 6.1659,
"step": 66
},
{
"epoch": 0.6203703703703703,
"grad_norm": 1.5707837343215942,
"learning_rate": 2.0100000000000002e-06,
"loss": 6.1741,
"step": 67
},
{
"epoch": 0.6296296296296297,
"grad_norm": 0.9905802607536316,
"learning_rate": 2.0400000000000004e-06,
"loss": 5.9072,
"step": 68
},
{
"epoch": 0.6388888888888888,
"grad_norm": 1.134399652481079,
"learning_rate": 2.07e-06,
"loss": 5.8005,
"step": 69
},
{
"epoch": 0.6481481481481481,
"grad_norm": 1.7359548807144165,
"learning_rate": 2.1e-06,
"loss": 6.7931,
"step": 70
},
{
"epoch": 0.6574074074074074,
"grad_norm": 1.9637112617492676,
"learning_rate": 2.13e-06,
"loss": 6.0,
"step": 71
},
{
"epoch": 0.6666666666666666,
"grad_norm": 1.908047080039978,
"learning_rate": 2.16e-06,
"loss": 6.9322,
"step": 72
},
{
"epoch": 0.6759259259259259,
"grad_norm": 1.6848489046096802,
"learning_rate": 2.19e-06,
"loss": 6.3743,
"step": 73
},
{
"epoch": 0.6851851851851852,
"grad_norm": 1.158486247062683,
"learning_rate": 2.22e-06,
"loss": 5.7395,
"step": 74
},
{
"epoch": 0.6944444444444444,
"grad_norm": 2.9409470558166504,
"learning_rate": 2.25e-06,
"loss": 7.1889,
"step": 75
},
{
"epoch": 0.7037037037037037,
"grad_norm": 1.5408318042755127,
"learning_rate": 2.28e-06,
"loss": 6.5631,
"step": 76
},
{
"epoch": 0.7129629629629629,
"grad_norm": 1.3003695011138916,
"learning_rate": 2.31e-06,
"loss": 5.8228,
"step": 77
},
{
"epoch": 0.7222222222222222,
"grad_norm": 1.6015976667404175,
"learning_rate": 2.34e-06,
"loss": 6.0852,
"step": 78
},
{
"epoch": 0.7314814814814815,
"grad_norm": 1.282989501953125,
"learning_rate": 2.37e-06,
"loss": 6.0135,
"step": 79
},
{
"epoch": 0.7407407407407407,
"grad_norm": 1.3845688104629517,
"learning_rate": 2.4000000000000003e-06,
"loss": 5.9315,
"step": 80
},
{
"epoch": 0.75,
"grad_norm": 1.431152105331421,
"learning_rate": 2.43e-06,
"loss": 5.7324,
"step": 81
},
{
"epoch": 0.75,
"eval_loss": 5.23203182220459,
"eval_runtime": 10.3071,
"eval_samples_per_second": 10.187,
"eval_steps_per_second": 10.187,
"step": 81
},
{
"epoch": 0.7592592592592593,
"grad_norm": 1.7849000692367554,
"learning_rate": 2.4599999999999997e-06,
"loss": 6.3697,
"step": 82
},
{
"epoch": 0.7685185185185185,
"grad_norm": 1.2546958923339844,
"learning_rate": 2.49e-06,
"loss": 6.4323,
"step": 83
},
{
"epoch": 0.7777777777777778,
"grad_norm": 1.3903110027313232,
"learning_rate": 2.52e-06,
"loss": 6.1479,
"step": 84
},
{
"epoch": 0.7870370370370371,
"grad_norm": 1.8783302307128906,
"learning_rate": 2.55e-06,
"loss": 5.7606,
"step": 85
},
{
"epoch": 0.7962962962962963,
"grad_norm": 1.2064532041549683,
"learning_rate": 2.58e-06,
"loss": 6.0706,
"step": 86
},
{
"epoch": 0.8055555555555556,
"grad_norm": 1.9301965236663818,
"learning_rate": 2.61e-06,
"loss": 6.2393,
"step": 87
},
{
"epoch": 0.8148148148148148,
"grad_norm": 1.259318232536316,
"learning_rate": 2.64e-06,
"loss": 5.8821,
"step": 88
},
{
"epoch": 0.8240740740740741,
"grad_norm": 1.88141667842865,
"learning_rate": 2.6700000000000003e-06,
"loss": 6.8863,
"step": 89
},
{
"epoch": 0.8333333333333334,
"grad_norm": 1.1480059623718262,
"learning_rate": 2.7e-06,
"loss": 5.7941,
"step": 90
},
{
"epoch": 0.8425925925925926,
"grad_norm": 1.1357027292251587,
"learning_rate": 2.73e-06,
"loss": 5.7938,
"step": 91
},
{
"epoch": 0.8518518518518519,
"grad_norm": 1.2564626932144165,
"learning_rate": 2.7600000000000003e-06,
"loss": 5.8955,
"step": 92
},
{
"epoch": 0.8611111111111112,
"grad_norm": 1.5674831867218018,
"learning_rate": 2.7900000000000004e-06,
"loss": 6.0711,
"step": 93
},
{
"epoch": 0.8703703703703703,
"grad_norm": 2.784726142883301,
"learning_rate": 2.82e-06,
"loss": 6.9214,
"step": 94
},
{
"epoch": 0.8796296296296297,
"grad_norm": 1.2815853357315063,
"learning_rate": 2.85e-06,
"loss": 5.9669,
"step": 95
},
{
"epoch": 0.8888888888888888,
"grad_norm": 3.059992551803589,
"learning_rate": 2.88e-06,
"loss": 7.6911,
"step": 96
},
{
"epoch": 0.8981481481481481,
"grad_norm": 1.2001030445098877,
"learning_rate": 2.91e-06,
"loss": 6.1174,
"step": 97
},
{
"epoch": 0.9074074074074074,
"grad_norm": 1.685596227645874,
"learning_rate": 2.9400000000000002e-06,
"loss": 6.4517,
"step": 98
},
{
"epoch": 0.9166666666666666,
"grad_norm": 1.5668795108795166,
"learning_rate": 2.97e-06,
"loss": 6.3579,
"step": 99
},
{
"epoch": 0.9259259259259259,
"grad_norm": 1.2336190938949585,
"learning_rate": 3e-06,
"loss": 6.2871,
"step": 100
},
{
"epoch": 0.9351851851851852,
"grad_norm": 1.331573247909546,
"learning_rate": 2.9998524776393626e-06,
"loss": 5.9677,
"step": 101
},
{
