18068 lines
494 KiB
JSON
18068 lines
494 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.7517540928833946,
|
|
"eval_steps": 3000,
|
|
"global_step": 9000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.69201889038086,
|
|
"epoch": 0.000417641162712997,
|
|
"grad_norm": 14.0,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8059,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 9371.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.691970920562744,
|
|
"epoch": 0.000835282325425994,
|
|
"grad_norm": 12.875,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7231,
|
|
"mean_token_accuracy": 0.0003899427130818367,
|
|
"num_tokens": 18155.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.691130447387696,
|
|
"epoch": 0.001252923488138991,
|
|
"grad_norm": 9.125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.4903,
|
|
"mean_token_accuracy": 0.024901279783807694,
|
|
"num_tokens": 27776.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.681210708618163,
|
|
"epoch": 0.001670564650851988,
|
|
"grad_norm": 6.34375,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.1859,
|
|
"mean_token_accuracy": 0.04129145070910454,
|
|
"num_tokens": 37166.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.632552528381348,
|
|
"epoch": 0.002088205813564985,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 9.8516,
|
|
"mean_token_accuracy": 0.04321358092129231,
|
|
"num_tokens": 46667.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.590499591827392,
|
|
"epoch": 0.002505846976277982,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.6786,
|
|
"mean_token_accuracy": 0.04258152581751347,
|
|
"num_tokens": 55738.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.598013877868652,
|
|
"epoch": 0.002923488138990979,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.6768,
|
|
"mean_token_accuracy": 0.04020156487822533,
|
|
"num_tokens": 65303.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.575642108917236,
|
|
"epoch": 0.003341129301703976,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.5538,
|
|
"mean_token_accuracy": 0.044753269851207735,
|
|
"num_tokens": 74876.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.562861919403076,
|
|
"epoch": 0.003758770464416973,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.515,
|
|
"mean_token_accuracy": 0.04800709597766399,
|
|
"num_tokens": 84683.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.554056072235108,
|
|
"epoch": 0.00417641162712997,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.4698,
|
|
"mean_token_accuracy": 0.045513217151165006,
|
|
"num_tokens": 94511.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.544468021392822,
|
|
"epoch": 0.004594052789842967,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.3749,
|
|
"mean_token_accuracy": 0.056402480229735374,
|
|
"num_tokens": 103820.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.37349443435669,
|
|
"epoch": 0.005011693952555964,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.2941,
|
|
"mean_token_accuracy": 0.059941830858588216,
|
|
"num_tokens": 112398.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.357733345031738,
|
|
"epoch": 0.005429335115268961,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.2329,
|
|
"mean_token_accuracy": 0.058718277141451836,
|
|
"num_tokens": 121167.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.474106597900391,
|
|
"epoch": 0.005846976277981958,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.1346,
|
|
"mean_token_accuracy": 0.05946669317781925,
|
|
"num_tokens": 129399.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.413960456848145,
|
|
"epoch": 0.006264617440694955,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.0661,
|
|
"mean_token_accuracy": 0.05361619554460049,
|
|
"num_tokens": 138512.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.455136489868163,
|
|
"epoch": 0.006682258603407952,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.027,
|
|
"mean_token_accuracy": 0.058849292993545535,
|
|
"num_tokens": 147712.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.360787677764893,
|
|
"epoch": 0.007099899766120949,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 8.8732,
|
|
"mean_token_accuracy": 0.06726518124341965,
|
|
"num_tokens": 156759.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.307044124603271,
|
|
"epoch": 0.007517540928833946,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.7741,
|
|
"mean_token_accuracy": 0.06508033163845539,
|
|
"num_tokens": 166395.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.328545475006104,
|
|
"epoch": 0.007935182091546943,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.6533,
|
|
"mean_token_accuracy": 0.06614198088645935,
|
|
"num_tokens": 174739.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.214155673980713,
|
|
"epoch": 0.00835282325425994,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.4788,
|
|
"mean_token_accuracy": 0.07055597789585591,
|
|
"num_tokens": 183010.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.180351448059081,
|
|
"epoch": 0.008770464416972937,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.4699,
|
|
"mean_token_accuracy": 0.06824311949312686,
|
|
"num_tokens": 192589.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.146885681152344,
|
|
"epoch": 0.009188105579685933,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.3311,
|
|
"mean_token_accuracy": 0.07665134817361832,
|
|
"num_tokens": 201638.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.078996276855468,
|
|
"epoch": 0.00960574674239893,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.2014,
|
|
"mean_token_accuracy": 0.07701764479279519,
|
|
"num_tokens": 209862.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.014488697052002,
|
|
"epoch": 0.010023387905111928,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.2213,
|
|
"mean_token_accuracy": 0.0736879549920559,
|
|
"num_tokens": 218897.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.855342769622803,
|
|
"epoch": 0.010441029067824925,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.1073,
|
|
"mean_token_accuracy": 0.07421992868185043,
|
|
"num_tokens": 227682.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.788538360595703,
|
|
"epoch": 0.010858670230537921,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.9192,
|
|
"mean_token_accuracy": 0.07975538857281209,
|
|
"num_tokens": 236170.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.63622751235962,
|
|
"epoch": 0.011276311393250919,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.8973,
|
|
"mean_token_accuracy": 0.07390527278184891,
|
|
"num_tokens": 245710.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.484860038757324,
|
|
"epoch": 0.011693952555963916,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.7354,
|
|
"mean_token_accuracy": 0.07942189872264863,
|
|
"num_tokens": 254751.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.272345066070557,
|
|
"epoch": 0.012111593718676913,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.6203,
|
|
"mean_token_accuracy": 0.08180429227650166,
|
|
"num_tokens": 264210.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.060223388671876,
|
|
"epoch": 0.01252923488138991,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.5703,
|
|
"mean_token_accuracy": 0.0850793406367302,
|
|
"num_tokens": 272944.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.841773128509521,
|
|
"epoch": 0.012946876044102907,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.4347,
|
|
"mean_token_accuracy": 0.08460724949836732,
|
|
"num_tokens": 281311.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.642339897155761,
|
|
"epoch": 0.013364517206815904,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.3341,
|
|
"mean_token_accuracy": 0.08855588883161544,
|
|
"num_tokens": 289701.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.47796277999878,
|
|
"epoch": 0.013782158369528901,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.3955,
|
|
"mean_token_accuracy": 0.08427253440022468,
|
|
"num_tokens": 299459.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.328273963928222,
|
|
"epoch": 0.014199799532241897,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.3601,
|
|
"mean_token_accuracy": 0.08567551225423813,
|
|
"num_tokens": 309343.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.229494094848633,
|
|
"epoch": 0.014617440694954895,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.3237,
|
|
"mean_token_accuracy": 0.07697097286581993,
|
|
"num_tokens": 318840.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.055557680130004,
|
|
"epoch": 0.015035081857667892,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.1265,
|
|
"mean_token_accuracy": 0.08917100429534912,
|
|
"num_tokens": 328689.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.041841316223145,
|
|
"epoch": 0.01545272302038089,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.2541,
|
|
"mean_token_accuracy": 0.08379325792193412,
|
|
"num_tokens": 338209.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.833249950408936,
|
|
"epoch": 0.015870364183093885,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.1264,
|
|
"mean_token_accuracy": 0.08980818912386894,
|
|
"num_tokens": 347270.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.8264617919921875,
|
|
"epoch": 0.016288005345806884,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.1514,
|
|
"mean_token_accuracy": 0.09062685966491699,
|
|
"num_tokens": 356366.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.812281751632691,
|
|
"epoch": 0.01670564650851988,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.1091,
|
|
"mean_token_accuracy": 0.08819653950631619,
|
|
"num_tokens": 365980.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.708438777923584,
|
|
"epoch": 0.017123287671232876,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.0677,
|
|
"mean_token_accuracy": 0.09280576929450035,
|
|
"num_tokens": 374591.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.678690814971924,
|
|
"epoch": 0.017540928833945875,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.0653,
|
|
"mean_token_accuracy": 0.09315739646553993,
|
|
"num_tokens": 383250.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.6943333625793455,
|
|
"epoch": 0.01795856999665887,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.9805,
|
|
"mean_token_accuracy": 0.08931331932544709,
|
|
"num_tokens": 391502.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.598643970489502,
|
|
"epoch": 0.018376211159371866,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.901,
|
|
"mean_token_accuracy": 0.09360511749982833,
|
|
"num_tokens": 400225.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.616733074188232,
|
|
"epoch": 0.018793852322084866,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.1181,
|
|
"mean_token_accuracy": 0.0864988811314106,
|
|
"num_tokens": 410008.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.581192922592163,
|
|
"epoch": 0.01921149348479786,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.0294,
|
|
"mean_token_accuracy": 0.09357244744896889,
|
|
"num_tokens": 418979.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.522384977340698,
|
|
"epoch": 0.01962913464751086,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.0167,
|
|
"mean_token_accuracy": 0.0893492966890335,
|
|
"num_tokens": 428139.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.554843139648438,
|
|
"epoch": 0.020046775810223856,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.9224,
|
|
"mean_token_accuracy": 0.09392503276467323,
|
|
"num_tokens": 437113.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.548024368286133,
|
|
"epoch": 0.020464416972936852,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.1405,
|
|
"mean_token_accuracy": 0.09140172526240349,
|
|
"num_tokens": 446879.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.432359743118286,
|
|
"epoch": 0.02088205813564985,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.0354,
|
|
"mean_token_accuracy": 0.08848990350961686,
|
|
"num_tokens": 456362.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.506717348098755,
|
|
"epoch": 0.021299699298362847,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.8268,
|
|
"mean_token_accuracy": 0.09714673981070518,
|
|
"num_tokens": 464930.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.499800443649292,
|
|
"epoch": 0.021717340461075842,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.0129,
|
|
"mean_token_accuracy": 0.08504997566342354,
|
|
"num_tokens": 474303.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.423412275314331,
|
|
"epoch": 0.02213498162378884,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.0134,
|
|
"mean_token_accuracy": 0.08980379328131675,
|
|
"num_tokens": 483750.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.405795764923096,
|
|
"epoch": 0.022552622786501837,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.9026,
|
|
"mean_token_accuracy": 0.09115351662039757,
|
|
"num_tokens": 493325.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.417911052703857,
|
|
"epoch": 0.022970263949214833,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.8963,
|
|
"mean_token_accuracy": 0.08686210587620735,
|
|
"num_tokens": 501907.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.393596076965332,
|
|
"epoch": 0.023387905111927832,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.9521,
|
|
"mean_token_accuracy": 0.09035036042332649,
|
|
"num_tokens": 511522.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.3399505615234375,
|
|
"epoch": 0.023805546274640828,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.8929,
|
|
"mean_token_accuracy": 0.09046279191970825,
|
|
"num_tokens": 521287.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.400482702255249,
|
|
"epoch": 0.024223187437353827,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.9731,
|
|
"mean_token_accuracy": 0.0870087906718254,
|
|
"num_tokens": 530631.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.305219221115112,
|
|
"epoch": 0.024640828600066823,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.8415,
|
|
"mean_token_accuracy": 0.10079794302582741,
|
|
"num_tokens": 540386.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.363999080657959,
|
|
"epoch": 0.02505846976277982,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.9284,
|
|
"mean_token_accuracy": 0.09086689502000808,
|
|
"num_tokens": 550121.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.154841661453247,
|
|
"epoch": 0.025476110925492818,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.7948,
|
|
"mean_token_accuracy": 0.09512273818254471,
|
|
"num_tokens": 559460.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.282400894165039,
|
|
"epoch": 0.025893752088205813,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.7419,
|
|
"mean_token_accuracy": 0.10121037140488624,
|
|
"num_tokens": 568392.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.279255533218384,
|
|
"epoch": 0.02631139325091881,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.8451,
|
|
"mean_token_accuracy": 0.09345789849758149,
|
|
"num_tokens": 578248.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.27221417427063,
|
|
"epoch": 0.026729034413631808,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.9144,
|
|
"mean_token_accuracy": 0.09365530461072921,
|
|
"num_tokens": 588164.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.197469997406006,
|
|
"epoch": 0.027146675576344804,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.8342,
|
|
"mean_token_accuracy": 0.09261370748281479,
|
|
"num_tokens": 598715.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.274549579620361,
|
|
"epoch": 0.027564316739057803,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.7664,
|
|
"mean_token_accuracy": 0.09446420967578888,
|
|
"num_tokens": 606939.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.175267553329467,
|
|
"epoch": 0.0279819579017708,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8544,
|
|
"mean_token_accuracy": 0.0952809251844883,
|
|
