3584a19a58
Model: fpadovani/zho-hans-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.585308750365818,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 2.9766478300094605,
|
|
"epoch": 0.0009755145839430299,
|
|
"grad_norm": 19.125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.6417,
|
|
"mean_token_accuracy": 0.023680092487484216,
|
|
"num_tokens": 17120.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 2.8746404886245727,
|
|
"epoch": 0.0019510291678860598,
|
|
"grad_norm": 17.25,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.6326,
|
|
"mean_token_accuracy": 0.024563737865537404,
|
|
"num_tokens": 34182.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 3.093658471107483,
|
|
"epoch": 0.0029265437518290896,
|
|
"grad_norm": 18.75,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.6219,
|
|
"mean_token_accuracy": 0.019473212491720914,
|
|
"num_tokens": 51205.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 3.302582025527954,
|
|
"epoch": 0.0039020583357721197,
|
|
"grad_norm": 24.625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 14.4842,
|
|
"mean_token_accuracy": 0.014939527865499258,
|
|
"num_tokens": 67722.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 3.4576565742492678,
|
|
"epoch": 0.00487757291971515,
|
|
"grad_norm": 26.875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 14.1318,
|
|
"mean_token_accuracy": 0.016859303461387753,
|
|
"num_tokens": 84230.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 4.007175302505493,
|
|
"epoch": 0.005853087503658179,
|
|
"grad_norm": 36.0,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 13.5415,
|
|
"mean_token_accuracy": 0.021240592701360583,
|
|
"num_tokens": 100967.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.149684953689575,
|
|
"epoch": 0.00682860208760121,
|
|
"grad_norm": 32.25,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 12.3571,
|
|
"mean_token_accuracy": 0.014938191510736942,
|
|
"num_tokens": 117450.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 9.185105991363525,
|
|
"epoch": 0.007804116671544239,
|
|
"grad_norm": 15.8125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 11.1352,
|
|
"mean_token_accuracy": 0.013616356626152992,
|
|
"num_tokens": 135328.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.538428592681885,
|
|
"epoch": 0.00877963125548727,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.7242,
|
|
"mean_token_accuracy": 0.007964215148240328,
|
|
"num_tokens": 152571.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.594391059875488,
|
|
"epoch": 0.0097551458394303,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.5051,
|
|
"mean_token_accuracy": 0.020350533118471504,
|
|
"num_tokens": 170216.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.461821460723877,
|
|
"epoch": 0.010730660423373329,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.3579,
|
|
"mean_token_accuracy": 0.023615096881985664,
|
|
"num_tokens": 186513.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.629265594482423,
|
|
"epoch": 0.011706175007316359,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.1783,
|
|
"mean_token_accuracy": 0.06680442728102207,
|
|
"num_tokens": 202600.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.548507595062256,
|
|
"epoch": 0.01268168959125939,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 10.0232,
|
|
"mean_token_accuracy": 0.0800214022397995,
|
|
"num_tokens": 220270.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.453729629516602,
|
|
"epoch": 0.01365720417520242,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.8986,
|
|
"mean_token_accuracy": 0.08365228101611137,
|
|
"num_tokens": 236810.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.486371517181396,
|
|
"epoch": 0.014632718759145449,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.8701,
|
|
"mean_token_accuracy": 0.07463902905583382,
|
|
"num_tokens": 252559.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.375898456573486,
|
|
"epoch": 0.015608233343088479,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.7318,
|
|
"mean_token_accuracy": 0.08457129299640656,
|
|
"num_tokens": 268507.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.432976818084716,
|
|
"epoch": 0.01658374792703151,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.6967,
|
|
"mean_token_accuracy": 0.08318854123353958,
|
|
"num_tokens": 284776.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.440800666809082,
|
|
"epoch": 0.01755926251097454,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.6802,
|
|
"mean_token_accuracy": 0.07657109946012497,
|
|
"num_tokens": 300937.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.422488117218018,
|
|
"epoch": 0.01853477709491757,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.5994,
|
|
"mean_token_accuracy": 0.07628178820014,
|
|
"num_tokens": 317464.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.335647296905517,
|
|
"epoch": 0.0195102916788606,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.4601,
|
|
"mean_token_accuracy": 0.07984406501054764,
|
|
"num_tokens": 334022.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.338857746124267,
|
|
"epoch": 0.02048580626280363,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.4204,
|
|
"mean_token_accuracy": 0.08062015175819397,
|
|
"num_tokens": 350545.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.264245700836181,
|
|
"epoch": 0.021461320846746658,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.3381,
|
|
"mean_token_accuracy": 0.08677204474806785,
|
|
"num_tokens": 368878.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.274968814849853,
|
|
"epoch": 0.022436835430689687,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.3003,
|
|
"mean_token_accuracy": 0.08115394040942192,
|
|
"num_tokens": 388381.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.184232711791992,
|
|
"epoch": 0.023412350014632717,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 9.2366,
|
|
"mean_token_accuracy": 0.07711499892175197,
|
|
"num_tokens": 403727.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.163524627685547,
|
|
"epoch": 0.02438786459857575,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 9.1629,
|
|
"mean_token_accuracy": 0.08056230619549751,
|
|
"num_tokens": 419046.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.040641689300537,
|
|
"epoch": 0.02536337918251878,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 9.0382,
|
|
"mean_token_accuracy": 0.08940373361110687,
|
|
"num_tokens": 435186.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.979869842529297,
|
|
"epoch": 0.02633889376646181,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.9974,
|
|
"mean_token_accuracy": 0.08406480178236961,
|
|
"num_tokens": 451552.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.885489559173584,
|
|
"epoch": 0.02731440835040484,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.9502,
|
|
"mean_token_accuracy": 0.08568493612110614,
|
|
"num_tokens": 468006.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.81715898513794,
|
|
"epoch": 0.02828992293434787,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.883,
|
|
"mean_token_accuracy": 0.08229759335517883,
|
|
"num_tokens": 484381.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.719689846038818,
|
|
"epoch": 0.029265437518290898,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.8508,
|
|
"mean_token_accuracy": 0.08485062494874,
|
|
"num_tokens": 501309.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.652300357818604,
|
|
"epoch": 0.030240952102233928,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.7928,
|
|
"mean_token_accuracy": 0.07957165949046612,
|
|
"num_tokens": 518290.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.658570861816406,
|
|
"epoch": 0.031216466686176957,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.7429,
|
|
"mean_token_accuracy": 0.08276331052184105,
|
|
"num_tokens": 533700.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.452359008789063,
|
|
"epoch": 0.03219198127011999,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.5971,
|
|
"mean_token_accuracy": 0.08969579339027405,
|
|
"num_tokens": 548935.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.373422050476075,
|
|
"epoch": 0.03316749585406302,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.6277,
|
|
"mean_token_accuracy": 0.08311848118901252,
|
|
"num_tokens": 565869.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.318701362609863,
|
|
"epoch": 0.03414301043800605,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.6477,
|
|
"mean_token_accuracy": 0.08514618873596191,
|
|
"num_tokens": 583065.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 9.249837398529053,
|
|
"epoch": 0.03511852502194908,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.6293,
|
|
"mean_token_accuracy": 0.08451943099498749,
|
|
"num_tokens": 599875.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 9.101829338073731,
|
|
"epoch": 0.03609403960589211,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.5864,
|
|
"mean_token_accuracy": 0.08677933588624001,
|
|
"num_tokens": 616296.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 9.112464332580567,
|
|
"epoch": 0.03706955418983514,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.5376,
|
|
"mean_token_accuracy": 0.07994686216115951,
|
|
"num_tokens": 632548.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 9.068296527862548,
|
|
"epoch": 0.03804506877377817,
|
|
"grad_norm": 0.66015625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.5451,
|
|
"mean_token_accuracy": 0.08514821305871009,
|
|
"num_tokens": 650395.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.906174850463866,
|
|
"epoch": 0.0390205833577212,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.5329,
|
|
"mean_token_accuracy": 0.09522328898310661,
|
|
"num_tokens": 668453.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.815705966949462,
|
|
"epoch": 0.03999609794166423,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.4799,
|
|
"mean_token_accuracy": 0.08324785456061363,
|
|
"num_tokens": 683914.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.980221557617188,
|
|
"epoch": 0.04097161252560726,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.5327,
|
|
"mean_token_accuracy": 0.08584341704845429,
|
|
"num_tokens": 700480.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.843296813964844,
|
|
"epoch": 0.041947127109550286,
|
|
"grad_norm": 0.625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.5087,
|
|
"mean_token_accuracy": 0.08261171132326126,
|
|
"num_tokens": 716604.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.82944040298462,
|
|
"epoch": 0.042922641693493316,
|
|
"grad_norm": 0.625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.4928,
|
|
"mean_token_accuracy": 0.08608382642269134,
|
|
"num_tokens": 732697.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.857663631439209,
|
|
"epoch": 0.043898156277436345,
|
|
"grad_norm": 0.6171875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.5591,
|
|
"mean_token_accuracy": 0.08012843132019043,
|
|
"num_tokens": 749072.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.810017681121826,
|
|
"epoch": 0.044873670861379375,
|
|
"grad_norm": 0.62109375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.5164,
|
|
"mean_token_accuracy": 0.083363825827837,
|
|
"num_tokens": 767826.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.809004497528075,
|
|
"epoch": 0.045849185445322405,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.4454,
|
|
"mean_token_accuracy": 0.08511443473398686,
|
|
"num_tokens": 786863.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.765242576599121,
|
|
"epoch": 0.046824700029265434,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.4296,
|
|
"mean_token_accuracy": 0.09359418824315072,
|
|
"num_tokens": 803925.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.702787971496582,
|
|
"epoch": 0.04780021461320847,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.4898,
|
|
"mean_token_accuracy": 0.08749726414680481,
|
|
"num_tokens": 822088.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.754209804534913,
|
|
"epoch": 0.0487757291971515,
|
|
"grad_norm": 0.6328125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.4886,
|
|
"mean_token_accuracy": 0.08777656331658364,
|
|
"num_tokens": 837991.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.69994945526123,
|
|
"epoch": 0.04975124378109453,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.4096,
|
|
"mean_token_accuracy": 0.09531000778079032,
|
|
"num_tokens": 855593.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.814885520935059,
|
|
"epoch": 0.05072675836503756,
|
|
"grad_norm": 0.6328125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.4121,
|
|
"mean_token_accuracy": 0.08780986666679383,
|
|
"num_tokens": 873696.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.691367816925048,
|
|
"epoch": 0.05170227294898059,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.4116,
|
|
"mean_token_accuracy": 0.08613176308572293,
|
|
"num_tokens": 890023.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.771553230285644,
|
|
"epoch": 0.05267778753292362,
|
|
"grad_norm": 0.66015625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.5322,
|
|
"mean_token_accuracy": 0.08385844901204109,
|
|
"num_tokens": 906492.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.613368129730224,
|
|
"epoch": 0.05365330211686665,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.4744,
|
|
"mean_token_accuracy": 0.0832776077091694,
|
|
"num_tokens": 921837.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.749843883514405,
|
|
"epoch": 0.05462881670080968,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.4188,
|
|
"mean_token_accuracy": 0.09616234973073005,
|
|
"num_tokens": 938771.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.634615898132324,
|
|
"epoch": 0.05560433128475271,
|
|
"grad_norm": 0.6875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.4207,
|
|
"mean_token_accuracy": 0.08592401072382927,
|
|
"num_tokens": 954562.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.681969547271729,
|
|
"epoch": 0.05657984586869574,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.384,
|
|
"mean_token_accuracy": 0.09005839563906193,
|
|
"num_tokens": 973700.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.68220386505127,
|
|
"epoch": 0.05755536045263877,
|
|
"grad_norm": 0.6015625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.4173,
|
|
"mean_token_accuracy": 0.08547075390815735,
|
|
"num_tokens": 990688.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.626276206970214,
|
|
"epoch": 0.058530875036581796,
|
|
"grad_norm": 0.609375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.487,
|
|
"mean_token_accuracy": 0.08393812403082848,
|
|
"num_tokens": 1008144.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.651608943939209,
|
|
"epoch": 0.059506389620524826,
|
|
"grad_norm": 0.609375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.4422,
|
|
"mean_token_accuracy": 0.08627958744764327,
|
|
"num_tokens": 1027379.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.613696575164795,
|
|
"epoch": 0.060481904204467855,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.4289,
|
|
"mean_token_accuracy": 0.09238211661577225,
|
|
"num_tokens": 1043999.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.620658779144287,
|
|
"epoch": 0.061457418788410885,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.4301,
|
|
"mean_token_accuracy": 0.08504614084959031,
|
|
"num_tokens": 1062237.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.677656650543213,
|
|
"epoch": 0.062432933372353915,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.3701,
|
|
"mean_token_accuracy": 0.0938310906291008,
|
|
"num_tokens": 1078092.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.577167224884032,
|
|
"epoch": 0.06340844795629695,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.4129,
|
|
"mean_token_accuracy": 0.09372566789388656,
|
|
"num_tokens": 1095124.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.622019290924072,
|
|
"epoch": 0.06438396254023998,
|
|
"grad_norm": 0.6875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.4042,
|
|
"mean_token_accuracy": 0.08834576904773712,
|
|
"num_tokens": 1112775.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.616455364227296,
|
|
"epoch": 0.06535947712418301,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.3566,
|
|
"mean_token_accuracy": 0.09236226156353951,
|
|
"num_tokens": 1129726.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.567400646209716,
|
|
"epoch": 0.06633499170812604,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.4042,
|
|
"mean_token_accuracy": 0.09315266758203507,
|
|
"num_tokens": 1144034.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.621097087860107,
|
|
"epoch": 0.06731050629206907,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.3507,
|
|
"mean_token_accuracy": 0.09208079949021339,
|
|
"num_tokens": 1159633.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.543352127075195,
|
|
"epoch": 0.0682860208760121,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 8.301,
|
|
"mean_token_accuracy": 0.09103573486208916,
|
|
"num_tokens": 1175350.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.433770656585693,
|
|
"epoch": 0.06926153545995513,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.251,
|
|
"mean_token_accuracy": 0.09555190205574035,
|
|
"num_tokens": 1193121.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.62976531982422,
|
|
"epoch": 0.07023705004389816,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 8.3979,
|
|
"mean_token_accuracy": 0.09072723165154457,
|
|
"num_tokens": 1209896.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.566699409484864,
|
|
"epoch": 0.07121256462784119,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 8.3737,
|
|
"mean_token_accuracy": 0.08897408023476601,
|
|
"num_tokens": 1227011.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.508051204681397,
|
|
"epoch": 0.07218807921178422,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 8.3105,
|
|
"mean_token_accuracy": 0.09084449261426926,
|
|
"num_tokens": 1241595.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.531622886657715,
|
|
"epoch": 0.07316359379572725,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 8.3269,
|
|
"mean_token_accuracy": 0.08802430108189582,
|
|
"num_tokens": 1256919.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.544854354858398,
|
|
"epoch": 0.07413910837967028,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.3217,
|
|
"mean_token_accuracy": 0.10469982475042343,
|
|
"num_tokens": 1274344.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.513376903533935,
|
|
"epoch": 0.0751146229636133,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 8.2985,
|
|
"mean_token_accuracy": 0.09606277942657471,
|
|
"num_tokens": 1290252.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.597062873840333,
|
|
"epoch": 0.07609013754755634,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 8.3631,
|
|
"mean_token_accuracy": 0.08963260576128959,
|
|
"num_tokens": 1306987.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.604188060760498,
|
|
"epoch": 0.07706565213149937,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 8.3807,
|
|
"mean_token_accuracy": 0.08827338665723801,
|
|
"num_tokens": 1323031.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.52640790939331,
|
|
"epoch": 0.0780411667154424,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 8.3226,
|
|
