t5-small-lora-finetune-tweetsumm / trainer_state.json
samuellimabraz's picture
End of training
f9d2f34 verified
raw
history blame
58.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 330,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00909090909090909,
"grad_norm": 5.2518181800842285,
"learning_rate": 0.000996969696969697,
"loss": 3.3367,
"step": 1
},
{
"epoch": 0.01818181818181818,
"grad_norm": 4.880982875823975,
"learning_rate": 0.000993939393939394,
"loss": 3.0289,
"step": 2
},
{
"epoch": 0.02727272727272727,
"grad_norm": 5.23956823348999,
"learning_rate": 0.000990909090909091,
"loss": 3.0669,
"step": 3
},
{
"epoch": 0.03636363636363636,
"grad_norm": 4.678460121154785,
"learning_rate": 0.000987878787878788,
"loss": 2.8465,
"step": 4
},
{
"epoch": 0.045454545454545456,
"grad_norm": 3.9929628372192383,
"learning_rate": 0.000984848484848485,
"loss": 3.1352,
"step": 5
},
{
"epoch": 0.05454545454545454,
"grad_norm": 3.6919984817504883,
"learning_rate": 0.0009818181818181818,
"loss": 2.9963,
"step": 6
},
{
"epoch": 0.06363636363636363,
"grad_norm": 3.3434791564941406,
"learning_rate": 0.0009787878787878787,
"loss": 2.1743,
"step": 7
},
{
"epoch": 0.07272727272727272,
"grad_norm": 4.237480163574219,
"learning_rate": 0.0009757575757575757,
"loss": 3.1647,
"step": 8
},
{
"epoch": 0.08181818181818182,
"grad_norm": 3.7974822521209717,
"learning_rate": 0.0009727272727272728,
"loss": 2.7749,
"step": 9
},
{
"epoch": 0.09090909090909091,
"grad_norm": 4.91433048248291,
"learning_rate": 0.0009696969696969698,
"loss": 2.4019,
"step": 10
},
{
"epoch": 0.1,
"grad_norm": 4.127438545227051,
"learning_rate": 0.0009666666666666667,
"loss": 2.6962,
"step": 11
},
{
"epoch": 0.10909090909090909,
"grad_norm": 4.643143653869629,
"learning_rate": 0.0009636363636363637,
"loss": 2.9149,
"step": 12
},
{
"epoch": 0.11818181818181818,
"grad_norm": 4.401607036590576,
"learning_rate": 0.0009606060606060606,
"loss": 2.531,
"step": 13
},
{
"epoch": 0.12727272727272726,
"grad_norm": 5.990690231323242,
"learning_rate": 0.0009575757575757576,
"loss": 2.7423,
"step": 14
},
{
"epoch": 0.13636363636363635,
"grad_norm": 4.293227672576904,
"learning_rate": 0.0009545454545454546,
"loss": 2.7091,
"step": 15
},
{
"epoch": 0.14545454545454545,
"grad_norm": 4.075765132904053,
"learning_rate": 0.0009515151515151516,
"loss": 2.4489,
"step": 16
},
{
"epoch": 0.15454545454545454,
"grad_norm": 4.711447238922119,
"learning_rate": 0.0009484848484848486,
"loss": 2.5161,
"step": 17
},
{
"epoch": 0.16363636363636364,
"grad_norm": 3.57441782951355,
"learning_rate": 0.0009454545454545454,
"loss": 2.6451,
"step": 18
},
{
"epoch": 0.17272727272727273,
"grad_norm": 3.8768248558044434,
"learning_rate": 0.0009424242424242424,
"loss": 2.8677,
"step": 19
},
{
"epoch": 0.18181818181818182,
"grad_norm": 3.802804470062256,
"learning_rate": 0.0009393939393939394,
"loss": 2.6496,
"step": 20
},
{
"epoch": 0.19090909090909092,
"grad_norm": 3.2413487434387207,
"learning_rate": 0.0009363636363636364,
"loss": 2.319,
"step": 21
},
{
"epoch": 0.2,
"grad_norm": 4.118133068084717,
"learning_rate": 0.0009333333333333333,
"loss": 2.5911,
"step": 22
},
{
"epoch": 0.20909090909090908,
"grad_norm": 3.9800240993499756,
"learning_rate": 0.0009303030303030303,
"loss": 2.6266,
"step": 23
},
{
"epoch": 0.21818181818181817,
"grad_norm": 3.355109691619873,
"learning_rate": 0.0009272727272727273,
"loss": 1.9672,
"step": 24
},
{
"epoch": 0.22727272727272727,
"grad_norm": 3.477891683578491,
"learning_rate": 0.0009242424242424242,
"loss": 2.4351,
"step": 25
},
{
"epoch": 0.23636363636363636,
"grad_norm": 3.3365089893341064,
"learning_rate": 0.0009212121212121213,
"loss": 2.2669,
"step": 26
},
{
"epoch": 0.24545454545454545,
"grad_norm": 3.8154420852661133,
"learning_rate": 0.0009181818181818182,
"loss": 2.8762,
"step": 27
},
{
"epoch": 0.2545454545454545,
"grad_norm": 4.117005348205566,
"learning_rate": 0.0009151515151515152,
"loss": 3.0168,
"step": 28
},
{
"epoch": 0.2636363636363636,
"grad_norm": 3.2977471351623535,
"learning_rate": 0.0009121212121212121,
"loss": 2.7348,
"step": 29
},
{
"epoch": 0.2727272727272727,
"grad_norm": 3.7002816200256348,
"learning_rate": 0.0009090909090909091,
"loss": 2.4564,
"step": 30
},
{
"epoch": 0.2818181818181818,
"grad_norm": 3.8529574871063232,
"learning_rate": 0.000906060606060606,
"loss": 2.4686,
"step": 31
},
{
"epoch": 0.2909090909090909,
"grad_norm": 4.335300922393799,
"learning_rate": 0.0009030303030303031,
"loss": 2.7986,
"step": 32
},
{
"epoch": 0.3,
"grad_norm": 3.7472643852233887,
"learning_rate": 0.0009000000000000001,
"loss": 2.4992,
"step": 33
},
{
"epoch": 0.3090909090909091,
"grad_norm": 3.529536485671997,
"learning_rate": 0.000896969696969697,
"loss": 2.6301,
"step": 34
},
{
"epoch": 0.3181818181818182,
"grad_norm": 6.698845386505127,
"learning_rate": 0.000893939393939394,
"loss": 2.5353,
"step": 35
},
{
"epoch": 0.32727272727272727,
"grad_norm": 3.8375208377838135,
"learning_rate": 0.0008909090909090909,
"loss": 2.0059,
"step": 36
},
{
"epoch": 0.33636363636363636,
"grad_norm": 3.387864112854004,
"learning_rate": 0.000887878787878788,
"loss": 2.6231,
"step": 37
},
{
"epoch": 0.34545454545454546,
"grad_norm": 4.848170280456543,
"learning_rate": 0.0008848484848484849,
"loss": 2.7781,
"step": 38
},
{
"epoch": 0.35454545454545455,
"grad_norm": 3.2476627826690674,
"learning_rate": 0.0008818181818181819,
"loss": 2.1748,
"step": 39
},
{
"epoch": 0.36363636363636365,
"grad_norm": 3.628349781036377,
"learning_rate": 0.0008787878787878789,
"loss": 2.1451,
"step": 40
},
{
"epoch": 0.37272727272727274,
"grad_norm": 5.355284690856934,
"learning_rate": 0.0008757575757575757,
"loss": 2.7246,
"step": 41