"num_tokens": 615803.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.135472536087036,
|
|
"epoch": 0.028399599064483794,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.7134,
|
|
"mean_token_accuracy": 0.0974463865160942,
|
|
"num_tokens": 624730.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.221632957458496,
|
|
"epoch": 0.028817240227196794,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.8097,
|
|
"mean_token_accuracy": 0.09591780230402946,
|
|
"num_tokens": 634082.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.172988319396973,
|
|
"epoch": 0.02923488138990979,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.7906,
|
|
"mean_token_accuracy": 0.09750410541892052,
|
|
"num_tokens": 643367.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.093995666503906,
|
|
"epoch": 0.029652522552622785,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.6148,
|
|
"mean_token_accuracy": 0.10173115655779838,
|
|
"num_tokens": 651861.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.0821737289428714,
|
|
"epoch": 0.030070163715335784,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.7571,
|
|
"mean_token_accuracy": 0.0948550172150135,
|
|
"num_tokens": 661064.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.153480052947998,
|
|
"epoch": 0.03048780487804878,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.7307,
|
|
"mean_token_accuracy": 0.10703616738319396,
|
|
"num_tokens": 669299.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.030750942230225,
|
|
"epoch": 0.03090544604076178,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.8063,
|
|
"mean_token_accuracy": 0.09672270379960538,
|
|
"num_tokens": 678631.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.175200462341309,
|
|
"epoch": 0.03132308720347477,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.7998,
|
|
"mean_token_accuracy": 0.09658469036221504,
|
|
"num_tokens": 688511.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.161194705963135,
|
|
"epoch": 0.03174072836618777,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.7375,
|
|
"mean_token_accuracy": 0.09603499248623848,
|
|
"num_tokens": 697956.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.05234808921814,
|
|
"epoch": 0.03215836952890077,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.6413,
|
|
"mean_token_accuracy": 0.10262225940823555,
|
|
"num_tokens": 706779.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.056643486022949,
|
|
"epoch": 0.03257601069161377,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.6241,
|
|
"mean_token_accuracy": 0.10087177231907844,
|
|
"num_tokens": 715749.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.9739141941070555,
|
|
"epoch": 0.03299365185432676,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.6158,
|
|
"mean_token_accuracy": 0.09956808760762215,
|
|
"num_tokens": 724756.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.9772045612335205,
|
|
"epoch": 0.03341129301703976,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.6336,
|
|
"mean_token_accuracy": 0.09985274448990822,
|
|
"num_tokens": 733288.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.113308477401733,
|
|
"epoch": 0.03382893417975276,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.7437,
|
|
"mean_token_accuracy": 0.09781895428895951,
|
|
"num_tokens": 741629.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.011357355117798,
|
|
"epoch": 0.03424657534246575,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.6754,
|
|
"mean_token_accuracy": 0.10406573414802552,
|
|
"num_tokens": 751336.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.130186605453491,
|
|
"epoch": 0.03466421650517875,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.7513,
|
|
"mean_token_accuracy": 0.09732639789581299,
|
|
"num_tokens": 759725.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.069876623153687,
|
|
"epoch": 0.03508185766789175,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.7657,
|
|
"mean_token_accuracy": 0.09712367430329323,
|
|
"num_tokens": 769752.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.016468811035156,
|
|
"epoch": 0.03549949883060474,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.6428,
|
|
"mean_token_accuracy": 0.10409499630331993,
|
|
"num_tokens": 779124.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.8530608177185055,
|
|
"epoch": 0.03591713999331774,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.602,
|
|
"mean_token_accuracy": 0.10306296646595,
|
|
"num_tokens": 788892.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.865619564056397,
|
|
"epoch": 0.03633478115603074,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.5647,
|
|
"mean_token_accuracy": 0.10568981394171714,
|
|
"num_tokens": 798265.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.853310251235962,
|
|
"epoch": 0.03675242231874373,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.5224,
|
|
"mean_token_accuracy": 0.10847331061959267,
|
|
"num_tokens": 806896.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.006761074066162,
|
|
"epoch": 0.03717006348145673,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.5879,
|
|
"mean_token_accuracy": 0.10766485631465912,
|
|
"num_tokens": 815540.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.854085683822632,
|
|
"epoch": 0.03758770464416973,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.6495,
|
|
"mean_token_accuracy": 0.10323781818151474,
|
|
"num_tokens": 824555.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.022783946990967,
|
|
"epoch": 0.03800534580688272,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.6988,
|
|
"mean_token_accuracy": 0.10127760544419288,
|
|
"num_tokens": 833414.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.811462020874023,
|
|
"epoch": 0.03842298696959572,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.5436,
|
|
"mean_token_accuracy": 0.11053832620382309,
|
|
"num_tokens": 842644.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.894090795516968,
|
|
"epoch": 0.03884062813230872,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.5682,
|
|
"mean_token_accuracy": 0.10382608100771903,
|
|
"num_tokens": 851786.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.843556022644043,
|
|
"epoch": 0.03925826929502172,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.6229,
|
|
"mean_token_accuracy": 0.10601722747087479,
|
|
"num_tokens": 861508.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.869661664962768,
|
|
"epoch": 0.03967591045773471,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.4919,
|
|
"mean_token_accuracy": 0.10929096192121505,
|
|
"num_tokens": 870433.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.916244745254517,
|
|
"epoch": 0.04009355162044771,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6124,
|
|
"mean_token_accuracy": 0.1070750541985035,
|
|
"num_tokens": 879059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.885466527938843,
|
|
"epoch": 0.04051119278316071,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.6607,
|
|
"mean_token_accuracy": 0.10065596923232079,
|
|
"num_tokens": 888009.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.7803881645202635,
|
|
"epoch": 0.040928833945873704,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.529,
|
|
"mean_token_accuracy": 0.10448121652007103,
|
|
"num_tokens": 897335.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.953722333908081,
|
|
"epoch": 0.0413464751085867,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.5241,
|
|
"mean_token_accuracy": 0.10960079357028008,
|
|
"num_tokens": 905802.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.839751958847046,
|
|
"epoch": 0.0417641162712997,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.5288,
|
|
"mean_token_accuracy": 0.10939614027738571,
|
|
"num_tokens": 914836.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.722894287109375,
|
|
"epoch": 0.042181757434012694,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.4752,
|
|
"mean_token_accuracy": 0.11474435329437256,
|
|
"num_tokens": 924254.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.799596691131592,
|
|
"epoch": 0.04259939859672569,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.5715,
|
|
"mean_token_accuracy": 0.10900455489754676,
|
|
"num_tokens": 933841.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.8436116695404055,
|
|
"epoch": 0.04301703975943869,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.6245,
|
|
"mean_token_accuracy": 0.10766134932637214,
|
|
"num_tokens": 943304.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.756516551971435,
|
|
"epoch": 0.043434680922151685,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.4616,
|
|
"mean_token_accuracy": 0.11000765487551689,
|
|
"num_tokens": 952915.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.807320642471313,
|
|
"epoch": 0.043852322084864684,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.5169,
|
|
"mean_token_accuracy": 0.11124896109104157,
|
|
"num_tokens": 962752.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.805405187606811,
|
|
"epoch": 0.04426996324757768,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.5271,
|
|
"mean_token_accuracy": 0.09916252493858338,
|
|
"num_tokens": 971240.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.747521448135376,
|
|
"epoch": 0.044687604410290675,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.5801,
|
|
"mean_token_accuracy": 0.10155974254012108,
|
|
"num_tokens": 981391.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.818302583694458,
|
|
"epoch": 0.045105245573003674,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.5666,
|
|
"mean_token_accuracy": 0.1143165647983551,
|
|
"num_tokens": 990551.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.7388129234313965,
|
|
"epoch": 0.045522886735716674,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.4962,
|
|
"mean_token_accuracy": 0.11189664974808693,
|
|
"num_tokens": 999593.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.785442161560058,
|
|
"epoch": 0.045940527898429666,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.5789,
|
|
"mean_token_accuracy": 0.10544709712266923,
|
|
"num_tokens": 1008785.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.757883024215698,
|
|
"epoch": 0.046358169061142665,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5604,
|
|
"mean_token_accuracy": 0.10769657045602798,
|
|
"num_tokens": 1016815.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.758020496368408,
|
|
"epoch": 0.046775810223855664,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.4344,
|
|
"mean_token_accuracy": 0.11475159376859664,
|
|
"num_tokens": 1026182.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.683844518661499,
|
|
"epoch": 0.04719345138656866,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.3739,
|
|
"mean_token_accuracy": 0.11326156556606293,
|
|
"num_tokens": 1034032.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.730586194992066,
|
|
"epoch": 0.047611092549281656,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.5731,
|
|
"mean_token_accuracy": 0.10969387739896774,
|
|
"num_tokens": 1043493.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.746386432647705,
|
|
"epoch": 0.048028733711994655,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.4697,
|
|
"mean_token_accuracy": 0.11479877978563309,
|
|
"num_tokens": 1052989.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.649836444854737,
|
|
"epoch": 0.048446374874707654,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.4517,
|
|
"mean_token_accuracy": 0.11029219925403595,
|
|
"num_tokens": 1061803.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.773694610595703,
|
|
"epoch": 0.048864016037420646,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.5561,
|
|
"mean_token_accuracy": 0.10948128178715706,
|
|
"num_tokens": 1071227.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.727704048156738,
|
|
"epoch": 0.049281657200133645,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.5617,
|
|
"mean_token_accuracy": 0.11164849177002907,
|
|
"num_tokens": 1080082.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.657727670669556,
|
|
"epoch": 0.049699298362846644,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.3975,
|
|
"mean_token_accuracy": 0.11562075838446617,
|
|
"num_tokens": 1089750.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.567789506912232,
|
|
"epoch": 0.05011693952555964,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.3956,
|
|
"mean_token_accuracy": 0.11055527701973915,
|
|
"num_tokens": 1098691.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.651774883270264,
|
|
"epoch": 0.050534580688272636,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.4191,
|
|
"mean_token_accuracy": 0.11506491899490356,
|
|
"num_tokens": 1107602.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.595056581497192,
|
|
"epoch": 0.050952221850985635,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.3422,
|
|
"mean_token_accuracy": 0.11736676096916199,
|
|
"num_tokens": 1116426.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.746117305755615,
|
|
"epoch": 0.05136986301369863,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.5262,
|
|
"mean_token_accuracy": 0.11227416917681694,
|
|
"num_tokens": 1126221.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.536876583099366,
|
|
"epoch": 0.051787504176411626,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.401,
|
|
"mean_token_accuracy": 0.11846380457282066,
|
|
"num_tokens": 1135662.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.675752067565918,
|
|
"epoch": 0.052205145339124626,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5017,
|
|
"mean_token_accuracy": 0.11206841841340065,
|
|
"num_tokens": 1143963.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.615093946456909,
|
|
"epoch": 0.05262278650183762,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.3808,
|
|
"mean_token_accuracy": 0.12234973758459092,
|
|
"num_tokens": 1152470.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.61521053314209,
|
|
"epoch": 0.05304042766455062,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.3481,
|
|
"mean_token_accuracy": 0.11505335196852684,
|
|
"num_tokens": 1161257.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.679902791976929,
|
|
"epoch": 0.053458068827263616,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.4666,
|
|
"mean_token_accuracy": 0.11135088875889779,
|
|
"num_tokens": 1170969.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.6380119800567625,
|
|
"epoch": 0.053875709989976615,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.6069,
|
|
"mean_token_accuracy": 0.11080317497253418,
|
|
"num_tokens": 1181127.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.6212114810943605,
|
|
"epoch": 0.05429335115268961,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4079,
|
|
"mean_token_accuracy": 0.11520254909992218,
|
|
"num_tokens": 1190260.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.626252603530884,
|
|
"epoch": 0.05471099231540261,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.483,
|
|
"mean_token_accuracy": 0.11253710016608238,
|
|
"num_tokens": 1200013.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.691232061386108,
|
|
"epoch": 0.055128633478115606,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.42,
|
|
"mean_token_accuracy": 0.1188363939523697,
|
|
"num_tokens": 1209239.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.489693546295166,
|
|
"epoch": 0.0555462746408286,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.3535,
|
|
"mean_token_accuracy": 0.11323748677968978,
|
|
"num_tokens": 1218552.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.521316194534302,
|
|
"epoch": 0.0559639158035416,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.4197,
|
|
"mean_token_accuracy": 0.1132273718714714,
|
|
"num_tokens": 1227632.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.628327083587647,
|
|
"epoch": 0.056381556966254597,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.4666,
|
|
"mean_token_accuracy": 0.11458859890699387,
|
|
