Guilherme34's picture
Upload folder using huggingface_hub
8c597e1 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 90,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02247191011235955,
"grad_norm": 0.2744160592556,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.7619,
"step": 1
},
{
"epoch": 0.0449438202247191,
"grad_norm": 0.32727673649787903,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.8704,
"step": 2
},
{
"epoch": 0.06741573033707865,
"grad_norm": 0.22079522907733917,
"learning_rate": 3e-06,
"loss": 0.7241,
"step": 3
},
{
"epoch": 0.0898876404494382,
"grad_norm": 0.3042285144329071,
"learning_rate": 4.000000000000001e-06,
"loss": 0.9591,
"step": 4
},
{
"epoch": 0.11235955056179775,
"grad_norm": 0.28325748443603516,
"learning_rate": 5e-06,
"loss": 1.061,
"step": 5
},
{
"epoch": 0.1348314606741573,
"grad_norm": 0.29770785570144653,
"learning_rate": 6e-06,
"loss": 1.0407,
"step": 6
},
{
"epoch": 0.15730337078651685,
"grad_norm": 0.2635294198989868,
"learning_rate": 7e-06,
"loss": 0.9524,
"step": 7
},
{
"epoch": 0.1797752808988764,
"grad_norm": 0.2629376947879791,
"learning_rate": 8.000000000000001e-06,
"loss": 1.0095,
"step": 8
},
{
"epoch": 0.20224719101123595,
"grad_norm": 0.30229848623275757,
"learning_rate": 9e-06,
"loss": 0.7805,
"step": 9
},
{
"epoch": 0.2247191011235955,
"grad_norm": 0.2629299759864807,
"learning_rate": 1e-05,
"loss": 0.8706,
"step": 10
},
{
"epoch": 0.24719101123595505,
"grad_norm": 0.26694297790527344,
"learning_rate": 9.999146252290264e-06,
"loss": 0.9653,
"step": 11
},
{
"epoch": 0.2696629213483146,
"grad_norm": 0.2794544994831085,
"learning_rate": 9.996585300715117e-06,
"loss": 0.7668,
"step": 12
},
{
"epoch": 0.29213483146067415,
"grad_norm": 0.30685344338417053,
"learning_rate": 9.992318019837171e-06,
"loss": 0.8074,
"step": 13
},
{
"epoch": 0.3146067415730337,
"grad_norm": 0.3292616605758667,
"learning_rate": 9.98634586692894e-06,
"loss": 0.8413,
"step": 14
},
{
"epoch": 0.33707865168539325,
"grad_norm": 0.34031111001968384,
"learning_rate": 9.978670881475173e-06,
"loss": 0.6885,
"step": 15
},
{
"epoch": 0.3595505617977528,
"grad_norm": 0.31020820140838623,
"learning_rate": 9.96929568447637e-06,
"loss": 1.0567,
"step": 16
},
{
"epoch": 0.38202247191011235,
"grad_norm": 0.28236857056617737,
"learning_rate": 9.958223477553715e-06,
"loss": 0.7969,
"step": 17
},
{
"epoch": 0.4044943820224719,
"grad_norm": 0.3202574551105499,
"learning_rate": 9.945458041855732e-06,
"loss": 0.8376,
"step": 18
},
{
"epoch": 0.42696629213483145,
"grad_norm": 0.2797839045524597,
"learning_rate": 9.931003736767013e-06,
"loss": 0.8911,
"step": 19
},
{
"epoch": 0.449438202247191,
"grad_norm": 0.3114033639431,
"learning_rate": 9.91486549841951e-06,
"loss": 0.9042,
"step": 20
},
{
"epoch": 0.47191011235955055,
"grad_norm": 0.288392037153244,
"learning_rate": 9.89704883800683e-06,
"loss": 0.9409,
"step": 21
},
{
"epoch": 0.4943820224719101,
"grad_norm": 0.31594759225845337,
"learning_rate": 9.877559839902185e-06,
"loss": 0.7856,
"step": 22
},
{
"epoch": 0.5168539325842697,
"grad_norm": 0.33034929633140564,