},
{
"epoch": 0.38181818181818183,
"grad_norm": Infinity,
"learning_rate": 0.0008757575757575757,
"loss": 3.0379,
"step": 42
},
{
"epoch": 0.39090909090909093,
"grad_norm": 4.581727027893066,
"learning_rate": 0.0008727272727272727,
"loss": 2.6156,
"step": 43
},
{
"epoch": 0.4,
"grad_norm": 3.789523124694824,
"learning_rate": 0.0008696969696969697,
"loss": 1.9819,
"step": 44
},
{
"epoch": 0.4090909090909091,
"grad_norm": 3.176393985748291,
"learning_rate": 0.0008666666666666667,
"loss": 2.147,
"step": 45
},
{
"epoch": 0.41818181818181815,
"grad_norm": 3.3732335567474365,
"learning_rate": 0.0008636363636363636,
"loss": 2.1358,
"step": 46
},
{
"epoch": 0.42727272727272725,
"grad_norm": 4.747837066650391,
"learning_rate": 0.0008606060606060606,
"loss": 2.726,
"step": 47
},
{
"epoch": 0.43636363636363634,
"grad_norm": 3.452475070953369,
"learning_rate": 0.0008575757575757575,
"loss": 2.3285,
"step": 48
},
{
"epoch": 0.44545454545454544,
"grad_norm": 3.300018072128296,
"learning_rate": 0.0008545454545454545,
"loss": 2.0528,
"step": 49
},
{
"epoch": 0.45454545454545453,
"grad_norm": 3.376659870147705,
"learning_rate": 0.0008515151515151516,
"loss": 2.6693,
"step": 50
},
{
"epoch": 0.4636363636363636,
"grad_norm": 3.4894306659698486,
"learning_rate": 0.0008484848484848485,
"loss": 2.8337,
"step": 51
},
{
"epoch": 0.4727272727272727,
"grad_norm": 3.39812970161438,
"learning_rate": 0.0008454545454545455,
"loss": 2.7285,
"step": 52
},
{
"epoch": 0.4818181818181818,
"grad_norm": 3.9138715267181396,
"learning_rate": 0.0008424242424242424,
"loss": 2.533,
"step": 53
},
{
"epoch": 0.4909090909090909,
"grad_norm": 6.068693161010742,
"learning_rate": 0.0008393939393939394,
"loss": 2.5452,
"step": 54
},
{
"epoch": 0.5,
"grad_norm": 3.239271640777588,
"learning_rate": 0.0008363636363636363,
"loss": 2.2065,
"step": 55
},
{
"epoch": 0.509090909090909,
"grad_norm": 3.618382692337036,
"learning_rate": 0.0008333333333333334,
"loss": 1.9538,
"step": 56
},
{
"epoch": 0.5181818181818182,
"grad_norm": 3.508000612258911,
"learning_rate": 0.0008303030303030304,
"loss": 2.6809,
"step": 57
},
{
"epoch": 0.5272727272727272,
"grad_norm": 4.77998161315918,
"learning_rate": 0.0008272727272727273,
"loss": 2.3727,
"step": 58
},
{
"epoch": 0.5363636363636364,
"grad_norm": 3.7970476150512695,
"learning_rate": 0.0008242424242424243,
"loss": 2.5909,
"step": 59
},
{
"epoch": 0.5454545454545454,
"grad_norm": 3.4571659564971924,
"learning_rate": 0.0008212121212121212,
"loss": 2.1278,
"step": 60
},
{
"epoch": 0.5545454545454546,
"grad_norm": 3.7409794330596924,
"learning_rate": 0.0008181818181818183,
"loss": 2.5653,
"step": 61
},
{
"epoch": 0.5636363636363636,
"grad_norm": 3.4741013050079346,
"learning_rate": 0.0008151515151515152,
"loss": 2.1841,
"step": 62
},
{
"epoch": 0.5727272727272728,
"grad_norm": 3.597646951675415,
"learning_rate": 0.0008121212121212122,
"loss": 2.169,
"step": 63
},
{
"epoch": 0.5818181818181818,
"grad_norm": 3.0322861671447754,
"learning_rate": 0.0008090909090909092,
"loss": 1.9148,
"step": 64
},
{
"epoch": 0.5909090909090909,
"grad_norm": 3.946357488632202,
"learning_rate": 0.000806060606060606,
"loss": 2.2571,
"step": 65
},
{
"epoch": 0.6,
"grad_norm": 4.600891590118408,
"learning_rate": 0.000803030303030303,
"loss": 2.3041,
"step": 66
},
{
"epoch": 0.6090909090909091,
"grad_norm": 3.838850498199463,
"learning_rate": 0.0008,
"loss": 3.0572,
"step": 67
},
{
"epoch": 0.6181818181818182,
"grad_norm": 4.015396595001221,
"learning_rate": 0.000796969696969697,
"loss": 2.406,
"step": 68
},
{
"epoch": 0.6272727272727273,
"grad_norm": 3.3290698528289795,
"learning_rate": 0.0007939393939393939,
"loss": 2.3905,
"step": 69
},
{
"epoch": 0.6363636363636364,
"grad_norm": 2.841418504714966,
"learning_rate": 0.0007909090909090909,
"loss": 1.8905,
"step": 70
},
{
"epoch": 0.6454545454545455,
"grad_norm": 3.089731454849243,
"learning_rate": 0.0007878787878787878,
"loss": 2.1672,
"step": 71
},
{
"epoch": 0.6545454545454545,
"grad_norm": 3.329467296600342,
"learning_rate": 0.0007848484848484848,
"loss": 2.4988,
"step": 72
},
{
"epoch": 0.6636363636363637,
"grad_norm": 10.238970756530762,
"learning_rate": 0.0007818181818181819,
"loss": 2.3279,
"step": 73
},
{
"epoch": 0.6727272727272727,
"grad_norm": 3.1716997623443604,
"learning_rate": 0.0007787878787878788,
"loss": 2.4611,
"step": 74
},
{
"epoch": 0.6818181818181818,
"grad_norm": 3.4082698822021484,
"learning_rate": 0.0007757575757575758,
"loss": 2.3856,
"step": 75
},
{
"epoch": 0.6909090909090909,
"grad_norm": 3.9740962982177734,
"learning_rate": 0.0007727272727272727,
"loss": 2.1877,
"step": 76
},
{
"epoch": 0.7,
"grad_norm": 3.353031635284424,
"learning_rate": 0.0007696969696969697,
"loss": 2.2395,
"step": 77
},
{
"epoch": 0.7090909090909091,
"grad_norm": 3.203476905822754,
"learning_rate": 0.0007666666666666667,
"loss": 2.1856,
"step": 78
},
{
"epoch": 0.7181818181818181,
"grad_norm": 2.897700786590576,
"learning_rate": 0.0007636363636363637,
"loss": 2.2488,
"step": 79
},
{
"epoch": 0.7272727272727273,
"grad_norm": 3.560061454772949,
"learning_rate": 0.0007606060606060607,
"loss": 1.9751,
"step": 80
},
{
"epoch": 0.7363636363636363,
"grad_norm": 3.838275671005249,
"learning_rate": 0.0007575757575757576,
"loss": 2.3823,
"step": 81
},
{
"epoch": 0.7454545454545455,
"grad_norm": 3.104668378829956,
"learning_rate": 0.0007545454545454546,
"loss": 2.2405,
"step": 82
},
{
"epoch": 0.7545454545454545,
"grad_norm": 3.5294268131256104,
"learning_rate": 0.0007515151515151515,
"loss": 2.6297,
"step": 83
},
{
"epoch": 0.7636363636363637,
"grad_norm": 3.474611282348633,
"learning_rate": 0.0007484848484848486,
"loss": 2.1731,
"step": 84
},
{