"mean_token_accuracy": 0.08803676143288612,
|
|
"num_tokens": 1339592.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.56795015335083,
|
|
"epoch": 0.07901668129938542,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 8.3038,
|
|
"mean_token_accuracy": 0.09822543263435364,
|
|
"num_tokens": 1358131.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.49936819076538,
|
|
"epoch": 0.07999219588332845,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 8.2416,
|
|
"mean_token_accuracy": 0.09935245588421822,
|
|
"num_tokens": 1375705.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.438391208648682,
|
|
"epoch": 0.08096771046727148,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 8.2639,
|
|
"mean_token_accuracy": 0.0976213738322258,
|
|
"num_tokens": 1392736.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.477056121826172,
|
|
"epoch": 0.08194322505121451,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 8.2869,
|
|
"mean_token_accuracy": 0.09002979025244713,
|
|
"num_tokens": 1408536.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.45663366317749,
|
|
"epoch": 0.08291873963515754,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 8.2624,
|
|
"mean_token_accuracy": 0.09269042685627937,
|
|
"num_tokens": 1425423.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.54402027130127,
|
|
"epoch": 0.08389425421910057,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 8.2807,
|
|
"mean_token_accuracy": 0.09243328273296356,
|
|
"num_tokens": 1442420.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.46742868423462,
|
|
"epoch": 0.0848697688030436,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 8.2373,
|
|
"mean_token_accuracy": 0.09734182208776473,
|
|
"num_tokens": 1458835.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.510400676727295,
|
|
"epoch": 0.08584528338698663,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 8.3307,
|
|
"mean_token_accuracy": 0.08899251222610474,
|
|
"num_tokens": 1475563.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.55044527053833,
|
|
"epoch": 0.08682079797092966,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 8.2798,
|
|
"mean_token_accuracy": 0.10081091448664665,
|
|
"num_tokens": 1492687.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.521657180786132,
|
|
"epoch": 0.08779631255487269,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 8.3,
|
|
"mean_token_accuracy": 0.08999344632029534,
|
|
"num_tokens": 1508394.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.461956119537353,
|
|
"epoch": 0.08877182713881572,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 8.2722,
|
|
"mean_token_accuracy": 0.09951426908373832,
|
|
"num_tokens": 1527112.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.371872329711914,
|
|
"epoch": 0.08974734172275875,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 8.3059,
|
|
"mean_token_accuracy": 0.09823538959026337,
|
|
"num_tokens": 1545401.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.571519374847412,
|
|
"epoch": 0.09072285630670178,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 8.177,
|
|
"mean_token_accuracy": 0.09758451730012893,
|
|
"num_tokens": 1561621.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.506033992767334,
|
|
"epoch": 0.09169837089064481,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 8.2855,
|
|
"mean_token_accuracy": 0.09499907344579697,
|
|
"num_tokens": 1579225.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.468109607696533,
|
|
"epoch": 0.09267388547458784,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 8.1943,
|
|
"mean_token_accuracy": 0.09583869129419327,
|
|
"num_tokens": 1596125.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.43943977355957,
|
|
"epoch": 0.09364940005853087,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 8.2995,
|
|
"mean_token_accuracy": 0.08718594834208489,
|
|
"num_tokens": 1613451.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.463754653930664,
|
|
"epoch": 0.09462491464247391,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 8.2581,
|
|
"mean_token_accuracy": 0.09351714700460434,
|
|
"num_tokens": 1630929.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.477511882781982,
|
|
"epoch": 0.09560042922641694,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 8.2527,
|
|
"mean_token_accuracy": 0.09388960897922516,
|
|
"num_tokens": 1647379.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.438141918182373,
|
|
"epoch": 0.09657594381035997,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 8.0326,
|
|
"mean_token_accuracy": 0.11119685173034669,
|
|
"num_tokens": 1664415.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.311398983001709,
|
|
"epoch": 0.097551458394303,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 8.0968,
|
|
"mean_token_accuracy": 0.10252611264586449,
|
|
"num_tokens": 1679556.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.327784490585326,
|
|
"epoch": 0.09852697297824603,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 8.0437,
|
|
"mean_token_accuracy": 0.11204132661223412,
|
|
"num_tokens": 1696727.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.415677928924561,
|
|
"epoch": 0.09950248756218906,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 8.104,
|
|
"mean_token_accuracy": 0.10669132620096207,
|
|
"num_tokens": 1713918.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.345568943023682,
|
|
"epoch": 0.10047800214613209,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 8.2521,
|
|
"mean_token_accuracy": 0.08853555247187614,
|
|
"num_tokens": 1729581.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.433890056610107,
|
|
"epoch": 0.10145351673007512,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 8.1225,
|
|
"mean_token_accuracy": 0.08972057402133941,
|
|
"num_tokens": 1746367.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.47779598236084,
|
|
"epoch": 0.10242903131401815,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 8.2143,
|
|
"mean_token_accuracy": 0.0906743973493576,
|
|
"num_tokens": 1765009.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.399079418182373,
|
|
"epoch": 0.10340454589796118,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 8.2183,
|
|
"mean_token_accuracy": 0.09412049129605293,
|
|
"num_tokens": 1782113.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 8.368115329742432,
|
|
"epoch": 0.10438006048190421,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 8.1187,
|
|
"mean_token_accuracy": 0.09834975972771645,
|
|
"num_tokens": 1798301.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.39275369644165,
|
|
"epoch": 0.10535557506584724,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 8.1437,
|
|
"mean_token_accuracy": 0.09389334619045257,
|
|
"num_tokens": 1815059.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.319794654846191,
|
|
"epoch": 0.10633108964979027,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 8.0478,
|
|
"mean_token_accuracy": 0.10134888738393784,
|
|
"num_tokens": 1831699.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 8.288005542755126,
|
|
"epoch": 0.1073066042337333,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 8.1305,
|
|
"mean_token_accuracy": 0.09792774692177772,
|
|
"num_tokens": 1847993.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.41219367980957,
|
|
"epoch": 0.10828211881767633,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.965,
|
|
"mean_token_accuracy": 0.1107750415802002,
|
|
"num_tokens": 1864753.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 8.307417011260986,
|
|
"epoch": 0.10925763340161936,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 8.137,
|
|
"mean_token_accuracy": 0.09887706562876701,
|
|
"num_tokens": 1882154.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.317179346084595,
|
|
"epoch": 0.11023314798556239,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 8.0218,
|
|
"mean_token_accuracy": 0.10580694973468781,
|
|
"num_tokens": 1899683.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 8.264959573745728,
|
|
"epoch": 0.11120866256950541,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 8.0135,
|
|
"mean_token_accuracy": 0.10168145447969437,
|
|
"num_tokens": 1918489.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 8.32475643157959,
|
|
"epoch": 0.11218417715344844,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 8.071,
|
|
"mean_token_accuracy": 0.0985498882830143,
|
|
"num_tokens": 1935609.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 8.260710334777832,
|
|
"epoch": 0.11315969173739147,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 8.1,
|
|
"mean_token_accuracy": 0.09357691556215286,
|
|
"num_tokens": 1951311.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 8.354738426208495,
|
|
"epoch": 0.1141352063213345,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 8.156,
|
|
"mean_token_accuracy": 0.09314567148685456,
|
|
"num_tokens": 1968908.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 8.301233768463135,
|
|
"epoch": 0.11511072090527753,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 8.0673,
|
|
"mean_token_accuracy": 0.09737929850816726,
|
|
"num_tokens": 1983807.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 8.437208557128907,
|
|
"epoch": 0.11608623548922056,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 8.1226,
|
|
"mean_token_accuracy": 0.09786574244499206,
|
|
"num_tokens": 2000219.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 8.26841425895691,
|
|
"epoch": 0.11706175007316359,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 8.0493,
|
|
"mean_token_accuracy": 0.10386537536978721,
|
|
"num_tokens": 2017360.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 8.208323240280151,
|
|
"epoch": 0.11803726465710662,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 8.0325,
|
|
"mean_token_accuracy": 0.10569393783807754,
|
|
"num_tokens": 2034953.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 8.277615022659301,
|
|
"epoch": 0.11901277924104965,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.993,
|
|
"mean_token_accuracy": 0.10249293968081474,
|
|
"num_tokens": 2051551.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 8.315507698059083,
|
|
"epoch": 0.11998829382499268,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.9897,
|
|
"mean_token_accuracy": 0.10581940934062004,
|
|
"num_tokens": 2067188.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 8.157993602752686,
|
|
"epoch": 0.12096380840893571,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 8.0163,
|
|
"mean_token_accuracy": 0.10181707590818405,
|
|
"num_tokens": 2082569.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 8.331413459777831,
|
|
"epoch": 0.12193932299287874,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 8.0899,
|
|
"mean_token_accuracy": 0.09741123840212822,
|
|
"num_tokens": 2099446.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 8.284016227722168,
|
|
"epoch": 0.12291483757682177,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 8.0523,
|
|
"mean_token_accuracy": 0.10069476068019867,
|
|
"num_tokens": 2116526.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 8.347427368164062,
|
|
"epoch": 0.1238903521607648,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000317,
|
|
"loss": 8.0739,
|
|
"mean_token_accuracy": 0.09274140894412994,
|
|
"num_tokens": 2134624.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 8.17642421722412,
|
|
"epoch": 0.12486586674470783,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.9284,
|
|
"mean_token_accuracy": 0.10417634472250939,
|
|
"num_tokens": 2152872.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 8.278553771972657,
|
|
"epoch": 0.12584138132865086,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 8.0703,
|
|
"mean_token_accuracy": 0.09806257262825965,
|
|
"num_tokens": 2169480.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 8.279256868362427,
|
|
"epoch": 0.1268168959125939,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.9221,
|
|
"mean_token_accuracy": 0.10904301851987838,
|
|
"num_tokens": 2186054.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 8.170163297653199,
|
|
"epoch": 0.12779241049653692,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 8.0554,
|
|
"mean_token_accuracy": 0.09454990327358245,
|
|
"num_tokens": 2202320.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 8.168533563613892,
|
|
"epoch": 0.12876792508047996,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.9295,
|
|
"mean_token_accuracy": 0.10270216390490532,
|
|
"num_tokens": 2218817.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 8.262005805969238,
|
|
"epoch": 0.12974343966442298,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 8.0883,
|
|
"mean_token_accuracy": 0.09590112790465355,
|
|
"num_tokens": 2234845.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 8.226708889007568,
|
|
"epoch": 0.13071895424836602,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 8.0229,
|
|
"mean_token_accuracy": 0.09793693721294403,
|
|
"num_tokens": 2251904.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 8.197064971923828,
|
|
"epoch": 0.13169446883230904,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 8.0052,
|
|
"mean_token_accuracy": 0.10008159801363944,
|
|
"num_tokens": 2268343.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 8.28106460571289,
|
|
"epoch": 0.13266998341625208,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 8.0169,
|
|
"mean_token_accuracy": 0.10061499997973442,
|
|
"num_tokens": 2284524.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 8.108173322677612,
|
|
"epoch": 0.1336454980001951,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.9327,
|
|
"mean_token_accuracy": 0.10620496347546578,
|
|
"num_tokens": 2302350.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 8.193976497650146,
|
|
"epoch": 0.13462101258413814,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 8.0104,
|
|
"mean_token_accuracy": 0.09774896204471588,
|
|
"num_tokens": 2319953.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 8.22156057357788,
|
|
"epoch": 0.13559652716808115,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.8902,
|
|
"mean_token_accuracy": 0.10564312934875489,
|
|
"num_tokens": 2336698.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 8.09106740951538,
|
|
"epoch": 0.1365720417520242,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.8486,
|
|
"mean_token_accuracy": 0.10666879042983055,
|
|
"num_tokens": 2353986.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 8.187975788116455,
|
|
"epoch": 0.1375475563359672,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.9007,
|
|
"mean_token_accuracy": 0.10359529629349709,
|
|
"num_tokens": 2370320.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 8.145122528076172,
|
|
"epoch": 0.13852307091991026,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.9484,
|
|
"mean_token_accuracy": 0.0991167202591896,
|
|
"num_tokens": 2385453.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 8.20379581451416,
|
|
"epoch": 0.13949858550385327,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.9353,
|
|
"mean_token_accuracy": 0.09990701898932457,
|
|
"num_tokens": 2401545.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 8.169508171081542,
|
|
"epoch": 0.14047410008779632,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.9268,
|
|
"mean_token_accuracy": 0.10343603938817977,
|
|
"num_tokens": 2418414.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 8.133510541915893,
|
|
"epoch": 0.14144961467173933,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.9911,
|
|
"mean_token_accuracy": 0.10218351557850838,
|
|
"num_tokens": 2434973.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 8.22615032196045,
|
|
"epoch": 0.14242512925568238,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.9854,
|
|
"mean_token_accuracy": 0.0952131688594818,
|
|
"num_tokens": 2451053.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 8.125102138519287,
|
|
"epoch": 0.1434006438396254,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.9439,
|
|
"mean_token_accuracy": 0.09622853323817253,
|
|
"num_tokens": 2467280.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 8.165161323547363,
|
|
"epoch": 0.14437615842356843,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.8658,
|
|
"mean_token_accuracy": 0.10867365226149558,
|
|
"num_tokens": 2484588.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 8.123753595352174,
|
|
"epoch": 0.14535167300751145,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.8897,
|
|
"mean_token_accuracy": 0.10328481942415238,
|
|
"num_tokens": 2501200.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 8.075188684463502,
|
|
"epoch": 0.1463271875914545,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.8228,
|
|
"mean_token_accuracy": 0.11175378635525704,
|
|
"num_tokens": 2517199.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 8.09429202079773,
|
|
"epoch": 0.1473027021753975,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.8873,
|
|
"mean_token_accuracy": 0.0976559154689312,
|
|
"num_tokens": 2534824.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 8.048625040054322,
|
|
"epoch": 0.14827821675934055,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.7714,
|
|
"mean_token_accuracy": 0.10451071038842201,
|
|
"num_tokens": 2550842.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 8.110934829711914,
|
|
"epoch": 0.14925373134328357,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.7364,
|
|
"mean_token_accuracy": 0.10827255919575692,
|
|
"num_tokens": 2567878.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 8.061486721038818,
|
|
"epoch": 0.1502292459272266,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.8314,
|
|
"mean_token_accuracy": 0.10438120588660241,
|
|
"num_tokens": 2584148.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 8.036616230010987,
|
|
"epoch": 0.15120476051116966,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.823,
|
|
"mean_token_accuracy": 0.10429293811321258,
|
|
"num_tokens": 2600067.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 8.141137790679931,
|
|
"epoch": 0.15218027509511267,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.817,
|
|
"mean_token_accuracy": 0.09778935462236404,
|
|
"num_tokens": 2615746.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 8.06767463684082,
|
|
"epoch": 0.15315578967905571,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.8416,
|
|
"mean_token_accuracy": 0.10115923956036568,
|
|
"num_tokens": 2631641.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 8.011779356002808,
|
|
"epoch": 0.15413130426299873,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.8457,
|
|
"mean_token_accuracy": 0.10367136746644974,
|
|
"num_tokens": 2647015.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 8.038083267211913,
|
|
"epoch": 0.15510681884694177,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.7483,
|
|
"mean_token_accuracy": 0.10468006283044815,
|
|
"num_tokens": 2664045.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 8.054866456985474,
|
|
"epoch": 0.1560823334308848,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.7354,
|
|
"mean_token_accuracy": 0.10361607670783997,
|
|
"num_tokens": 2680774.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 8.057617807388306,
|
|
"epoch": 0.15705784801482783,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.8212,
|
|
"mean_token_accuracy": 0.10198491960763931,
|
|
"num_tokens": 2697719.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 8.083775091171265,
|
|
"epoch": 0.15803336259877085,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.7933,