"num_tokens": 1236433.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.535047388076782,
|
|
"epoch": 0.05679919812896759,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.4887,
|
|
"mean_token_accuracy": 0.10250034034252167,
|
|
"num_tokens": 1245700.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.58137092590332,
|
|
"epoch": 0.05721683929168059,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.3208,
|
|
"mean_token_accuracy": 0.11790363714098931,
|
|
"num_tokens": 1254206.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.546811771392822,
|
|
"epoch": 0.05763448045439359,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.3787,
|
|
"mean_token_accuracy": 0.11770905256271362,
|
|
"num_tokens": 1263302.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.6236083984375,
|
|
"epoch": 0.05805212161710658,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4224,
|
|
"mean_token_accuracy": 0.11309175118803978,
|
|
"num_tokens": 1272998.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.480911111831665,
|
|
"epoch": 0.05846976277981958,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.396,
|
|
"mean_token_accuracy": 0.11966503635048867,
|
|
"num_tokens": 1281955.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.559855842590332,
|
|
"epoch": 0.05888740394253258,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4235,
|
|
"mean_token_accuracy": 0.11396420970559121,
|
|
"num_tokens": 1291219.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.5371620655059814,
|
|
"epoch": 0.05930504510524557,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.4288,
|
|
"mean_token_accuracy": 0.11189143359661102,
|
|
"num_tokens": 1300963.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.616220235824585,
|
|
"epoch": 0.05972268626795857,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.4596,
|
|
"mean_token_accuracy": 0.11059518307447433,
|
|
"num_tokens": 1310112.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.549956035614014,
|
|
"epoch": 0.06014032743067157,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.3884,
|
|
"mean_token_accuracy": 0.12019749581813813,
|
|
"num_tokens": 1319309.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.4225273609161375,
|
|
"epoch": 0.06055796859338457,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.3737,
|
|
"mean_token_accuracy": 0.11447888761758804,
|
|
"num_tokens": 1329049.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.456729459762573,
|
|
"epoch": 0.06097560975609756,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.2122,
|
|
"mean_token_accuracy": 0.11689538508653641,
|
|
"num_tokens": 1337770.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.3992725849151615,
|
|
"epoch": 0.06139325091881056,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.3188,
|
|
"mean_token_accuracy": 0.11989094093441963,
|
|
"num_tokens": 1346705.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.454647445678711,
|
|
"epoch": 0.06181089208152356,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.3721,
|
|
"mean_token_accuracy": 0.11653787791728973,
|
|
"num_tokens": 1354860.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.486315011978149,
|
|
"epoch": 0.06222853324423655,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3431,
|
|
"mean_token_accuracy": 0.11571619734168052,
|
|
"num_tokens": 1364140.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.577937173843384,
|
|
"epoch": 0.06264617440694954,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.474,
|
|
"mean_token_accuracy": 0.10803929641842842,
|
|
"num_tokens": 1373645.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.493966341018677,
|
|
"epoch": 0.06306381556966255,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.3496,
|
|
"mean_token_accuracy": 0.12465299069881439,
|
|
"num_tokens": 1383291.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.395097112655639,
|
|
"epoch": 0.06348145673237554,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.2609,
|
|
"mean_token_accuracy": 0.12159460708498955,
|
|
"num_tokens": 1391172.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.490391969680786,
|
|
"epoch": 0.06389909789508853,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.2816,
|
|
"mean_token_accuracy": 0.11841546595096589,
|
|
"num_tokens": 1400864.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.427747774124145,
|
|
"epoch": 0.06431673905780154,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.3416,
|
|
"mean_token_accuracy": 0.12262844294309616,
|
|
"num_tokens": 1410570.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.404248476028442,
|
|
"epoch": 0.06473438022051453,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.3088,
|
|
"mean_token_accuracy": 0.11854264065623284,
|
|
"num_tokens": 1419536.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.388956737518311,
|
|
"epoch": 0.06515202138322754,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.2301,
|
|
"mean_token_accuracy": 0.12381713986396789,
|
|
"num_tokens": 1428000.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.417420148849487,
|
|
"epoch": 0.06556966254594053,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.4262,
|
|
"mean_token_accuracy": 0.11879310831427574,
|
|
"num_tokens": 1437789.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.386681938171387,
|
|
"epoch": 0.06598730370865352,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.2391,
|
|
"mean_token_accuracy": 0.12141718417406082,
|
|
"num_tokens": 1446848.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.396657800674438,
|
|
"epoch": 0.06640494487136653,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.2814,
|
|
"mean_token_accuracy": 0.1192056655883789,
|
|
"num_tokens": 1455749.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.357221508026123,
|
|
"epoch": 0.06682258603407952,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.2013,
|
|
"mean_token_accuracy": 0.12639149650931358,
|
|
"num_tokens": 1464556.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.398760557174683,
|
|
"epoch": 0.06724022719679251,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.3614,
|
|
"mean_token_accuracy": 0.11781241819262504,
|
|
"num_tokens": 1473617.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.494735813140869,
|
|
"epoch": 0.06765786835950552,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3559,
|
|
"mean_token_accuracy": 0.11977834030985832,
|
|
"num_tokens": 1483006.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.457280921936035,
|
|
"epoch": 0.06807550952221851,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.3836,
|
|
"mean_token_accuracy": 0.11731792315840721,
|
|
"num_tokens": 1493009.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.363678503036499,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.2556,
|
|
"mean_token_accuracy": 0.12392903044819832,
|
|
"num_tokens": 1501261.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.3693873405456545,
|
|
"epoch": 0.06891079184764451,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3709,
|
|
"mean_token_accuracy": 0.11665059328079223,
|
|
"num_tokens": 1511623.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.428213024139405,
|
|
"epoch": 0.0693284330103575,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3659,
|
|
"mean_token_accuracy": 0.11537070199847221,
|
|
"num_tokens": 1521741.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.409314584732056,
|
|
"epoch": 0.0697460741730705,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.3035,
|
|
"mean_token_accuracy": 0.12089102566242219,
|
|
"num_tokens": 1530988.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.339814519882202,
|
|
"epoch": 0.0701637153357835,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.1285,
|
|
"mean_token_accuracy": 0.12743735313415527,
|
|
"num_tokens": 1539415.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.378707456588745,
|
|
"epoch": 0.07058135649849649,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.3338,
|
|
"mean_token_accuracy": 0.11762123182415962,
|
|
"num_tokens": 1547969.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.275123023986817,
|
|
"epoch": 0.07099899766120948,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.193,
|
|
"mean_token_accuracy": 0.12221964225172996,
|
|
"num_tokens": 1557526.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.299358463287353,
|
|
"epoch": 0.07141663882392249,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.1699,
|
|
"mean_token_accuracy": 0.12564374953508378,
|
|
"num_tokens": 1565982.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.304647016525268,
|
|
"epoch": 0.07183427998663548,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.2293,
|
|
"mean_token_accuracy": 0.12849857807159423,
|
|
"num_tokens": 1574492.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.269746017456055,
|
|
"epoch": 0.07225192114934847,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.2051,
|
|
"mean_token_accuracy": 0.12123230844736099,
|
|
"num_tokens": 1583726.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.284060335159301,
|
|
"epoch": 0.07266956231206148,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2154,
|
|
"mean_token_accuracy": 0.11842950582504272,
|
|
"num_tokens": 1593780.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.351301908493042,
|
|
"epoch": 0.07308720347477447,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.2104,
|
|
"mean_token_accuracy": 0.12493377402424813,
|
|
"num_tokens": 1602746.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.353745460510254,
|
|
"epoch": 0.07350484463748747,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.2485,
|
|
"mean_token_accuracy": 0.12405433133244514,
|
|
"num_tokens": 1611767.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.375559568405151,
|
|
"epoch": 0.07392248580020047,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.3327,
|
|
"mean_token_accuracy": 0.12374300360679627,
|
|
"num_tokens": 1621568.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.310373783111572,
|
|
"epoch": 0.07434012696291346,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.2722,
|
|
"mean_token_accuracy": 0.12864986136555673,
|
|
"num_tokens": 1630650.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.326134872436524,
|
|
"epoch": 0.07475776812562646,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.2808,
|
|
"mean_token_accuracy": 0.11709838211536408,
|
|
"num_tokens": 1640482.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.344818496704102,
|
|
"epoch": 0.07517540928833946,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3133,
|
|
"mean_token_accuracy": 0.12154146954417229,
|
|
"num_tokens": 1649344.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.331745386123657,
|
|
"epoch": 0.07559305045105245,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.2463,
|
|
"mean_token_accuracy": 0.12590100318193437,
|
|
"num_tokens": 1658962.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.229383707046509,
|
|
"epoch": 0.07601069161376545,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.2623,
|
|
"mean_token_accuracy": 0.12040851265192032,
|
|
"num_tokens": 1668615.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.35636830329895,
|
|
"epoch": 0.07642833277647845,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.1982,
|
|
"mean_token_accuracy": 0.12516034319996833,
|
|
"num_tokens": 1679282.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.20735993385315,
|
|
"epoch": 0.07684597393919144,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.2958,
|
|
"mean_token_accuracy": 0.1260470613837242,
|
|
"num_tokens": 1688362.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.310071229934692,
|
|
"epoch": 0.07726361510190444,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.1767,
|
|
"mean_token_accuracy": 0.12261404544115066,
|
|
"num_tokens": 1697593.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.316716861724854,
|
|
"epoch": 0.07768125626461744,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.2492,
|
|
"mean_token_accuracy": 0.12079507783055306,
|
|
"num_tokens": 1706961.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.359928178787231,
|
|
"epoch": 0.07809889742733044,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.2909,
|
|
"mean_token_accuracy": 0.1333912968635559,
|
|
"num_tokens": 1716222.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.185659694671631,
|
|
"epoch": 0.07851653859004344,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.1649,
|
|
"mean_token_accuracy": 0.11959992647171021,
|
|
"num_tokens": 1726750.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.369044351577759,
|
|
"epoch": 0.07893417975275643,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.2557,
|
|
"mean_token_accuracy": 0.1164586953818798,
|
|
"num_tokens": 1736262.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.249402666091919,
|
|
"epoch": 0.07935182091546943,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.2714,
|
|
"mean_token_accuracy": 0.12722517997026445,
|
|
"num_tokens": 1745555.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.137383937835693,
|
|
"epoch": 0.07976946207818243,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.1563,
|
|
"mean_token_accuracy": 0.12104023173451424,
|
|
"num_tokens": 1754107.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.396907472610474,
|
|
"epoch": 0.08018710324089542,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3493,
|
|
"mean_token_accuracy": 0.1176336333155632,
|
|
"num_tokens": 1762982.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.245203161239624,
|
|
"epoch": 0.08060474440360842,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.12653560936450958,
|
|
"num_tokens": 1772545.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.3770890712738035,
|
|
"epoch": 0.08102238556632142,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3507,
|
|
"mean_token_accuracy": 0.11759537160396576,
|
|
"num_tokens": 1782052.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.178989744186401,
|
|
"epoch": 0.08144002672903441,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.1567,
|
|
"mean_token_accuracy": 0.12350800633430481,
|
|
"num_tokens": 1791682.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.251344394683838,
|
|
"epoch": 0.08185766789174741,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.1646,
|
|
"mean_token_accuracy": 0.12833068072795867,
|
|
"num_tokens": 1800526.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.298021268844605,
|
|
"epoch": 0.08227530905446041,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2999,
|
|
"mean_token_accuracy": 0.1231074184179306,
|
|
"num_tokens": 1810062.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.250222015380859,
|
|
"epoch": 0.0826929502171734,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.12629790231585503,
|
|
"num_tokens": 1818909.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.297880029678344,
|
|
"epoch": 0.0831105913798864,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.2327,
|
|
"mean_token_accuracy": 0.13256481513381005,
|
|
"num_tokens": 1827978.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.1916309833526615,
|
|
"epoch": 0.0835282325425994,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.2013,
|
|
"mean_token_accuracy": 0.12940397188067437,
|
|
"num_tokens": 1837955.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.246883821487427,
|
|
"epoch": 0.0839458737053124,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999999987395534,
|
|
"loss": 6.2853,
|
|
"mean_token_accuracy": 0.12494878992438316,
|
|
"num_tokens": 1847699.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.375528335571289,
|
|
"epoch": 0.08436351486802539,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999936189888,
|
|
"loss": 6.218,
|
|
"mean_token_accuracy": 0.12546755075454713,
|
|
"num_tokens": 1856490.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.195798301696778,
|
|
"epoch": 0.0847811560307384,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999845595285,
|
|
"loss": 6.2219,
|
|
"mean_token_accuracy": 0.1272422730922699,
|
|