"epoch": 0.9444444444444444,
"grad_norm": 1.5391007661819458,
"learning_rate": 2.9994099395745795e-06,
"loss": 6.6068,
"step": 102
},
{
"epoch": 0.9537037037037037,
"grad_norm": 4.519767761230469,
"learning_rate": 2.9986724728513302e-06,
"loss": 8.1238,
"step": 103
},
{
"epoch": 0.9629629629629629,
"grad_norm": 1.5254385471343994,
"learning_rate": 2.997640222526725e-06,
"loss": 6.4137,
"step": 104
},
{
"epoch": 0.9722222222222222,
"grad_norm": 1.28110671043396,
"learning_rate": 2.996313391640769e-06,
"loss": 5.887,
"step": 105
},
{
"epoch": 0.9814814814814815,
"grad_norm": 3.4707837104797363,
"learning_rate": 2.994692241176429e-06,
"loss": 7.9841,
"step": 106
},
{
"epoch": 0.9907407407407407,
"grad_norm": 1.5300663709640503,
"learning_rate": 2.9927770900082955e-06,
"loss": 6.2007,
"step": 107
},
{
"epoch": 1.0,
"grad_norm": 1.747676134109497,
"learning_rate": 2.9905683148398643e-06,
"loss": 6.5292,
"step": 108
},
{
"epoch": 1.0,
"eval_loss": 5.185390949249268,
"eval_runtime": 10.6897,
"eval_samples_per_second": 9.823,
"eval_steps_per_second": 9.823,
"step": 108
},
{
"epoch": 1.0092592592592593,
"grad_norm": 1.57361900806427,
"learning_rate": 2.988066350129437e-06,
"loss": 6.1537,
"step": 109
},
{
"epoch": 1.0185185185185186,
"grad_norm": 5.155310153961182,
"learning_rate": 2.9852716880046687e-06,
"loss": 7.9648,
"step": 110
},
{
"epoch": 1.0277777777777777,
"grad_norm": 1.0643362998962402,
"learning_rate": 2.982184878165763e-06,
"loss": 5.1748,
"step": 111
},
{
"epoch": 1.0092592592592593,
"grad_norm": 1.0376684665679932,
"learning_rate": 2.9788065277773537e-06,
"loss": 5.6556,
"step": 112
},
{
"epoch": 1.0185185185185186,
"grad_norm": 1.228864073753357,
"learning_rate": 2.9751373013490727e-06,
"loss": 5.7668,
"step": 113
},
{
"epoch": 1.0277777777777777,
"grad_norm": 1.7278510332107544,
"learning_rate": 2.971177920604846e-06,
"loss": 6.3775,
"step": 114
},
{
"epoch": 1.037037037037037,
"grad_norm": 1.1904284954071045,
"learning_rate": 2.9669291643409314e-06,
"loss": 5.7487,
"step": 115
},
{
"epoch": 1.0462962962962963,
"grad_norm": 2.941854238510132,
"learning_rate": 2.9623918682727352e-06,
"loss": 7.2423,
"step": 116
},
{
"epoch": 1.0555555555555556,
"grad_norm": 1.5035470724105835,
"learning_rate": 2.9575669248704265e-06,
"loss": 6.1212,
"step": 117
},
{
"epoch": 1.0648148148148149,
"grad_norm": 1.4733242988586426,
"learning_rate": 2.9524552831833926e-06,
"loss": 6.3059,
"step": 118
},
{
"epoch": 1.074074074074074,
"grad_norm": 1.3305742740631104,
"learning_rate": 2.947057948653564e-06,
"loss": 6.1691,
"step": 119
},
{
"epoch": 1.0833333333333333,
"grad_norm": 1.2160289287567139,
"learning_rate": 2.9413759829176495e-06,
"loss": 5.9701,
"step": 120
},
{
"epoch": 1.0925925925925926,
"grad_norm": 1.9012755155563354,
"learning_rate": 2.935410503598313e-06,
"loss": 6.6399,
"step": 121
},
{
"epoch": 1.1018518518518519,
"grad_norm": 1.3863564729690552,
"learning_rate": 2.9291626840843446e-06,
"loss": 6.0122,
"step": 122
},
{
"epoch": 1.1111111111111112,
"grad_norm": 1.1440134048461914,
"learning_rate": 2.9226337532998544e-06,
"loss": 5.9895,
"step": 123
},
{
"epoch": 1.1203703703703705,
"grad_norm": 1.4871304035186768,
"learning_rate": 2.9158249954625514e-06,
"loss": 6.3919,
"step": 124
},
{
"epoch": 1.1296296296296295,
"grad_norm": 1.574532389640808,
"learning_rate": 2.908737749831142e-06,
"loss": 6.489,
"step": 125
},
{
"epoch": 1.1388888888888888,
"grad_norm": 2.674992322921753,
"learning_rate": 2.9013734104419e-06,
"loss": 6.965,
"step": 126
},
{
"epoch": 1.1481481481481481,
"grad_norm": 1.4959555864334106,
"learning_rate": 2.8937334258344676e-06,
"loss": 5.8652,
"step": 127
},
{
"epoch": 1.1574074074074074,
"grad_norm": 3.064631223678589,
"learning_rate": 2.88581929876693e-06,
"loss": 7.1246,
"step": 128
},
{
"epoch": 1.1666666666666667,
"grad_norm": 1.7988754510879517,
"learning_rate": 2.8776325859202315e-06,
"loss": 6.1511,
"step": 129
},
{
"epoch": 1.175925925925926,
"grad_norm": 1.4231789112091064,
"learning_rate": 2.869174897591978e-06,
"loss": 6.0368,
"step": 130
},
{
"epoch": 1.1851851851851851,
"grad_norm": 2.6319122314453125,
"learning_rate": 2.8604478973797005e-06,
"loss": 7.1228,
"step": 131
},
{
"epoch": 1.1944444444444444,
"grad_norm": 1.4405936002731323,
"learning_rate": 2.851453301853629e-06,
"loss": 5.9765,
"step": 132
},
{
"epoch": 1.2037037037037037,
"grad_norm": 1.669622540473938,
"learning_rate": 2.842192880219049e-06,
"loss": 6.4033,
"step": 133
},
{
"epoch": 1.212962962962963,
"grad_norm": 1.1244466304779053,