|
|
"mean_token_accuracy": 0.09653408601880073,
|
|
"num_tokens": 2714518.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.978687858581543,
|
|
"epoch": 0.1590088771827139,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.8318,
|
|
"mean_token_accuracy": 0.1021594025194645,
|
|
"num_tokens": 2729288.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 8.02365493774414,
|
|
"epoch": 0.1599843917666569,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.824,
|
|
"mean_token_accuracy": 0.10453630164265633,
|
|
"num_tokens": 2746782.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 8.045251560211181,
|
|
"epoch": 0.16095990635059995,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.8503,
|
|
"mean_token_accuracy": 0.09497486725449562,
|
|
"num_tokens": 2763159.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.998881816864014,
|
|
"epoch": 0.16193542093454297,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.795,
|
|
"mean_token_accuracy": 0.1032567098736763,
|
|
"num_tokens": 2780338.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.997481441497802,
|
|
"epoch": 0.162910935518486,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.6981,
|
|
"mean_token_accuracy": 0.11289086565375328,
|
|
"num_tokens": 2796214.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 8.008633089065551,
|
|
"epoch": 0.16388645010242903,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.8104,
|
|
"mean_token_accuracy": 0.09806878343224526,
|
|
"num_tokens": 2812745.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 8.013679552078248,
|
|
"epoch": 0.16486196468637207,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.6763,
|
|
"mean_token_accuracy": 0.1046956017613411,
|
|
"num_tokens": 2828288.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.96496810913086,
|
|
"epoch": 0.16583747927031509,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.8118,
|
|
"mean_token_accuracy": 0.09764731749892235,
|
|
"num_tokens": 2843618.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.9342896938323975,
|
|
"epoch": 0.16681299385425813,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.638,
|
|
"mean_token_accuracy": 0.11073757931590081,
|
|
"num_tokens": 2860659.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.926680088043213,
|
|
"epoch": 0.16778850843820114,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.7311,
|
|
"mean_token_accuracy": 0.09983963668346404,
|
|
"num_tokens": 2877482.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 8.004765701293945,
|
|
"epoch": 0.1687640230221442,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.8248,
|
|
"mean_token_accuracy": 0.09446612447500229,
|
|
"num_tokens": 2895868.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.990339183807373,
|
|
"epoch": 0.1697395376060872,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.7898,
|
|
"mean_token_accuracy": 0.10080718472599984,
|
|
"num_tokens": 2913103.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 8.011733198165894,
|
|
"epoch": 0.17071505219003025,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.7093,
|
|
"mean_token_accuracy": 0.10168140456080436,
|
|
"num_tokens": 2928291.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.907622814178467,
|
|
"epoch": 0.17169056677397326,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.7554,
|
|
"mean_token_accuracy": 0.10273576974868774,
|
|
"num_tokens": 2945115.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.979650259017944,
|
|
"epoch": 0.1726660813579163,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.6537,
|
|
"mean_token_accuracy": 0.10307829454541206,
|
|
"num_tokens": 2962869.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.939433670043945,
|
|
"epoch": 0.17364159594185932,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.7621,
|
|
"mean_token_accuracy": 0.09926085323095321,
|
|
"num_tokens": 2979298.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.992295932769776,
|
|
"epoch": 0.17461711052580237,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.6683,
|
|
"mean_token_accuracy": 0.10740073993802071,
|
|
"num_tokens": 2996146.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.92843713760376,
|
|
"epoch": 0.17559262510974538,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.7393,
|
|
"mean_token_accuracy": 0.10424527525901794,
|
|
"num_tokens": 3013075.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.951166343688965,
|
|
"epoch": 0.17656813969368843,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.7016,
|
|
"mean_token_accuracy": 0.10156236663460731,
|
|
"num_tokens": 3029494.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.856925392150879,
|
|
"epoch": 0.17754365427763144,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.7065,
|
|
"mean_token_accuracy": 0.1026519075036049,
|
|
"num_tokens": 3046333.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.910739088058472,
|
|
"epoch": 0.17851916886157448,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.689,
|
|
"mean_token_accuracy": 0.09965933263301849,
|
|
"num_tokens": 3062714.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.998983573913574,
|
|
"epoch": 0.1794946834455175,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.6614,
|
|
"mean_token_accuracy": 0.10865851864218712,
|
|
"num_tokens": 3080711.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.869256687164307,
|
|
"epoch": 0.18047019802946054,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.7516,
|
|
"mean_token_accuracy": 0.09757809489965438,
|
|
"num_tokens": 3096885.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.857804298400879,
|
|
"epoch": 0.18144571261340356,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.6516,
|
|
"mean_token_accuracy": 0.10818476155400276,
|
|
"num_tokens": 3114536.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.862835264205932,
|
|
"epoch": 0.1824212271973466,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.6205,
|
|
"mean_token_accuracy": 0.10782845094799995,
|
|
"num_tokens": 3131921.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.903980445861817,
|
|
"epoch": 0.18339674178128962,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.7483,
|
|
"mean_token_accuracy": 0.10211937054991722,
|
|
"num_tokens": 3148064.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.798565435409546,
|
|
"epoch": 0.18437225636523266,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.5706,
|
|
"mean_token_accuracy": 0.11158995479345321,
|
|
"num_tokens": 3165822.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.8984582901000975,
|
|
"epoch": 0.18534777094917568,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.6823,
|
|
"mean_token_accuracy": 0.10740678608417512,
|
|
"num_tokens": 3183286.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.908296346664429,
|
|
"epoch": 0.18632328553311872,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.6987,
|
|
"mean_token_accuracy": 0.09706289395689964,
|
|
"num_tokens": 3198522.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.8415247917175295,
|
|
"epoch": 0.18729880011706174,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.6859,
|
|
"mean_token_accuracy": 0.102730280905962,
|
|
"num_tokens": 3218422.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.9004473209381105,
|
|
"epoch": 0.18827431470100478,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.7389,
|
|
"mean_token_accuracy": 0.0962198369204998,
|
|
"num_tokens": 3236407.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.824180984497071,
|
|
"epoch": 0.18924982928494782,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.665,
|
|
"mean_token_accuracy": 0.10327286049723625,
|
|
"num_tokens": 3252740.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.8457554340362545,
|
|
"epoch": 0.19022534386889084,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.6377,
|
|
"mean_token_accuracy": 0.09953682199120521,
|
|
"num_tokens": 3269874.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.8571250438690186,
|
|
"epoch": 0.19120085845283388,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.66,
|
|
"mean_token_accuracy": 0.10009194761514664,
|
|
"num_tokens": 3286515.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.676314449310302,
|
|
"epoch": 0.1921763730367769,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.463,
|
|
"mean_token_accuracy": 0.11996801793575287,
|
|
"num_tokens": 3303700.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.836467838287353,
|
|
"epoch": 0.19315188762071994,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.6392,
|
|
"mean_token_accuracy": 0.10528602078557014,
|
|
"num_tokens": 3319768.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.831499481201172,
|
|
"epoch": 0.19412740220466296,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.5441,
|
|
"mean_token_accuracy": 0.11213586702942849,
|
|
"num_tokens": 3336555.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.728083324432373,
|
|
"epoch": 0.195102916788606,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.5374,
|
|
"mean_token_accuracy": 0.11284950450062751,
|
|
"num_tokens": 3353273.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.766850423812866,
|
|
"epoch": 0.19607843137254902,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999999929644166,
|
|
"loss": 7.458,
|
|
"mean_token_accuracy": 0.11537115946412087,
|
|
"num_tokens": 3369408.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.702146863937378,
|
|
"epoch": 0.19705394595649206,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004999999643823598,
|
|
"loss": 7.5047,
|
|
"mean_token_accuracy": 0.10958963334560394,
|
|
"num_tokens": 3385834.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.730606269836426,
|
|
"epoch": 0.19802946054043508,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999999138141084,
|
|
"loss": 7.6164,
|
|
"mean_token_accuracy": 0.10567712634801865,
|
|
"num_tokens": 3401407.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.849634265899658,
|
|
"epoch": 0.19900497512437812,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004999998412596673,
|
|
"loss": 7.6103,
|
|
"mean_token_accuracy": 0.09972117766737938,
|
|
"num_tokens": 3418256.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.711845064163208,
|
|
"epoch": 0.19998048970832114,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999997467190435,
|
|
"loss": 7.5729,
|
|
"mean_token_accuracy": 0.10977239757776261,
|
|
"num_tokens": 3433932.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.786155748367309,
|
|
"epoch": 0.20095600429226418,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999996301922465,
|
|
"loss": 7.6225,
|
|
"mean_token_accuracy": 0.09969384595751762,
|
|
"num_tokens": 3451723.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.765552568435669,
|
|
"epoch": 0.2019315188762072,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999994916792876,
|
|
"loss": 7.5964,
|
|
"mean_token_accuracy": 0.1037816658616066,
|
|
"num_tokens": 3469170.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.782831335067749,
|
|
"epoch": 0.20290703346015024,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004999993311801802,
|
|
"loss": 7.6074,
|
|
"mean_token_accuracy": 0.10148395821452141,
|
|
"num_tokens": 3485282.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.750444602966309,
|
|
"epoch": 0.20388254804409325,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.00049999914869494,
|
|
"loss": 7.5837,
|
|
"mean_token_accuracy": 0.09637042209506035,
|
|
"num_tokens": 3502206.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.780744171142578,
|
|
"epoch": 0.2048580626280363,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000499998944223585,
|
|
"loss": 7.5286,
|
|
"mean_token_accuracy": 0.10399909391999244,
|
|
"num_tokens": 3520384.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.646545886993408,
|
|
"epoch": 0.2058335772119793,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004999987177661351,
|
|
"loss": 7.5325,
|
|
"mean_token_accuracy": 0.10673871040344238,
|
|
"num_tokens": 3536314.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.667942762374878,
|
|
"epoch": 0.20680909179592236,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999984693226124,
|
|
"loss": 7.5006,
|
|
"mean_token_accuracy": 0.11377354860305786,
|
|
"num_tokens": 3551510.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.709918117523193,
|
|
"epoch": 0.20778460637986537,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999981988930411,
|
|
"loss": 7.4953,
|
|
"mean_token_accuracy": 0.10841540396213531,
|
|
"num_tokens": 3568515.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.713051176071167,
|
|
"epoch": 0.20876012096380842,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999979064774478,
|
|
"loss": 7.5475,
|
|
"mean_token_accuracy": 0.10868918970227241,
|
|
"num_tokens": 3585183.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.6893140316009525,
|
|
"epoch": 0.20973563554775143,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499997592075861,
|
|
"loss": 7.4811,
|
|
"mean_token_accuracy": 0.11249382048845291,
|
|
"num_tokens": 3601898.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.7741923332214355,
|
|
"epoch": 0.21071115013169447,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999972556883113,
|
|
"loss": 7.5495,
|
|
"mean_token_accuracy": 0.1062250018119812,
|
|
"num_tokens": 3616699.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.711087846755982,
|
|
"epoch": 0.2116866647156375,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999968973148318,
|
|
"loss": 7.5547,
|
|
"mean_token_accuracy": 0.10500202104449272,
|
|
"num_tokens": 3634030.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.749816131591797,
|
|
"epoch": 0.21266217929958053,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004999965169554573,
|
|
"loss": 7.553,
|
|
"mean_token_accuracy": 0.10362249612808228,
|
|
"num_tokens": 3650495.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.726291227340698,
|
|
"epoch": 0.21363769388352355,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999961146102251,
|
|
"loss": 7.5087,
|
|
"mean_token_accuracy": 0.1067997545003891,
|
|
"num_tokens": 3666926.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.668747425079346,
|
|
"epoch": 0.2146132084674666,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004999956902791746,
|
|
"loss": 7.466,
|
|
"mean_token_accuracy": 0.11422103717923164,
|
|
"num_tokens": 3683061.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.6107062816619875,
|
|
"epoch": 0.2155887230514096,
|
|
"grad_norm": 0.6640625,
|
|
"learning_rate": 0.0004999952439623469,
|
|
"loss": 7.5367,
|
|
"mean_token_accuracy": 0.10903864130377769,
|
|
"num_tokens": 3703013.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.642146492004395,
|
|
"epoch": 0.21656423763535265,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499994775659786,
|
|
"loss": 7.3883,
|
|
"mean_token_accuracy": 0.11650970131158829,
|
|
"num_tokens": 3719885.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.6744856357574465,
|
|
"epoch": 0.21753975221929567,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999942853715375,
|
|
"loss": 7.5348,
|
|
"mean_token_accuracy": 0.10337460115551948,
|
|
"num_tokens": 3735122.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.748628759384156,
|
|
"epoch": 0.2185152668032387,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999937730976494,
|
|
"loss": 7.5183,
|
|
"mean_token_accuracy": 0.10299875438213349,
|
|
"num_tokens": 3751627.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.568105840682984,
|
|
"epoch": 0.21949078138718173,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999932388381716,
|
|
"loss": 7.5283,
|
|
"mean_token_accuracy": 0.10320912525057793,
|
|
"num_tokens": 3768165.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.754065418243409,
|
|
"epoch": 0.22046629597112477,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004999926825931564,
|
|
"loss": 7.5476,
|
|
"mean_token_accuracy": 0.10562212169170379,
|
|
"num_tokens": 3784245.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.570663118362427,
|
|
"epoch": 0.2214418105550678,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004999921043626582,
|
|
"loss": 7.3027,
|
|
"mean_token_accuracy": 0.11853051409125329,
|
|
"num_tokens": 3802057.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.6651441097259525,
|
|
"epoch": 0.22241732513901083,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999915041467333,
|
|
"loss": 7.4887,
|
|
"mean_token_accuracy": 0.10487050712108612,
|
|
"num_tokens": 3817104.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.625360202789307,
|
|
"epoch": 0.22339283972295385,
|
|
"grad_norm": 0.6875,
|
|
"learning_rate": 0.0004999908819454407,
|
|
"loss": 7.481,
|
|
"mean_token_accuracy": 0.10812832191586494,
|
|
"num_tokens": 3833037.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.634897947311401,
|
|
"epoch": 0.2243683543068969,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999902377588408,
|
|
"loss": 7.3567,
|
|
"mean_token_accuracy": 0.1091596469283104,
|
|
"num_tokens": 3849634.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.632895231246948,
|
|
"epoch": 0.2253438688908399,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000499989571586997,
|
|
"loss": 7.5244,
|
|
"mean_token_accuracy": 0.10523541867733002,
|
|
"num_tokens": 3865949.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.592898559570313,
|
|
"epoch": 0.22631938347478295,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004999888834299739,
|
|
"loss": 7.4256,
|
|
"mean_token_accuracy": 0.11436262503266334,
|
|
"num_tokens": 3884646.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.635993766784668,
|
|
"epoch": 0.227294898058726,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004999881732878391,
|
|
"loss": 7.5121,
|
|
"mean_token_accuracy": 0.1088767409324646,
|
|
"num_tokens": 3900740.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.695001745223999,
|
|
"epoch": 0.228270412642669,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999874411606618,
|
|
"loss": 7.4629,
|
|
"mean_token_accuracy": 0.10891817137598991,
|
|
"num_tokens": 3918619.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.566552305221558,
|
|
"epoch": 0.22924592722661205,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999866870485137,
|
|
"loss": 7.416,
|
|
"mean_token_accuracy": 0.11045783907175064,
|
|
"num_tokens": 3938161.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.675890779495239,
|
|
"epoch": 0.23022144181055507,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999859109514684,
|
|
"loss": 7.4696,
|
|
"mean_token_accuracy": 0.10821386948227882,
|
|
"num_tokens": 3953582.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.626031160354614,
|
|
"epoch": 0.2311969563944981,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004999851128696017,
|
|
"loss": 7.4498,
|
|
"mean_token_accuracy": 0.10112769156694412,
|
|
"num_tokens": 3969747.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.688938951492309,
|
|
"epoch": 0.23217247097844113,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004999842928029917,
|
|
"loss": 7.4847,
|
|
"mean_token_accuracy": 0.10447191521525383,
|
|
"num_tokens": 3984646.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.5848808765411375,
|
|
"epoch": 0.23314798556238417,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999834507517184,
|
|
"loss": 7.4676,
|
|
"mean_token_accuracy": 0.10352744907140732,
|
|
"num_tokens": 4003108.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.656303977966308,