"num_tokens": 1865644.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.2077044486999515,
|
|
"epoch": 0.08519879719345139,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999999715611727,
|
|
"loss": 6.1602,
|
|
"mean_token_accuracy": 0.12565038353204727,
|
|
"num_tokens": 1874450.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.16418948173523,
|
|
"epoch": 0.08561643835616438,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999999546239215,
|
|
"loss": 6.1804,
|
|
"mean_token_accuracy": 0.12442194074392318,
|
|
"num_tokens": 1883259.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.259844875335693,
|
|
"epoch": 0.08603407951887738,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999999337477753,
|
|
"loss": 6.2624,
|
|
"mean_token_accuracy": 0.12271653115749359,
|
|
"num_tokens": 1891897.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.2629540920257565,
|
|
"epoch": 0.08645172068159038,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999999089327344,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.12325521185994148,
|
|
"num_tokens": 1901011.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.100732040405274,
|
|
"epoch": 0.08686936184430337,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999998801787993,
|
|
"loss": 6.1432,
|
|
"mean_token_accuracy": 0.13062310665845872,
|
|
"num_tokens": 1910132.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.287595129013061,
|
|
"epoch": 0.08728700300701638,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999998474859704,
|
|
"loss": 6.259,
|
|
"mean_token_accuracy": 0.12846295088529586,
|
|
"num_tokens": 1919938.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.134413957595825,
|
|
"epoch": 0.08770464416972937,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999998108542483,
|
|
"loss": 6.1267,
|
|
"mean_token_accuracy": 0.12628429979085923,
|
|
"num_tokens": 1928199.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.208824634552002,
|
|
"epoch": 0.08812228533244236,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999997702836339,
|
|
"loss": 6.1162,
|
|
"mean_token_accuracy": 0.12950822934508324,
|
|
"num_tokens": 1937133.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.2759356021881105,
|
|
"epoch": 0.08853992649515537,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999997257741274,
|
|
"loss": 6.2783,
|
|
"mean_token_accuracy": 0.1283426858484745,
|
|
"num_tokens": 1946580.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.123747396469116,
|
|
"epoch": 0.08895756765786836,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049999967732573,
|
|
"loss": 6.2076,
|
|
"mean_token_accuracy": 0.12349388226866723,
|
|
"num_tokens": 1955413.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.401907300949096,
|
|
"epoch": 0.08937520882058135,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999996249384425,
|
|
"loss": 6.2811,
|
|
"mean_token_accuracy": 0.12440942004323005,
|
|
"num_tokens": 1964716.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.09635558128357,
|
|
"epoch": 0.08979284998329436,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999995686122657,
|
|
"loss": 6.1292,
|
|
"mean_token_accuracy": 0.1341006152331829,
|
|
"num_tokens": 1974081.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.034217596054077,
|
|
"epoch": 0.09021049114600735,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999995083472006,
|
|
"loss": 6.0911,
|
|
"mean_token_accuracy": 0.12835043892264367,
|
|
"num_tokens": 1983035.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.26309871673584,
|
|
"epoch": 0.09062813230872034,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999994441432481,
|
|
"loss": 6.1167,
|
|
"mean_token_accuracy": 0.13723048493266105,
|
|
"num_tokens": 1992475.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.088156604766846,
|
|
"epoch": 0.09104577347143335,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999993760004097,
|
|
"loss": 6.1961,
|
|
"mean_token_accuracy": 0.12458470240235328,
|
|
"num_tokens": 2002729.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.078368520736694,
|
|
"epoch": 0.09146341463414634,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999993039186864,
|
|
"loss": 6.0401,
|
|
"mean_token_accuracy": 0.1297457695007324,
|
|
"num_tokens": 2011319.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.207320833206177,
|
|
"epoch": 0.09188105579685933,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999992278980794,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.12979096546769142,
|
|
"num_tokens": 2020456.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.020119953155517,
|
|
"epoch": 0.09229869695957234,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999991479385901,
|
|
"loss": 6.1668,
|
|
"mean_token_accuracy": 0.13272762671113014,
|
|
"num_tokens": 2029417.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.307196569442749,
|
|
"epoch": 0.09271633812228533,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999990640402198,
|
|
"loss": 6.2571,
|
|
"mean_token_accuracy": 0.12967613935470582,
|
|
"num_tokens": 2039290.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.152990007400513,
|
|
"epoch": 0.09313397928499834,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999989762029701,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.13426292017102243,
|
|
"num_tokens": 2048485.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 5.983977270126343,
|
|
"epoch": 0.09355162044771133,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999988844268425,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.13763293251395226,
|
|
"num_tokens": 2057131.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.102506446838379,
|
|
"epoch": 0.09396926161042432,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999987887118387,
|
|
"loss": 6.0427,
|
|
"mean_token_accuracy": 0.12984845265746117,
|
|
"num_tokens": 2066295.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.096871328353882,
|
|
"epoch": 0.09438690277313733,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999986890579602,
|
|
"loss": 6.0481,
|
|
"mean_token_accuracy": 0.13764009922742843,
|
|
"num_tokens": 2075656.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.084485101699829,
|
|
"epoch": 0.09480454393585032,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999985854652087,
|
|
"loss": 6.2038,
|
|
"mean_token_accuracy": 0.12579603642225265,
|
|
"num_tokens": 2086046.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.256638288497925,
|
|
"epoch": 0.09522218509856331,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999984779335862,
|
|
"loss": 6.2003,
|
|
"mean_token_accuracy": 0.12873548045754432,
|
|
"num_tokens": 2094808.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.063794231414795,
|
|
"epoch": 0.09563982626127632,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999983664630945,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.13587065562605857,
|
|
"num_tokens": 2104155.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.138120031356811,
|
|
"epoch": 0.09605746742398931,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999982510537357,
|
|
"loss": 6.0142,
|
|
"mean_token_accuracy": 0.13489947393536567,
|
|
"num_tokens": 2112517.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 5.968696737289429,
|
|
"epoch": 0.0964751085867023,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999981317055116,
|
|
"loss": 5.9811,
|
|
"mean_token_accuracy": 0.13498256728053093,
|
|
"num_tokens": 2121355.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.164517164230347,
|
|
"epoch": 0.09689274974941531,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999980084184244,
|
|
"loss": 6.1112,
|
|
"mean_token_accuracy": 0.1324291430413723,
|
|
"num_tokens": 2129278.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.211386203765869,
|
|
"epoch": 0.0973103909121283,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999978811924762,
|
|
"loss": 6.2848,
|
|
"mean_token_accuracy": 0.12834196388721467,
|
|
"num_tokens": 2139548.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.049183940887451,
|
|
"epoch": 0.09772803207484129,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999977500276693,
|
|
"loss": 6.1727,
|
|
"mean_token_accuracy": 0.12752494290471078,
|
|
"num_tokens": 2148765.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.184184598922729,
|
|
"epoch": 0.0981456732375543,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999976149240058,
|
|
"loss": 6.0723,
|
|
"mean_token_accuracy": 0.13661946654319762,
|
|
"num_tokens": 2157482.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.077676248550415,
|
|
"epoch": 0.09856331440026729,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999974758814884,
|
|
"loss": 6.1873,
|
|
"mean_token_accuracy": 0.12640749365091325,
|
|
"num_tokens": 2167320.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.120995664596558,
|
|
"epoch": 0.09898095556298028,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999973329001193,
|
|
"loss": 6.1323,
|
|
"mean_token_accuracy": 0.13020789697766305,
|
|
"num_tokens": 2175454.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.151616096496582,
|
|
"epoch": 0.09939859672569329,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999971859799009,
|
|
"loss": 6.0682,
|
|
"mean_token_accuracy": 0.13091856390237808,
|
|
"num_tokens": 2184391.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 5.982958078384399,
|
|
"epoch": 0.09981623788840628,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999970351208361,
|
|
"loss": 5.9463,
|
|
"mean_token_accuracy": 0.13676698952913285,
|
|
"num_tokens": 2193309.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.130738019943237,
|
|
"epoch": 0.10023387905111927,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999968803229275,
|
|
"loss": 6.099,
|
|
"mean_token_accuracy": 0.12918018624186517,
|
|
"num_tokens": 2202057.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.048878574371338,
|
|
"epoch": 0.10065152021383228,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999967215861775,
|
|
"loss": 6.1954,
|
|
"mean_token_accuracy": 0.12895920276641845,
|
|
"num_tokens": 2212384.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.216175651550293,
|
|
"epoch": 0.10106916137654527,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499996558910589,
|
|
"loss": 6.094,
|
|
"mean_token_accuracy": 0.13314013928174973,
|
|
"num_tokens": 2221451.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 5.950415802001953,
|
|
"epoch": 0.10148680253925826,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499996392296165,
|
|
"loss": 6.0078,
|
|
"mean_token_accuracy": 0.13325752466917037,
|
|
"num_tokens": 2230440.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.147376155853271,
|
|
"epoch": 0.10190444370197127,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999962217429083,
|
|
"loss": 6.191,
|
|
"mean_token_accuracy": 0.12644386813044547,
|
|
"num_tokens": 2239985.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.079806327819824,
|
|
"epoch": 0.10232208486468426,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999960472508219,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.1319073148071766,
|
|
"num_tokens": 2250391.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.162016820907593,
|
|
"epoch": 0.10273972602739725,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499995868819909,
|
|
"loss": 6.1621,
|
|
"mean_token_accuracy": 0.12812372222542762,
|
|
"num_tokens": 2260620.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.1506141185760494,
|
|
"epoch": 0.10315736719011026,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999956864501725,
|
|
"loss": 6.1254,
|
|
"mean_token_accuracy": 0.1344836674630642,
|
|
"num_tokens": 2271176.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.071055316925049,
|
|
"epoch": 0.10357500835282325,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999955001416156,
|
|
"loss": 6.0197,
|
|
"mean_token_accuracy": 0.1391293317079544,
|
|
"num_tokens": 2280371.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 5.98853645324707,
|
|
"epoch": 0.10399264951553625,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999953098942417,
|
|
"loss": 5.9859,
|
|
"mean_token_accuracy": 0.13849394246935845,
|
|
"num_tokens": 2289015.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.034357261657715,
|
|
"epoch": 0.10441029067824925,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999951157080541,
|
|
"loss": 6.0661,
|
|
"mean_token_accuracy": 0.13927728608250617,
|
|
"num_tokens": 2297409.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.035771656036377,
|
|
"epoch": 0.10482793184096224,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999949175830561,
|
|
"loss": 6.0999,
|
|
"mean_token_accuracy": 0.1318223387002945,
|
|
"num_tokens": 2307017.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.02630467414856,
|
|
"epoch": 0.10524557300367524,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999947155192514,
|
|
"loss": 5.9257,
|
|
"mean_token_accuracy": 0.14496939480304719,
|
|
"num_tokens": 2316014.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.0644933700561525,
|
|
"epoch": 0.10566321416638824,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999945095166433,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.13692282512784004,
|
|
"num_tokens": 2326326.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.156657695770264,
|
|
"epoch": 0.10608085532910123,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999942995752354,
|
|
"loss": 6.1305,
|
|
"mean_token_accuracy": 0.13163789063692094,
|
|
"num_tokens": 2335108.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.030630016326905,
|
|
"epoch": 0.10649849649181423,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999940856950315,
|
|
"loss": 6.0516,
|
|
"mean_token_accuracy": 0.14165214449167252,
|
|
"num_tokens": 2343971.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.095973300933838,
|
|
"epoch": 0.10691613765452723,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999938678760354,
|
|
"loss": 6.1169,
|
|
"mean_token_accuracy": 0.12894785180687904,
|
|
"num_tokens": 2353742.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.044046449661255,
|
|
"epoch": 0.10733377881724022,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999936461182507,
|
|
"loss": 6.0673,
|
|
"mean_token_accuracy": 0.14003410264849664,
|
|
"num_tokens": 2363629.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 5.9364416122436525,
|
|
"epoch": 0.10775141997995323,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999934204216814,
|
|
"loss": 5.9119,
|
|
"mean_token_accuracy": 0.14370162710547446,
|
|
"num_tokens": 2372705.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.036751222610474,
|
|
"epoch": 0.10816906114266622,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999931907863315,
|
|
"loss": 6.0254,
|
|
"mean_token_accuracy": 0.14308105707168578,
|
|
"num_tokens": 2382136.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 5.983735466003418,
|
|
"epoch": 0.10858670230537922,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499992957212205,
|
|
"loss": 6.0058,
|
|
"mean_token_accuracy": 0.13456499874591826,
|
|
"num_tokens": 2391060.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.100954914093018,
|
|
"epoch": 0.10900434346809222,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999927196993059,
|
|
"loss": 6.1417,
|
|
"mean_token_accuracy": 0.13201688900589942,
|
|
"num_tokens": 2399885.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.102160978317261,
|
|
"epoch": 0.10942198463080521,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999924782476384,
|
|
"loss": 5.9898,
|
|
"mean_token_accuracy": 0.1415901854634285,
|
|
"num_tokens": 2409654.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.028567504882813,
|
|
"epoch": 0.1098396257935182,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999922328572068,
|
|
"loss": 6.0838,
|
|
"mean_token_accuracy": 0.1362982250750065,
|
|
"num_tokens": 2419342.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 5.955235624313355,