"learning_rate": 2.832668453968309e-06,
"loss": 5.5845,
"step": 134
},
{
"epoch": 1.2222222222222223,
"grad_norm": 1.0342087745666504,
"learning_rate": 2.8228818965225326e-06,
"loss": 5.6106,
"step": 135
},
{
"epoch": 1.2222222222222223,
"eval_loss": 5.1238203048706055,
"eval_runtime": 10.8032,
"eval_samples_per_second": 9.719,
"eval_steps_per_second": 9.719,
"step": 135
},
{
"epoch": 1.2314814814814814,
"grad_norm": 2.5150041580200195,
"learning_rate": 2.8128351328631308e-06,
"loss": 6.5318,
"step": 136
},
{
"epoch": 1.2407407407407407,
"grad_norm": 1.7575809955596924,
"learning_rate": 2.8025301391531584e-06,
"loss": 6.225,
"step": 137
},
{
"epoch": 1.25,
"grad_norm": 1.5736333131790161,
"learning_rate": 2.7919689423486137e-06,
"loss": 5.6247,
"step": 138
},
{
"epoch": 1.2592592592592593,
"grad_norm": 0.9995443820953369,
"learning_rate": 2.781153619799741e-06,
"loss": 5.4866,
"step": 139
},
{
"epoch": 1.2685185185185186,
"grad_norm": 1.7936508655548096,
"learning_rate": 2.7700862988424264e-06,
"loss": 6.4679,
"step": 140
},
{
"epoch": 1.2777777777777777,
"grad_norm": 1.4072571992874146,
"learning_rate": 2.7587691563797533e-06,
"loss": 6.0924,
"step": 141
},
{
"epoch": 1.287037037037037,
"grad_norm": 1.9437594413757324,
"learning_rate": 2.747204418453818e-06,
"loss": 6.3988,
"step": 142
},
{
"epoch": 1.2962962962962963,
"grad_norm": 1.1792351007461548,
"learning_rate": 2.735394359807872e-06,
"loss": 6.0245,
"step": 143
},
{
"epoch": 1.3055555555555556,
"grad_norm": 1.2097288370132446,
"learning_rate": 2.7233413034388904e-06,
"loss": 6.0232,
"step": 144
},
{
"epoch": 1.3148148148148149,
"grad_norm": 1.5997315645217896,
"learning_rate": 2.711047620140644e-06,
"loss": 5.9724,
"step": 145
},
{
"epoch": 1.324074074074074,
"grad_norm": 1.9537619352340698,
"learning_rate": 2.6985157280373736e-06,
"loss": 6.336,
"step": 146
},
{
"epoch": 1.3333333333333333,
"grad_norm": 1.4596198797225952,
"learning_rate": 2.685748092108155e-06,
"loss": 6.2286,
"step": 147
},
{
"epoch": 1.3425925925925926,
"grad_norm": 1.2177029848098755,
"learning_rate": 2.6727472237020448e-06,
"loss": 5.8753,
"step": 148
},
{
"epoch": 1.3518518518518519,
"grad_norm": 1.5970029830932617,
"learning_rate": 2.6595156800441053e-06,
"loss": 6.2522,
"step": 149
},
{
"epoch": 1.3611111111111112,
"grad_norm": 1.1032902002334595,
"learning_rate": 2.646056063732411e-06,
"loss": 5.795,
"step": 150
},
{
"epoch": 1.3703703703703702,
"grad_norm": 1.10838782787323,
"learning_rate": 2.632371022226124e-06,
"loss": 5.4648,
"step": 151
},
{
"epoch": 1.3796296296296298,
"grad_norm": 1.3732211589813232,
"learning_rate": 2.6184632473247484e-06,
"loss": 5.568,
"step": 152
},
{
"epoch": 1.3888888888888888,
"grad_norm": 1.188904881477356,
"learning_rate": 2.6043354746386645e-06,
"loss": 5.8007,
"step": 153
},
{
"epoch": 1.3981481481481481,
"grad_norm": 1.3125028610229492,
"learning_rate": 2.5899904830510406e-06,
"loss": 5.7965,
"step": 154
},
{
"epoch": 1.4074074074074074,
"grad_norm": 1.2234677076339722,
"learning_rate": 2.575431094171241e-06,
"loss": 5.9759,
"step": 155
},
{
"epoch": 1.4166666666666667,
"grad_norm": 2.0235507488250732,
"learning_rate": 2.5606601717798212e-06,
"loss": 6.5055,
"step": 156
},
{
"epoch": 1.425925925925926,
"grad_norm": 1.3678350448608398,
"learning_rate": 2.5456806212652348e-06,
"loss": 5.8768,
"step": 157
},
{
"epoch": 1.4351851851851851,
"grad_norm": 1.309804081916809,
"learning_rate": 2.5304953890523524e-06,
"loss": 6.0516,
"step": 158
},
{
"epoch": 1.4444444444444444,
"grad_norm": 1.4316556453704834,
"learning_rate": 2.5151074620229114e-06,
"loss": 6.2186,
"step": 159
},
{
"epoch": 1.4537037037037037,
"grad_norm": 1.308398723602295,
"learning_rate": 2.499519866928006e-06,
"loss": 5.9185,
"step": 160
},
{
"epoch": 1.462962962962963,
"grad_norm": 1.7772057056427002,
"learning_rate": 2.4837356697927366e-06,
"loss": 6.4643,
"step": 161
},
{
"epoch": 1.4722222222222223,
"grad_norm": 1.4515641927719116,
"learning_rate": 2.4677579753131316e-06,
"loss": 6.3981,
"step": 162
},
{
"epoch": 1.4722222222222223,
"eval_loss": 5.054426193237305,
"eval_runtime": 10.7718,
"eval_samples_per_second": 9.748,
"eval_steps_per_second": 9.748,
"step": 162
},
{
"epoch": 1.4814814814814814,
"grad_norm": 2.9240331649780273,
"learning_rate": 2.4515899262454685e-06,
"loss": 6.8221,
"step": 163
},
{
"epoch": 1.4907407407407407,
"grad_norm": 3.2064929008483887,
"learning_rate": 2.4352347027881005e-06,
"loss": 7.6826,
"step": 164
},
{
"epoch": 1.5,
"grad_norm": 1.6117157936096191,
"learning_rate": 2.4186955219559254e-06,