|
|
"epoch": 0.23412350014632718,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999825867158642,
|
|
"loss": 7.5318,
|
|
"mean_token_accuracy": 0.10171960368752479,
|
|
"num_tokens": 4019944.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.67695837020874,
|
|
"epoch": 0.23509901473027023,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.0004999817006955134,
|
|
"loss": 7.4148,
|
|
"mean_token_accuracy": 0.1110982745885849,
|
|
"num_tokens": 4037617.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.564828205108642,
|
|
"epoch": 0.23607452931421324,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999807926907527,
|
|
"loss": 7.4196,
|
|
"mean_token_accuracy": 0.1058736652135849,
|
|
"num_tokens": 4053483.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.650463819503784,
|
|
"epoch": 0.2370500438981563,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004999798627016707,
|
|
"loss": 7.4938,
|
|
"mean_token_accuracy": 0.10973084867000579,
|
|
"num_tokens": 4070165.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.666395378112793,
|
|
"epoch": 0.2380255584820993,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999789107283586,
|
|
"loss": 7.4592,
|
|
"mean_token_accuracy": 0.10479641184210778,
|
|
"num_tokens": 4086208.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.536335611343384,
|
|
"epoch": 0.23900107306604235,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.000499977936770909,
|
|
"loss": 7.4284,
|
|
"mean_token_accuracy": 0.11059935465455055,
|
|
"num_tokens": 4101790.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.596198606491089,
|
|
"epoch": 0.23997658764998536,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999769408294173,
|
|
"loss": 7.3564,
|
|
"mean_token_accuracy": 0.11463292688131332,
|
|
"num_tokens": 4117633.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.543298625946045,
|
|
"epoch": 0.2409521022339284,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004999759229039807,
|
|
"loss": 7.4117,
|
|
"mean_token_accuracy": 0.1110031045973301,
|
|
"num_tokens": 4132634.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.637632036209107,
|
|
"epoch": 0.24192761681787142,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004999748829946988,
|
|
"loss": 7.4597,
|
|
"mean_token_accuracy": 0.10480623170733452,
|
|
"num_tokens": 4150702.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.529221677780152,
|
|
"epoch": 0.24290313140181446,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004999738211016732,
|
|
"loss": 7.3414,
|
|
"mean_token_accuracy": 0.12164942622184753,
|
|
"num_tokens": 4168483.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.461252737045288,
|
|
"epoch": 0.24387864598575748,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004999727372250076,
|
|
"loss": 7.2849,
|
|
"mean_token_accuracy": 0.11414404958486557,
|
|
"num_tokens": 4186199.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.577147388458252,
|
|
"epoch": 0.24485416056970052,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999716313648079,
|
|
"loss": 7.4275,
|
|
"mean_token_accuracy": 0.11002629846334458,
|
|
"num_tokens": 4202303.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.628062963485718,
|
|
"epoch": 0.24582967515364354,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004999705035211822,
|
|
"loss": 7.4749,
|
|
"mean_token_accuracy": 0.10410321578383445,
|
|
"num_tokens": 4218541.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.629666185379028,
|
|
"epoch": 0.24680518973758658,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999693536942406,
|
|
"loss": 7.4488,
|
|
"mean_token_accuracy": 0.10713504701852798,
|
|
"num_tokens": 4234025.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.61506085395813,
|
|
"epoch": 0.2477807043215296,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999681818840957,
|
|
"loss": 7.4348,
|
|
"mean_token_accuracy": 0.11027696803212166,
|
|
"num_tokens": 4250798.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.53934416770935,
|
|
"epoch": 0.24875621890547264,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499966988090862,
|
|
"loss": 7.4477,
|
|
"mean_token_accuracy": 0.1014046274125576,
|
|
"num_tokens": 4266453.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.6491199970245365,
|
|
"epoch": 0.24973173348941566,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999657723146558,
|
|
"loss": 7.4039,
|
|
"mean_token_accuracy": 0.10734148547053338,
|
|
"num_tokens": 4281825.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.421799039840698,
|
|
"epoch": 0.2507072480733587,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004999645345555962,
|
|
"loss": 7.2436,
|
|
"mean_token_accuracy": 0.12358821108937264,
|
|
"num_tokens": 4298821.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.555448579788208,
|
|
"epoch": 0.2516827626573017,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999632748138041,
|
|
"loss": 7.2814,
|
|
"mean_token_accuracy": 0.11623628512024879,
|
|
"num_tokens": 4314076.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.4973656177520756,
|
|
"epoch": 0.25265827724124473,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999619930894025,
|
|
"loss": 7.2886,
|
|
"mean_token_accuracy": 0.11894373595714569,
|
|
"num_tokens": 4330909.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.584926414489746,
|
|
"epoch": 0.2536337918251878,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999606893825168,
|
|
"loss": 7.3895,
|
|
"mean_token_accuracy": 0.1105497196316719,
|
|
"num_tokens": 4346927.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.53502926826477,
|
|
"epoch": 0.2546093064091308,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004999593636932742,
|
|
"loss": 7.4231,
|
|
"mean_token_accuracy": 0.1062544658780098,
|
|
"num_tokens": 4364956.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.570472669601441,
|
|
"epoch": 0.25558482099307384,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004999580160218044,
|
|
"loss": 7.3341,
|
|
"mean_token_accuracy": 0.11137348413467407,
|
|
"num_tokens": 4383014.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.464001560211182,
|
|
"epoch": 0.25656033557701685,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004999566463682391,
|
|
"loss": 7.4446,
|
|
"mean_token_accuracy": 0.11059048622846604,
|
|
"num_tokens": 4401050.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.527480792999268,
|
|
"epoch": 0.2575358501609599,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004999552547327119,
|
|
"loss": 7.3368,
|
|
"mean_token_accuracy": 0.1074261873960495,
|
|
"num_tokens": 4415453.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.471518182754517,
|
|
"epoch": 0.25851136474490294,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999538411153591,
|
|
"loss": 7.3057,
|
|
"mean_token_accuracy": 0.118268571048975,
|
|
"num_tokens": 4433107.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.5838682651519775,
|
|
"epoch": 0.25948687932884595,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999524055163187,
|
|
"loss": 7.3985,
|
|
"mean_token_accuracy": 0.1033043161034584,
|
|
"num_tokens": 4449440.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.609823369979859,
|
|
"epoch": 0.26046239391278897,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.000499950947935731,
|
|
"loss": 7.3672,
|
|
"mean_token_accuracy": 0.10769027024507523,
|
|
"num_tokens": 4465327.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.551059675216675,
|
|
"epoch": 0.26143790849673204,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004999494683737384,
|
|
"loss": 7.4104,
|
|
"mean_token_accuracy": 0.10487848818302155,
|
|
"num_tokens": 4481518.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.610081195831299,
|
|
"epoch": 0.26241342308067506,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004999479668304854,
|
|
"loss": 7.4236,
|
|
"mean_token_accuracy": 0.10805536955595016,
|
|
"num_tokens": 4497632.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.3706573963165285,
|
|
"epoch": 0.2633889376646181,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004999464433061188,
|
|
"loss": 7.1752,
|
|
"mean_token_accuracy": 0.12156692147254944,
|
|
"num_tokens": 4513790.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.450050258636475,
|
|
"epoch": 0.26436445224856114,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999448978007876,
|
|
"loss": 7.2988,
|
|
"mean_token_accuracy": 0.11536605134606362,
|
|
"num_tokens": 4530802.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.5716697692871096,
|
|
"epoch": 0.26533996683250416,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004999433303146426,
|
|
"loss": 7.3542,
|
|
"mean_token_accuracy": 0.106167721003294,
|
|
"num_tokens": 4546208.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.514369773864746,
|
|
"epoch": 0.2663154814164472,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 0.0004999417408478371,
|
|
"loss": 7.4105,
|
|
"mean_token_accuracy": 0.10686387866735458,
|
|
"num_tokens": 4563753.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.500036001205444,
|
|
"epoch": 0.2672909960003902,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999401294005264,
|
|
"loss": 7.2931,
|
|
"mean_token_accuracy": 0.11594824194908142,
|
|
"num_tokens": 4580274.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.477007007598877,
|
|
"epoch": 0.26826651058433326,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499938495972868,
|
|
"loss": 7.3767,
|
|
"mean_token_accuracy": 0.11033575236797333,
|
|
"num_tokens": 4596085.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.576802349090576,
|
|
"epoch": 0.2692420251682763,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004999368405650214,
|
|
"loss": 7.3969,
|
|
"mean_token_accuracy": 0.10646035224199295,
|
|
"num_tokens": 4613258.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.310148572921753,
|
|
"epoch": 0.2702175397522193,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004999351631771485,
|
|
"loss": 7.2223,
|
|
"mean_token_accuracy": 0.11963125318288803,
|
|
"num_tokens": 4630128.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.567701387405395,
|
|
"epoch": 0.2711930543361623,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004999334638094131,
|
|
"loss": 7.2757,
|
|
"mean_token_accuracy": 0.11379968002438545,
|
|
"num_tokens": 4646181.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.498345851898193,
|
|
"epoch": 0.2721685689201054,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999317424619812,
|
|
"loss": 7.327,
|
|
"mean_token_accuracy": 0.10955062061548233,
|
|
"num_tokens": 4661804.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.484235525131226,
|
|
"epoch": 0.2731440835040484,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999299991350212,
|
|
"loss": 7.2476,
|
|
"mean_token_accuracy": 0.11625512018799782,
|
|
"num_tokens": 4678163.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.488172292709351,
|
|
"epoch": 0.2741195980879914,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999282338287034,
|
|
"loss": 7.2452,
|
|
"mean_token_accuracy": 0.11395767405629158,
|
|
"num_tokens": 4695469.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.5351776599884035,
|
|
"epoch": 0.2750951126719344,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004999264465432001,
|
|
"loss": 7.3608,
|
|
"mean_token_accuracy": 0.11114447489380837,
|
|
"num_tokens": 4711599.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.51265058517456,
|
|
"epoch": 0.2760706272558775,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004999246372786862,
|
|
"loss": 7.3643,
|
|
"mean_token_accuracy": 0.1071487732231617,
|
|
"num_tokens": 4728381.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.449716854095459,
|
|
"epoch": 0.2770461418398205,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004999228060353385,
|
|
"loss": 7.3541,
|
|
"mean_token_accuracy": 0.10885404273867608,
|
|
"num_tokens": 4745348.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.6108174324035645,
|
|
"epoch": 0.27802165642376353,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004999209528133357,
|
|
"loss": 7.3598,
|
|
"mean_token_accuracy": 0.10185754671692848,
|
|
"num_tokens": 4763011.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.426053524017334,
|
|
"epoch": 0.27899717100770655,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.000499919077612859,
|
|
"loss": 7.3047,
|
|
"mean_token_accuracy": 0.11357978358864784,
|
|
"num_tokens": 4779462.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.401883459091186,
|
|
"epoch": 0.2799726855916496,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999171804340917,
|
|
"loss": 7.2526,
|
|
"mean_token_accuracy": 0.1170469731092453,
|
|
"num_tokens": 4796844.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.454334831237793,
|
|
"epoch": 0.28094820017559263,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004999152612772191,
|
|
"loss": 7.275,
|
|
"mean_token_accuracy": 0.11510033011436463,
|
|
"num_tokens": 4812851.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.410532236099243,
|
|
"epoch": 0.28192371475953565,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999133201424288,
|
|
"loss": 7.2144,
|
|
"mean_token_accuracy": 0.11656784042716026,
|
|
"num_tokens": 4830144.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.5702674865722654,
|
|
"epoch": 0.28289922934347866,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004999113570299105,
|
|
"loss": 7.316,
|
|
"mean_token_accuracy": 0.10677381530404091,
|
|
"num_tokens": 4846981.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.518744707107544,
|
|
"epoch": 0.28387474392742174,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004999093719398561,
|
|
"loss": 7.4632,
|
|
"mean_token_accuracy": 0.10185813456773758,
|
|
"num_tokens": 4864404.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.519454765319824,
|
|
"epoch": 0.28485025851136475,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999073648724592,
|
|
"loss": 7.3551,
|
|
"mean_token_accuracy": 0.1059863179922104,
|
|
"num_tokens": 4882004.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.459197568893432,
|
|
"epoch": 0.28582577309530777,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999053358279164,
|
|
"loss": 7.2935,
|
|
"mean_token_accuracy": 0.10663619711995125,
|
|
"num_tokens": 4899444.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.563556718826294,
|
|
"epoch": 0.2868012876792508,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999032848064256,
|
|
"loss": 7.2887,
|
|
"mean_token_accuracy": 0.10705682784318923,
|
|
"num_tokens": 4917214.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.376403284072876,
|
|
"epoch": 0.28777680226319385,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999012118081875,
|
|
"loss": 7.3614,
|
|
"mean_token_accuracy": 0.10581159889698029,
|
|
"num_tokens": 4934534.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.575308418273925,
|
|
"epoch": 0.28875231684713687,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004998991168334045,
|
|
"loss": 7.283,
|
|
"mean_token_accuracy": 0.10879023000597954,
|
|
"num_tokens": 4950740.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.423694849014282,
|
|
"epoch": 0.2897278314310799,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998969998822814,
|
|
"loss": 7.3787,
|
|
"mean_token_accuracy": 0.10367386490106582,
|
|
"num_tokens": 4966720.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.5524180889129635,
|
|
"epoch": 0.2907033460150229,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004998948609550249,
|
|
"loss": 7.2646,
|
|
"mean_token_accuracy": 0.10495304986834526,
|
|
"num_tokens": 4982195.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.48098726272583,
|
|
"epoch": 0.29167886059896597,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998927000518442,
|
|
"loss": 7.3698,
|
|
"mean_token_accuracy": 0.10665831938385964,
|
|
"num_tokens": 4997487.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.4441125869750975,
|
|
"epoch": 0.292654375182909,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998905171729505,
|
|
"loss": 7.2544,
|
|
"mean_token_accuracy": 0.10893786400556564,
|
|
"num_tokens": 5012913.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.356356573104859,
|
|
"epoch": 0.293629889766852,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004998883123185568,
|
|
"loss": 7.2187,
|
|
"mean_token_accuracy": 0.11964470073580742,
|
|
"num_tokens": 5031462.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.506862783432007,
|
|
"epoch": 0.294605404350795,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998860854888788,
|
|
"loss": 7.2106,
|
|
"mean_token_accuracy": 0.11758186593651772,
|
|
"num_tokens": 5047354.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.398953914642334,
|
|
"epoch": 0.2955809189347381,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004998838366841341,
|
|
"loss": 7.2889,
|
|
"mean_token_accuracy": 0.11200916841626167,
|
|
"num_tokens": 5065268.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.458558130264282,
|
|
"epoch": 0.2965564335186811,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004998815659045423,
|
|
"loss": 7.2642,
|
|
"mean_token_accuracy": 0.11022249981760979,
|
|
"num_tokens": 5081066.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.4308922290802,
|
|
"epoch": 0.2975319481026241,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004998792731503254,
|
|
"loss": 7.3087,
|
|
"mean_token_accuracy": 0.11247767508029938,
|
|
"num_tokens": 5099440.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.424282217025757,
|
|
"epoch": 0.29850746268656714,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004998769584217074,
|
|
"loss": 7.2695,
|
|
"mean_token_accuracy": 0.11871928125619888,
|
|
"num_tokens": 5116573.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.267613458633423,
|
|
"epoch": 0.2994829772705102,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004998746217189145,
|
|
"loss": 7.0415,
|
|
"mean_token_accuracy": 0.12954215258359908,
|
|
"num_tokens": 5132920.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.544499349594116,
|
|
"epoch": 0.3004584918544532,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.000499872263042175,
|
|
"loss": 7.2875,
|
|
"mean_token_accuracy": 0.10873164162039757,
|
|
"num_tokens": 5150681.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.285702896118164,
|
|
"epoch": 0.30143400643839624,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998698823917196,
|
|
"loss": 7.077,
|
|
"mean_token_accuracy": 0.12807691991329193,
|
|
"num_tokens": 5167473.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.463721036911011,
|
|
"epoch": 0.3024095210223393,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004998674797677805,
|
|
"loss": 7.3473,
|
|
"mean_token_accuracy": 0.10609673261642456,
|
|
"num_tokens": 5183847.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.475162935256958,
|
|
"epoch": 0.3033850356062823,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004998650551705929,
|
|
"loss": 7.2916,
|
|
"mean_token_accuracy": 0.10924788787961007,
|
|
"num_tokens": 5200019.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.362889242172241,
|
|
"epoch": 0.30436055019022534,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998626086003934,
|
|
"loss": 7.1448,
|
|
"mean_token_accuracy": 0.11549173519015313,
|
|
"num_tokens": 5217245.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.38791127204895,