"epoch": 0.7727272727272727,
"grad_norm": 2.875084638595581,
"learning_rate": 0.0007454545454545455,
"loss": 1.9173,
"step": 85
},
{
"epoch": 0.7818181818181819,
"grad_norm": 3.2007133960723877,
"learning_rate": 0.0007424242424242425,
"loss": 2.6975,
"step": 86
},
{
"epoch": 0.7909090909090909,
"grad_norm": 3.0429532527923584,
"learning_rate": 0.0007393939393939393,
"loss": 2.2078,
"step": 87
},
{
"epoch": 0.8,
"grad_norm": 3.6955785751342773,
"learning_rate": 0.0007363636363636363,
"loss": 3.0928,
"step": 88
},
{
"epoch": 0.8090909090909091,
"grad_norm": 3.4884259700775146,
"learning_rate": 0.0007333333333333333,
"loss": 2.5716,
"step": 89
},
{
"epoch": 0.8181818181818182,
"grad_norm": 4.282299041748047,
"learning_rate": 0.0007303030303030303,
"loss": 2.2967,
"step": 90
},
{
"epoch": 0.8272727272727273,
"grad_norm": 2.812239170074463,
"learning_rate": 0.0007272727272727273,
"loss": 2.4012,
"step": 91
},
{
"epoch": 0.8363636363636363,
"grad_norm": 2.932528257369995,
"learning_rate": 0.0007242424242424242,
"loss": 2.0868,
"step": 92
},
{
"epoch": 0.8454545454545455,
"grad_norm": 3.935401439666748,
"learning_rate": 0.0007212121212121212,
"loss": 2.3244,
"step": 93
},
{
"epoch": 0.8545454545454545,
"grad_norm": 3.2733335494995117,
"learning_rate": 0.0007181818181818181,
"loss": 2.1079,
"step": 94
},
{
"epoch": 0.8636363636363636,
"grad_norm": 3.452592134475708,
"learning_rate": 0.0007151515151515152,
"loss": 1.897,
"step": 95
},
{
"epoch": 0.8727272727272727,
"grad_norm": 3.8487422466278076,
"learning_rate": 0.0007121212121212122,
"loss": 2.1049,
"step": 96
},
{
"epoch": 0.8818181818181818,
"grad_norm": 3.40667986869812,
"learning_rate": 0.0007090909090909091,
"loss": 1.9498,
"step": 97
},
{
"epoch": 0.8909090909090909,
"grad_norm": 3.897969961166382,
"learning_rate": 0.0007060606060606061,
"loss": 2.4093,
"step": 98
},
{
"epoch": 0.9,
"grad_norm": 4.002754211425781,
"learning_rate": 0.000703030303030303,
"loss": 2.2212,
"step": 99
},
{
"epoch": 0.9090909090909091,
"grad_norm": 6.137336730957031,
"learning_rate": 0.0007,
"loss": 2.2547,
"step": 100
},
{
"epoch": 0.9181818181818182,
"grad_norm": 3.92399001121521,
"learning_rate": 0.000696969696969697,
"loss": 2.2178,
"step": 101
},
{
"epoch": 0.9272727272727272,
"grad_norm": 3.8081912994384766,
"learning_rate": 0.000693939393939394,
"loss": 2.5065,
"step": 102
},
{
"epoch": 0.9363636363636364,
"grad_norm": 3.6582956314086914,
"learning_rate": 0.0006909090909090909,
"loss": 2.2296,
"step": 103
},
{
"epoch": 0.9454545454545454,
"grad_norm": 3.624040365219116,
"learning_rate": 0.0006878787878787879,
"loss": 2.3475,
"step": 104
},
{
"epoch": 0.9545454545454546,
"grad_norm": 3.157224178314209,
"learning_rate": 0.0006848484848484849,
"loss": 2.0646,
"step": 105
},
{
"epoch": 0.9636363636363636,
"grad_norm": 3.4677720069885254,
"learning_rate": 0.0006818181818181818,
"loss": 2.1445,
"step": 106
},
{
"epoch": 0.9727272727272728,
"grad_norm": 3.4308862686157227,
"learning_rate": 0.0006787878787878789,
"loss": 1.9616,
"step": 107
},
{
"epoch": 0.9818181818181818,
"grad_norm": 2.8956782817840576,
"learning_rate": 0.0006757575757575758,
"loss": 1.8463,
"step": 108
},
{
"epoch": 0.990909090909091,
"grad_norm": 2.9389758110046387,
"learning_rate": 0.0006727272727272728,
"loss": 2.6711,
"step": 109
},
{
"epoch": 1.0,
"grad_norm": 3.623382568359375,
"learning_rate": 0.0006696969696969696,
"loss": 2.3972,
"step": 110
},
{
"epoch": 1.0,
"eval_f1": 0.8833,
"eval_gen_len": 49.9818,
"eval_loss": 2.138414144515991,
"eval_precision": 0.8806,
"eval_recall": 0.8861,
"eval_rouge1": 0.4219,
"eval_rouge2": 0.1801,
"eval_rougeL": 0.3545,
"eval_rougeLsum": 0.3925,
"eval_runtime": 11.6131,
"eval_samples_per_second": 9.472,
"eval_steps_per_second": 1.206,
"step": 110
},
{
"epoch": 1.009090909090909,
"grad_norm": 3.4820663928985596,
"learning_rate": 0.0006666666666666666,
"loss": 2.3964,
"step": 111
},
{
"epoch": 1.018181818181818,
"grad_norm": 2.838667154312134,
"learning_rate": 0.0006636363636363638,
"loss": 1.9329,
"step": 112
},
{
"epoch": 1.0272727272727273,
"grad_norm": 3.149284601211548,
"learning_rate": 0.0006606060606060606,
"loss": 2.2014,
"step": 113
},
{
"epoch": 1.0363636363636364,
"grad_norm": 4.511423587799072,
"learning_rate": 0.0006575757575757576,
"loss": 2.8422,
"step": 114
},
{
"epoch": 1.0454545454545454,
"grad_norm": 2.4003782272338867,
"learning_rate": 0.0006545454545454545,
"loss": 1.7917,
"step": 115
},
{
"epoch": 1.0545454545454545,
"grad_norm": 3.4949734210968018,
"learning_rate": 0.0006515151515151515,
"loss": 2.232,
"step": 116
},
{
"epoch": 1.0636363636363637,
"grad_norm": 3.4572432041168213,
"learning_rate": 0.0006484848484848484,
"loss": 1.7402,
"step": 117
},
{
"epoch": 1.0727272727272728,
"grad_norm": 2.961136817932129,
"learning_rate": 0.0006454545454545455,
"loss": 2.0877,
"step": 118
},
{
"epoch": 1.0818181818181818,
"grad_norm": 2.7831802368164062,
"learning_rate": 0.0006424242424242425,
"loss": 2.3089,
"step": 119
},
{
"epoch": 1.0909090909090908,
"grad_norm": 3.5909435749053955,
"learning_rate": 0.0006393939393939394,
"loss": 2.5869,
"step": 120
},
{
"epoch": 1.1,
"grad_norm": 3.3193140029907227,
"learning_rate": 0.0006363636363636364,
"loss": 1.9844,
"step": 121
},
{
"epoch": 1.1090909090909091,
"grad_norm": 3.4833359718322754,
"learning_rate": 0.0006333333333333333,
"loss": 1.9743,
"step": 122
},
{
"epoch": 1.1181818181818182,
"grad_norm": 3.77689266204834,
"learning_rate": 0.0006303030303030303,
"loss": 2.4139,
"step": 123
},
{
"epoch": 1.1272727272727272,
"grad_norm": 3.071627140045166,
"learning_rate": 0.0006272727272727273,
"loss": 2.2144,
"step": 124
},
{
"epoch": 1.1363636363636362,
"grad_norm": 3.109482526779175,