"loss": 5.5413,
"step": 165
},
{
"epoch": 1.5092592592592593,
"grad_norm": 1.5916537046432495,
"learning_rate": 2.401975636947609e-06,
"loss": 6.1638,
"step": 166
},
{
"epoch": 1.5185185185185186,
"grad_norm": 1.6315852403640747,
"learning_rate": 2.3850783365056922e-06,
"loss": 6.3381,
"step": 167
},
{
"epoch": 1.5277777777777777,
"grad_norm": 1.1859897375106812,
"learning_rate": 2.368006944269709e-06,
"loss": 5.7726,
"step": 168
},
{
"epoch": 1.5370370370370372,
"grad_norm": 1.2986359596252441,
"learning_rate": 2.3507648181224336e-06,
"loss": 5.5423,
"step": 169
},
{
"epoch": 1.5462962962962963,
"grad_norm": 1.3099842071533203,
"learning_rate": 2.3333553495294033e-06,
"loss": 6.2081,
"step": 170
},
{
"epoch": 1.5555555555555556,
"grad_norm": 1.8448351621627808,
"learning_rate": 2.315781962871823e-06,
"loss": 6.4411,
"step": 171
},
{
"epoch": 1.5648148148148149,
"grad_norm": 1.263071894645691,
"learning_rate": 2.298048114773005e-06,
"loss": 5.769,
"step": 172
},
{
"epoch": 1.574074074074074,
"grad_norm": 1.4397268295288086,
"learning_rate": 2.280157293418462e-06,
"loss": 6.1988,
"step": 173
},
{
"epoch": 1.5833333333333335,
"grad_norm": 1.3311412334442139,
"learning_rate": 2.262113017869794e-06,
"loss": 5.9678,
"step": 174
},
{
"epoch": 1.5925925925925926,
"grad_norm": 1.5137203931808472,
"learning_rate": 2.243918837372502e-06,
"loss": 6.4093,
"step": 175
},
{
"epoch": 1.6018518518518519,
"grad_norm": 2.532318115234375,
"learning_rate": 2.22557833065786e-06,
"loss": 6.573,
"step": 176
},
{
"epoch": 1.6111111111111112,
"grad_norm": 1.7535362243652344,
"learning_rate": 2.207095105238997e-06,
"loss": 6.1462,
"step": 177
},
{
"epoch": 1.6203703703703702,
"grad_norm": 1.3252042531967163,
"learning_rate": 2.1884727967013063e-06,
"loss": 5.7489,
"step": 178
},
{
"epoch": 1.6296296296296298,
"grad_norm": 2.172076463699341,
"learning_rate": 2.1697150679873442e-06,
"loss": 6.3797,
"step": 179
},
{
"epoch": 1.6388888888888888,
"grad_norm": 0.8812606334686279,
"learning_rate": 2.150825608676337e-06,
"loss": 5.4227,
"step": 180
},
{
"epoch": 1.6481481481481481,
"grad_norm": 1.4979366064071655,
"learning_rate": 2.1318081342584566e-06,
"loss": 5.811,
"step": 181
},
{
"epoch": 1.6574074074074074,
"grad_norm": 1.277028203010559,
"learning_rate": 2.1126663854039945e-06,
"loss": 5.9072,
"step": 182
},
{
"epoch": 1.6666666666666665,
"grad_norm": 1.668641448020935,
"learning_rate": 2.0934041272275884e-06,
"loss": 6.1502,
"step": 183
},
{
"epoch": 1.675925925925926,
"grad_norm": 0.8518059849739075,
"learning_rate": 2.074025148547635e-06,
"loss": 5.2586,
"step": 184
},
{
"epoch": 1.6851851851851851,
"grad_norm": 1.7262235879898071,
"learning_rate": 2.0545332611410427e-06,
"loss": 5.9965,
"step": 185
},
{
"epoch": 1.6944444444444444,
"grad_norm": 4.665543079376221,
"learning_rate": 2.0349322989934695e-06,
"loss": 7.4106,
"step": 186
},
{
"epoch": 1.7037037037037037,
"grad_norm": 1.1285862922668457,
"learning_rate": 2.0152261175451915e-06,
"loss": 5.6628,
"step": 187
},
{
"epoch": 1.7129629629629628,
"grad_norm": 1.108992338180542,
"learning_rate": 1.9954185929327507e-06,
"loss": 5.4876,
"step": 188
},
{
"epoch": 1.7222222222222223,
"grad_norm": 1.1134352684020996,
"learning_rate": 1.9755136212265323e-06,
"loss": 5.602,
"step": 189
},
{
"epoch": 1.7222222222222223,
"eval_loss": 4.992879867553711,
"eval_runtime": 10.5803,
"eval_samples_per_second": 9.924,
"eval_steps_per_second": 9.924,
"step": 189
},
{
"epoch": 1.7314814814814814,
"grad_norm": 1.215661883354187,
"learning_rate": 1.9555151176644222e-06,
"loss": 5.7391,
"step": 190
},
{
"epoch": 1.7407407407407407,
"grad_norm": 1.2140839099884033,
"learning_rate": 1.9354270158816935e-06,
"loss": 5.4932,
"step": 191
},
{
"epoch": 1.75,
"grad_norm": 1.3728704452514648,
"learning_rate": 1.915253267137274e-06,
"loss": 5.7001,
"step": 192
},
{
"epoch": 1.7592592592592593,
"grad_norm": 5.121810436248779,
"learning_rate": 1.894997839536547e-06,
"loss": 7.9136,
"step": 193
},
{
"epoch": 1.7685185185185186,
"grad_norm": 1.3116612434387207,
"learning_rate": 1.8746647172508404e-06,
"loss": 5.7987,
"step": 194
},
{
"epoch": 1.7777777777777777,
"grad_norm": 1.1180241107940674,
"learning_rate": 1.8542578997337519e-06,
"loss": 5.9064,
"step": 195
},
{
"epoch": 1.7870370370370372,
"grad_norm": 5.294866561889648,
"learning_rate": 1.8337814009344715e-06,
"loss": 8.2684,
"step": 196
},
{
"epoch": 1.7962962962962963,
"grad_norm": 1.0381337404251099,
"learning_rate": 1.813239248508255e-06,
"loss": 5.487,
"step": 197
},
{