|
|
"epoch": 0.30533606477416836,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004998601400574213,
|
|
"loss": 7.0583,
|
|
"mean_token_accuracy": 0.12249146774411201,
|
|
"num_tokens": 5234822.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.376275300979614,
|
|
"epoch": 0.30631157935811143,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998576495419177,
|
|
"loss": 7.2157,
|
|
"mean_token_accuracy": 0.10978191494941711,
|
|
"num_tokens": 5251282.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.348541307449341,
|
|
"epoch": 0.30728709394205445,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 0.000499855137054126,
|
|
"loss": 7.1775,
|
|
"mean_token_accuracy": 0.11414216682314873,
|
|
"num_tokens": 5269630.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.451559972763062,
|
|
"epoch": 0.30826260852599746,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998526025942917,
|
|
"loss": 7.2624,
|
|
"mean_token_accuracy": 0.11020819023251534,
|
|
"num_tokens": 5287106.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.460999155044556,
|
|
"epoch": 0.3092381231099405,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004998500461626625,
|
|
"loss": 7.2832,
|
|
"mean_token_accuracy": 0.10537893772125244,
|
|
"num_tokens": 5303387.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.494349813461303,
|
|
"epoch": 0.31021363769388355,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000499847467759488,
|
|
"loss": 7.2782,
|
|
"mean_token_accuracy": 0.1071275532245636,
|
|
"num_tokens": 5320482.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.3614997386932375,
|
|
"epoch": 0.31118915227782656,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004998448673850205,
|
|
"loss": 7.2244,
|
|
"mean_token_accuracy": 0.11353383362293243,
|
|
"num_tokens": 5336420.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.350383996963501,
|
|
"epoch": 0.3121646668617696,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998422450395139,
|
|
"loss": 7.142,
|
|
"mean_token_accuracy": 0.11666039228439332,
|
|
"num_tokens": 5353464.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.396124601364136,
|
|
"epoch": 0.3131401814457126,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004998396007232244,
|
|
"loss": 7.234,
|
|
"mean_token_accuracy": 0.11493151038885116,
|
|
"num_tokens": 5372607.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.3827756404876705,
|
|
"epoch": 0.31411569602965567,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998369344364105,
|
|
"loss": 7.2535,
|
|
"mean_token_accuracy": 0.11560017913579941,
|
|
"num_tokens": 5390134.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.394735050201416,
|
|
"epoch": 0.3150912106135987,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004998342461793328,
|
|
"loss": 7.1559,
|
|
"mean_token_accuracy": 0.11589187011122704,
|
|
"num_tokens": 5407083.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.252396011352539,
|
|
"epoch": 0.3160667251975417,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004998315359522538,
|
|
"loss": 7.0531,
|
|
"mean_token_accuracy": 0.1292327970266342,
|
|
"num_tokens": 5424617.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.308001565933227,
|
|
"epoch": 0.3170422397814847,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004998288037554383,
|
|
"loss": 7.1977,
|
|
"mean_token_accuracy": 0.12096902504563331,
|
|
"num_tokens": 5440913.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.372673082351684,
|
|
"epoch": 0.3180177543654278,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004998260495891535,
|
|
"loss": 7.225,
|
|
"mean_token_accuracy": 0.11702024266123771,
|
|
"num_tokens": 5457157.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.383390712738037,
|
|
"epoch": 0.3189932689493708,
|
|
"grad_norm": 0.66015625,
|
|
"learning_rate": 0.0004998232734536685,
|
|
"loss": 7.1484,
|
|
"mean_token_accuracy": 0.11764496192336082,
|
|
"num_tokens": 5474520.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.418297576904297,
|
|
"epoch": 0.3199687835333138,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998204753492544,
|
|
"loss": 7.2159,
|
|
"mean_token_accuracy": 0.11754014566540719,
|
|
"num_tokens": 5490599.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.389422082901001,
|
|
"epoch": 0.32094429811725683,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004998176552761848,
|
|
"loss": 7.2857,
|
|
"mean_token_accuracy": 0.10174136385321617,
|
|
"num_tokens": 5506714.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.40252423286438,
|
|
"epoch": 0.3219198127011999,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004998148132347352,
|
|
"loss": 7.2392,
|
|
"mean_token_accuracy": 0.11066171750426293,
|
|
"num_tokens": 5522894.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.364075708389282,
|
|
"epoch": 0.3228953272851429,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004998119492251832,
|
|
"loss": 7.1208,
|
|
"mean_token_accuracy": 0.12099760472774505,
|
|
"num_tokens": 5540054.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.415332651138305,
|
|
"epoch": 0.32387084186908593,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998090632478088,
|
|
"loss": 7.2627,
|
|
"mean_token_accuracy": 0.10254106968641281,
|
|
"num_tokens": 5556189.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.4424889087677,
|
|
"epoch": 0.32484635645302895,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000499806155302894,
|
|
"loss": 7.2877,
|
|
"mean_token_accuracy": 0.1063154935836792,
|
|
"num_tokens": 5572562.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.465411758422851,
|
|
"epoch": 0.325821871036972,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000499803225390723,
|
|
"loss": 7.2694,
|
|
"mean_token_accuracy": 0.10791720896959305,
|
|
"num_tokens": 5588992.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.400199127197266,
|
|
"epoch": 0.32679738562091504,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998002735115819,
|
|
"loss": 7.187,
|
|
"mean_token_accuracy": 0.11241097077727318,
|
|
"num_tokens": 5604143.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.4391865730285645,
|
|
"epoch": 0.32777290020485805,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004997972996657593,
|
|
"loss": 7.3002,
|
|
"mean_token_accuracy": 0.10091334953904152,
|
|
"num_tokens": 5620887.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.372653961181641,
|
|
"epoch": 0.32874841478880107,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997943038535459,
|
|
"loss": 7.2412,
|
|
"mean_token_accuracy": 0.11132050454616546,
|
|
"num_tokens": 5637156.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.445284605026245,
|
|
"epoch": 0.32972392937274414,
|
|
"grad_norm": 0.6875,
|
|
"learning_rate": 0.0004997912860752341,
|
|
"loss": 7.1991,
|
|
"mean_token_accuracy": 0.10926434695720673,
|
|
"num_tokens": 5654024.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.381779670715332,
|
|
"epoch": 0.33069944395668716,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997882463311192,
|
|
"loss": 7.1537,
|
|
"mean_token_accuracy": 0.11310063973069191,
|
|
"num_tokens": 5671538.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.348152542114258,
|
|
"epoch": 0.33167495854063017,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004997851846214979,
|
|
"loss": 7.1949,
|
|
"mean_token_accuracy": 0.1151057593524456,
|
|
"num_tokens": 5688788.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.329300737380981,
|
|
"epoch": 0.3326504731245732,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004997821009466695,
|
|
"loss": 7.1359,
|
|
"mean_token_accuracy": 0.1145908311009407,
|
|
"num_tokens": 5706066.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.346020078659057,
|
|
"epoch": 0.33362598770851626,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997789953069354,
|
|
"loss": 7.1175,
|
|
"mean_token_accuracy": 0.11305170506238937,
|
|
"num_tokens": 5722100.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.361113500595093,
|
|
"epoch": 0.3346015022924593,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.0004997758677025989,
|
|
"loss": 7.2428,
|
|
"mean_token_accuracy": 0.10920800790190696,
|
|
"num_tokens": 5739068.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.354664897918701,
|
|
"epoch": 0.3355770168764023,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004997727181339658,
|
|
"loss": 7.2139,
|
|
"mean_token_accuracy": 0.10852341279387474,
|
|
"num_tokens": 5756147.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.3808012962341305,
|
|
"epoch": 0.3365525314603453,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004997695466013438,
|
|
"loss": 7.1814,
|
|
"mean_token_accuracy": 0.11239296644926071,
|
|
"num_tokens": 5772157.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.395117616653442,
|
|
"epoch": 0.3375280460442884,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004997663531050427,
|
|
"loss": 7.2161,
|
|
"mean_token_accuracy": 0.11248084828257561,
|
|
"num_tokens": 5788128.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.3364479541778564,
|
|
"epoch": 0.3385035606282314,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004997631376453749,
|
|
"loss": 7.1879,
|
|
"mean_token_accuracy": 0.11148244142532349,
|
|
"num_tokens": 5804793.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.323251390457154,
|
|
"epoch": 0.3394790752121744,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997599002226541,
|
|
"loss": 7.1203,
|
|
"mean_token_accuracy": 0.11626422554254531,
|
|
"num_tokens": 5822409.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.30807671546936,
|
|
"epoch": 0.3404545897961175,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499756640837197,
|
|
"loss": 7.1627,
|
|
"mean_token_accuracy": 0.11140080466866494,
|
|
"num_tokens": 5839023.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.368128967285156,
|
|
"epoch": 0.3414301043800605,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000499753359489322,
|
|
"loss": 7.1665,
|
|
"mean_token_accuracy": 0.10992935597896576,
|
|
"num_tokens": 5855804.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.333204317092895,
|
|
"epoch": 0.3424056189640035,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004997500561793498,
|
|
"loss": 7.1786,
|
|
"mean_token_accuracy": 0.11211245954036712,
|
|
"num_tokens": 5872372.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.41660327911377,
|
|
"epoch": 0.3433811335479465,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004997467309076031,
|
|
"loss": 7.2211,
|
|
"mean_token_accuracy": 0.10542100667953491,
|
|
"num_tokens": 5888666.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.291812181472778,
|
|
"epoch": 0.3443566481318896,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004997433836744069,
|
|
"loss": 7.1705,
|
|
"mean_token_accuracy": 0.11156053617596626,
|
|
"num_tokens": 5905577.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 7.315142011642456,
|
|
"epoch": 0.3453321627158326,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997400144800882,
|
|
"loss": 7.1508,
|
|
"mean_token_accuracy": 0.11506888642907143,
|
|
"num_tokens": 5922570.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 7.223569536209107,
|
|
"epoch": 0.34630767729977563,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997366233249762,
|
|
"loss": 7.0883,
|
|
"mean_token_accuracy": 0.12366917207837105,
|
|
"num_tokens": 5938995.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.272809743881226,
|
|
"epoch": 0.34728319188371864,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004997332102094024,
|
|
"loss": 7.1118,
|
|
"mean_token_accuracy": 0.11795152202248574,
|
|
"num_tokens": 5954869.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.464500522613525,
|
|
"epoch": 0.3482587064676617,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004997297751337004,
|
|
"loss": 7.2125,
|
|
"mean_token_accuracy": 0.11424987763166428,
|
|
"num_tokens": 5972750.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.2483217239379885,
|
|
"epoch": 0.34923422105160473,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004997263180982055,
|
|
"loss": 7.1325,
|
|
"mean_token_accuracy": 0.11683203727006912,
|
|
"num_tokens": 5989004.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.29300446510315,
|
|
"epoch": 0.35020973563554775,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004997228391032559,
|
|
"loss": 7.1455,
|
|
"mean_token_accuracy": 0.1135661095380783,
|
|
"num_tokens": 6004749.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 7.337142848968506,
|
|
"epoch": 0.35118525021949076,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004997193381491913,
|
|
"loss": 7.0415,
|
|
"mean_token_accuracy": 0.11597696542739869,
|
|
"num_tokens": 6022235.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.260811042785645,
|
|
"epoch": 0.35216076480343383,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000499715815236354,
|
|
"loss": 7.2043,
|
|
"mean_token_accuracy": 0.10821624919772148,
|
|
"num_tokens": 6039194.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 7.412096691131592,
|
|
"epoch": 0.35313627938737685,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.000499712270365088,
|
|
"loss": 7.0791,
|
|
"mean_token_accuracy": 0.11110314354300499,
|
|
"num_tokens": 6055376.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.298790311813354,
|
|
"epoch": 0.35411179397131987,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004997087035357398,
|
|
"loss": 7.127,
|
|
"mean_token_accuracy": 0.11343505010008811,
|
|
"num_tokens": 6071105.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 7.204732227325439,
|
|
"epoch": 0.3550873085552629,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997051147486582,
|
|
"loss": 7.0515,
|
|
"mean_token_accuracy": 0.11854118779301644,
|
|
"num_tokens": 6087964.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.260140800476075,
|
|
"epoch": 0.35606282313920595,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004997015040041935,
|
|
"loss": 7.1154,
|
|
"mean_token_accuracy": 0.11081360802054405,
|
|
"num_tokens": 6105245.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.286773014068603,
|
|
"epoch": 0.35703833772314897,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996978713026986,
|
|
"loss": 7.0775,
|
|
"mean_token_accuracy": 0.12042444795370102,
|
|
"num_tokens": 6121736.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.306388807296753,
|
|
"epoch": 0.358013852307092,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996942166445287,
|
|
"loss": 7.1244,
|
|
"mean_token_accuracy": 0.11466041356325149,
|
|
"num_tokens": 6137751.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.33421745300293,
|
|
"epoch": 0.358989366891035,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004996905400300407,
|
|
"loss": 7.1875,
|
|
"mean_token_accuracy": 0.11488941907882691,
|
|
"num_tokens": 6154655.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.345286226272583,
|
|
"epoch": 0.35996488147497807,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000499686841459594,
|
|
"loss": 7.1894,
|
|
"mean_token_accuracy": 0.10912730991840362,
|
|
"num_tokens": 6172230.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 7.290603160858154,
|
|
"epoch": 0.3609403960589211,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004996831209335497,
|
|
"loss": 7.125,
|
|
"mean_token_accuracy": 0.10650177523493767,
|
|
"num_tokens": 6188520.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 7.2695581912994385,
|
|
"epoch": 0.3619159106428641,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004996793784522719,
|
|
"loss": 7.1608,
|
|
"mean_token_accuracy": 0.1108959175646305,
|
|
"num_tokens": 6205555.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.395503807067871,
|
|
"epoch": 0.3628914252268071,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004996756140161259,
|
|
"loss": 7.1466,
|
|
"mean_token_accuracy": 0.11458924412727356,
|
|
"num_tokens": 6223548.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.251076316833496,
|
|
"epoch": 0.3638669398107502,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004996718276254797,
|
|
"loss": 7.1532,
|
|
"mean_token_accuracy": 0.10857186615467071,
|
|
"num_tokens": 6239266.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.347242403030395,
|
|
"epoch": 0.3648424543946932,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004996680192807032,
|
|
"loss": 7.1199,
|
|
"mean_token_accuracy": 0.11347832977771759,
|
|
"num_tokens": 6255020.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.319795846939087,
|
|
"epoch": 0.3658179689786362,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004996641889821686,
|
|
"loss": 7.0746,
|
|
"mean_token_accuracy": 0.11083570644259452,
|
|
"num_tokens": 6272774.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 7.267253398895264,
|
|
"epoch": 0.36679348356257924,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004996603367302502,
|
|
"loss": 7.0742,
|
|
"mean_token_accuracy": 0.11343652233481408,
|
|
"num_tokens": 6290478.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.28585729598999,
|
|
"epoch": 0.3677689981465223,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004996564625253244,
|
|
"loss": 7.15,
|
|
"mean_token_accuracy": 0.11109395548701287,
|
|
"num_tokens": 6308003.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 7.2919114112854,
|
|
"epoch": 0.3687445127304653,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004996525663677697,
|
|
"loss": 7.1184,
|
|
"mean_token_accuracy": 0.1092761978507042,
|
|
"num_tokens": 6325748.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.274161243438721,
|
|
"epoch": 0.36972002731440834,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000499648648257967,
|
|
"loss": 7.0485,
|
|
"mean_token_accuracy": 0.12817562222480774,
|
|
"num_tokens": 6344031.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 7.239025402069092,
|
|
"epoch": 0.37069554189835136,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.000499644708196299,
|
|
"loss": 7.1088,
|
|
"mean_token_accuracy": 0.1161065973341465,
|
|
"num_tokens": 6359821.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 7.177339696884156,
|
|
"epoch": 0.3716710564822944,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004996407461831507,
|
|
"loss": 6.9521,
|
|
"mean_token_accuracy": 0.1276794709265232,
|
|
"num_tokens": 6376464.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 7.350318479537964,
|
|
"epoch": 0.37264657106623744,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004996367622189094,
|
|
"loss": 7.127,
|
|
"mean_token_accuracy": 0.11131031289696694,
|
|
"num_tokens": 6392415.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 7.206513071060181,
|
|
"epoch": 0.37362208565018046,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004996327563039643,
|
|
"loss": 7.1209,
|
|
"mean_token_accuracy": 0.11124824956059456,
|
|
"num_tokens": 6409151.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 7.344724702835083,
|
|
"epoch": 0.3745976002341235,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004996287284387068,
|
|
"loss": 7.079,
|
|
"mean_token_accuracy": 0.11743810772895813,
|
|
"num_tokens": 6426997.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 7.238914442062378,
|
|
"epoch": 0.37557311481806654,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004996246786235306,
|
|
"loss": 7.0857,
|
|
"mean_token_accuracy": 0.11670200452208519,
|
|