|
|
"epoch": 0.11025726695623121,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999919835280154,
|
|
"loss": 5.9448,
|
|
"mean_token_accuracy": 0.141665992885828,
|
|
"num_tokens": 2428845.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.083720779418945,
|
|
"epoch": 0.1106749081189442,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999917302600684,
|
|
"loss": 5.9526,
|
|
"mean_token_accuracy": 0.14230969846248626,
|
|
"num_tokens": 2437134.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 5.869806337356567,
|
|
"epoch": 0.1110925492816572,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999914730533704,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.14912110045552254,
|
|
"num_tokens": 2445438.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 5.9724204540252686,
|
|
"epoch": 0.1115101904443702,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999912119079258,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.13888705000281334,
|
|
"num_tokens": 2455039.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.091151475906372,
|
|
"epoch": 0.1119278316070832,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999909468237393,
|
|
"loss": 6.0499,
|
|
"mean_token_accuracy": 0.13516307920217513,
|
|
"num_tokens": 2465170.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 5.9298077583312985,
|
|
"epoch": 0.11234547276979619,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999906778008153,
|
|
"loss": 5.8051,
|
|
"mean_token_accuracy": 0.1507083296775818,
|
|
"num_tokens": 2473688.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 5.883486986160278,
|
|
"epoch": 0.11276311393250919,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999904048391588,
|
|
"loss": 6.0757,
|
|
"mean_token_accuracy": 0.1353744611144066,
|
|
"num_tokens": 2482335.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.085854721069336,
|
|
"epoch": 0.11318075509522219,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999901279387743,
|
|
"loss": 5.9809,
|
|
"mean_token_accuracy": 0.14239128828048705,
|
|
"num_tokens": 2491808.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.159217739105225,
|
|
"epoch": 0.11359839625793518,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999898470996669,
|
|
"loss": 6.1325,
|
|
"mean_token_accuracy": 0.1258760765194893,
|
|
"num_tokens": 2501422.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 5.951807594299316,
|
|
"epoch": 0.11401603742064818,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999895623218415,
|
|
"loss": 5.9229,
|
|
"mean_token_accuracy": 0.14330672323703766,
|
|
"num_tokens": 2511201.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.010347700119018,
|
|
"epoch": 0.11443367858336118,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999892736053027,
|
|
"loss": 5.9507,
|
|
"mean_token_accuracy": 0.1380159690976143,
|
|
"num_tokens": 2519798.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 5.919538259506226,
|
|
"epoch": 0.11485131974607417,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999889809500561,
|
|
"loss": 5.9262,
|
|
"mean_token_accuracy": 0.1453268438577652,
|
|
"num_tokens": 2529177.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.072020483016968,
|
|
"epoch": 0.11526896090878717,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999886843561065,
|
|
"loss": 5.9368,
|
|
"mean_token_accuracy": 0.1449681594967842,
|
|
"num_tokens": 2537571.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 5.872820711135864,
|
|
"epoch": 0.11568660207150017,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999883838234592,
|
|
"loss": 5.8471,
|
|
"mean_token_accuracy": 0.14640183076262475,
|
|
"num_tokens": 2546258.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 5.917314434051514,
|
|
"epoch": 0.11610424323421316,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999880793521194,
|
|
"loss": 5.871,
|
|
"mean_token_accuracy": 0.13499426245689392,
|
|
"num_tokens": 2555862.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 5.775463819503784,
|
|
"epoch": 0.11652188439692616,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999877709420924,
|
|
"loss": 5.8884,
|
|
"mean_token_accuracy": 0.1478126809000969,
|
|
"num_tokens": 2564583.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 5.995883417129517,
|
|
"epoch": 0.11693952555963916,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999874585933837,
|
|
"loss": 5.984,
|
|
"mean_token_accuracy": 0.14109486490488052,
|
|
"num_tokens": 2574217.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 5.964802837371826,
|
|
"epoch": 0.11735716672235215,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999871423059987,
|
|
"loss": 5.894,
|
|
"mean_token_accuracy": 0.14622340500354766,
|
|
"num_tokens": 2582821.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 5.935116100311279,
|
|
"epoch": 0.11777480788506516,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499986822079943,
|
|
"loss": 6.0564,
|
|
"mean_token_accuracy": 0.1343017913401127,
|
|
"num_tokens": 2592748.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.061121129989624,
|
|
"epoch": 0.11819244904777815,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999864979152221,
|
|
"loss": 5.9453,
|
|
"mean_token_accuracy": 0.14890442043542862,
|
|
"num_tokens": 2602053.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 5.839966821670532,
|
|
"epoch": 0.11861009021049114,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999861698118417,
|
|
"loss": 6.0227,
|
|
"mean_token_accuracy": 0.13928924277424812,
|
|
"num_tokens": 2610557.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.0450952529907225,
|
|
"epoch": 0.11902773137320415,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999858377698076,
|
|
"loss": 5.9138,
|
|
"mean_token_accuracy": 0.14148174971342087,
|
|
"num_tokens": 2619628.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.103807687759399,
|
|
"epoch": 0.11944537253591714,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999855017891256,
|
|
"loss": 6.0716,
|
|
"mean_token_accuracy": 0.13505364283919336,
|
|
"num_tokens": 2629284.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 5.925868225097656,
|
|
"epoch": 0.11986301369863013,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999851618698017,
|
|
"loss": 5.9931,
|
|
"mean_token_accuracy": 0.14457735493779184,
|
|
"num_tokens": 2638001.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 5.955863618850708,
|
|
"epoch": 0.12028065486134314,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999848180118416,
|
|
"loss": 5.9773,
|
|
"mean_token_accuracy": 0.1491648070514202,
|
|
"num_tokens": 2647071.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.025531244277954,
|
|
"epoch": 0.12069829602405613,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999844702152516,
|
|
"loss": 5.9622,
|
|
"mean_token_accuracy": 0.1447582259774208,
|
|
"num_tokens": 2655826.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.899601125717163,
|
|
"epoch": 0.12111593718676913,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999841184800374,
|
|
"loss": 5.8222,
|
|
"mean_token_accuracy": 0.15455349087715148,
|
|
"num_tokens": 2664431.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.779673719406128,
|
|
"epoch": 0.12153357834948213,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999837628062055,
|
|
"loss": 5.7455,
|
|
"mean_token_accuracy": 0.15094979852437973,
|
|
"num_tokens": 2673631.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 5.896817064285278,
|
|
"epoch": 0.12195121951219512,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999834031937621,
|
|
"loss": 6.0289,
|
|
"mean_token_accuracy": 0.14003881290555,
|
|
"num_tokens": 2683363.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.015520000457764,
|
|
"epoch": 0.12236886067490813,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999830396427133,
|
|
"loss": 5.979,
|
|
"mean_token_accuracy": 0.1428418278694153,
|
|
"num_tokens": 2692533.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 5.897101259231567,
|
|
"epoch": 0.12278650183762112,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999826721530657,
|
|
"loss": 5.9693,
|
|
"mean_token_accuracy": 0.14741405099630356,
|
|
"num_tokens": 2701211.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.052044248580932,
|
|
"epoch": 0.12320414300033411,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999823007248255,
|
|
"loss": 5.9683,
|
|
"mean_token_accuracy": 0.14251434803009033,
|
|
"num_tokens": 2709543.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.990947246551514,
|
|
"epoch": 0.12362178416304712,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999819253579992,
|
|
"loss": 5.973,
|
|
"mean_token_accuracy": 0.14051907062530516,
|
|
"num_tokens": 2718336.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 5.9257396221160885,
|
|
"epoch": 0.12403942532576011,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999815460525938,
|
|
"loss": 5.9216,
|
|
"mean_token_accuracy": 0.14473359286785126,
|
|
"num_tokens": 2726504.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 5.933391046524048,
|
|
"epoch": 0.1244570664884731,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999811628086155,
|
|
"loss": 5.9363,
|
|
"mean_token_accuracy": 0.1432306505739689,
|
|
"num_tokens": 2736076.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.884974098205566,
|
|
"epoch": 0.1248747076511861,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499980775626071,
|
|
"loss": 5.8638,
|
|
"mean_token_accuracy": 0.14747666344046592,
|
|
"num_tokens": 2745497.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.883179140090943,
|
|
"epoch": 0.12529234881389908,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999803845049674,
|
|
"loss": 5.9851,
|
|
"mean_token_accuracy": 0.14409718811511993,
|
|
"num_tokens": 2754455.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.054201316833496,
|
|
"epoch": 0.1257099899766121,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999799894453112,
|
|
"loss": 6.0131,
|
|
"mean_token_accuracy": 0.14107876718044282,
|
|
"num_tokens": 2763603.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.904917526245117,
|
|
"epoch": 0.1261276311393251,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999795904471095,
|
|
"loss": 5.8727,
|
|
"mean_token_accuracy": 0.14535894691944123,
|
|
"num_tokens": 2772152.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.038354587554932,
|
|
"epoch": 0.12654527230203808,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999791875103694,
|
|
"loss": 5.9741,
|
|
"mean_token_accuracy": 0.1499622419476509,
|
|
"num_tokens": 2781459.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.9492429256439205,
|
|
"epoch": 0.12696291346475108,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999787806350977,
|
|
"loss": 5.9293,
|
|
"mean_token_accuracy": 0.1426587760448456,
|
|
"num_tokens": 2791177.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.861308526992798,
|
|
"epoch": 0.1273805546274641,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999783698213016,
|
|
"loss": 5.9155,
|
|
"mean_token_accuracy": 0.15418764054775239,
|
|
"num_tokens": 2800543.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 5.828676509857178,
|
|
"epoch": 0.12779819579017707,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999779550689885,
|
|
"loss": 5.7677,
|
|
"mean_token_accuracy": 0.1490427389740944,
|
|
"num_tokens": 2809301.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.975144577026367,
|
|
"epoch": 0.12821583695289007,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999775363781654,
|
|
"loss": 5.9798,
|
|
"mean_token_accuracy": 0.1374480627477169,
|
|
"num_tokens": 2818269.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.888175773620605,
|
|
"epoch": 0.12863347811560308,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999771137488395,
|
|
"loss": 5.8394,
|
|
"mean_token_accuracy": 0.14905280917882918,
|
|
"num_tokens": 2827170.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.831831455230713,
|
|
"epoch": 0.12905111927831608,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999766871810188,
|
|
"loss": 5.8317,
|
|
"mean_token_accuracy": 0.15102441906929015,
|
|
"num_tokens": 2835320.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.931498861312866,
|
|
"epoch": 0.12946876044102906,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999762566747101,
|
|
"loss": 5.9071,
|
|
"mean_token_accuracy": 0.14569202587008476,
|
|
"num_tokens": 2843755.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.002191972732544,
|
|
"epoch": 0.12988640160374207,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999758222299214,
|
|
"loss": 5.9512,
|
|
"mean_token_accuracy": 0.13484849333763121,
|
|
"num_tokens": 2853462.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.833185768127441,
|
|
"epoch": 0.13030404276645507,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999753838466601,
|
|
"loss": 5.8504,
|
|
"mean_token_accuracy": 0.14550600945949554,
|
|
"num_tokens": 2863041.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.038375997543335,
|
|
"epoch": 0.13072168392916805,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999749415249338,
|
|
"loss": 6.0665,
|
|
"mean_token_accuracy": 0.14647892266511917,
|
|
"num_tokens": 2873019.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.836305475234985,
|
|
"epoch": 0.13113932509188106,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999744952647505,
|
|
"loss": 5.815,
|
|
"mean_token_accuracy": 0.14850633218884468,
|
|
"num_tokens": 2881467.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 5.894457483291626,
|
|
"epoch": 0.13155696625459407,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999740450661176,
|
|
"loss": 5.9128,
|
|
"mean_token_accuracy": 0.14054032042622566,
|
|
"num_tokens": 2890914.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.885600280761719,
|
|
"epoch": 0.13197460741730704,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999735909290436,
|
|
"loss": 5.8276,
|
|
"mean_token_accuracy": 0.14965800568461418,
|
|
"num_tokens": 2901164.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.899939250946045,
|
|
"epoch": 0.13239224858002005,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999731328535358,
|
|
"loss": 5.972,
|
|
"mean_token_accuracy": 0.14218765646219253,
|
|
"num_tokens": 2910560.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.862451267242432,
|
|
"epoch": 0.13280988974273306,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999726708396026,
|
|
"loss": 5.7887,
|
|
"mean_token_accuracy": 0.15113321989774703,
|
|
"num_tokens": 2918980.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.894169282913208,
|
|
"epoch": 0.13322753090544603,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499972204887252,
|
|
"loss": 5.9799,
|
|
"mean_token_accuracy": 0.14003576040267945,
|
|
"num_tokens": 2929516.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.951022052764893,
|
|
"epoch": 0.13364517206815904,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999717349964922,
|
|
"loss": 6.0633,
|
|
"mean_token_accuracy": 0.1349113292992115,
|
|
"num_tokens": 2940603.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.994172143936157,
|
|
"epoch": 0.13406281323087205,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999712611673313,
|
|
"loss": 5.8962,
|
|
"mean_token_accuracy": 0.14273757338523865,
|
|
"num_tokens": 2950082.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.814873790740966,
|
|
"epoch": 0.13448045439358502,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999707833997777,
|
|
"loss": 5.7629,
|
|
"mean_token_accuracy": 0.15739804357290268,
|
|
"num_tokens": 2959098.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.9581045627594,
|
|
"epoch": 0.13489809555629803,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999703016938398,
|
|
"loss": 5.8869,
|
|
"mean_token_accuracy": 0.14871252477169036,
|
|
"num_tokens": 2968585.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.870134258270264,
|
|