"learning_rate": 9.85640515958057e-06,
"loss": 0.8219,
"step": 23
},
{
"epoch": 0.5393258426966292,
"grad_norm": 0.3292032778263092,
"learning_rate": 9.833592021345938e-06,
"loss": 0.7739,
"step": 24
},
{
"epoch": 0.5617977528089888,
"grad_norm": 0.2713082432746887,
"learning_rate": 9.809128215864096e-06,
"loss": 0.6795,
"step": 25
},
{
"epoch": 0.5842696629213483,
"grad_norm": 0.28911784291267395,
"learning_rate": 9.783022097502204e-06,
"loss": 0.8294,
"step": 26
},
{
"epoch": 0.6067415730337079,
"grad_norm": 0.2532961666584015,
"learning_rate": 9.755282581475769e-06,
"loss": 0.8253,
"step": 27
},
{
"epoch": 0.6292134831460674,
"grad_norm": 0.23403476178646088,
"learning_rate": 9.7259191408041e-06,
"loss": 0.8501,
"step": 28
},
{
"epoch": 0.651685393258427,
"grad_norm": 0.2743186056613922,
"learning_rate": 9.694941803075285e-06,
"loss": 1.2514,
"step": 29
},
{
"epoch": 0.6741573033707865,
"grad_norm": 0.22719059884548187,
"learning_rate": 9.66236114702178e-06,
"loss": 0.7012,
"step": 30
},
{
"epoch": 0.6966292134831461,
"grad_norm": 0.22790080308914185,
"learning_rate": 9.628188298907782e-06,
"loss": 0.7681,
"step": 31
},
{
"epoch": 0.7191011235955056,
"grad_norm": 0.18746985495090485,
"learning_rate": 9.592434928729617e-06,
"loss": 0.8587,
"step": 32
},
{
"epoch": 0.7415730337078652,
"grad_norm": 0.19890236854553223,
"learning_rate": 9.555113246230443e-06,
"loss": 0.8129,
"step": 33
},
{
"epoch": 0.7640449438202247,
"grad_norm": 0.16481083631515503,
"learning_rate": 9.516235996730645e-06,
"loss": 0.658,
"step": 34
},
{
"epoch": 0.7865168539325843,
"grad_norm": 0.19077646732330322,
"learning_rate": 9.475816456775313e-06,
"loss": 0.6721,
"step": 35
},
{
"epoch": 0.8089887640449438,
"grad_norm": 0.20115327835083008,
"learning_rate": 9.43386842960031e-06,
"loss": 0.7361,
"step": 36
},
{
"epoch": 0.8314606741573034,
"grad_norm": 0.16515249013900757,
"learning_rate": 9.39040624041849e-06,
"loss": 0.6858,
"step": 37
},
{
"epoch": 0.8539325842696629,
"grad_norm": 0.16454002261161804,
"learning_rate": 9.345444731527642e-06,
"loss": 0.902,
"step": 38
},
{
"epoch": 0.8764044943820225,
"grad_norm": 0.12956053018569946,
"learning_rate": 9.298999257241862e-06,
"loss": 0.7653,
"step": 39
},
{
"epoch": 0.898876404494382,
"grad_norm": 0.1354527771472931,
"learning_rate": 9.251085678648072e-06,
"loss": 0.6624,
"step": 40
},
{
"epoch": 0.9213483146067416,
"grad_norm": 0.14311733841896057,
"learning_rate": 9.201720358189464e-06,
"loss": 0.6757,
"step": 41
},
{
"epoch": 0.9438202247191011,
"grad_norm": 0.14996573328971863,
"learning_rate": 9.150920154077753e-06,
"loss": 0.639,
"step": 42
},
{
"epoch": 0.9662921348314607,
"grad_norm": 0.1524282693862915,
"learning_rate": 9.098702414536107e-06,
"loss": 0.8575,
"step": 43
},
{
"epoch": 0.9887640449438202,
"grad_norm": 0.1349412202835083,
"learning_rate": 9.045084971874738e-06,
"loss": 0.6459,
"step": 44
},
{
"epoch": 1.0112359550561798,
"grad_norm": 0.12348250299692154,
"learning_rate": 8.990086136401199e-06,
"loss": 0.6682,
"step": 45
},
{
"epoch": 1.0167597765363128,
"grad_norm": 0.12682083249092102,