"num_tokens": 6442871.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 7.203385543823242,
|
|
"epoch": 0.37654862940200956,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004996206068588314,
|
|
"loss": 7.0849,
|
|
"mean_token_accuracy": 0.11218000873923302,
|
|
"num_tokens": 6459677.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.336028528213501,
|
|
"epoch": 0.3775241439859526,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004996165131450071,
|
|
"loss": 7.2134,
|
|
"mean_token_accuracy": 0.10741019994020462,
|
|
"num_tokens": 6477239.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 7.308997726440429,
|
|
"epoch": 0.37849965856989565,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004996123974824576,
|
|
"loss": 7.0856,
|
|
"mean_token_accuracy": 0.11888976544141769,
|
|
"num_tokens": 6493277.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 7.210962915420533,
|
|
"epoch": 0.37947517315383866,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004996082598715852,
|
|
"loss": 7.0907,
|
|
"mean_token_accuracy": 0.11501143723726273,
|
|
"num_tokens": 6509204.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 7.223517417907715,
|
|
"epoch": 0.3804506877377817,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499604100312794,
|
|
"loss": 6.9496,
|
|
"mean_token_accuracy": 0.12535614222288133,
|
|
"num_tokens": 6525486.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.211537933349609,
|
|
"epoch": 0.3814262023217247,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004995999188064908,
|
|
"loss": 7.1591,
|
|
"mean_token_accuracy": 0.10634085834026337,
|
|
"num_tokens": 6542227.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 7.360594367980957,
|
|
"epoch": 0.38240171690566777,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000499595715353084,
|
|
"loss": 7.2246,
|
|
"mean_token_accuracy": 0.10380557775497437,
|
|
"num_tokens": 6558951.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.310774660110473,
|
|
"epoch": 0.3833772314896108,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004995914899529844,
|
|
"loss": 7.1393,
|
|
"mean_token_accuracy": 0.11187061816453933,
|
|
"num_tokens": 6574696.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 7.347577524185181,
|
|
"epoch": 0.3843527460735538,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004995872426066048,
|
|
"loss": 7.1385,
|
|
"mean_token_accuracy": 0.1089790977537632,
|
|
"num_tokens": 6591628.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 7.25405855178833,
|
|
"epoch": 0.3853282606574968,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995829733143602,
|
|
"loss": 7.0549,
|
|
"mean_token_accuracy": 0.11590226516127586,
|
|
"num_tokens": 6608107.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 7.251243686676025,
|
|
"epoch": 0.3863037752414399,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000499578682076668,
|
|
"loss": 7.1676,
|
|
"mean_token_accuracy": 0.1179898962378502,
|
|
"num_tokens": 6626699.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 7.352150535583496,
|
|
"epoch": 0.3872792898253829,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004995743688939474,
|
|
"loss": 7.1801,
|
|
"mean_token_accuracy": 0.1051247276365757,
|
|
"num_tokens": 6644540.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 7.301030969619751,
|
|
"epoch": 0.3882548044093259,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004995700337666199,
|
|
"loss": 7.1345,
|
|
"mean_token_accuracy": 0.1087101012468338,
|
|
"num_tokens": 6660653.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 7.358835697174072,
|
|
"epoch": 0.38923031899326893,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000499565676695109,
|
|
"loss": 7.1277,
|
|
"mean_token_accuracy": 0.10916693210601806,
|
|
"num_tokens": 6677553.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 7.234071826934814,
|
|
"epoch": 0.390205833577212,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004995612976798406,
|
|
"loss": 7.1097,
|
|
"mean_token_accuracy": 0.1076956108212471,
|
|
"num_tokens": 6695274.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 7.21323447227478,
|
|
"epoch": 0.391181348161155,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004995568967212425,
|
|
"loss": 7.0513,
|
|
"mean_token_accuracy": 0.11473157033324241,
|
|
"num_tokens": 6711166.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 7.2274092674255375,
|
|
"epoch": 0.39215686274509803,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004995524738197448,
|
|
"loss": 7.0293,
|
|
"mean_token_accuracy": 0.11371998265385627,
|
|
"num_tokens": 6728827.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 7.157890892028808,
|
|
"epoch": 0.39313237732904105,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004995480289757796,
|
|
"loss": 7.0112,
|
|
"mean_token_accuracy": 0.12422050759196282,
|
|
"num_tokens": 6745901.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 7.203786039352417,
|
|
"epoch": 0.3941078919129841,
|
|
"grad_norm": 0.6953125,
|
|
"learning_rate": 0.0004995435621897815,
|
|
"loss": 6.9848,
|
|
"mean_token_accuracy": 0.12129663527011872,
|
|
"num_tokens": 6762176.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 7.2202558517456055,
|
|
"epoch": 0.39508340649692714,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004995390734621867,
|
|
"loss": 7.1429,
|
|
"mean_token_accuracy": 0.11030717268586158,
|
|
"num_tokens": 6779322.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 7.357947063446045,
|
|
"epoch": 0.39605892108087015,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004995345627934338,
|
|
"loss": 7.0667,
|
|
"mean_token_accuracy": 0.11798961833119392,
|
|
"num_tokens": 6794293.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 7.010815858840942,
|
|
"epoch": 0.39703443566481317,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004995300301839637,
|
|
"loss": 6.8932,
|
|
"mean_token_accuracy": 0.13526565283536912,
|
|
"num_tokens": 6812880.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 7.340814161300659,
|
|
"epoch": 0.39800995024875624,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004995254756342194,
|
|
"loss": 7.1137,
|
|
"mean_token_accuracy": 0.11127207204699516,
|
|
"num_tokens": 6829230.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 7.22826657295227,
|
|
"epoch": 0.39898546483269925,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004995208991446458,
|
|
"loss": 7.0891,
|
|
"mean_token_accuracy": 0.11383116319775581,
|
|
"num_tokens": 6846787.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 7.199024486541748,
|
|
"epoch": 0.39996097941664227,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995163007156902,
|
|
"loss": 6.9725,
|
|
"mean_token_accuracy": 0.11578162759542465,
|
|
"num_tokens": 6862990.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 7.287556838989258,
|
|
"epoch": 0.4009364940005853,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995116803478018,
|
|
"loss": 7.1234,
|
|
"mean_token_accuracy": 0.10940696746110916,
|
|
"num_tokens": 6879170.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 7.188670206069946,
|
|
"epoch": 0.40191200858452836,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004995070380414321,
|
|
"loss": 7.0969,
|
|
"mean_token_accuracy": 0.11105065271258355,
|
|
"num_tokens": 6895635.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 7.228735542297363,
|
|
"epoch": 0.4028875231684714,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.000499502373797035,
|
|
"loss": 6.9947,
|
|
"mean_token_accuracy": 0.11994706392288208,
|
|
"num_tokens": 6912836.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 7.202665185928344,
|
|
"epoch": 0.4038630377524144,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000499497687615066,
|
|
"loss": 7.04,
|
|
"mean_token_accuracy": 0.1209272637963295,
|
|
"num_tokens": 6929507.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 7.279792213439942,
|
|
"epoch": 0.4048385523363574,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000499492979495983,
|
|
"loss": 7.0821,
|
|
"mean_token_accuracy": 0.11026716157793999,
|
|
"num_tokens": 6946527.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 7.286045885086059,
|
|
"epoch": 0.4058140669203005,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994882494402462,
|
|
"loss": 7.0544,
|
|
"mean_token_accuracy": 0.1166168913245201,
|
|
"num_tokens": 6962582.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 7.198511600494385,
|
|
"epoch": 0.4067895815042435,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004994834974483178,
|
|
"loss": 7.0457,
|
|
"mean_token_accuracy": 0.11867324039340019,
|
|
"num_tokens": 6979389.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 7.157386112213135,
|
|
"epoch": 0.4077650960881865,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004994787235206621,
|
|
"loss": 7.0181,
|
|
"mean_token_accuracy": 0.11740831509232522,
|
|
"num_tokens": 6996637.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 7.290577459335327,
|
|
"epoch": 0.4087406106721295,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004994739276577456,
|
|
"loss": 7.1354,
|
|
"mean_token_accuracy": 0.10963407009840012,
|
|
"num_tokens": 7013013.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 7.162953281402588,
|
|
"epoch": 0.4097161252560726,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004994691098600369,
|
|
"loss": 7.0902,
|
|
"mean_token_accuracy": 0.11748966127634049,
|
|
"num_tokens": 7031476.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 7.288568019866943,
|
|
"epoch": 0.4106916398400156,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004994642701280068,
|
|
"loss": 6.9969,
|
|
"mean_token_accuracy": 0.11634306013584136,
|
|
"num_tokens": 7047424.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 7.2204046726226805,
|
|
"epoch": 0.4116671544239586,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0004994594084621282,
|
|
"loss": 7.0924,
|
|
"mean_token_accuracy": 0.11025368198752403,
|
|
"num_tokens": 7063793.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 7.326669406890869,
|
|
"epoch": 0.41264266900790164,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004994545248628762,
|
|
"loss": 7.1347,
|
|
"mean_token_accuracy": 0.11028839871287346,
|
|
"num_tokens": 7079026.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 7.240088605880738,
|
|
"epoch": 0.4136181835918447,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000499449619330728,
|
|
"loss": 7.0483,
|
|
"mean_token_accuracy": 0.11729857921600342,
|
|
"num_tokens": 7097524.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 7.251145744323731,
|
|
"epoch": 0.41459369817578773,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.000499444691866163,
|
|
"loss": 7.1188,
|
|
"mean_token_accuracy": 0.11070149391889572,
|
|
"num_tokens": 7115514.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 7.220455503463745,
|
|
"epoch": 0.41556921275973074,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004994397424696625,
|
|
"loss": 7.0571,
|
|
"mean_token_accuracy": 0.11697743535041809,
|
|
"num_tokens": 7132589.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 7.24340329170227,
|
|
"epoch": 0.4165447273436738,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004994347711417105,
|
|
"loss": 7.0813,
|
|
"mean_token_accuracy": 0.11018647104501725,
|
|
"num_tokens": 7149416.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 7.190200424194336,
|
|
"epoch": 0.41752024192761683,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004994297778827924,
|
|
"loss": 7.0129,
|
|
"mean_token_accuracy": 0.12009462714195251,
|
|
"num_tokens": 7165763.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 7.142020797729492,
|
|
"epoch": 0.41849575651155985,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004994247626933964,
|
|
"loss": 6.9991,
|
|
"mean_token_accuracy": 0.12152125090360641,
|
|
"num_tokens": 7183131.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 7.182233715057373,
|
|
"epoch": 0.41947127109550286,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004994197255740124,
|
|
"loss": 7.01,
|
|
"mean_token_accuracy": 0.118393162637949,
|
|
"num_tokens": 7200467.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 7.227328300476074,
|
|
"epoch": 0.42044678567944593,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004994146665251327,
|
|
"loss": 7.0119,
|
|
"mean_token_accuracy": 0.1158651627600193,
|
|
"num_tokens": 7217311.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 7.172503805160522,
|
|
"epoch": 0.42142230026338895,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004994095855472516,
|
|
"loss": 7.0171,
|
|
"mean_token_accuracy": 0.11699589043855667,
|
|
"num_tokens": 7235244.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 7.2362464427947994,
|
|
"epoch": 0.42239781484733196,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004994044826408656,
|
|
"loss": 7.0608,
|
|
"mean_token_accuracy": 0.11110096648335457,
|
|
"num_tokens": 7252235.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 7.2224701881408695,
|
|
"epoch": 0.423373329431275,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004993993578064733,
|
|
"loss": 7.0665,
|
|
"mean_token_accuracy": 0.11295148506760597,
|
|
"num_tokens": 7269367.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 7.241343593597412,
|
|
"epoch": 0.42434884401521805,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993942110445756,
|
|
"loss": 7.0492,
|
|
"mean_token_accuracy": 0.11112753674387932,
|
|
"num_tokens": 7287198.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 7.2085083484649655,
|
|
"epoch": 0.42532435859916107,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004993890423556753,
|
|
"loss": 6.9817,
|
|
"mean_token_accuracy": 0.11444118842482567,
|
|
"num_tokens": 7302356.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 7.246829843521118,
|
|
"epoch": 0.4262998731831041,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004993838517402775,
|
|
"loss": 6.9793,
|
|
"mean_token_accuracy": 0.12212472409009933,
|
|
"num_tokens": 7318530.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 7.199738931655884,
|
|
"epoch": 0.4272753877670471,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004993786391988894,
|
|
"loss": 6.9694,
|
|
"mean_token_accuracy": 0.11767075285315513,
|
|
"num_tokens": 7335195.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 7.093324899673462,
|
|
"epoch": 0.42825090235099017,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004993734047320206,
|
|
"loss": 6.9834,
|
|
"mean_token_accuracy": 0.11373086497187615,
|
|
"num_tokens": 7352233.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 7.248805379867553,
|
|
"epoch": 0.4292264169349332,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004993681483401821,
|
|
"loss": 7.0368,
|
|
"mean_token_accuracy": 0.1148251011967659,
|
|
"num_tokens": 7368569.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 7.125283527374267,
|
|
"epoch": 0.4302019315188762,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004993628700238879,
|
|
"loss": 7.0675,
|
|
"mean_token_accuracy": 0.11216622069478036,
|
|
"num_tokens": 7384669.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 7.305088520050049,
|
|
"epoch": 0.4311774461028192,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004993575697836537,
|
|
"loss": 7.0773,
|
|
"mean_token_accuracy": 0.10974156260490417,
|
|
"num_tokens": 7401833.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 7.186111354827881,
|
|
"epoch": 0.4321529606867623,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004993522476199975,
|
|
"loss": 6.9899,
|
|
"mean_token_accuracy": 0.11291198059916496,
|
|
"num_tokens": 7418663.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 7.202877998352051,
|
|
"epoch": 0.4331284752707053,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004993469035334392,
|
|
"loss": 6.9632,
|
|
"mean_token_accuracy": 0.12589747905731202,
|
|
"num_tokens": 7434701.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 7.186607360839844,
|
|
"epoch": 0.4341039898546483,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.000499341537524501,
|
|
"loss": 7.0437,
|
|
"mean_token_accuracy": 0.10907271057367325,
|
|
"num_tokens": 7450154.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 7.0651970386505125,
|
|
"epoch": 0.43507950443859134,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004993361495937074,
|
|
"loss": 6.8384,
|
|
"mean_token_accuracy": 0.13577248379588128,
|
|
"num_tokens": 7468110.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 7.126219892501831,
|
|
"epoch": 0.4360550190225344,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004993307397415848,
|
|
"loss": 6.9731,
|
|
"mean_token_accuracy": 0.11543633043766022,
|
|
"num_tokens": 7482962.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 7.264739990234375,
|
|
"epoch": 0.4370305336064774,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004993253079686619,
|
|
"loss": 7.1058,
|
|
"mean_token_accuracy": 0.10994061902165413,
|
|
"num_tokens": 7499116.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 7.228064966201782,
|
|
"epoch": 0.43800604819042044,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004993198542754692,
|
|
"loss": 7.0671,
|
|
"mean_token_accuracy": 0.11247695907950402,
|
|
"num_tokens": 7515765.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 7.207043170928955,
|
|
"epoch": 0.43898156277436345,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004993143786625401,
|
|
"loss": 7.054,
|
|
"mean_token_accuracy": 0.11409633979201317,
|
|
"num_tokens": 7532074.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 7.118841218948364,
|
|
"epoch": 0.4399570773583065,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004993088811304092,
|
|
"loss": 6.8809,
|
|
"mean_token_accuracy": 0.1264127030968666,
|
|
"num_tokens": 7547704.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 7.175853538513183,
|
|
"epoch": 0.44093259194224954,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004993033616796139,
|
|
"loss": 7.004,
|
|
"mean_token_accuracy": 0.11399397403001785,
|
|
"num_tokens": 7563317.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 7.130023050308227,
|
|
"epoch": 0.44190810652619256,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004992978203106936,
|
|
"loss": 6.9969,
|
|
"mean_token_accuracy": 0.11112530082464218,
|
|
"num_tokens": 7580770.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 7.160404348373413,
|
|
"epoch": 0.4428836211101356,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004992922570241896,
|
|
"loss": 6.9677,
|
|
"mean_token_accuracy": 0.11711665615439415,
|
|
"num_tokens": 7598181.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 7.22194128036499,
|
|
"epoch": 0.44385913569407864,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004992866718206457,
|
|
"loss": 6.9795,
|
|
"mean_token_accuracy": 0.11797806024551391,
|
|
"num_tokens": 7613739.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 7.147187185287476,
|
|
"epoch": 0.44483465027802166,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004992810647006077,
|
|
"loss": 7.0605,
|
|
"mean_token_accuracy": 0.11274358704686165,
|
|
"num_tokens": 7629297.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 7.254347705841065,
|
|
"epoch": 0.4458101648619647,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004992754356646234,
|
|
"loss": 7.0438,
|
|
"mean_token_accuracy": 0.11101290956139565,
|
|
"num_tokens": 7645273.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 7.220282363891601,