"epoch": 1.8055555555555556,
"grad_norm": 1.2923859357833862,
"learning_rate": 1.7926354830241926e-06,
"loss": 6.0108,
"step": 198
},
{
"epoch": 1.8148148148148149,
"grad_norm": 1.3527953624725342,
"learning_rate": 1.7719741571704477e-06,
"loss": 6.3468,
"step": 199
},
{
"epoch": 1.824074074074074,
"grad_norm": 1.4213413000106812,
"learning_rate": 1.7512593349571046e-06,
"loss": 6.0251,
"step": 200
},
{
"epoch": 1.8333333333333335,
"grad_norm": 1.3854726552963257,
"learning_rate": 1.730495090916795e-06,
"loss": 5.8197,
"step": 201
},
{
"epoch": 1.8425925925925926,
"grad_norm": 0.9397538304328918,
"learning_rate": 1.7096855093032494e-06,
"loss": 5.4813,
"step": 202
},
{
"epoch": 1.8518518518518519,
"grad_norm": 0.7849190831184387,
"learning_rate": 1.6888346832879382e-06,
"loss": 5.3213,
"step": 203
},
{
"epoch": 1.8611111111111112,
"grad_norm": 1.316622018814087,
"learning_rate": 1.6679467141549617e-06,
"loss": 5.358,
"step": 204
},
{
"epoch": 1.8703703703703702,
"grad_norm": 1.1983349323272705,
"learning_rate": 1.6470257104943413e-06,
"loss": 5.8328,
"step": 205
},
{
"epoch": 1.8796296296296298,
"grad_norm": 1.1115864515304565,
"learning_rate": 1.6260757873938715e-06,
"loss": 5.6616,
"step": 206
},
{
"epoch": 1.8888888888888888,
"grad_norm": 1.6418949365615845,
"learning_rate": 1.6051010656297009e-06,
"loss": 5.8618,
"step": 207
},
{
"epoch": 1.8981481481481481,
"grad_norm": 1.2098896503448486,
"learning_rate": 1.5841056708557877e-06,
"loss": 5.7551,
"step": 208
},
{
"epoch": 1.9074074074074074,
"grad_norm": 2.523620843887329,
"learning_rate": 1.5630937327923979e-06,
"loss": 6.0457,
"step": 209
},
{
"epoch": 1.9166666666666665,
"grad_norm": 1.2053682804107666,
"learning_rate": 1.5420693844138035e-06,
"loss": 5.7501,
"step": 210
},
{
"epoch": 1.925925925925926,
"grad_norm": 1.0068210363388062,
"learning_rate": 1.5210367611353436e-06,
"loss": 5.2868,
"step": 211
},
{
"epoch": 1.9351851851851851,
"grad_norm": 1.0384793281555176,
"learning_rate": 1.5e-06,
"loss": 5.5413,
"step": 212
},
{
"epoch": 1.9444444444444444,
"grad_norm": 0.9215264916419983,
"learning_rate": 1.4789632388646567e-06,
"loss": 5.3834,
"step": 213
},
{
"epoch": 1.9537037037037037,
"grad_norm": 1.250044584274292,
"learning_rate": 1.4579306155861968e-06,
"loss": 5.9769,
"step": 214
},
{
"epoch": 1.9629629629629628,
"grad_norm": 0.9464189410209656,
"learning_rate": 1.4369062672076026e-06,
"loss": 5.3573,
"step": 215
},
{
"epoch": 1.9722222222222223,
"grad_norm": 0.9586074352264404,
"learning_rate": 1.4158943291442122e-06,
"loss": 5.3998,
"step": 216
},
{
"epoch": 1.9722222222222223,
"eval_loss": 4.946777820587158,
"eval_runtime": 10.6655,
"eval_samples_per_second": 9.845,
"eval_steps_per_second": 9.845,
"step": 216
},
{
"epoch": 1.9814814814814814,
"grad_norm": 1.4538060426712036,
"learning_rate": 1.394898934370299e-06,
"loss": 6.2383,
"step": 217
},
{
"epoch": 1.9907407407407407,
"grad_norm": 1.114857792854309,
"learning_rate": 1.3739242126061288e-06,
"loss": 5.3067,
"step": 218
},
{
"epoch": 2.0,
"grad_norm": 1.250162959098816,
"learning_rate": 1.352974289505659e-06,
"loss": 5.6571,
"step": 219
},
{
"epoch": 2.0092592592592595,
"grad_norm": 1.8700934648513794,
"learning_rate": 1.3320532858450384e-06,
"loss": 6.4708,
"step": 220
},
{
"epoch": 2.0185185185185186,
"grad_norm": 1.8928983211517334,
"learning_rate": 1.3111653167120623e-06,
"loss": 5.9964,
"step": 221
},
{
"epoch": 2.0277777777777777,
"grad_norm": 1.5304040908813477,
"learning_rate": 1.2903144906967513e-06,
"loss": 4.7131,
"step": 222
},
{
"epoch": 2.009259259259259,
"grad_norm": 1.2288047075271606,
"learning_rate": 1.2695049090832047e-06,
"loss": 5.8606,
"step": 223
},
{
"epoch": 2.0185185185185186,
"grad_norm": 1.6722135543823242,
"learning_rate": 1.2487406650428957e-06,
"loss": 5.824,
"step": 224
},
{
"epoch": 2.0277777777777777,
"grad_norm": 1.4619513750076294,
"learning_rate": 1.2280258428295526e-06,
"loss": 5.7594,
"step": 225
},
{
"epoch": 2.037037037037037,
"grad_norm": 1.3389699459075928,
"learning_rate": 1.2073645169758077e-06,
"loss": 5.9157,
"step": 226
},
{
"epoch": 2.0462962962962963,
"grad_norm": 1.0063234567642212,
"learning_rate": 1.1867607514917454e-06,
"loss": 5.7464,
"step": 227
},
{
"epoch": 2.0555555555555554,
"grad_norm": 0.9406788945198059,
"learning_rate": 1.1662185990655286e-06,
"loss": 5.2862,
"step": 228
},
{
"epoch": 2.064814814814815,
"grad_norm": 1.4217416048049927,
"learning_rate": 1.1457421002662489e-06,
"loss": 5.7137,
"step": 229
},
{
"epoch": 2.074074074074074,
"grad_norm": 1.1130520105361938,