"learning_rate": 8.933724690167417e-06,
"loss": 0.6996,
"step": 46
},
{
"epoch": 1.0391061452513966,
"grad_norm": 0.14481687545776367,
"learning_rate": 8.87601988055565e-06,
"loss": 0.9028,
"step": 47
},
{
"epoch": 1.0614525139664805,
"grad_norm": 0.20267356932163239,
"learning_rate": 8.816991413705515e-06,
"loss": 0.7655,
"step": 48
},
{
"epoch": 1.0837988826815643,
"grad_norm": 0.16279681026935577,
"learning_rate": 8.756659447784367e-06,
"loss": 0.6583,
"step": 49
},
{
"epoch": 1.106145251396648,
"grad_norm": 0.1354082226753235,
"learning_rate": 8.695044586103297e-06,
"loss": 0.8319,
"step": 50
},
{
"epoch": 1.1284916201117319,
"grad_norm": 0.14600947499275208,
"learning_rate": 8.632167870081122e-06,
"loss": 0.6148,
"step": 51
},
{
"epoch": 1.1508379888268156,
"grad_norm": 0.2995755672454834,
"learning_rate": 8.568050772058763e-06,
"loss": 0.8722,
"step": 52
},
{
"epoch": 1.1731843575418994,
"grad_norm": 0.1370067149400711,
"learning_rate": 8.502715187966455e-06,
"loss": 0.8219,
"step": 53
},
{
"epoch": 1.1955307262569832,
"grad_norm": 0.14704233407974243,
"learning_rate": 8.436183429846314e-06,
"loss": 0.8698,
"step": 54
},
{
"epoch": 1.217877094972067,
"grad_norm": 0.13113325834274292,
"learning_rate": 8.368478218232787e-06,
"loss": 0.6741,
"step": 55
},
{
"epoch": 1.2402234636871508,
"grad_norm": 0.15853165090084076,
"learning_rate": 8.299622674393615e-06,
"loss": 0.6672,
"step": 56
},
{
"epoch": 1.2625698324022347,
"grad_norm": 0.12545864284038544,
"learning_rate": 8.229640312433938e-06,
"loss": 0.6325,
"step": 57
},
{
"epoch": 1.2849162011173183,
"grad_norm": 0.13042129576206207,
"learning_rate": 8.158555031266255e-06,
"loss": 0.8421,
"step": 58
},
{
"epoch": 1.3072625698324023,
"grad_norm": 0.12107989937067032,
"learning_rate": 8.086391106448965e-06,
"loss": 0.849,
"step": 59
},
{
"epoch": 1.329608938547486,
"grad_norm": 0.12185141444206238,
"learning_rate": 8.013173181896283e-06,
"loss": 0.6157,
"step": 60
},
{
"epoch": 1.3519553072625698,
"grad_norm": 0.14786343276500702,
"learning_rate": 7.938926261462366e-06,
"loss": 0.8534,
"step": 61
},
{
"epoch": 1.3743016759776536,
"grad_norm": 0.1170087456703186,
"learning_rate": 7.863675700402527e-06,
"loss": 0.6024,
"step": 62
},
{
"epoch": 1.3966480446927374,
"grad_norm": 0.12368728965520859,
"learning_rate": 7.787447196714428e-06,
"loss": 0.621,
"step": 63
},
{
"epoch": 1.4189944134078212,
"grad_norm": 0.13665403425693512,
"learning_rate": 7.710266782362248e-06,
"loss": 0.8647,
"step": 64
},
{
"epoch": 1.441340782122905,
"grad_norm": 0.14922167360782623,
"learning_rate": 7.63216081438678e-06,
"loss": 0.6963,
"step": 65
},
{
"epoch": 1.463687150837989,
"grad_norm": 0.20886604487895966,
"learning_rate": 7.553155965904535e-06,
"loss": 0.9604,
"step": 66
},
{
"epoch": 1.4860335195530725,
"grad_norm": 0.12474123388528824,
"learning_rate": 7.473279216998896e-06,
"loss": 0.7405,
"step": 67
},
{
"epoch": 1.5083798882681565,
"grad_norm": 0.12420104444026947,
"learning_rate": 7.392557845506433e-06,
"loss": 0.6579,
"step": 68
},
{
"epoch": 1.5307262569832403,
"grad_norm": 0.13506121933460236,