"learning_rate": 0.0006242424242424243,
"loss": 2.1402,
"step": 125
},
{
"epoch": 1.1454545454545455,
"grad_norm": 4.04578971862793,
"learning_rate": 0.0006212121212121212,
"loss": 2.0318,
"step": 126
},
{
"epoch": 1.1545454545454545,
"grad_norm": 2.571721315383911,
"learning_rate": 0.0006181818181818182,
"loss": 2.0998,
"step": 127
},
{
"epoch": 1.1636363636363636,
"grad_norm": 6.96982479095459,
"learning_rate": 0.0006151515151515152,
"loss": 2.1176,
"step": 128
},
{
"epoch": 1.1727272727272728,
"grad_norm": 3.4528586864471436,
"learning_rate": 0.0006121212121212121,
"loss": 2.3724,
"step": 129
},
{
"epoch": 1.1818181818181819,
"grad_norm": 3.7283544540405273,
"learning_rate": 0.0006090909090909092,
"loss": 2.4293,
"step": 130
},
{
"epoch": 1.190909090909091,
"grad_norm": 3.005866765975952,
"learning_rate": 0.0006060606060606061,
"loss": 2.0742,
"step": 131
},
{
"epoch": 1.2,
"grad_norm": 2.9893100261688232,
"learning_rate": 0.0006030303030303031,
"loss": 2.2275,
"step": 132
},
{
"epoch": 1.209090909090909,
"grad_norm": 3.2736032009124756,
"learning_rate": 0.0006,
"loss": 1.8893,
"step": 133
},
{
"epoch": 1.2181818181818183,
"grad_norm": 3.703336477279663,
"learning_rate": 0.0005969696969696969,
"loss": 2.1683,
"step": 134
},
{
"epoch": 1.2272727272727273,
"grad_norm": 3.564338445663452,
"learning_rate": 0.000593939393939394,
"loss": 2.4923,
"step": 135
},
{
"epoch": 1.2363636363636363,
"grad_norm": 3.481875419616699,
"learning_rate": 0.0005909090909090909,
"loss": 2.3251,
"step": 136
},
{
"epoch": 1.2454545454545454,
"grad_norm": 2.7357468605041504,
"learning_rate": 0.0005878787878787879,
"loss": 1.6328,
"step": 137
},
{
"epoch": 1.2545454545454544,
"grad_norm": 2.977414608001709,
"learning_rate": 0.0005848484848484848,
"loss": 1.9178,
"step": 138
},
{
"epoch": 1.2636363636363637,
"grad_norm": 2.976820468902588,
"learning_rate": 0.0005818181818181818,
"loss": 2.1413,
"step": 139
},
{
"epoch": 1.2727272727272727,
"grad_norm": 3.3343393802642822,
"learning_rate": 0.0005787878787878787,
"loss": 2.4427,
"step": 140
},
{
"epoch": 1.2818181818181817,
"grad_norm": 3.282231092453003,
"learning_rate": 0.0005757575757575758,
"loss": 2.2933,
"step": 141
},
{
"epoch": 1.290909090909091,
"grad_norm": 2.9428188800811768,
"learning_rate": 0.0005727272727272727,
"loss": 1.8861,
"step": 142
},
{
"epoch": 1.3,
"grad_norm": 8.139079093933105,
"learning_rate": 0.0005696969696969697,
"loss": 2.5037,
"step": 143
},
{
"epoch": 1.309090909090909,
"grad_norm": 2.6978557109832764,
"learning_rate": 0.0005666666666666667,
"loss": 1.8142,
"step": 144
},
{
"epoch": 1.3181818181818181,
"grad_norm": 3.5968875885009766,
"learning_rate": 0.0005636363636363636,
"loss": 2.3725,
"step": 145
},
{
"epoch": 1.3272727272727272,
"grad_norm": 4.022060394287109,
"learning_rate": 0.0005606060606060606,
"loss": 2.2109,
"step": 146
},
{
"epoch": 1.3363636363636364,
"grad_norm": 4.272978782653809,
"learning_rate": 0.0005575757575757576,
"loss": 2.1179,
"step": 147
},
{
"epoch": 1.3454545454545455,
"grad_norm": 3.887815237045288,
"learning_rate": 0.0005545454545454546,
"loss": 2.4651,
"step": 148
},
{
"epoch": 1.3545454545454545,
"grad_norm": 4.284169673919678,
"learning_rate": 0.0005515151515151515,
"loss": 1.9982,
"step": 149
},
{
"epoch": 1.3636363636363638,
"grad_norm": 4.994478225708008,
"learning_rate": 0.0005484848484848485,
"loss": 1.9375,
"step": 150
},
{
"epoch": 1.3727272727272728,
"grad_norm": 4.021026134490967,
"learning_rate": 0.0005454545454545455,
"loss": 2.3054,
"step": 151
},
{
"epoch": 1.3818181818181818,
"grad_norm": 3.356945276260376,
"learning_rate": 0.0005424242424242425,
"loss": 2.2106,
"step": 152
},
{
"epoch": 1.3909090909090909,
"grad_norm": 3.4492499828338623,
"learning_rate": 0.0005393939393939395,
"loss": 2.0621,
"step": 153
},
{
"epoch": 1.4,
"grad_norm": 3.036426544189453,
"learning_rate": 0.0005363636363636364,
"loss": 2.0976,
"step": 154
},
{
"epoch": 1.4090909090909092,
"grad_norm": 3.342853307723999,
"learning_rate": 0.0005333333333333334,
"loss": 2.159,
"step": 155
},
{
"epoch": 1.4181818181818182,
"grad_norm": 3.7631382942199707,
"learning_rate": 0.0005303030303030302,
"loss": 2.2283,
"step": 156
},
{
"epoch": 1.4272727272727272,
"grad_norm": 2.992854595184326,
"learning_rate": 0.0005272727272727272,
"loss": 1.745,
"step": 157
},
{
"epoch": 1.4363636363636363,
"grad_norm": 3.1116650104522705,
"learning_rate": 0.0005242424242424244,
"loss": 2.1848,
"step": 158
},
{
"epoch": 1.4454545454545453,
"grad_norm": 3.336103916168213,
"learning_rate": 0.0005212121212121212,
"loss": 2.2004,
"step": 159
},
{
"epoch": 1.4545454545454546,
"grad_norm": 3.174536943435669,
"learning_rate": 0.0005181818181818182,
"loss": 2.4022,
"step": 160
},
{
"epoch": 1.4636363636363636,
"grad_norm": 3.145228147506714,
"learning_rate": 0.0005151515151515151,
"loss": 2.0569,
"step": 161
},
{
"epoch": 1.4727272727272727,
"grad_norm": 3.1418628692626953,
"learning_rate": 0.0005121212121212121,
"loss": 1.5927,
"step": 162
},
{
"epoch": 1.481818181818182,
"grad_norm": 3.7994742393493652,
"learning_rate": 0.000509090909090909,
"loss": 2.5287,
"step": 163
},
{
"epoch": 1.490909090909091,
"grad_norm": 3.5320212841033936,
"learning_rate": 0.0005060606060606061,
"loss": 1.9246,
"step": 164
},
{
"epoch": 1.5,
"grad_norm": 3.514688014984131,
"learning_rate": 0.000503030303030303,
"loss": 1.6729,
"step": 165
},
{
"epoch": 1.509090909090909,
"grad_norm": 3.678908348083496,
"learning_rate": 0.0005,
"loss": 2.3773,
"step": 166
},
{
"epoch": 1.518181818181818,
"grad_norm": 3.337244749069214,
"learning_rate": 0.000496969696969697,
"loss": 2.1421,
"step": 167
},
{
"epoch": 1.5272727272727273,