"learning_rate": 1.1253352827491595e-06,
"loss": 5.3391,
"step": 230
},
{
"epoch": 2.0833333333333335,
"grad_norm": 1.0606895685195923,
"learning_rate": 1.1050021604634526e-06,
"loss": 5.6953,
"step": 231
},
{
"epoch": 2.0925925925925926,
"grad_norm": 2.6643784046173096,
"learning_rate": 1.084746732862726e-06,
"loss": 6.9906,
"step": 232
},
{
"epoch": 2.1018518518518516,
"grad_norm": 1.0088460445404053,
"learning_rate": 1.0645729841183068e-06,
"loss": 5.5864,
"step": 233
},
{
"epoch": 2.111111111111111,
"grad_norm": 0.9418116211891174,
"learning_rate": 1.0444848823355779e-06,
"loss": 5.502,
"step": 234
},
{
"epoch": 2.1203703703703702,
"grad_norm": 1.597672462463379,
"learning_rate": 1.0244863787734682e-06,
"loss": 6.141,
"step": 235
},
{
"epoch": 2.1296296296296298,
"grad_norm": 1.1460810899734497,
"learning_rate": 1.0045814070672498e-06,
"loss": 5.5834,
"step": 236
},
{
"epoch": 2.138888888888889,
"grad_norm": 1.4463963508605957,
"learning_rate": 9.847738824548082e-07,
"loss": 5.867,
"step": 237
},
{
"epoch": 2.148148148148148,
"grad_norm": 1.1600419282913208,
"learning_rate": 9.650677010065305e-07,
"loss": 5.7531,
"step": 238
},
{
"epoch": 2.1574074074074074,
"grad_norm": 0.9038326144218445,
"learning_rate": 9.454667388589576e-07,
"loss": 5.2356,
"step": 239
},
{
"epoch": 2.1666666666666665,
"grad_norm": 1.5344514846801758,
"learning_rate": 9.259748514523654e-07,
"loss": 6.1354,
"step": 240
},
{
"epoch": 2.175925925925926,
"grad_norm": 1.1884032487869263,
"learning_rate": 9.065958727724121e-07,
"loss": 5.7438,
"step": 241
},
{
"epoch": 2.185185185185185,
"grad_norm": 0.8460777401924133,
"learning_rate": 8.87333614596006e-07,
"loss": 5.4901,
"step": 242
},
{
"epoch": 2.1944444444444446,
"grad_norm": 0.8021849393844604,
"learning_rate": 8.681918657415443e-07,
"loss": 5.1841,
"step": 243
},
{
"epoch": 2.1944444444444446,
"eval_loss": 4.917133331298828,
"eval_runtime": 10.6391,
"eval_samples_per_second": 9.869,
"eval_steps_per_second": 9.869,
"step": 243
},
{
"epoch": 2.2037037037037037,
"grad_norm": 5.063238620758057,
"learning_rate": 8.49174391323663e-07,
"loss": 7.8621,
"step": 244
},
{
"epoch": 2.212962962962963,
"grad_norm": 1.4641467332839966,
"learning_rate": 8.302849320126558e-07,
"loss": 5.8469,
"step": 245
},
{
"epoch": 2.2222222222222223,
"grad_norm": 1.4936150312423706,
"learning_rate": 8.115272032986932e-07,
"loss": 5.7606,
"step": 246
},
{
"epoch": 2.2314814814814814,
"grad_norm": 0.9228253364562988,
"learning_rate": 7.929048947610034e-07,
"loss": 5.4861,
"step": 247
},
{
"epoch": 2.240740740740741,
"grad_norm": 0.9733036160469055,
"learning_rate": 7.744216693421403e-07,
"loss": 5.5735,
"step": 248
},
{
"epoch": 2.25,
"grad_norm": 0.7804141044616699,
"learning_rate": 7.560811626274989e-07,
"loss": 5.2257,
"step": 249
},
{
"epoch": 2.259259259259259,
"grad_norm": 0.8710982799530029,
"learning_rate": 7.378869821302062e-07,
"loss": 5.5369,
"step": 250
},
{
"epoch": 2.2685185185185186,
"grad_norm": 1.0422347784042358,
"learning_rate": 7.19842706581538e-07,
"loss": 5.4223,
"step": 251
},
{
"epoch": 2.2777777777777777,
"grad_norm": 0.8307288885116577,
"learning_rate": 7.019518852269954e-07,
"loss": 5.2439,
"step": 252
},
{
"epoch": 2.287037037037037,
"grad_norm": 2.0869851112365723,
"learning_rate": 6.842180371281773e-07,
"loss": 6.6325,
"step": 253
},
{
"epoch": 2.2962962962962963,
"grad_norm": 0.8685571551322937,
"learning_rate": 6.666446504705971e-07,
"loss": 5.5038,
"step": 254
},
{
"epoch": 2.3055555555555554,
"grad_norm": 1.5917941331863403,
"learning_rate": 6.492351818775662e-07,
"loss": 6.0099,
"step": 255
},
{
"epoch": 2.314814814814815,
"grad_norm": 2.5297560691833496,
"learning_rate": 6.319930557302914e-07,
"loss": 6.3499,
"step": 256
},
{
"epoch": 2.324074074074074,
"grad_norm": 1.365795612335205,
"learning_rate": 6.14921663494308e-07,
"loss": 5.8755,
"step": 257
},
{
"epoch": 2.3333333333333335,
"grad_norm": 1.1725842952728271,
"learning_rate": 5.980243630523911e-07,
"loss": 5.8095,
"step": 258
},
{
"epoch": 2.3425925925925926,
"grad_norm": 1.5456892251968384,
"learning_rate": 5.813044780440748e-07,
"loss": 6.1433,
"step": 259
},
{
"epoch": 2.351851851851852,
"grad_norm": 0.8776403665542603,
"learning_rate": 5.647652972118998e-07,
"loss": 5.4915,
"step": 260
},
{
"epoch": 2.361111111111111,
"grad_norm": 1.428396224975586,
"learning_rate": 5.48410073754532e-07,
"loss": 6.2122,
"step": 261
},
{
"epoch": 2.3703703703703702,
"grad_norm": 1.048996090888977,
"learning_rate": 5.322420246868689e-07,
"loss": 5.6461,