"learning_rate": 7.311019417701567e-06,
"loss": 0.8146,
"step": 69
},
{
"epoch": 1.553072625698324,
"grad_norm": 0.13394294679164886,
"learning_rate": 7.2286917788826926e-06,
"loss": 0.6438,
"step": 70
},
{
"epoch": 1.5754189944134078,
"grad_norm": 0.12186373025178909,
"learning_rate": 7.145603043863045e-06,
"loss": 0.6964,
"step": 71
},
{
"epoch": 1.5977653631284916,
"grad_norm": 0.12778373062610626,
"learning_rate": 7.061781587369518e-06,
"loss": 0.6403,
"step": 72
},
{
"epoch": 1.6201117318435754,
"grad_norm": 0.12650710344314575,
"learning_rate": 6.977256034352713e-06,
"loss": 0.7991,
"step": 73
},
{
"epoch": 1.6424581005586592,
"grad_norm": 0.12929368019104004,
"learning_rate": 6.892055250211552e-06,
"loss": 0.731,
"step": 74
},
{
"epoch": 1.6648044692737431,
"grad_norm": 0.11519794166088104,
"learning_rate": 6.806208330935766e-06,
"loss": 0.787,
"step": 75
},
{
"epoch": 1.6871508379888267,
"grad_norm": 0.11956265568733215,
"learning_rate": 6.719744593169642e-06,
"loss": 0.7078,
"step": 76
},
{
"epoch": 1.7094972067039107,
"grad_norm": 0.11849120259284973,
"learning_rate": 6.6326935642004165e-06,
"loss": 0.6098,
"step": 77
},
{
"epoch": 1.7318435754189943,
"grad_norm": 0.1370634287595749,
"learning_rate": 6.545084971874738e-06,
"loss": 0.775,
"step": 78
},
{
"epoch": 1.7541899441340782,
"grad_norm": 0.1339302361011505,
"learning_rate": 6.456948734446624e-06,
"loss": 0.7778,
"step": 79
},
{
"epoch": 1.776536312849162,
"grad_norm": 0.1872129589319229,
"learning_rate": 6.368314950360416e-06,
"loss": 0.7051,
"step": 80
},
{
"epoch": 1.7988826815642458,
"grad_norm": 0.13236720860004425,
"learning_rate": 6.279213887972179e-06,
"loss": 0.6648,
"step": 81
},
{
"epoch": 1.8212290502793296,
"grad_norm": 0.14064921438694,
"learning_rate": 6.189675975213094e-06,
"loss": 0.9904,
"step": 82
},
{
"epoch": 1.8435754189944134,
"grad_norm": 0.14369916915893555,
"learning_rate": 6.099731789198344e-06,
"loss": 0.7428,
"step": 83
},
{
"epoch": 1.8659217877094973,
"grad_norm": 0.12341982126235962,
"learning_rate": 6.009412045785051e-06,
"loss": 0.679,
"step": 84
},
{
"epoch": 1.888268156424581,
"grad_norm": 0.12746700644493103,
"learning_rate": 5.918747589082853e-06,
"loss": 0.8121,
"step": 85
},
{
"epoch": 1.910614525139665,
"grad_norm": 0.1257738620042801,
"learning_rate": 5.82776938092065e-06,
"loss": 0.75,
"step": 86
},
{
"epoch": 1.9329608938547485,
"grad_norm": 0.1163194552063942,
"learning_rate": 5.736508490273189e-06,
"loss": 0.6534,
"step": 87
},
{
"epoch": 1.9553072625698324,
"grad_norm": 0.14038220047950745,
"learning_rate": 5.644996082651018e-06,
"loss": 0.6898,
"step": 88
},
{
"epoch": 1.9776536312849162,
"grad_norm": 0.11753737926483154,
"learning_rate": 5.553263409457504e-06,
"loss": 0.5927,
"step": 89
},
{
"epoch": 2.0,
"grad_norm": 0.1380361169576645,
"learning_rate": 5.46134179731651e-06,
"loss": 0.5046,
"step": 90
}
],
"logging_steps": 1,
"max_steps": 180,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 45,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.822342948814848e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}