"epoch": 0.13531573671901104,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499969816049526,
|
|
"loss": 5.9327,
|
|
"mean_token_accuracy": 0.1441057324409485,
|
|
"num_tokens": 2978430.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.060405111312866,
|
|
"epoch": 0.13573337788172402,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999693264668446,
|
|
"loss": 5.9705,
|
|
"mean_token_accuracy": 0.1415616549551487,
|
|
"num_tokens": 2988398.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.9228941917419435,
|
|
"epoch": 0.13615101904443702,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999688329458045,
|
|
"loss": 6.0189,
|
|
"mean_token_accuracy": 0.1370128683745861,
|
|
"num_tokens": 2999255.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.015878582000733,
|
|
"epoch": 0.13656866020715003,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999683354864141,
|
|
"loss": 5.8821,
|
|
"mean_token_accuracy": 0.14219623506069184,
|
|
"num_tokens": 3008638.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.79380989074707,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999678340886823,
|
|
"loss": 5.893,
|
|
"mean_token_accuracy": 0.14931328296661378,
|
|
"num_tokens": 3018070.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.795630550384521,
|
|
"epoch": 0.137403942532576,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999673287526176,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.1456718251109123,
|
|
"num_tokens": 3027878.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.055118751525879,
|
|
"epoch": 0.13782158369528902,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999668194782291,
|
|
"loss": 6.0385,
|
|
"mean_token_accuracy": 0.14034320637583733,
|
|
"num_tokens": 3037031.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.01564655303955,
|
|
"epoch": 0.138239224858002,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999663062655257,
|
|
"loss": 5.9779,
|
|
"mean_token_accuracy": 0.13667403906583786,
|
|
"num_tokens": 3046311.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.877610874176026,
|
|
"epoch": 0.138656866020715,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999657891145162,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.14991068840026855,
|
|
"num_tokens": 3055108.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.8218607902526855,
|
|
"epoch": 0.139074507183428,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999652680252099,
|
|
"loss": 5.8356,
|
|
"mean_token_accuracy": 0.15323519706726074,
|
|
"num_tokens": 3063492.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.0089860439300535,
|
|
"epoch": 0.139492148346141,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999647429976157,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.150077623128891,
|
|
"num_tokens": 3072572.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.950778341293335,
|
|
"epoch": 0.139909789508854,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999642140317429,
|
|
"loss": 5.9306,
|
|
"mean_token_accuracy": 0.14366639852523805,
|
|
"num_tokens": 3082942.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.84227180480957,
|
|
"epoch": 0.140327430671567,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999636811276007,
|
|
"loss": 5.8983,
|
|
"mean_token_accuracy": 0.1497769057750702,
|
|
"num_tokens": 3091410.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.025895690917968,
|
|
"epoch": 0.14074507183427998,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999631442851986,
|
|
"loss": 5.9669,
|
|
"mean_token_accuracy": 0.1470497116446495,
|
|
"num_tokens": 3100626.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.820451116561889,
|
|
"epoch": 0.14116271299699298,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999626035045458,
|
|
"loss": 5.763,
|
|
"mean_token_accuracy": 0.15730037465691565,
|
|
"num_tokens": 3109339.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.946425104141236,
|
|
"epoch": 0.141580354159706,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999620587856519,
|
|
"loss": 5.8886,
|
|
"mean_token_accuracy": 0.14283772855997084,
|
|
"num_tokens": 3118636.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.853169965744018,
|
|
"epoch": 0.14199799532241897,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999615101285262,
|
|
"loss": 5.8703,
|
|
"mean_token_accuracy": 0.14250073656439782,
|
|
"num_tokens": 3128162.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.882144975662231,
|
|
"epoch": 0.14241563648513197,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999609575331786,
|
|
"loss": 5.8669,
|
|
"mean_token_accuracy": 0.14853606820106507,
|
|
"num_tokens": 3136451.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.879884481430054,
|
|
"epoch": 0.14283327764784498,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999604009996186,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.14338908046483995,
|
|
"num_tokens": 3146599.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.972683095932007,
|
|
"epoch": 0.14325091881055796,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499959840527856,
|
|
"loss": 5.9275,
|
|
"mean_token_accuracy": 0.14261688515543938,
|
|
"num_tokens": 3155941.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.865710830688476,
|
|
"epoch": 0.14366855997327097,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999592761179007,
|
|
"loss": 5.849,
|
|
"mean_token_accuracy": 0.1503235414624214,
|
|
"num_tokens": 3164641.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.8569518566131595,
|
|
"epoch": 0.14408620113598397,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999587077697624,
|
|
"loss": 5.8752,
|
|
"mean_token_accuracy": 0.15404415428638457,
|
|
"num_tokens": 3173701.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.823041582107544,
|
|
"epoch": 0.14450384229869695,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999581354834512,
|
|
"loss": 5.7338,
|
|
"mean_token_accuracy": 0.15567242205142975,
|
|
"num_tokens": 3182268.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.754219198226929,
|
|
"epoch": 0.14492148346140996,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499957559258977,
|
|
"loss": 5.8158,
|
|
"mean_token_accuracy": 0.14996908158063887,
|
|
"num_tokens": 3191513.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.853840494155884,
|
|
"epoch": 0.14533912462412296,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049995697909635,
|
|
"loss": 5.7625,
|
|
"mean_token_accuracy": 0.14906580671668052,
|
|
"num_tokens": 3200580.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.7556675434112545,
|
|
"epoch": 0.14575676578683594,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999563949955803,
|
|
"loss": 5.8603,
|
|
"mean_token_accuracy": 0.15062788128852844,
|
|
"num_tokens": 3209053.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.928824186325073,
|
|
"epoch": 0.14617440694954895,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499955806956678,
|
|
"loss": 5.8441,
|
|
"mean_token_accuracy": 0.15138443186879158,
|
|
"num_tokens": 3218241.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.8904777526855465,
|
|
"epoch": 0.14659204811226195,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999552149796536,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.14435181394219398,
|
|
"num_tokens": 3227887.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.815938091278076,
|
|
"epoch": 0.14700968927497493,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999546190645175,
|
|
"loss": 5.7054,
|
|
"mean_token_accuracy": 0.15759559869766235,
|
|
"num_tokens": 3237281.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.811881685256958,
|
|
"epoch": 0.14742733043768794,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999540192112799,
|
|
"loss": 5.7542,
|
|
"mean_token_accuracy": 0.14863720834255217,
|
|
"num_tokens": 3246907.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.687792444229126,
|
|
"epoch": 0.14784497160040094,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999534154199514,
|
|
"loss": 5.7613,
|
|
"mean_token_accuracy": 0.14564004242420198,
|
|
"num_tokens": 3256312.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.997764968872071,
|
|
"epoch": 0.14826261276311392,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999528076905426,
|
|
"loss": 5.8538,
|
|
"mean_token_accuracy": 0.14647961109876634,
|
|
"num_tokens": 3265554.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.653895521163941,
|
|
"epoch": 0.14868025392582693,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999521960230641,
|
|
"loss": 5.701,
|
|
"mean_token_accuracy": 0.15505964308977127,
|
|
"num_tokens": 3274731.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.814744377136231,
|
|
"epoch": 0.14909789508853993,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999515804175268,
|
|
"loss": 5.8403,
|
|
"mean_token_accuracy": 0.14269457161426544,
|
|
"num_tokens": 3283518.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.923381757736206,
|
|
"epoch": 0.1495155362512529,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499950960873941,
|
|
"loss": 5.8509,
|
|
"mean_token_accuracy": 0.15064001828432083,
|
|
"num_tokens": 3292244.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.874558019638061,
|
|
"epoch": 0.14993317741396592,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999503373923182,
|
|
"loss": 5.8117,
|
|
"mean_token_accuracy": 0.15160613209009172,
|
|
"num_tokens": 3301198.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.772550582885742,
|
|
"epoch": 0.15035081857667892,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999497099726687,
|
|
"loss": 5.8039,
|
|
"mean_token_accuracy": 0.1560743421316147,
|
|
"num_tokens": 3309983.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.89383111000061,
|
|
"epoch": 0.1507684597393919,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999490786150039,
|
|
"loss": 5.88,
|
|
"mean_token_accuracy": 0.15231931060552598,
|
|
"num_tokens": 3319313.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.842616891860962,
|
|
"epoch": 0.1511861009021049,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999484433193348,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.15028464645147324,
|
|
"num_tokens": 3327497.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.748625373840332,
|
|
"epoch": 0.15160374206481791,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999478040856722,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.15894282311201097,
|
|
"num_tokens": 3337029.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.683879041671753,
|
|
"epoch": 0.1520213832275309,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999471609140276,
|
|
"loss": 5.7233,
|
|
"mean_token_accuracy": 0.15257363468408586,
|
|
"num_tokens": 3346243.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.895862579345703,
|
|
"epoch": 0.1524390243902439,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999465138044122,
|
|
"loss": 5.8765,
|
|
"mean_token_accuracy": 0.14993367940187455,
|
|
"num_tokens": 3354846.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.8310247421264645,
|
|
"epoch": 0.1528566655529569,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999458627568373,
|
|
"loss": 5.8289,
|
|
"mean_token_accuracy": 0.14543151631951332,
|
|
"num_tokens": 3364683.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.878261423110962,
|
|
"epoch": 0.15327430671566988,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999452077713144,
|
|
"loss": 5.7708,
|
|
"mean_token_accuracy": 0.15320614725351334,
|
|
"num_tokens": 3374652.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.796768140792847,
|
|
"epoch": 0.1536919478783829,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999445488478547,
|
|
"loss": 5.7856,
|
|
"mean_token_accuracy": 0.1481989949941635,
|
|
"num_tokens": 3384040.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.8385844230651855,
|
|
"epoch": 0.1541095890410959,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00049994388598647,
|
|
"loss": 5.855,
|
|
"mean_token_accuracy": 0.14915144294500352,
|
|
"num_tokens": 3393185.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.814882135391235,
|
|
"epoch": 0.15452723020380887,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999432191871719,
|
|
"loss": 5.8005,
|
|
"mean_token_accuracy": 0.15439388900995255,
|
|
"num_tokens": 3403077.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.855295944213867,
|
|
"epoch": 0.15494487136652188,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999425484499718,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.15828135311603547,
|
|
"num_tokens": 3412165.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.789868879318237,
|
|
"epoch": 0.1553625125292349,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999418737748817,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.1457912042737007,
|
|
"num_tokens": 3421162.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.93405933380127,
|
|
"epoch": 0.15578015369194786,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999411951619134,
|
|
"loss": 5.9043,
|
|
"mean_token_accuracy": 0.14147294089198112,
|
|
"num_tokens": 3430363.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.850097751617431,
|
|
"epoch": 0.15619779485466087,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999405126110786,
|
|
"loss": 5.8087,
|
|
"mean_token_accuracy": 0.15039258375763892,
|
|
"num_tokens": 3439199.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.958965682983399,
|
|
"epoch": 0.15661543601737388,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999398261223895,
|
|
"loss": 5.9212,
|
|
"mean_token_accuracy": 0.14575616419315338,
|
|
"num_tokens": 3448720.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.840033674240113,
|
|
"epoch": 0.15703307718008688,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999391356958579,
|
|
"loss": 5.8919,
|
|
"mean_token_accuracy": 0.14604691565036773,
|
|
"num_tokens": 3458472.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.856070518493652,
|
|
"epoch": 0.15745071834279986,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499938441331496,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.14574070572853087,
|
|
"num_tokens": 3467140.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.903375244140625,
|
|
"epoch": 0.15786835950551287,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999377430293159,
|
|
"loss": 5.817,
|
|
"mean_token_accuracy": 0.1542054980993271,
|
|
"num_tokens": 3476431.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.774544668197632,
|
|
"epoch": 0.15828600066822587,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999370407893299,
|
|
"loss": 5.7404,
|
|
"mean_token_accuracy": 0.14861033111810684,
|
|
"num_tokens": 3485768.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.885667562484741,
|
|
"epoch": 0.15870364183093885,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999363346115501,
|
|
"loss": 5.895,
|
|
"mean_token_accuracy": 0.14465293884277344,
|
|
"num_tokens": 3495678.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.832116174697876,
|
|
"epoch": 0.15912128299365186,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999356244959893,
|
|
"loss": 5.8763,
|
|
"mean_token_accuracy": 0.14869818314909936,
|
|
"num_tokens": 3505168.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.854088401794433,
|
|
"epoch": 0.15953892415636486,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999349104426594,
|
|
"loss": 5.83,
|
|
"mean_token_accuracy": 0.14758925139904022,
|
|
"num_tokens": 3514498.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.874787092208862,
|
|
"epoch": 0.15995656531907784,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999341924515732,
|
|
"loss": 5.7422,
|
|
"mean_token_accuracy": 0.14831667989492417,
|
|
"num_tokens": 3524617.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.707592535018921,
|
|
"epoch": 0.16037420648179085,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999334705227431,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.1557302623987198,