"step": 262
},
{
"epoch": 2.3796296296296298,
"grad_norm": 0.9285644888877869,
"learning_rate": 5.162643302072639e-07,
"loss": 5.4518,
"step": 263
},
{
"epoch": 2.388888888888889,
"grad_norm": 0.8765868544578552,
"learning_rate": 5.004801330719941e-07,
"loss": 5.3568,
"step": 264
},
{
"epoch": 2.398148148148148,
"grad_norm": 5.609752178192139,
"learning_rate": 4.848925379770883e-07,
"loss": 6.9303,
"step": 265
},
{
"epoch": 2.4074074074074074,
"grad_norm": 1.008718729019165,
"learning_rate": 4.6950461094764745e-07,
"loss": 5.4784,
"step": 266
},
{
"epoch": 2.4166666666666665,
"grad_norm": 0.8718838095664978,
"learning_rate": 4.5431937873476516e-07,
"loss": 5.5294,
"step": 267
},
{
"epoch": 2.425925925925926,
"grad_norm": 1.0140756368637085,
"learning_rate": 4.3933982822017883e-07,
"loss": 5.3527,
"step": 268
},
{
"epoch": 2.435185185185185,
"grad_norm": 1.2150001525878906,
"learning_rate": 4.245689058287592e-07,
"loss": 5.4179,
"step": 269
},
{
"epoch": 2.4444444444444446,
"grad_norm": 1.3026584386825562,
"learning_rate": 4.100095169489597e-07,
"loss": 6.0764,
"step": 270
},
{
"epoch": 2.4444444444444446,
"eval_loss": 4.900852203369141,
"eval_runtime": 10.63,
"eval_samples_per_second": 9.878,
"eval_steps_per_second": 9.878,
"step": 270
},
{
"epoch": 2.4537037037037037,
"grad_norm": 1.6737775802612305,
"learning_rate": 3.956645253613363e-07,
"loss": 5.8735,
"step": 271
},
{
"epoch": 2.462962962962963,
"grad_norm": 0.9497735500335693,
"learning_rate": 3.8153675267525163e-07,
"loss": 5.509,
"step": 272
},
{
"epoch": 2.4722222222222223,
"grad_norm": 0.8875224590301514,
"learning_rate": 3.6762897777387626e-07,
"loss": 5.2877,
"step": 273
},
{
"epoch": 2.4814814814814814,
"grad_norm": 0.774486780166626,
"learning_rate": 3.539439362675888e-07,
"loss": 5.1427,
"step": 274
},
{
"epoch": 2.490740740740741,
"grad_norm": 0.9570311307907104,
"learning_rate": 3.404843199558945e-07,
"loss": 5.379,
"step": 275
},
{
"epoch": 2.5,
"grad_norm": 0.908612847328186,
"learning_rate": 3.272527762979553e-07,
"loss": 5.4819,
"step": 276
},
{
"epoch": 2.5092592592592595,
"grad_norm": 2.0357730388641357,
"learning_rate": 3.142519078918449e-07,
"loss": 6.3469,
"step": 277
},
{
"epoch": 2.5185185185185186,
"grad_norm": 2.1806082725524902,
"learning_rate": 3.014842719626268e-07,
"loss": 5.5354,
"step": 278
},
{
"epoch": 2.5277777777777777,
"grad_norm": 0.9985087513923645,
"learning_rate": 2.8895237985935643e-07,
"loss": 5.5649,
"step": 279
},
{
"epoch": 2.537037037037037,
"grad_norm": 0.9574006199836731,
"learning_rate": 2.7665869656110975e-07,
"loss": 5.5855,
"step": 280
},
{
"epoch": 2.5462962962962963,
"grad_norm": 0.6676331758499146,
"learning_rate": 2.6460564019212803e-07,
"loss": 5.3543,
"step": 281
},
{
"epoch": 2.5555555555555554,
"grad_norm": 1.2132998704910278,
"learning_rate": 2.52795581546182e-07,
"loss": 5.5964,
"step": 282
},
{
"epoch": 2.564814814814815,
"grad_norm": 1.157404899597168,
"learning_rate": 2.412308436202468e-07,
"loss": 5.7387,
"step": 283
},
{
"epoch": 2.574074074074074,
"grad_norm": 1.2162729501724243,
"learning_rate": 2.299137011575738e-07,
"loss": 5.4369,
"step": 284
},
{
"epoch": 2.5833333333333335,
"grad_norm": 1.804641842842102,
"learning_rate": 2.1884638020025895e-07,
"loss": 6.428,
"step": 285
},
{
"epoch": 2.5925925925925926,
"grad_norm": 0.9699422717094421,
"learning_rate": 2.080310576513866e-07,
"loss": 5.6471,
"step": 286
},
{
"epoch": 2.601851851851852,
"grad_norm": 0.9756860136985779,
"learning_rate": 1.9746986084684186e-07,
"loss": 5.647,
"step": 287
},
{
"epoch": 2.611111111111111,
"grad_norm": 1.4492071866989136,
"learning_rate": 1.8716486713686948e-07,
"loss": 5.7286,
"step": 288
},
{
"epoch": 2.6203703703703702,
"grad_norm": 0.8920571208000183,
"learning_rate": 1.771181034774676e-07,
"loss": 5.25,
"step": 289
},
{
"epoch": 2.6296296296296298,
"grad_norm": 1.1408250331878662,
"learning_rate": 1.6733154603169176e-07,
"loss": 5.9142,
"step": 290
},
{
"epoch": 2.638888888888889,
"grad_norm": 1.3304352760314941,
"learning_rate": 1.5780711978095092e-07,
"loss": 5.8842,
"step": 291
},
{
"epoch": 2.648148148148148,
"grad_norm": 0.9941169619560242,
"learning_rate": 1.4854669814637145e-07,
"loss": 5.5157,
"step": 292
},
{
"epoch": 2.6574074074074074,
"grad_norm": 2.4659430980682373,
"learning_rate": 1.3955210262029917e-07,
"loss": 5.5099,
"step": 293
},
{
"epoch": 2.6666666666666665,
"grad_norm": 1.0898157358169556,
"learning_rate": 1.3082510240802165e-07,
"loss": 5.6562,
"step": 294
},
{
"epoch": 2.675925925925926,