|
|
"epoch": 0.4467856794459077,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004992697847132427,
|
|
"loss": 7.0027,
|
|
"mean_token_accuracy": 0.11301476284861564,
|
|
"num_tokens": 7661296.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 7.037471199035645,
|
|
"epoch": 0.44776119402985076,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000499264111847018,
|
|
"loss": 6.9902,
|
|
"mean_token_accuracy": 0.1159727394580841,
|
|
"num_tokens": 7678658.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 7.243689489364624,
|
|
"epoch": 0.4487367086137938,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004992584170665037,
|
|
"loss": 7.0281,
|
|
"mean_token_accuracy": 0.11064428091049194,
|
|
"num_tokens": 7693678.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 7.168780279159546,
|
|
"epoch": 0.4497122231977368,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000499252700372256,
|
|
"loss": 7.0243,
|
|
"mean_token_accuracy": 0.1131410151720047,
|
|
"num_tokens": 7709526.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 7.1957385540008545,
|
|
"epoch": 0.4506877377816798,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004992469617648337,
|
|
"loss": 6.9315,
|
|
"mean_token_accuracy": 0.114837134629488,
|
|
"num_tokens": 7725055.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 7.01217885017395,
|
|
"epoch": 0.4516632523656229,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004992412012447976,
|
|
"loss": 6.8246,
|
|
"mean_token_accuracy": 0.13443369641900063,
|
|
"num_tokens": 7742047.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 7.173456907272339,
|
|
"epoch": 0.4526387669495659,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004992354188127105,
|
|
"loss": 6.9924,
|
|
"mean_token_accuracy": 0.11481999903917313,
|
|
"num_tokens": 7758283.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 7.123820018768311,
|
|
"epoch": 0.4536142815335089,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004992296144691375,
|
|
"loss": 6.9428,
|
|
"mean_token_accuracy": 0.11760515496134757,
|
|
"num_tokens": 7774660.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 7.0660059452056885,
|
|
"epoch": 0.454589796117452,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004992237882146456,
|
|
"loss": 6.9425,
|
|
"mean_token_accuracy": 0.1202511541545391,
|
|
"num_tokens": 7792147.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 7.123804235458374,
|
|
"epoch": 0.455565310701395,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004992179400498044,
|
|
"loss": 6.8921,
|
|
"mean_token_accuracy": 0.11974749714136124,
|
|
"num_tokens": 7809021.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 7.169484567642212,
|
|
"epoch": 0.456540825285338,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004992120699751852,
|
|
"loss": 6.9622,
|
|
"mean_token_accuracy": 0.11758237481117248,
|
|
"num_tokens": 7825074.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 7.045835208892822,
|
|
"epoch": 0.45751633986928103,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004992061779913616,
|
|
"loss": 6.8805,
|
|
"mean_token_accuracy": 0.12335293963551522,
|
|
"num_tokens": 7843413.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 7.171706199645996,
|
|
"epoch": 0.4584918544532241,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004992002640989094,
|
|
"loss": 6.9833,
|
|
"mean_token_accuracy": 0.1096218541264534,
|
|
"num_tokens": 7859874.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 7.07806077003479,
|
|
"epoch": 0.4594673690371671,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004991943282984065,
|
|
"loss": 6.9123,
|
|
"mean_token_accuracy": 0.12037121206521988,
|
|
"num_tokens": 7877302.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 7.143974542617798,
|
|
"epoch": 0.46044288362111013,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004991883705904328,
|
|
"loss": 7.0312,
|
|
"mean_token_accuracy": 0.11270724460482598,
|
|
"num_tokens": 7893207.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 7.093389081954956,
|
|
"epoch": 0.46141839820505315,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004991823909755705,
|
|
"loss": 6.8767,
|
|
"mean_token_accuracy": 0.12375643104314804,
|
|
"num_tokens": 7910239.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 7.15909104347229,
|
|
"epoch": 0.4623939127889962,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004991763894544041,
|
|
"loss": 7.0037,
|
|
"mean_token_accuracy": 0.11504495963454246,
|
|
"num_tokens": 7928030.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 7.108256673812866,
|
|
"epoch": 0.46336942737293924,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004991703660275199,
|
|
"loss": 6.9586,
|
|
"mean_token_accuracy": 0.11801588907837868,
|
|
"num_tokens": 7943653.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 7.180034732818603,
|
|
"epoch": 0.46434494195688225,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004991643206955064,
|
|
"loss": 7.0141,
|
|
"mean_token_accuracy": 0.11293180361390114,
|
|
"num_tokens": 7960564.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 7.160725498199463,
|
|
"epoch": 0.46532045654082527,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004991582534589544,
|
|
"loss": 6.9894,
|
|
"mean_token_accuracy": 0.11833145692944527,
|
|
"num_tokens": 7978045.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 7.136874103546143,
|
|
"epoch": 0.46629597112476834,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004991521643184567,
|
|
"loss": 7.0206,
|
|
"mean_token_accuracy": 0.11553193107247353,
|
|
"num_tokens": 7995074.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 7.189276313781738,
|
|
"epoch": 0.46727148570871135,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004991460532746087,
|
|
"loss": 7.0168,
|
|
"mean_token_accuracy": 0.10875729024410248,
|
|
"num_tokens": 8011800.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 7.149040699005127,
|
|
"epoch": 0.46824700029265437,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000499139920328007,
|
|
"loss": 7.0033,
|
|
"mean_token_accuracy": 0.11477693393826485,
|
|
"num_tokens": 8028090.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 7.163629055023193,
|
|
"epoch": 0.4692225148765974,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004991337654792512,
|
|
"loss": 6.9504,
|
|
"mean_token_accuracy": 0.11679124534130096,
|
|
"num_tokens": 8044140.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 7.113048505783081,
|
|
"epoch": 0.47019802946054046,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004991275887289427,
|
|
"loss": 6.8872,
|
|
"mean_token_accuracy": 0.11912243366241455,
|
|
"num_tokens": 8060030.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 7.146053218841553,
|
|
"epoch": 0.47117354404448347,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004991213900776849,
|
|
"loss": 6.9467,
|
|
"mean_token_accuracy": 0.11257586479187012,
|
|
"num_tokens": 8075445.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 7.189834117889404,
|
|
"epoch": 0.4721490586284265,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004991151695260838,
|
|
"loss": 6.9366,
|
|
"mean_token_accuracy": 0.11540788263082505,
|
|
"num_tokens": 8093250.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 7.001761102676392,
|
|
"epoch": 0.4731245732123695,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499108927074747,
|
|
"loss": 6.8852,
|
|
"mean_token_accuracy": 0.13078338652849197,
|
|
"num_tokens": 8109615.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 7.098208570480347,
|
|
"epoch": 0.4741000877963126,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004991026627242846,
|
|
"loss": 6.9992,
|
|
"mean_token_accuracy": 0.1125226378440857,
|
|
"num_tokens": 8126591.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 7.1108416557312015,
|
|
"epoch": 0.4750756023802556,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004990963764753088,
|
|
"loss": 6.921,
|
|
"mean_token_accuracy": 0.11847438141703606,
|
|
"num_tokens": 8141360.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 7.174690628051758,
|
|
"epoch": 0.4760511169641986,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004990900683284337,
|
|
"loss": 7.0195,
|
|
"mean_token_accuracy": 0.11938564106822014,
|
|
"num_tokens": 8159688.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 7.0785839557647705,
|
|
"epoch": 0.4770266315481416,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004990837382842758,
|
|
"loss": 6.9716,
|
|
"mean_token_accuracy": 0.1167504571378231,
|
|
"num_tokens": 8176887.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 7.041645193099976,
|
|
"epoch": 0.4780021461320847,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004990773863434537,
|
|
"loss": 6.7927,
|
|
"mean_token_accuracy": 0.12661411613225937,
|
|
"num_tokens": 8193372.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 7.114064455032349,
|
|
"epoch": 0.4789776607160277,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004990710125065879,
|
|
"loss": 6.9984,
|
|
"mean_token_accuracy": 0.11455680429935455,
|
|
"num_tokens": 8209713.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 7.175408935546875,
|
|
"epoch": 0.4799531752999707,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004990646167743015,
|
|
"loss": 6.9945,
|
|
"mean_token_accuracy": 0.11661134958267212,
|
|
"num_tokens": 8226359.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 7.050619268417359,
|
|
"epoch": 0.48092868988391374,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004990581991472193,
|
|
"loss": 6.9652,
|
|
"mean_token_accuracy": 0.11523666009306907,
|
|
"num_tokens": 8243182.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 7.144983100891113,
|
|
"epoch": 0.4819042044678568,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004990517596259684,
|
|
"loss": 6.9658,
|
|
"mean_token_accuracy": 0.11646326631307602,
|
|
"num_tokens": 8259185.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 7.181390762329102,
|
|
"epoch": 0.4828797190517998,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004990452982111781,
|
|
"loss": 7.0372,
|
|
"mean_token_accuracy": 0.11256692185997963,
|
|
"num_tokens": 8275941.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 7.104955339431763,
|
|
"epoch": 0.48385523363574284,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004990388149034797,
|
|
"loss": 6.9584,
|
|
"mean_token_accuracy": 0.11884309574961663,
|
|
"num_tokens": 8292535.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 7.13123836517334,
|
|
"epoch": 0.48483074821968586,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.0004990323097035069,
|
|
"loss": 6.9307,
|
|
"mean_token_accuracy": 0.12303741350769996,
|
|
"num_tokens": 8310562.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 7.124442195892334,
|
|
"epoch": 0.48580626280362893,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004990257826118952,
|
|
"loss": 6.955,
|
|
"mean_token_accuracy": 0.10985321253538131,
|
|
"num_tokens": 8327241.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 7.076820802688599,
|
|
"epoch": 0.48678177738757195,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004990192336292824,
|
|
"loss": 6.895,
|
|
"mean_token_accuracy": 0.12121580988168716,
|
|
"num_tokens": 8343516.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.965652370452881,
|
|
"epoch": 0.48775729197151496,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004990126627563087,
|
|
"loss": 6.7601,
|
|
"mean_token_accuracy": 0.126581072807312,
|
|
"num_tokens": 8361809.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 7.016221237182617,
|
|
"epoch": 0.488732806555458,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004990060699936159,
|
|
"loss": 6.8245,
|
|
"mean_token_accuracy": 0.13123030737042427,
|
|
"num_tokens": 8378632.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 7.107016372680664,
|
|
"epoch": 0.48970832113940105,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004989994553418483,
|
|
"loss": 6.9758,
|
|
"mean_token_accuracy": 0.11068461835384369,
|
|
"num_tokens": 8396201.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 7.074777603149414,
|
|
"epoch": 0.49068383572334406,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004989928188016522,
|
|
"loss": 6.867,
|
|
"mean_token_accuracy": 0.12368853688240052,
|
|
"num_tokens": 8412851.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.954995393753052,
|
|
"epoch": 0.4916593503072871,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004989861603736762,
|
|
"loss": 6.7041,
|
|
"mean_token_accuracy": 0.1324455052614212,
|
|
"num_tokens": 8430026.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 7.097962379455566,
|
|
"epoch": 0.49263486489123015,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004989794800585711,
|
|
"loss": 6.929,
|
|
"mean_token_accuracy": 0.11492649167776108,
|
|
"num_tokens": 8446696.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 7.173016881942749,
|
|
"epoch": 0.49361037947517317,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004989727778569893,
|
|
"loss": 7.0136,
|
|
"mean_token_accuracy": 0.11455728113651276,
|
|
"num_tokens": 8464827.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 7.1289381980896,
|
|
"epoch": 0.4945858940591162,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004989660537695859,
|
|
"loss": 6.9686,
|
|
"mean_token_accuracy": 0.11377329379320145,
|
|
"num_tokens": 8480185.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 7.025111484527588,
|
|
"epoch": 0.4955614086430592,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.000498959307797018,
|
|
"loss": 6.8552,
|
|
"mean_token_accuracy": 0.12900338247418403,
|
|
"num_tokens": 8497511.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 7.081435346603394,
|
|
"epoch": 0.49653692322700227,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004989525399399447,
|
|
"loss": 6.9268,
|
|
"mean_token_accuracy": 0.1170234128832817,
|
|
"num_tokens": 8514394.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 7.128200626373291,
|
|
"epoch": 0.4975124378109453,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004989457501990275,
|
|
"loss": 6.926,
|
|
"mean_token_accuracy": 0.11452330276370049,
|
|
"num_tokens": 8531659.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 7.127494764328003,
|
|
"epoch": 0.4984879523948883,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004989389385749297,
|
|
"loss": 6.9749,
|
|
"mean_token_accuracy": 0.11825178265571594,
|
|
"num_tokens": 8547986.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 7.1158746719360355,
|
|
"epoch": 0.4994634669788313,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004989321050683169,
|
|
"loss": 6.9369,
|
|
"mean_token_accuracy": 0.11873245164752007,
|
|
"num_tokens": 8565021.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 7.071340703964234,
|
|
"epoch": 0.5004389815627743,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000498925249679857,
|
|
"loss": 6.9247,
|
|
"mean_token_accuracy": 0.11657378003001213,
|
|
"num_tokens": 8582135.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 7.039323854446411,
|
|
"epoch": 0.5014144961467174,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004989183724102196,
|
|
"loss": 6.9423,
|
|
"mean_token_accuracy": 0.12093305140733719,
|
|
"num_tokens": 8599946.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 7.159321308135986,
|
|
"epoch": 0.5023900107306605,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004989114732600771,
|
|
"loss": 6.9715,
|
|
"mean_token_accuracy": 0.11231624186038972,
|
|
"num_tokens": 8615831.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 7.071893787384033,
|
|
"epoch": 0.5033655253146034,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004989045522301033,
|
|
"loss": 6.8815,
|
|
"mean_token_accuracy": 0.11533841118216515,
|
|
"num_tokens": 8631886.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 7.124193572998047,
|
|
"epoch": 0.5043410398985465,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004988976093209747,
|
|
"loss": 6.9161,
|
|
"mean_token_accuracy": 0.1157707080245018,
|
|
"num_tokens": 8647520.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 7.062977647781372,
|
|
"epoch": 0.5053165544824895,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004988906445333698,
|
|
"loss": 6.8174,
|
|
"mean_token_accuracy": 0.12863881513476372,
|
|
"num_tokens": 8663995.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 7.071657800674439,
|
|
"epoch": 0.5062920690664325,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004988836578679691,
|
|
"loss": 6.8979,
|
|
"mean_token_accuracy": 0.11505225896835328,
|
|
"num_tokens": 8680201.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 7.0627415657043455,
|
|
"epoch": 0.5072675836503756,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004988766493254552,
|
|
"loss": 6.8753,
|
|
"mean_token_accuracy": 0.12590638771653176,
|
|
"num_tokens": 8696978.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 7.030006551742554,
|
|
"epoch": 0.5082430982343186,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.000498869618906513,
|
|
"loss": 6.9493,
|
|
"mean_token_accuracy": 0.11933218762278557,
|
|
"num_tokens": 8713335.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 7.1116760730743405,
|
|
"epoch": 0.5092186128182616,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004988625666118296,
|
|
"loss": 6.9083,
|
|
"mean_token_accuracy": 0.12209226936101913,
|
|
"num_tokens": 8730722.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 7.036452674865723,
|
|
"epoch": 0.5101941274022047,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000498855492442094,
|
|
"loss": 6.8433,
|
|
"mean_token_accuracy": 0.12098629549145698,
|
|
"num_tokens": 8747430.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 7.0425543785095215,
|
|
"epoch": 0.5111696419861477,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004988483963979975,
|
|
"loss": 6.9401,
|
|
"mean_token_accuracy": 0.11743757128715515,
|
|
"num_tokens": 8764817.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 7.143441200256348,
|
|
"epoch": 0.5121451565700907,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004988412784802336,
|
|
"loss": 6.9506,
|
|
"mean_token_accuracy": 0.115484768897295,
|
|
"num_tokens": 8780412.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 7.124314498901367,
|
|
"epoch": 0.5131206711540337,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004988341386894977,
|
|
"loss": 7.0179,
|
|
"mean_token_accuracy": 0.11527534648776054,
|
|
"num_tokens": 8795526.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 7.061612367630005,
|
|
"epoch": 0.5140961857379768,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004988269770264876,
|
|
"loss": 6.8028,
|
|
"mean_token_accuracy": 0.12942168042063712,
|
|
"num_tokens": 8813568.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 7.138605356216431,
|
|
"epoch": 0.5150717003219198,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004988197934919029,
|
|
"loss": 6.973,
|
|
"mean_token_accuracy": 0.11437882855534554,
|
|
"num_tokens": 8831807.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 7.109950590133667,
|
|
"epoch": 0.5160472149058628,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004988125880864458,
|
|
"loss": 6.9667,
|
|
"mean_token_accuracy": 0.11574166715145111,
|
|
"num_tokens": 8848875.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.932233238220215,
|
|