|
|
"num_tokens": 3533523.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.86808819770813,
|
|
"epoch": 0.16079184764450385,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499932744656182,
|
|
"loss": 5.8106,
|
|
"mean_token_accuracy": 0.148667673766613,
|
|
"num_tokens": 3542922.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.842382860183716,
|
|
"epoch": 0.16120948880721683,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999320148519024,
|
|
"loss": 5.7929,
|
|
"mean_token_accuracy": 0.15389788001775742,
|
|
"num_tokens": 3551827.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.769865942001343,
|
|
"epoch": 0.16162712996992984,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999312811099171,
|
|
"loss": 5.764,
|
|
"mean_token_accuracy": 0.15155478119850158,
|
|
"num_tokens": 3560911.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.744738578796387,
|
|
"epoch": 0.16204477113264285,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999305434302391,
|
|
"loss": 5.7932,
|
|
"mean_token_accuracy": 0.14804999828338622,
|
|
"num_tokens": 3569473.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.809125232696533,
|
|
"epoch": 0.16246241229535582,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499929801812881,
|
|
"loss": 5.7955,
|
|
"mean_token_accuracy": 0.1538992702960968,
|
|
"num_tokens": 3578843.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.8280191898345945,
|
|
"epoch": 0.16288005345806883,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999290562578561,
|
|
"loss": 5.7991,
|
|
"mean_token_accuracy": 0.1495085433125496,
|
|
"num_tokens": 3588304.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.762173223495483,
|
|
"epoch": 0.16329769462078184,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999283067651773,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.14699322879314422,
|
|
"num_tokens": 3598354.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.967223978042602,
|
|
"epoch": 0.16371533578349481,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999275533348577,
|
|
"loss": 5.8872,
|
|
"mean_token_accuracy": 0.14445243775844574,
|
|
"num_tokens": 3607503.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.690870523452759,
|
|
"epoch": 0.16413297694620782,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999267959669106,
|
|
"loss": 5.6962,
|
|
"mean_token_accuracy": 0.15905150175094604,
|
|
"num_tokens": 3617467.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.84067850112915,
|
|
"epoch": 0.16455061810892083,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999260346613491,
|
|
"loss": 5.7142,
|
|
"mean_token_accuracy": 0.14913540482521057,
|
|
"num_tokens": 3627048.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.721961498260498,
|
|
"epoch": 0.1649682592716338,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999252694181867,
|
|
"loss": 5.7598,
|
|
"mean_token_accuracy": 0.1523315817117691,
|
|
"num_tokens": 3636683.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.77244200706482,
|
|
"epoch": 0.1653859004343468,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999245002374367,
|
|
"loss": 5.6602,
|
|
"mean_token_accuracy": 0.16195474863052367,
|
|
"num_tokens": 3645231.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.743553972244262,
|
|
"epoch": 0.16580354159705982,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999237271191125,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.15497519820928574,
|
|
"num_tokens": 3653851.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.739997816085816,
|
|
"epoch": 0.1662211827597728,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999229500632279,
|
|
"loss": 5.7126,
|
|
"mean_token_accuracy": 0.153715518116951,
|
|
"num_tokens": 3662720.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.651612234115601,
|
|
"epoch": 0.1666388239224858,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999221690697961,
|
|
"loss": 5.6529,
|
|
"mean_token_accuracy": 0.1546758532524109,
|
|
"num_tokens": 3671777.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.773471879959106,
|
|
"epoch": 0.1670564650851988,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999213841388312,
|
|
"loss": 5.7392,
|
|
"mean_token_accuracy": 0.1595829591155052,
|
|
"num_tokens": 3681390.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.864161586761474,
|
|
"epoch": 0.16747410624791179,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999205952703466,
|
|
"loss": 5.7938,
|
|
"mean_token_accuracy": 0.15263195633888244,
|
|
"num_tokens": 3690899.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.887154245376587,
|
|
"epoch": 0.1678917474106248,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999198024643563,
|
|
"loss": 5.8879,
|
|
"mean_token_accuracy": 0.13942136317491532,
|
|
"num_tokens": 3699891.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.657262086868286,
|
|
"epoch": 0.1683093885733378,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999190057208741,
|
|
"loss": 5.6816,
|
|
"mean_token_accuracy": 0.1632775440812111,
|
|
"num_tokens": 3709860.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.774410057067871,
|
|
"epoch": 0.16872702973605078,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499918205039914,
|
|
"loss": 5.8156,
|
|
"mean_token_accuracy": 0.14972853809595107,
|
|
"num_tokens": 3718896.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.787345123291016,
|
|
"epoch": 0.16914467089876378,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999174004214899,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.15970027893781663,
|
|
"num_tokens": 3727355.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.7231813907623295,
|
|
"epoch": 0.1695623120614768,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999165918656161,
|
|
"loss": 5.7293,
|
|
"mean_token_accuracy": 0.14931901469826697,
|
|
"num_tokens": 3736191.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.816195106506347,
|
|
"epoch": 0.16997995322418977,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999157793723065,
|
|
"loss": 5.7601,
|
|
"mean_token_accuracy": 0.1600704610347748,
|
|
"num_tokens": 3744832.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.696157789230346,
|
|
"epoch": 0.17039759438690277,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999149629415755,
|
|
"loss": 5.7095,
|
|
"mean_token_accuracy": 0.14830667823553084,
|
|
"num_tokens": 3753835.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.9111795902252195,
|
|
"epoch": 0.17081523554961578,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999141425734374,
|
|
"loss": 5.7839,
|
|
"mean_token_accuracy": 0.1511392444372177,
|
|
"num_tokens": 3762816.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.721945428848267,
|
|
"epoch": 0.17123287671232876,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999133182679064,
|
|
"loss": 5.8427,
|
|
"mean_token_accuracy": 0.1457610920071602,
|
|
"num_tokens": 3773244.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.812287282943726,
|
|
"epoch": 0.17165051787504176,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999124900249971,
|
|
"loss": 5.6946,
|
|
"mean_token_accuracy": 0.1568377897143364,
|
|
"num_tokens": 3782122.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.745067119598389,
|
|
"epoch": 0.17206815903775477,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999116578447239,
|
|
"loss": 5.6901,
|
|
"mean_token_accuracy": 0.16290647834539412,
|
|
"num_tokens": 3791303.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.75031156539917,
|
|
"epoch": 0.17248580020046775,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999108217271015,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.1540791168808937,
|
|
"num_tokens": 3800991.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.767945575714111,
|
|
"epoch": 0.17290344136318075,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999099816721444,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.14992420375347137,
|
|
"num_tokens": 3811293.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.840733480453491,
|
|
"epoch": 0.17332108252589376,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999091376798673,
|
|
"loss": 5.7827,
|
|
"mean_token_accuracy": 0.15033572688698768,
|
|
"num_tokens": 3820013.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.699107217788696,
|
|
"epoch": 0.17373872368860674,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999082897502849,
|
|
"loss": 5.6696,
|
|
"mean_token_accuracy": 0.15458893924951553,
|
|
"num_tokens": 3829099.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.677335739135742,
|
|
"epoch": 0.17415636485131974,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999074378834123,
|
|
"loss": 5.7674,
|
|
"mean_token_accuracy": 0.15095923766493796,
|
|
"num_tokens": 3838308.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.813047075271607,
|
|
"epoch": 0.17457400601403275,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999065820792644,
|
|
"loss": 5.7247,
|
|
"mean_token_accuracy": 0.15711767971515656,
|
|
"num_tokens": 3847650.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.866225051879883,
|
|
"epoch": 0.17499164717674573,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999057223378559,
|
|
"loss": 5.8998,
|
|
"mean_token_accuracy": 0.14039052203297614,
|
|
"num_tokens": 3857252.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.810293769836425,
|
|
"epoch": 0.17540928833945874,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499904858659202,
|
|
"loss": 5.7376,
|
|
"mean_token_accuracy": 0.1527712255716324,
|
|
"num_tokens": 3865747.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.748090505599976,
|
|
"epoch": 0.17582692950217174,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999039910433179,
|
|
"loss": 5.7179,
|
|
"mean_token_accuracy": 0.1610593318939209,
|
|
"num_tokens": 3874958.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.679863786697387,
|
|
"epoch": 0.17624457066488472,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999031194902187,
|
|
"loss": 5.6593,
|
|
"mean_token_accuracy": 0.16140231043100356,
|
|
"num_tokens": 3885216.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.738522243499756,
|
|
"epoch": 0.17666221182759773,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999022439999198,
|
|
"loss": 5.7147,
|
|
"mean_token_accuracy": 0.1608191043138504,
|
|
"num_tokens": 3893973.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.77422251701355,
|
|
"epoch": 0.17707985299031073,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999013645724362,
|
|
"loss": 5.7932,
|
|
"mean_token_accuracy": 0.1573753759264946,
|
|
"num_tokens": 3903532.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.834164810180664,
|
|
"epoch": 0.1774974941530237,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999004812077836,
|
|
"loss": 5.708,
|
|
"mean_token_accuracy": 0.15743714570999146,
|
|
"num_tokens": 3913427.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.739658546447754,
|
|
"epoch": 0.17791513531573672,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998995939059773,
|
|
"loss": 5.845,
|
|
"mean_token_accuracy": 0.1429277092218399,
|
|
"num_tokens": 3923870.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.769284439086914,
|
|
"epoch": 0.17833277647844972,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499898702667033,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.15647914707660676,
|
|
"num_tokens": 3933469.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.6842976093292235,
|
|
"epoch": 0.1787504176411627,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998978074909661,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.1610175371170044,
|
|
"num_tokens": 3942427.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.731369209289551,
|
|
"epoch": 0.1791680588038757,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998969083777925,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.1602757304906845,
|
|
"num_tokens": 3951250.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.755114364624023,
|
|
"epoch": 0.1795856999665887,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998960053275277,
|
|
"loss": 5.7129,
|
|
"mean_token_accuracy": 0.15325510650873184,
|
|
"num_tokens": 3959969.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.752820634841919,
|
|
"epoch": 0.1800033411293017,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998950983401875,
|
|
"loss": 5.7425,
|
|
"mean_token_accuracy": 0.15397500544786452,
|
|
"num_tokens": 3968171.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.7606171607971195,
|
|
"epoch": 0.1804209822920147,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998941874157882,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.16023926734924315,
|
|
"num_tokens": 3976686.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.6677477836608885,
|
|
"epoch": 0.1808386234547277,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998932725543453,
|
|
"loss": 5.7763,
|
|
"mean_token_accuracy": 0.14887330681085587,
|
|
"num_tokens": 3986552.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.758628177642822,
|
|
"epoch": 0.18125626461744068,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998923537558749,
|
|
"loss": 5.6363,
|
|
"mean_token_accuracy": 0.15045822262763978,
|
|
"num_tokens": 3995501.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.636182117462158,
|
|
"epoch": 0.1816739057801537,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998914310203932,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.15822093039751053,
|
|
"num_tokens": 4004423.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.749627637863159,
|
|
"epoch": 0.1820915469428667,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998905043479163,
|
|
"loss": 5.7937,
|
|
"mean_token_accuracy": 0.15634801089763642,
|
|
"num_tokens": 4013324.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.799656629562378,
|
|
"epoch": 0.18250918810557967,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998895737384605,
|
|
"loss": 5.7072,
|
|
"mean_token_accuracy": 0.1537037067115307,
|
|
"num_tokens": 4021896.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.648739194869995,
|
|
"epoch": 0.18292682926829268,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998886391920418,
|
|
"loss": 5.6855,
|
|
"mean_token_accuracy": 0.15282756984233856,
|
|
"num_tokens": 4030590.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.7324353694915775,
|
|
"epoch": 0.18334447043100568,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998877007086769,
|
|
"loss": 5.5813,
|
|
"mean_token_accuracy": 0.16229644566774368,
|
|
"num_tokens": 4040041.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.735997533798217,
|
|
"epoch": 0.18376211159371866,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998867582883821,
|
|
"loss": 5.7567,
|
|
"mean_token_accuracy": 0.14448343887925147,
|
|
"num_tokens": 4049119.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.758669328689575,
|
|
"epoch": 0.18417975275643167,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998858119311739,
|
|
"loss": 5.6837,
|
|
"mean_token_accuracy": 0.15333226174116135,
|
|
"num_tokens": 4059265.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.7284187316894535,
|
|
"epoch": 0.18459739391914468,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998848616370689,
|
|
"loss": 5.7337,
|
|
"mean_token_accuracy": 0.14927480071783067,
|
|
"num_tokens": 4068363.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.653486967086792,
|
|
"epoch": 0.18501503508185768,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998839074060837,
|
|
"loss": 5.6273,
|
|
"mean_token_accuracy": 0.16272631734609605,
|
|
"num_tokens": 4077390.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.7014764785766605,
|
|
"epoch": 0.18543267624457066,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499882949238235,
|
|
"loss": 5.6943,
|
|
"mean_token_accuracy": 0.14898738339543344,
|
|