"grad_norm": 1.2926898002624512,
"learning_rate": 1.2236741407976837e-07,
"loss": 5.7729,
"step": 295
},
{
"epoch": 2.685185185185185,
"grad_norm": 3.4110615253448486,
"learning_rate": 1.141807012330699e-07,
"loss": 5.7517,
"step": 296
},
{
"epoch": 2.6944444444444446,
"grad_norm": 1.9456055164337158,
"learning_rate": 1.0626657416553281e-07,
"loss": 5.2345,
"step": 297
},
{
"epoch": 2.6944444444444446,
"eval_loss": 4.896117210388184,
"eval_runtime": 10.4256,
"eval_samples_per_second": 10.071,
"eval_steps_per_second": 10.071,
"step": 297
},
{
"epoch": 2.7037037037037037,
"grad_norm": 1.2618635892868042,
"learning_rate": 9.862658955810045e-08,
"loss": 5.7653,
"step": 298
},
{
"epoch": 2.712962962962963,
"grad_norm": 1.0603694915771484,
"learning_rate": 9.126225016885858e-08,
"loss": 5.7454,
"step": 299
},
{
"epoch": 2.7222222222222223,
"grad_norm": 0.9327253699302673,
"learning_rate": 8.417500453744864e-08,
"loss": 5.6063,
"step": 300
},
{
"epoch": 2.7314814814814814,
"grad_norm": 1.8524595499038696,
"learning_rate": 7.736624670014602e-08,
"loss": 6.2174,
"step": 301
},
{
"epoch": 2.7407407407407405,
"grad_norm": 1.1083251237869263,
"learning_rate": 7.083731591565551e-08,
"loss": 5.5776,
"step": 302
},
{
"epoch": 2.75,
"grad_norm": 1.899492621421814,
"learning_rate": 6.458949640168676e-08,
"loss": 6.3714,
"step": 303
},
{
"epoch": 2.7592592592592595,
"grad_norm": 2.46284556388855,
"learning_rate": 5.8624017082350765e-08,
"loss": 6.619,
"step": 304
},
{
"epoch": 2.7685185185185186,
"grad_norm": 2.8916397094726562,
"learning_rate": 5.2942051346436315e-08,
"loss": 6.5435,
"step": 305
},
{
"epoch": 2.7777777777777777,
"grad_norm": 1.0509790182113647,
"learning_rate": 4.754471681660799e-08,
"loss": 5.4202,
"step": 306
},
{
"epoch": 2.787037037037037,
"grad_norm": 0.9211875200271606,
"learning_rate": 4.243307512957351e-08,
"loss": 5.4689,
"step": 307
},
{
"epoch": 2.7962962962962963,
"grad_norm": 0.8755972385406494,
"learning_rate": 3.7608131727264573e-08,
"loss": 5.2441,
"step": 308
},
{
"epoch": 2.8055555555555554,
"grad_norm": 1.1118243932724,
"learning_rate": 3.3070835659068596e-08,
"loss": 5.7712,
"step": 309
},
{
"epoch": 2.814814814814815,
"grad_norm": 1.214991569519043,
"learning_rate": 2.8822079395154353e-08,
"loss": 5.6607,
"step": 310
},
{
"epoch": 2.824074074074074,
"grad_norm": 0.8643071055412292,
"learning_rate": 2.4862698650927385e-08,
"loss": 5.4248,
"step": 311
},
{
"epoch": 2.8333333333333335,
"grad_norm": 1.9691087007522583,
"learning_rate": 2.1193472222646172e-08,
"loss": 6.127,
"step": 312
},
{
"epoch": 2.8425925925925926,
"grad_norm": 0.7883575558662415,
"learning_rate": 1.7815121834236837e-08,
"loss": 5.4039,
"step": 313
},
{
"epoch": 2.851851851851852,
"grad_norm": 1.6514503955841064,
"learning_rate": 1.4728311995331533e-08,
"loss": 5.8646,
"step": 314
},
{
"epoch": 2.861111111111111,
"grad_norm": 2.683927297592163,
"learning_rate": 1.1933649870563002e-08,
"loss": 6.0561,
"step": 315
},
{
"epoch": 2.8703703703703702,
"grad_norm": 1.158765435218811,
"learning_rate": 9.431685160136094e-09,
"loss": 5.594,
"step": 316
},
{
"epoch": 2.8796296296296298,
"grad_norm": 1.821207880973816,
"learning_rate": 7.222909991704774e-09,
"loss": 6.2595,
"step": 317
},
{
"epoch": 2.888888888888889,
"grad_norm": 1.1909257173538208,
"learning_rate": 5.307758823571374e-09,
"loss": 5.8222,
"step": 318
},
{
"epoch": 2.898148148148148,
"grad_norm": 1.9552392959594727,
"learning_rate": 3.6866083592309587e-09,
"loss": 6.2407,
"step": 319
},
{
"epoch": 2.9074074074074074,
"grad_norm": 1.438214898109436,
"learning_rate": 2.359777473275093e-09,
"loss": 5.8622,
"step": 320
},
{
"epoch": 2.9166666666666665,
"grad_norm": 5.569436073303223,
"learning_rate": 1.3275271486696826e-09,
"loss": 8.2884,
"step": 321
},
{
"epoch": 2.925925925925926,
"grad_norm": 0.8624269366264343,
"learning_rate": 5.900604254207021e-10,
"loss": 5.4493,
"step": 322
},
{
"epoch": 2.935185185185185,
"grad_norm": 1.1584603786468506,
"learning_rate": 1.4752236063747536e-10,
"loss": 5.7549,
"step": 323
},
{
"epoch": 2.9444444444444446,
"grad_norm": 1.3483120203018188,
"learning_rate": 0.0,
"loss": 5.4896,
"step": 324
},
{
"epoch": 2.9444444444444446,
"eval_loss": 4.894683837890625,
"eval_runtime": 10.7727,
"eval_samples_per_second": 9.747,
"eval_steps_per_second": 9.747,
"step": 324
}
],
"logging_steps": 1,
"max_steps": 324,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 108,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.044304041803776e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}