"grad_norm": 3.4535601139068604,
"learning_rate": 0.000493939393939394,
"loss": 1.7733,
"step": 168
},
{
"epoch": 1.5363636363636364,
"grad_norm": 3.455474853515625,
"learning_rate": 0.0004909090909090909,
"loss": 2.1553,
"step": 169
},
{
"epoch": 1.5454545454545454,
"grad_norm": 3.062847137451172,
"learning_rate": 0.00048787878787878784,
"loss": 1.7844,
"step": 170
},
{
"epoch": 1.5545454545454547,
"grad_norm": 4.101480960845947,
"learning_rate": 0.0004848484848484849,
"loss": 2.2217,
"step": 171
},
{
"epoch": 1.5636363636363635,
"grad_norm": 3.1846115589141846,
"learning_rate": 0.00048181818181818184,
"loss": 1.9468,
"step": 172
},
{
"epoch": 1.5727272727272728,
"grad_norm": 3.9083359241485596,
"learning_rate": 0.0004787878787878788,
"loss": 1.8599,
"step": 173
},
{
"epoch": 1.5818181818181818,
"grad_norm": 5.947788238525391,
"learning_rate": 0.0004757575757575758,
"loss": 2.2139,
"step": 174
},
{
"epoch": 1.5909090909090908,
"grad_norm": 3.882169008255005,
"learning_rate": 0.0004727272727272727,
"loss": 2.1455,
"step": 175
},
{
"epoch": 1.6,
"grad_norm": 4.504673957824707,
"learning_rate": 0.0004696969696969697,
"loss": 2.4196,
"step": 176
},
{
"epoch": 1.6090909090909091,
"grad_norm": 3.44627046585083,
"learning_rate": 0.00046666666666666666,
"loss": 2.004,
"step": 177
},
{
"epoch": 1.6181818181818182,
"grad_norm": 3.229856491088867,
"learning_rate": 0.00046363636363636366,
"loss": 2.2014,
"step": 178
},
{
"epoch": 1.6272727272727274,
"grad_norm": 3.0855553150177,
"learning_rate": 0.00046060606060606066,
"loss": 2.1409,
"step": 179
},
{
"epoch": 1.6363636363636362,
"grad_norm": 3.1679368019104004,
"learning_rate": 0.0004575757575757576,
"loss": 2.2041,
"step": 180
},
{
"epoch": 1.6454545454545455,
"grad_norm": 7.7114033699035645,
"learning_rate": 0.00045454545454545455,
"loss": 2.0694,
"step": 181
},
{
"epoch": 1.6545454545454545,
"grad_norm": 3.019507646560669,
"learning_rate": 0.00045151515151515154,
"loss": 1.6045,
"step": 182
},
{
"epoch": 1.6636363636363636,
"grad_norm": 5.119715690612793,
"learning_rate": 0.0004484848484848485,
"loss": 1.9407,
"step": 183
},
{
"epoch": 1.6727272727272728,
"grad_norm": 3.885646343231201,
"learning_rate": 0.00044545454545454543,
"loss": 2.6174,
"step": 184
},
{
"epoch": 1.6818181818181817,
"grad_norm": 3.4062960147857666,
"learning_rate": 0.00044242424242424243,
"loss": 2.3298,
"step": 185
},
{
"epoch": 1.690909090909091,
"grad_norm": 3.3024728298187256,
"learning_rate": 0.0004393939393939394,
"loss": 2.1404,
"step": 186
},
{
"epoch": 1.7,
"grad_norm": 2.913706064224243,
"learning_rate": 0.00043636363636363637,
"loss": 1.9673,
"step": 187
},
{
"epoch": 1.709090909090909,
"grad_norm": 3.2594282627105713,
"learning_rate": 0.00043333333333333337,
"loss": 2.2272,
"step": 188
},
{
"epoch": 1.7181818181818183,
"grad_norm": 2.8345882892608643,
"learning_rate": 0.0004303030303030303,
"loss": 1.6743,
"step": 189
},
{
"epoch": 1.7272727272727273,
"grad_norm": 3.7304282188415527,
"learning_rate": 0.00042727272727272726,
"loss": 2.1952,
"step": 190
},
{
"epoch": 1.7363636363636363,
"grad_norm": 3.3065695762634277,
"learning_rate": 0.00042424242424242425,
"loss": 1.9668,
"step": 191
},
{
"epoch": 1.7454545454545456,
"grad_norm": 3.9107859134674072,
"learning_rate": 0.0004212121212121212,
"loss": 2.1511,
"step": 192
},
{
"epoch": 1.7545454545454544,
"grad_norm": 2.8908228874206543,
"learning_rate": 0.00041818181818181814,
"loss": 1.9678,
"step": 193
},
{
"epoch": 1.7636363636363637,
"grad_norm": 3.057619571685791,
"learning_rate": 0.0004151515151515152,
"loss": 2.3442,
"step": 194
},
{
"epoch": 1.7727272727272727,
"grad_norm": 3.329041004180908,
"learning_rate": 0.00041212121212121214,
"loss": 2.1835,
"step": 195
},
{
"epoch": 1.7818181818181817,
"grad_norm": 3.7473957538604736,
"learning_rate": 0.00040909090909090913,
"loss": 2.3078,
"step": 196
},
{
"epoch": 1.790909090909091,
"grad_norm": 2.968825101852417,
"learning_rate": 0.0004060606060606061,
"loss": 1.6086,
"step": 197
},
{
"epoch": 1.8,
"grad_norm": 3.3219282627105713,
"learning_rate": 0.000403030303030303,
"loss": 2.1572,
"step": 198
},
{
"epoch": 1.809090909090909,
"grad_norm": 3.4427106380462646,
"learning_rate": 0.0004,
"loss": 2.393,
"step": 199
},
{
"epoch": 1.8181818181818183,
"grad_norm": 5.04589319229126,
"learning_rate": 0.00039696969696969696,
"loss": 2.3069,
"step": 200
},
{
"epoch": 1.8272727272727272,
"grad_norm": 2.9696149826049805,
"learning_rate": 0.0003939393939393939,
"loss": 2.1208,
"step": 201
},
{
"epoch": 1.8363636363636364,
"grad_norm": 3.635545492172241,
"learning_rate": 0.00039090909090909096,
"loss": 2.0613,
"step": 202
},
{
"epoch": 1.8454545454545455,
"grad_norm": 3.1097395420074463,
"learning_rate": 0.0003878787878787879,
"loss": 1.9141,
"step": 203
},
{
"epoch": 1.8545454545454545,
"grad_norm": 2.833266496658325,
"learning_rate": 0.00038484848484848485,
"loss": 1.9358,
"step": 204
},
{
"epoch": 1.8636363636363638,
"grad_norm": 2.9658091068267822,
"learning_rate": 0.00038181818181818184,
"loss": 1.8512,
"step": 205
},
{
"epoch": 1.8727272727272726,
"grad_norm": 3.205237865447998,
"learning_rate": 0.0003787878787878788,
"loss": 2.0815,
"step": 206
},
{
"epoch": 1.8818181818181818,
"grad_norm": 3.148261308670044,
"learning_rate": 0.00037575757575757573,
"loss": 2.0733,
"step": 207
},
{
"epoch": 1.8909090909090909,
"grad_norm": 3.3210079669952393,
"learning_rate": 0.00037272727272727273,
"loss": 2.0593,
"step": 208
},
{
"epoch": 1.9,
"grad_norm": 2.9433910846710205,
"learning_rate": 0.00036969696969696967,
"loss": 2.0443,
"step": 209
},
{
"epoch": 1.9090909090909092,
"grad_norm": 2.9857499599456787,
"learning_rate": 0.00036666666666666667,
"loss": 1.9256,