"epoch": 0.5170227294898059,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004988053608108203,
|
|
"loss": 6.6812,
|
|
"mean_token_accuracy": 0.12792798951268197,
|
|
"num_tokens": 8866317.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 7.056177854537964,
|
|
"epoch": 0.517998244073749,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004987981116657325,
|
|
"loss": 6.8404,
|
|
"mean_token_accuracy": 0.11871958747506142,
|
|
"num_tokens": 8882543.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 7.070244455337525,
|
|
"epoch": 0.5189737586576919,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004987908406518909,
|
|
"loss": 6.8537,
|
|
"mean_token_accuracy": 0.11586691364645958,
|
|
"num_tokens": 8898640.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 7.069869947433472,
|
|
"epoch": 0.519949273241635,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.000498783547770006,
|
|
"loss": 6.9469,
|
|
"mean_token_accuracy": 0.1181526742875576,
|
|
"num_tokens": 8914649.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 7.090184926986694,
|
|
"epoch": 0.5209247878255779,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987762330207903,
|
|
"loss": 6.9646,
|
|
"mean_token_accuracy": 0.1164260059595108,
|
|
"num_tokens": 8931585.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 7.000777053833008,
|
|
"epoch": 0.521900302409521,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004987688964049587,
|
|
"loss": 6.8651,
|
|
"mean_token_accuracy": 0.12208143025636672,
|
|
"num_tokens": 8948827.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.987697458267212,
|
|
"epoch": 0.5228758169934641,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.000498761537923228,
|
|
"loss": 6.8251,
|
|
"mean_token_accuracy": 0.1278835728764534,
|
|
"num_tokens": 8965680.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 7.12267837524414,
|
|
"epoch": 0.523851331577407,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004987541575763175,
|
|
"loss": 6.9497,
|
|
"mean_token_accuracy": 0.1097642183303833,
|
|
"num_tokens": 8982813.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 7.091774845123291,
|
|
"epoch": 0.5248268461613501,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.000498746755364948,
|
|
"loss": 6.9231,
|
|
"mean_token_accuracy": 0.11859667226672173,
|
|
"num_tokens": 9000497.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 7.050340270996093,
|
|
"epoch": 0.5258023607452932,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004987393312898431,
|
|
"loss": 6.8606,
|
|
"mean_token_accuracy": 0.11838527247309685,
|
|
"num_tokens": 9016195.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.987101221084595,
|
|
"epoch": 0.5267778753292361,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004987318853517282,
|
|
"loss": 6.8241,
|
|
"mean_token_accuracy": 0.1268692672252655,
|
|
"num_tokens": 9033295.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 7.055307531356812,
|
|
"epoch": 0.5277533899131792,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004987244175513308,
|
|
"loss": 6.9224,
|
|
"mean_token_accuracy": 0.11732791289687157,
|
|
"num_tokens": 9050725.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 7.064546012878418,
|
|
"epoch": 0.5287289044971223,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004987169278893807,
|
|
"loss": 6.8578,
|
|
"mean_token_accuracy": 0.12186623960733414,
|
|
"num_tokens": 9067842.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 7.077489614486694,
|
|
"epoch": 0.5297044190810652,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004987094163666098,
|
|
"loss": 6.8942,
|
|
"mean_token_accuracy": 0.11503920182585717,
|
|
"num_tokens": 9084602.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 7.005968332290649,
|
|
"epoch": 0.5306799336650083,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000498701882983752,
|
|
"loss": 6.8223,
|
|
"mean_token_accuracy": 0.12487047165632248,
|
|
"num_tokens": 9100530.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 7.117935609817505,
|
|
"epoch": 0.5316554482489513,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004986943277415435,
|
|
"loss": 6.9132,
|
|
"mean_token_accuracy": 0.12236565127968788,
|
|
"num_tokens": 9117304.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.957707405090332,
|
|
"epoch": 0.5326309628328944,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004986867506407225,
|
|
"loss": 6.8417,
|
|
"mean_token_accuracy": 0.13368361294269562,
|
|
"num_tokens": 9133974.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 7.037181806564331,
|
|
"epoch": 0.5336064774168374,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004986791516820295,
|
|
"loss": 6.8198,
|
|
"mean_token_accuracy": 0.12285887449979782,
|
|
"num_tokens": 9150600.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.951528167724609,
|
|
"epoch": 0.5345819920007804,
|
|
"grad_norm": 0.6796875,
|
|
"learning_rate": 0.000498671530866207,
|
|
"loss": 6.8322,
|
|
"mean_token_accuracy": 0.11800262033939361,
|
|
"num_tokens": 9167449.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 7.067008066177368,
|
|
"epoch": 0.5355575065847235,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004986638881939997,
|
|
"loss": 6.7545,
|
|
"mean_token_accuracy": 0.11939146891236305,
|
|
"num_tokens": 9184570.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 7.049952745437622,
|
|
"epoch": 0.5365330211686665,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004986562236661544,
|
|
"loss": 6.9376,
|
|
"mean_token_accuracy": 0.10987730026245117,
|
|
"num_tokens": 9200537.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 7.091079759597778,
|
|
"epoch": 0.5375085357526095,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.00049864853728342,
|
|
"loss": 6.8335,
|
|
"mean_token_accuracy": 0.12686262652277946,
|
|
"num_tokens": 9217252.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 7.022955989837646,
|
|
"epoch": 0.5384840503365526,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004986408290465476,
|
|
"loss": 6.8961,
|
|
"mean_token_accuracy": 0.11743080765008926,
|
|
"num_tokens": 9234108.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 7.026777029037476,
|
|
"epoch": 0.5394595649204955,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004986330989562906,
|
|
"loss": 6.7993,
|
|
"mean_token_accuracy": 0.12523364648222923,
|
|
"num_tokens": 9251017.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.946665239334107,
|
|
"epoch": 0.5404350795044386,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004986253470134042,
|
|
"loss": 6.7713,
|
|
"mean_token_accuracy": 0.12907842621207238,
|
|
"num_tokens": 9267922.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.906551218032837,
|
|
"epoch": 0.5414105940883817,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004986175732186459,
|
|
"loss": 6.7656,
|
|
"mean_token_accuracy": 0.13032744824886322,
|
|
"num_tokens": 9284954.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 7.107793951034546,
|
|
"epoch": 0.5423861086723246,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004986097775727752,
|
|
"loss": 6.8771,
|
|
"mean_token_accuracy": 0.12091203331947327,
|
|
"num_tokens": 9303306.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.967246198654175,
|
|
"epoch": 0.5433616232562677,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004986019600765541,
|
|
"loss": 6.7692,
|
|
"mean_token_accuracy": 0.12728926539421082,
|
|
"num_tokens": 9319754.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 7.039969730377197,
|
|
"epoch": 0.5443371378402108,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004985941207307462,
|
|
"loss": 6.8469,
|
|
"mean_token_accuracy": 0.12221098616719246,
|
|
"num_tokens": 9335736.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 7.011257457733154,
|
|
"epoch": 0.5453126524241537,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004985862595361179,
|
|
"loss": 6.8284,
|
|
"mean_token_accuracy": 0.12549932226538657,
|
|
"num_tokens": 9350435.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 7.0815362453460695,
|
|
"epoch": 0.5462881670080968,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004985783764934372,
|
|
"loss": 6.8864,
|
|
"mean_token_accuracy": 0.11744982227683068,
|
|
"num_tokens": 9367613.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.945830488204956,
|
|
"epoch": 0.5472636815920398,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004985704716034744,
|
|
"loss": 6.7813,
|
|
"mean_token_accuracy": 0.12381011322140693,
|
|
"num_tokens": 9385590.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 7.055399656295776,
|
|
"epoch": 0.5482391961759828,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985625448670019,
|
|
"loss": 6.906,
|
|
"mean_token_accuracy": 0.11092234849929809,
|
|
"num_tokens": 9403286.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 7.13700532913208,
|
|
"epoch": 0.5492147107599259,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004985545962847943,
|
|
"loss": 6.8965,
|
|
"mean_token_accuracy": 0.11672936603426934,
|
|
"num_tokens": 9419880.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 7.011618661880493,
|
|
"epoch": 0.5501902253438689,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004985466258576283,
|
|
"loss": 6.8482,
|
|
"mean_token_accuracy": 0.11878311857581139,
|
|
"num_tokens": 9436579.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 7.101798439025879,
|
|
"epoch": 0.5511657399278119,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004985386335862829,
|
|
"loss": 6.9297,
|
|
"mean_token_accuracy": 0.1124091014266014,
|
|
"num_tokens": 9452802.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 7.050691699981689,
|
|
"epoch": 0.552141254511755,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004985306194715387,
|
|
"loss": 6.9317,
|
|
"mean_token_accuracy": 0.11563575491309167,
|
|
"num_tokens": 9468297.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 7.097681140899658,
|
|
"epoch": 0.553116769095698,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004985225835141792,
|
|
"loss": 6.9387,
|
|
"mean_token_accuracy": 0.11293896734714508,
|
|
"num_tokens": 9484954.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 7.126778602600098,
|
|
"epoch": 0.554092283679641,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004985145257149895,
|
|
"loss": 6.9881,
|
|
"mean_token_accuracy": 0.11180973276495934,
|
|
"num_tokens": 9502211.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 7.063410711288452,
|
|
"epoch": 0.555067798263584,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004985064460747569,
|
|
"loss": 6.8693,
|
|
"mean_token_accuracy": 0.1153719663619995,
|
|
"num_tokens": 9518103.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.979598569869995,
|
|
"epoch": 0.5560433128475271,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000498498344594271,
|
|
"loss": 6.7968,
|
|
"mean_token_accuracy": 0.11760495081543923,
|
|
"num_tokens": 9534155.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.968579816818237,
|
|
"epoch": 0.5570188274314701,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004984902212743234,
|
|
"loss": 6.7948,
|
|
"mean_token_accuracy": 0.1295493483543396,
|
|
"num_tokens": 9549972.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.97542085647583,
|
|
"epoch": 0.5579943420154131,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004984820761157079,
|
|
"loss": 6.7089,
|
|
"mean_token_accuracy": 0.13295939341187477,
|
|
"num_tokens": 9567306.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 7.0255824565887455,
|
|
"epoch": 0.5589698565993562,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004984739091192205,
|
|
"loss": 6.9158,
|
|
"mean_token_accuracy": 0.11534090414643287,
|
|
"num_tokens": 9583488.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.914848470687867,
|
|
"epoch": 0.5599453711832992,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004984657202856592,
|
|
"loss": 6.7123,
|
|
"mean_token_accuracy": 0.13162725046277046,
|
|
"num_tokens": 9600030.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.918585586547851,
|
|
"epoch": 0.5609208857672422,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000498457509615824,
|
|
"loss": 6.8336,
|
|
"mean_token_accuracy": 0.12309335544705391,
|
|
"num_tokens": 9615791.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 7.134072399139404,
|
|
"epoch": 0.5618964003511853,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004984492771105175,
|
|
"loss": 6.9109,
|
|
"mean_token_accuracy": 0.11490531265735626,
|
|
"num_tokens": 9630955.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.908839178085327,
|
|
"epoch": 0.5628719149351282,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004984410227705439,
|
|
"loss": 6.8073,
|
|
"mean_token_accuracy": 0.12970414906740188,
|
|
"num_tokens": 9647743.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.939614868164062,
|
|
"epoch": 0.5638474295190713,
|
|
"grad_norm": 0.6875,
|
|
"learning_rate": 0.0004984327465967101,
|
|
"loss": 6.7516,
|
|
"mean_token_accuracy": 0.1281515948474407,
|
|
"num_tokens": 9665495.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 7.021985769271851,
|
|
"epoch": 0.5648229441030144,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 0.0004984244485898246,
|
|
"loss": 6.7867,
|
|
"mean_token_accuracy": 0.12167991697788239,
|
|
"num_tokens": 9683489.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.83103346824646,
|
|
"epoch": 0.5657984586869573,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004984161287506982,
|
|
"loss": 6.7093,
|
|
"mean_token_accuracy": 0.14059354737401009,
|
|
"num_tokens": 9700491.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 7.091452789306641,
|
|
"epoch": 0.5667739732709004,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000498407787080144,
|
|
"loss": 6.8794,
|
|
"mean_token_accuracy": 0.11457787230610847,
|
|
"num_tokens": 9715694.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 7.039381980895996,
|
|
"epoch": 0.5677494878548435,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000498399423578977,
|
|
"loss": 6.9421,
|
|
"mean_token_accuracy": 0.11171695366501808,
|
|
"num_tokens": 9731317.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 7.12079553604126,
|
|
"epoch": 0.5687250024387864,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004983910382480146,
|
|
"loss": 6.9078,
|
|
"mean_token_accuracy": 0.1148095577955246,
|
|
"num_tokens": 9747928.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 7.026090621948242,
|
|
"epoch": 0.5697005170227295,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004983826310880762,
|
|
"loss": 6.8298,
|
|
"mean_token_accuracy": 0.11673593521118164,
|
|
"num_tokens": 9765454.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 7.075426530838013,
|
|
"epoch": 0.5706760316066726,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004983742020999832,
|
|
"loss": 6.9054,
|
|
"mean_token_accuracy": 0.11131169497966767,
|
|
"num_tokens": 9782255.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.952255010604858,
|
|
"epoch": 0.5716515461906155,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004983657512845593,
|
|
"loss": 6.7133,
|
|
"mean_token_accuracy": 0.13050210028886794,
|
|
"num_tokens": 9798680.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.985753011703491,
|
|
"epoch": 0.5726270607745586,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004983572786426302,
|
|
"loss": 6.8772,
|
|
"mean_token_accuracy": 0.11791479736566543,
|
|
"num_tokens": 9813955.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.933854722976685,
|
|
"epoch": 0.5736025753585016,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004983487841750239,
|
|
"loss": 6.7597,
|
|
"mean_token_accuracy": 0.12929214611649514,
|
|
"num_tokens": 9830692.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 7.039998626708984,
|
|
"epoch": 0.5745780899424446,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004983402678825705,
|
|
"loss": 6.8655,
|
|
"mean_token_accuracy": 0.11815279945731164,
|
|
"num_tokens": 9848825.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 7.019101667404175,
|
|
"epoch": 0.5755536045263877,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004983317297661021,
|
|
"loss": 6.8691,
|
|
"mean_token_accuracy": 0.11934498324990273,
|
|
"num_tokens": 9865802.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 7.064760398864746,
|
|
"epoch": 0.5765291191103307,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004983231698264531,
|
|
"loss": 6.9049,
|
|
"mean_token_accuracy": 0.1151661865413189,
|
|
"num_tokens": 9883540.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 7.02940731048584,
|
|
"epoch": 0.5775046336942737,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004983145880644597,
|
|
"loss": 6.8455,
|
|
"mean_token_accuracy": 0.11909216940402985,
|
|
"num_tokens": 9897724.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 7.042118644714355,
|
|
"epoch": 0.5784801482782168,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004983059844809608,
|
|
"loss": 6.7889,
|
|
"mean_token_accuracy": 0.12654381543397902,
|
|
"num_tokens": 9914710.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.939293432235718,
|
|
"epoch": 0.5794556628621598,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0004982973590767969,
|
|
"loss": 6.9121,
|
|
"mean_token_accuracy": 0.1200237326323986,
|
|
"num_tokens": 9932362.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.96052393913269,
|
|
"epoch": 0.5804311774461028,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000498288711852811,
|
|
"loss": 6.7056,
|
|
"mean_token_accuracy": 0.12614807710051537,
|
|
"num_tokens": 9949409.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.974116563796997,
|
|
"epoch": 0.5814066920300458,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000498280042809848,
|
|
"loss": 6.8599,
|
|
"mean_token_accuracy": 0.118405020236969,
|
|
"num_tokens": 9967467.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 7.0648046970367435,
|
|
"epoch": 0.5823822066139889,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004982713519487549,
|
|
"loss": 6.7921,
|
|
"mean_token_accuracy": 0.12451607063412666,
|
|
"num_tokens": 9983082.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.94227089881897,
|
|
"epoch": 0.5833577211979319,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004982626392703812,
|
|
"loss": 6.8631,
|
|
"mean_token_accuracy": 0.121035036444664,
|
|
"num_tokens": 10000046.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 7.048401880264282,
|
|
"epoch": 0.5843332357818749,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000498253904775578,
|
|
"loss": 6.8047,
|
|
"mean_token_accuracy": 0.11983777582645416,
|
|
"num_tokens": 10014674.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.87097806930542,
|
|
"epoch": 0.585308750365818,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004982451484651988,
|
|
"loss": 6.6905,
|
|
"mean_token_accuracy": 0.12775660678744316,
|
|
"num_tokens": 10030647.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.585308750365818,
|
|
"eval_entropy": 6.702175416178135,
|
|
"eval_loss": 6.8473429679870605,
|
|
"eval_mean_token_accuracy": 0.12242404828310818,
|
|
"eval_num_tokens": 10030647.0,
|
|
"eval_runtime": 12.218,
|
|
"eval_samples_per_second": 1356.763,
|
|
"eval_steps_per_second": 169.667,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 51250,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 2013648974807040.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|