"step": 210
},
{
"epoch": 1.9181818181818182,
"grad_norm": 2.8231537342071533,
"learning_rate": 0.00036363636363636367,
"loss": 1.8467,
"step": 211
},
{
"epoch": 1.9272727272727272,
"grad_norm": 3.4465367794036865,
"learning_rate": 0.0003606060606060606,
"loss": 2.1766,
"step": 212
},
{
"epoch": 1.9363636363636365,
"grad_norm": 3.690007448196411,
"learning_rate": 0.0003575757575757576,
"loss": 1.967,
"step": 213
},
{
"epoch": 1.9454545454545453,
"grad_norm": 3.209928512573242,
"learning_rate": 0.00035454545454545455,
"loss": 2.1428,
"step": 214
},
{
"epoch": 1.9545454545454546,
"grad_norm": 3.186617851257324,
"learning_rate": 0.0003515151515151515,
"loss": 2.2433,
"step": 215
},
{
"epoch": 1.9636363636363636,
"grad_norm": 10.015161514282227,
"learning_rate": 0.0003484848484848485,
"loss": 2.2966,
"step": 216
},
{
"epoch": 1.9727272727272727,
"grad_norm": 3.2441928386688232,
"learning_rate": 0.00034545454545454544,
"loss": 1.991,
"step": 217
},
{
"epoch": 1.981818181818182,
"grad_norm": 2.8129360675811768,
"learning_rate": 0.00034242424242424244,
"loss": 1.7793,
"step": 218
},
{
"epoch": 1.990909090909091,
"grad_norm": 3.8411054611206055,
"learning_rate": 0.00033939393939393943,
"loss": 2.4961,
"step": 219
},
{
"epoch": 2.0,
"grad_norm": 3.3925347328186035,
"learning_rate": 0.0003363636363636364,
"loss": 2.2593,
"step": 220
},
{
"epoch": 2.0,
"eval_f1": 0.8853,
"eval_gen_len": 49.9091,
"eval_loss": 2.0981531143188477,
"eval_precision": 0.8822,
"eval_recall": 0.8886,
"eval_rouge1": 0.4125,
"eval_rouge2": 0.1843,
"eval_rougeL": 0.3448,
"eval_rougeLsum": 0.3837,
"eval_runtime": 11.6893,
"eval_samples_per_second": 9.41,
"eval_steps_per_second": 1.198,
"step": 220
},
{
"epoch": 2.0090909090909093,
"grad_norm": 2.528470039367676,
"learning_rate": 0.0003333333333333333,
"loss": 1.5054,
"step": 221
},
{
"epoch": 2.018181818181818,
"grad_norm": 2.865614891052246,
"learning_rate": 0.0003303030303030303,
"loss": 1.9352,
"step": 222
},
{
"epoch": 2.0272727272727273,
"grad_norm": 3.3467092514038086,
"learning_rate": 0.00032727272727272726,
"loss": 2.04,
"step": 223
},
{
"epoch": 2.036363636363636,
"grad_norm": 3.4223382472991943,
"learning_rate": 0.0003242424242424242,
"loss": 1.9573,
"step": 224
},
{
"epoch": 2.0454545454545454,
"grad_norm": 3.222435474395752,
"learning_rate": 0.00032121212121212126,
"loss": 2.1637,
"step": 225
},
{
"epoch": 2.0545454545454547,
"grad_norm": 3.591017007827759,
"learning_rate": 0.0003181818181818182,
"loss": 2.6879,
"step": 226
},
{
"epoch": 2.0636363636363635,
"grad_norm": 4.53701639175415,
"learning_rate": 0.00031515151515151515,
"loss": 2.0278,
"step": 227
},
{
"epoch": 2.0727272727272728,
"grad_norm": 2.7945427894592285,
"learning_rate": 0.00031212121212121214,
"loss": 1.9943,
"step": 228
},
{
"epoch": 2.081818181818182,
"grad_norm": 2.658731460571289,
"learning_rate": 0.0003090909090909091,
"loss": 1.6718,
"step": 229
},
{
"epoch": 2.090909090909091,
"grad_norm": 3.0230305194854736,
"learning_rate": 0.00030606060606060603,
"loss": 1.933,
"step": 230
},
{
"epoch": 2.1,
"grad_norm": 3.0633113384246826,
"learning_rate": 0.00030303030303030303,
"loss": 1.6638,
"step": 231
},
{
"epoch": 2.109090909090909,
"grad_norm": 2.8960585594177246,
"learning_rate": 0.0003,
"loss": 1.6142,
"step": 232
},
{
"epoch": 2.118181818181818,
"grad_norm": 3.0390872955322266,
"learning_rate": 0.000296969696969697,
"loss": 1.7663,
"step": 233
},
{
"epoch": 2.1272727272727274,
"grad_norm": 2.775212526321411,
"learning_rate": 0.00029393939393939397,
"loss": 1.8756,
"step": 234
},
{
"epoch": 2.1363636363636362,
"grad_norm": NaN,
"learning_rate": 0.00029393939393939397,
"loss": 1.8024,
"step": 235
},
{
"epoch": 2.1454545454545455,
"grad_norm": 4.173327922821045,
"learning_rate": 0.0002909090909090909,
"loss": 2.2607,
"step": 236
},
{
"epoch": 2.1545454545454543,
"grad_norm": 3.1332976818084717,
"learning_rate": 0.0002878787878787879,
"loss": 1.7647,
"step": 237
},
{
"epoch": 2.1636363636363636,
"grad_norm": 3.2332346439361572,
"learning_rate": 0.00028484848484848485,
"loss": 1.9875,
"step": 238
},
{
"epoch": 2.172727272727273,
"grad_norm": 4.6719536781311035,
"learning_rate": 0.0002818181818181818,
"loss": 2.0469,
"step": 239
},
{
"epoch": 2.1818181818181817,
"grad_norm": 3.472750425338745,
"learning_rate": 0.0002787878787878788,
"loss": 2.5291,
"step": 240
},
{
"epoch": 2.190909090909091,
"grad_norm": 5.792453289031982,
"learning_rate": 0.00027575757575757574,
"loss": 1.7036,
"step": 241
},
{
"epoch": 2.2,
"grad_norm": 3.294654607772827,
"learning_rate": 0.00027272727272727274,
"loss": 1.3701,
"step": 242
},
{
"epoch": 2.209090909090909,
"grad_norm": 3.6124680042266846,
"learning_rate": 0.00026969696969696974,
"loss": 2.4755,
"step": 243
},
{
"epoch": 2.2181818181818183,
"grad_norm": 3.8428094387054443,
"learning_rate": 0.0002666666666666667,
"loss": 2.2271,
"step": 244
},
{
"epoch": 2.227272727272727,
"grad_norm": 3.604736804962158,
"learning_rate": 0.0002636363636363636,
"loss": 2.0037,
"step": 245
},
{
"epoch": 2.2363636363636363,
"grad_norm": 3.890007495880127,
"learning_rate": 0.0002606060606060606,
"loss": 2.2793,
"step": 246
},
{
"epoch": 2.2454545454545456,
"grad_norm": 3.313204765319824,
"learning_rate": 0.00025757575757575756,
"loss": 2.0551,
"step": 247
},
{
"epoch": 2.2545454545454544,
"grad_norm": 3.3129971027374268,
"learning_rate": 0.0002545454545454545,
"loss": 2.1244,
"step": 248
},
{
"epoch": 2.2636363636363637,
"grad_norm": 3.695997714996338,
"learning_rate": 0.0002515151515151515,
"loss": 2.2076,
"step": 249
},
{
"epoch": 2.2727272727272725,
"grad_norm": 3.030856132507324,
"learning_rate": 0.0002484848484848485,
"loss": 2.4505,
"step": 250
},
{
"epoch": 2.2818181818181817,
"grad_norm": 2.8353431224823,
"learning_rate": 0.00024545454545454545,
"loss": 1.572,
"step": 251
},
{
"epoch": 2.290909090909091,
"grad_norm": 4.0871806144714355,
"learning_rate": 0.00024242424242424245,
"loss": 1.4687,
"step": 252
},
{
"epoch": 2.3,
"grad_norm": 2.9628946781158447,
"learning_rate": 0.0002393939393939394,
"loss": 1.9866,
"step": 253
},
{
"epoch": 2.309090909090909,
"grad_norm": 2.961716890335083,
"learning_rate": 0.00023636363636363636,
"loss": 2.2033,
"step": 254
},
{
"epoch": 2.3181818181818183,
"grad_norm": 3.783841371536255,
"learning_rate": 0.00023333333333333333,
"loss": 1.8624,
"step": 255
},
{
"epoch": 2.327272727272727,
"grad_norm": 3.51766037940979,
"learning_rate": 0.00023030303030303033,
"loss": 2.087,
"step": 256
},
{
"epoch": 2.3363636363636364,
"grad_norm": 3.115341901779175,
"learning_rate": 0.00022727272727272727,
"loss": 2.4484,
"step": 257
},
{
"epoch": 2.3454545454545457,
"grad_norm": 3.2531635761260986,
"learning_rate": 0.00022424242424242424,
"loss": 1.8732,
"step": 258
},
{
"epoch": 2.3545454545454545,
"grad_norm": 2.960334062576294,
"learning_rate": 0.00022121212121212121,
"loss": 2.0749,
"step": 259
},
{
"epoch": 2.3636363636363638,
"grad_norm": 3.014167308807373,
"learning_rate": 0.00021818181818181818,
"loss": 2.1352,
"step": 260
},
{
"epoch": 2.3727272727272726,
"grad_norm": 5.599313259124756,
"learning_rate": 0.00021515151515151516,
"loss": 1.844,
"step": 261
},
{
"epoch": 2.381818181818182,
"grad_norm": 2.889808416366577,
"learning_rate": 0.00021212121212121213,
"loss": 1.8171,
"step": 262
},
{
"epoch": 2.390909090909091,
"grad_norm": 3.555586099624634,
"learning_rate": 0.00020909090909090907,
"loss": 1.4792,
"step": 263
},
{
"epoch": 2.4,
"grad_norm": 2.8450050354003906,
"learning_rate": 0.00020606060606060607,
"loss": 2.2489,
"step": 264
},
{
"epoch": 2.409090909090909,
"grad_norm": 2.657527446746826,
"learning_rate": 0.00020303030303030304,
"loss": 1.8199,
"step": 265
},
{
"epoch": 2.418181818181818,
"grad_norm": 2.6506874561309814,
"learning_rate": 0.0002,
"loss": 1.7726,
"step": 266
},
{
"epoch": 2.4272727272727272,
"grad_norm": 2.997509002685547,
"learning_rate": 0.00019696969696969695,
"loss": 2.1782,
"step": 267
},
{
"epoch": 2.4363636363636365,
"grad_norm": 3.3739423751831055,
"learning_rate": 0.00019393939393939395,
"loss": 1.9597,
"step": 268
},
{
"epoch": 2.4454545454545453,
"grad_norm": 3.1809239387512207,
"learning_rate": 0.00019090909090909092,
"loss": 2.1039,
"step": 269
},
{
"epoch": 2.4545454545454546,
"grad_norm": 3.269407272338867,
"learning_rate": 0.00018787878787878787,
"loss": 2.0699,
"step": 270
},
{
"epoch": 2.463636363636364,
"grad_norm": 3.44803786277771,
"learning_rate": 0.00018484848484848484,
"loss": 2.013,
"step": 271
},
{
"epoch": 2.4727272727272727,
"grad_norm": 2.815349578857422,
"learning_rate": 0.00018181818181818183,
"loss": 1.6578,
"step": 272
},
{
"epoch": 2.481818181818182,
"grad_norm": 3.012932777404785,
"learning_rate": 0.0001787878787878788,
"loss": 1.7602,
"step": 273
},
{
"epoch": 2.4909090909090907,
"grad_norm": 3.768132448196411,
"learning_rate": 0.00017575757575757575,
"loss": 2.1302,
"step": 274
},
{
"epoch": 2.5,
"grad_norm": 3.2790582180023193,
"learning_rate": 0.00017272727272727272,
"loss": 2.0968,
"step": 275
},
{
"epoch": 2.509090909090909,
"grad_norm": 3.081514358520508,
"learning_rate": 0.00016969696969696972,
"loss": 1.8146,
"step": 276
},
{
"epoch": 2.518181818181818,
"grad_norm": 13.39486312866211,
"learning_rate": 0.00016666666666666666,
"loss": 1.8084,
"step": 277
},
{
"epoch": 2.5272727272727273,
"grad_norm": 3.1995341777801514,
"learning_rate": 0.00016363636363636363,
"loss": 2.0603,
"step": 278
},
{
"epoch": 2.536363636363636,
"grad_norm": 3.180493116378784,
"learning_rate": 0.00016060606060606063,
"loss": 2.2158,
"step": 279
},
{
"epoch": 2.5454545454545454,
"grad_norm": 2.8051111698150635,
"learning_rate": 0.00015757575757575757,
"loss": 1.8632,
"step": 280
},
{
"epoch": 2.5545454545454547,
"grad_norm": 13.768489837646484,
"learning_rate": 0.00015454545454545454,
"loss": 1.9395,
"step": 281
},
{
"epoch": 2.5636363636363635,
"grad_norm": 3.2339987754821777,
"learning_rate": 0.00015151515151515152,
"loss": 1.7868,
"step": 282
},
{
"epoch": 2.5727272727272728,
"grad_norm": 3.2292120456695557,
"learning_rate": 0.0001484848484848485,
"loss": 1.8017,
"step": 283
},
{
"epoch": 2.581818181818182,
"grad_norm": 3.0802104473114014,
"learning_rate": 0.00014545454545454546,
"loss": 1.8583,
"step": 284
},
{
"epoch": 2.590909090909091,
"grad_norm": 2.828216791152954,
"learning_rate": 0.00014242424242424243,
"loss": 2.0203,
"step": 285
},
{
"epoch": 2.6,
"grad_norm": 2.7820215225219727,
"learning_rate": 0.0001393939393939394,
"loss": 1.6293,
"step": 286
},
{
"epoch": 2.6090909090909093,
"grad_norm": 3.1628901958465576,
"learning_rate": 0.00013636363636363637,
"loss": 1.772,
"step": 287
},
{
"epoch": 2.618181818181818,
"grad_norm": 3.8483550548553467,
"learning_rate": 0.00013333333333333334,
"loss": 2.1176,
"step": 288
},
{
"epoch": 2.6272727272727274,
"grad_norm": 2.9097654819488525,
"learning_rate": 0.0001303030303030303,
"loss": 1.6703,
"step": 289
},
{
"epoch": 2.6363636363636362,
"grad_norm": 2.856644868850708,
"learning_rate": 0.00012727272727272725,
"loss": 2.009,
"step": 290
},
{
"epoch": 2.6454545454545455,
"grad_norm": 3.6364967823028564,
"learning_rate": 0.00012424242424242425,
"loss": 2.111,
"step": 291
},
{
"epoch": 2.6545454545454543,
"grad_norm": 3.5961639881134033,
"learning_rate": 0.00012121212121212122,
"loss": 2.6677,
"step": 292
},
{
"epoch": 2.6636363636363636,
"grad_norm": 3.2015624046325684,
"learning_rate": 0.00011818181818181818,
"loss": 2.0203,
"step": 293
},
{
"epoch": 2.672727272727273,
"grad_norm": 2.7893030643463135,
"learning_rate": 0.00011515151515151516,
"loss": 1.8248,
"step": 294
},
{
"epoch": 2.6818181818181817,
"grad_norm": 3.251176595687866,
"learning_rate": 0.00011212121212121212,
"loss": 2.408,
"step": 295
},
{
"epoch": 2.690909090909091,
"grad_norm": 3.2930307388305664,
"learning_rate": 0.00010909090909090909,
"loss": 2.1178,
"step": 296
},
{
"epoch": 2.7,
"grad_norm": 3.3087244033813477,
"learning_rate": 0.00010606060606060606,
"loss": 2.1747,
"step": 297
},
{
"epoch": 2.709090909090909,
"grad_norm": 3.336773633956909,
"learning_rate": 0.00010303030303030303,
"loss": 1.7466,
"step": 298
},
{
"epoch": 2.7181818181818183,
"grad_norm": 3.6153817176818848,
"learning_rate": 0.0001,
"loss": 1.7019,
"step": 299
},
{
"epoch": 2.7272727272727275,
"grad_norm": 3.600694179534912,
"learning_rate": 9.696969696969698e-05,
"loss": 2.6509,
"step": 300
},
{
"epoch": 2.7363636363636363,
"grad_norm": 2.662508487701416,
"learning_rate": 9.393939393939393e-05,
"loss": 1.6383,
"step": 301
},
{
"epoch": 2.7454545454545456,
"grad_norm": 3.2492973804473877,
"learning_rate": 9.090909090909092e-05,
"loss": 1.854,
"step": 302
},
{
"epoch": 2.7545454545454544,
"grad_norm": 4.045100688934326,
"learning_rate": 8.787878787878787e-05,
"loss": 1.8465,
"step": 303
},
{
"epoch": 2.7636363636363637,
"grad_norm": 3.93559193611145,
"learning_rate": 8.484848484848486e-05,
"loss": 1.6572,
"step": 304
},
{
"epoch": 2.7727272727272725,
"grad_norm": 2.555962324142456,
"learning_rate": 8.181818181818182e-05,
"loss": 1.4478,
"step": 305
},
{
"epoch": 2.7818181818181817,
"grad_norm": 3.3565707206726074,
"learning_rate": 7.878787878787879e-05,
"loss": 1.9765,
"step": 306
},
{
"epoch": 2.790909090909091,
"grad_norm": 4.662497043609619,
"learning_rate": 7.575757575757576e-05,
"loss": 2.4216,
"step": 307
},
{
"epoch": 2.8,
"grad_norm": 3.499770402908325,
"learning_rate": 7.272727272727273e-05,
"loss": 1.8676,
"step": 308
},
{
"epoch": 2.809090909090909,
"grad_norm": 3.0840108394622803,
"learning_rate": 6.96969696969697e-05,
"loss": 2.3141,
"step": 309
},
{
"epoch": 2.8181818181818183,
"grad_norm": 2.8939449787139893,
"learning_rate": 6.666666666666667e-05,
"loss": 1.684,
"step": 310
},
{
"epoch": 2.827272727272727,
"grad_norm": 3.333470582962036,
"learning_rate": 6.363636363636363e-05,
"loss": 2.2779,
"step": 311
},
{
"epoch": 2.8363636363636364,
"grad_norm": 4.036566734313965,
"learning_rate": 6.060606060606061e-05,
"loss": 1.972,
"step": 312
},
{
"epoch": 2.8454545454545457,
"grad_norm": 3.638002872467041,
"learning_rate": 5.757575757575758e-05,
"loss": 2.0617,
"step": 313
},
{
"epoch": 2.8545454545454545,
"grad_norm": 3.1803669929504395,
"learning_rate": 5.4545454545454546e-05,
"loss": 1.9395,
"step": 314
},
{
"epoch": 2.8636363636363638,
"grad_norm": 3.0630593299865723,
"learning_rate": 5.151515151515152e-05,
"loss": 1.6895,
"step": 315
},
{
"epoch": 2.8727272727272726,
"grad_norm": 3.2487800121307373,
"learning_rate": 4.848484848484849e-05,
"loss": 2.1938,
"step": 316
},
{
"epoch": 2.881818181818182,
"grad_norm": 3.0774974822998047,
"learning_rate": 4.545454545454546e-05,
"loss": 1.94,
"step": 317
},
{
"epoch": 2.8909090909090907,
"grad_norm": 3.3253180980682373,
"learning_rate": 4.242424242424243e-05,
"loss": 2.4585,
"step": 318
},
{
"epoch": 2.9,
"grad_norm": 3.01503586769104,
"learning_rate": 3.939393939393939e-05,
"loss": 2.2196,
"step": 319
},
{
"epoch": 2.909090909090909,
"grad_norm": 3.550036907196045,
"learning_rate": 3.6363636363636364e-05,
"loss": 1.7204,
"step": 320
},
{
"epoch": 2.918181818181818,
"grad_norm": 3.0467073917388916,
"learning_rate": 3.3333333333333335e-05,
"loss": 2.1365,
"step": 321
},
{
"epoch": 2.9272727272727272,
"grad_norm": 6.076046943664551,
"learning_rate": 3.0303030303030306e-05,
"loss": 1.5648,
"step": 322
},
{
"epoch": 2.9363636363636365,
"grad_norm": 2.946725606918335,
"learning_rate": 2.7272727272727273e-05,
"loss": 1.711,
"step": 323
},
{
"epoch": 2.9454545454545453,
"grad_norm": 5.3960652351379395,
"learning_rate": 2.4242424242424244e-05,
"loss": 2.1175,
"step": 324
},
{
"epoch": 2.9545454545454546,
"grad_norm": 3.22198224067688,
"learning_rate": 2.1212121212121215e-05,
"loss": 1.9957,
"step": 325
},
{
"epoch": 2.963636363636364,
"grad_norm": 3.2478060722351074,
"learning_rate": 1.8181818181818182e-05,
"loss": 2.2945,
"step": 326
},
{
"epoch": 2.9727272727272727,
"grad_norm": 4.0038743019104,
"learning_rate": 1.5151515151515153e-05,
"loss": 1.7658,
"step": 327
},
{
"epoch": 2.981818181818182,
"grad_norm": 3.221017360687256,
"learning_rate": 1.2121212121212122e-05,
"loss": 1.7757,
"step": 328
},
{
"epoch": 2.990909090909091,
"grad_norm": 3.0756263732910156,
"learning_rate": 9.090909090909091e-06,
"loss": 1.6078,
"step": 329
},
{
"epoch": 3.0,
"grad_norm": 3.273972272872925,
"learning_rate": 6.060606060606061e-06,
"loss": 1.9318,
"step": 330
},
{
"epoch": 3.0,
"eval_f1": 0.8896,
"eval_gen_len": 49.5909,
"eval_loss": 2.0811283588409424,
"eval_precision": 0.8881,
"eval_recall": 0.8913,
"eval_rouge1": 0.4387,
"eval_rouge2": 0.196,
"eval_rougeL": 0.3605,
"eval_rougeLsum": 0.4055,
"eval_runtime": 11.6259,
"eval_samples_per_second": 9.462,
"eval_steps_per_second": 1.204,
"step": 330
},
{
"epoch": 3.0,
"step": 330,
"total_flos": 361674414489600.0,
"train_loss": 2.1775987458951547,
"train_runtime": 101.4394,
"train_samples_per_second": 25.996,
"train_steps_per_second": 3.253
}
],
"logging_steps": 1,
"max_steps": 330,
"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": 361674414489600.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}