"num_tokens": 4087331.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.934384870529175,
|
|
"epoch": 0.18585031740728367,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998819871335396,
|
|
"loss": 5.8722,
|
|
"mean_token_accuracy": 0.14616972133517264,
|
|
"num_tokens": 4096425.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.685419225692749,
|
|
"epoch": 0.18626795856999667,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998810210920142,
|
|
"loss": 5.6401,
|
|
"mean_token_accuracy": 0.15437570661306382,
|
|
"num_tokens": 4106056.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.718805170059204,
|
|
"epoch": 0.18668559973270965,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998800511136759,
|
|
"loss": 5.7408,
|
|
"mean_token_accuracy": 0.15399838015437126,
|
|
"num_tokens": 4115133.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.710136127471924,
|
|
"epoch": 0.18710324089542266,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998790771985417,
|
|
"loss": 5.6286,
|
|
"mean_token_accuracy": 0.15800086557865142,
|
|
"num_tokens": 4123630.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.682529258728027,
|
|
"epoch": 0.18752088205813566,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998780993466284,
|
|
"loss": 5.7856,
|
|
"mean_token_accuracy": 0.1551293760538101,
|
|
"num_tokens": 4133337.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.789374923706054,
|
|
"epoch": 0.18793852322084864,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998771175579534,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.15884945541620255,
|
|
"num_tokens": 4142240.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.731400394439698,
|
|
"epoch": 0.18835616438356165,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998761318325337,
|
|
"loss": 5.6866,
|
|
"mean_token_accuracy": 0.1549566388130188,
|
|
"num_tokens": 4151297.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.672632312774658,
|
|
"epoch": 0.18877380554627465,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998751421703868,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.15859557688236237,
|
|
"num_tokens": 4160193.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.80642557144165,
|
|
"epoch": 0.18919144670898763,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998741485715297,
|
|
"loss": 5.7881,
|
|
"mean_token_accuracy": 0.1534851834177971,
|
|
"num_tokens": 4169948.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.929843711853027,
|
|
"epoch": 0.18960908787170064,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049987315103598,
|
|
"loss": 5.8201,
|
|
"mean_token_accuracy": 0.1431059531867504,
|
|
"num_tokens": 4179981.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.721387052536011,
|
|
"epoch": 0.19002672903441364,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998721495637551,
|
|
"loss": 5.8286,
|
|
"mean_token_accuracy": 0.15135889053344725,
|
|
"num_tokens": 4189172.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.771591997146606,
|
|
"epoch": 0.19044437019712662,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998711441548726,
|
|
"loss": 5.6287,
|
|
"mean_token_accuracy": 0.15496868789196014,
|
|
"num_tokens": 4197312.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.775719499588012,
|
|
"epoch": 0.19086201135983963,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998701348093499,
|
|
"loss": 5.7028,
|
|
"mean_token_accuracy": 0.1541793242096901,
|
|
"num_tokens": 4206828.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.774220943450928,
|
|
"epoch": 0.19127965252255263,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499869121527205,
|
|
"loss": 5.6556,
|
|
"mean_token_accuracy": 0.15856624841690065,
|
|
"num_tokens": 4214835.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.697559452056884,
|
|
"epoch": 0.1916972936852656,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998681043084553,
|
|
"loss": 5.8386,
|
|
"mean_token_accuracy": 0.1496319055557251,
|
|
"num_tokens": 4225119.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.692424154281616,
|
|
"epoch": 0.19211493484797862,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998670831531188,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.15529378354549409,
|
|
"num_tokens": 4235257.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.735343933105469,
|
|
"epoch": 0.19253257601069163,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998660580612135,
|
|
"loss": 5.754,
|
|
"mean_token_accuracy": 0.1595138430595398,
|
|
"num_tokens": 4244211.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.7877946376800535,
|
|
"epoch": 0.1929502171734046,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998650290327569,
|
|
"loss": 5.7569,
|
|
"mean_token_accuracy": 0.15316392183303834,
|
|
"num_tokens": 4253149.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.677975702285766,
|
|
"epoch": 0.1933678583361176,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998639960677675,
|
|
"loss": 5.6596,
|
|
"mean_token_accuracy": 0.15832507610321045,
|
|
"num_tokens": 4262557.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.718808221817016,
|
|
"epoch": 0.19378549949883062,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998629591662631,
|
|
"loss": 5.682,
|
|
"mean_token_accuracy": 0.15558916032314302,
|
|
"num_tokens": 4272881.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.675476217269898,
|
|
"epoch": 0.1942031406615436,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499861918328262,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.16360289007425308,
|
|
"num_tokens": 4281158.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.677481555938721,
|
|
"epoch": 0.1946207818242566,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998608735537822,
|
|
"loss": 5.6715,
|
|
"mean_token_accuracy": 0.15835799872875214,
|
|
"num_tokens": 4290319.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.709587240219117,
|
|
"epoch": 0.1950384229869696,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998598248428423,
|
|
"loss": 5.7666,
|
|
"mean_token_accuracy": 0.15781829208135606,
|
|
"num_tokens": 4299276.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.818220853805542,
|
|
"epoch": 0.19545606414968258,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998587721954604,
|
|
"loss": 5.7341,
|
|
"mean_token_accuracy": 0.1592143088579178,
|
|
"num_tokens": 4308291.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.6828516006469725,
|
|
"epoch": 0.1958737053123956,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998577156116551,
|
|
"loss": 5.6658,
|
|
"mean_token_accuracy": 0.15610508769750595,
|
|
"num_tokens": 4316654.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.653003692626953,
|
|
"epoch": 0.1962913464751086,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998566550914448,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.15679550021886826,
|
|
"num_tokens": 4325911.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.785430240631103,
|
|
"epoch": 0.19670898763782158,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998555906348481,
|
|
"loss": 5.794,
|
|
"mean_token_accuracy": 0.1561383381485939,
|
|
"num_tokens": 4334846.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.768541526794434,
|
|
"epoch": 0.19712662880053458,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998545222418836,
|
|
"loss": 5.6889,
|
|
"mean_token_accuracy": 0.1616716906428337,
|
|
"num_tokens": 4343728.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.662745571136474,
|
|
"epoch": 0.1975442699632476,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998534499125701,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.15771860778331756,
|
|
"num_tokens": 4352774.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.819053602218628,
|
|
"epoch": 0.19796191112596057,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998523736469263,
|
|
"loss": 5.7907,
|
|
"mean_token_accuracy": 0.15671314746141435,
|
|
"num_tokens": 4361663.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.743377780914306,
|
|
"epoch": 0.19837955228867357,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499851293444971,
|
|
"loss": 5.6366,
|
|
"mean_token_accuracy": 0.16553718596696854,
|
|
"num_tokens": 4370278.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.745715761184693,
|
|
"epoch": 0.19879719345138658,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998502093067231,
|
|
"loss": 5.6973,
|
|
"mean_token_accuracy": 0.15904364138841628,
|
|
"num_tokens": 4379010.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.693148374557495,
|
|
"epoch": 0.19921483461409956,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998491212322017,
|
|
"loss": 5.6679,
|
|
"mean_token_accuracy": 0.154359894990921,
|
|
"num_tokens": 4388145.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.703994178771973,
|
|
"epoch": 0.19963247577681256,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998480292214258,
|
|
"loss": 5.7985,
|
|
"mean_token_accuracy": 0.15730815529823303,
|
|
"num_tokens": 4396321.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.759179210662841,
|
|
"epoch": 0.20005011693952557,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998469332744144,
|
|
"loss": 5.5769,
|
|
"mean_token_accuracy": 0.16447094231843948,
|
|
"num_tokens": 4404854.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.507405042648315,
|
|
"epoch": 0.20046775810223855,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998458333911869,
|
|
"loss": 5.5746,
|
|
"mean_token_accuracy": 0.16705760657787322,
|
|
"num_tokens": 4413890.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.776613044738769,
|
|
"epoch": 0.20088539926495155,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998447295717624,
|
|
"loss": 5.7294,
|
|
"mean_token_accuracy": 0.15241889730095864,
|
|
"num_tokens": 4423019.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.735891437530517,
|
|
"epoch": 0.20130304042766456,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998436218161602,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.15640403777360917,
|
|
"num_tokens": 4432340.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.673480558395386,
|
|
"epoch": 0.20172068159037754,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998425101243999,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.15851726457476617,
|
|
"num_tokens": 4441834.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.637769412994385,
|
|
"epoch": 0.20213832275309054,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998413944965007,
|
|
"loss": 5.6713,
|
|
"mean_token_accuracy": 0.16047401875257492,
|
|
"num_tokens": 4450864.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.720356225967407,
|
|
"epoch": 0.20255596391580355,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998402749324823,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.15220133364200591,
|
|
"num_tokens": 4460697.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.90509066581726,
|
|
"epoch": 0.20297360507851653,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998391514323642,
|
|
"loss": 5.7588,
|
|
"mean_token_accuracy": 0.15590522438287735,
|
|
"num_tokens": 4469926.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.611506032943725,
|
|
"epoch": 0.20339124624122953,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998380239961661,
|
|
"loss": 5.6788,
|
|
"mean_token_accuracy": 0.15944595634937286,
|
|
"num_tokens": 4478818.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.822584009170532,
|
|
"epoch": 0.20380888740394254,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998368926239078,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.159269979596138,
|
|
"num_tokens": 4487451.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.65903000831604,
|
|
"epoch": 0.20422652856665552,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499835757315609,
|
|
"loss": 5.7008,
|
|
"mean_token_accuracy": 0.1526777759194374,
|
|
"num_tokens": 4497674.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.638183975219727,
|
|
"epoch": 0.20464416972936852,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998346180712898,
|
|
"loss": 5.6441,
|
|
"mean_token_accuracy": 0.1633292853832245,
|
|
"num_tokens": 4507666.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.711228942871093,
|
|
"epoch": 0.20506181089208153,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998334748909698,
|
|
"loss": 5.7809,
|
|
"mean_token_accuracy": 0.15110641419887544,
|
|
"num_tokens": 4517409.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.68793215751648,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998323277746694,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.1622202515602112,
|
|
"num_tokens": 4526495.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.698691320419312,
|
|
"epoch": 0.20589709321750752,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998311767224081,
|
|
"loss": 5.6345,
|
|
"mean_token_accuracy": 0.16896701455116273,
|
|
"num_tokens": 4535240.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.68572301864624,
|
|
"epoch": 0.20631473438022052,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998300217342067,
|
|
"loss": 5.7317,
|
|
"mean_token_accuracy": 0.15531685054302216,
|
|
"num_tokens": 4544716.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.664935541152954,
|
|
"epoch": 0.2067323755429335,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998288628100851,
|
|
"loss": 5.6548,
|
|
"mean_token_accuracy": 0.15997060686349868,
|
|
"num_tokens": 4553867.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.734103202819824,
|
|
"epoch": 0.2071500167056465,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998276999500636,
|
|
"loss": 5.7049,
|
|
"mean_token_accuracy": 0.15193945467472075,
|
|
"num_tokens": 4562529.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.626588201522827,
|
|
"epoch": 0.2075676578683595,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.17455072104930877,
|
|
"num_tokens": 4571041.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.593395090103149,
|
|
"epoch": 0.2079852990310725,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998253624224026,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.1611686021089554,
|
|
"num_tokens": 4579914.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.68196291923523,
|
|
"epoch": 0.2084029401937855,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499824187754804,
|
|
"loss": 5.7267,
|
|
"mean_token_accuracy": 0.15876575261354448,
|
|
"num_tokens": 4590277.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.762881946563721,
|
|
"epoch": 0.2088205813564985,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998230091513872,
|
|
"loss": 5.6413,
|
|
"mean_token_accuracy": 0.1610427275300026,
|
|
"num_tokens": 4598719.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.598127794265747,
|
|
"epoch": 0.20923822251921148,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998218266121731,
|
|
"loss": 5.6013,
|
|
"mean_token_accuracy": 0.15835593938827514,
|
|
"num_tokens": 4607804.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.5917142868042,
|
|
"epoch": 0.2096558636819245,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998206401371823,
|
|
"loss": 5.5838,
|
|
"mean_token_accuracy": 0.16652322113513945,
|
|
"num_tokens": 4616529.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.690482568740845,
|
|
"epoch": 0.2100735048446375,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998194497264357,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.15835141241550446,
|
|
"num_tokens": 4624545.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.662758302688599,
|
|
"epoch": 0.21049114600735047,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998182553799538,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.15359725803136826,
|
|
"num_tokens": 4633316.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.617012453079224,
|
|
"epoch": 0.21090878717006348,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998170570977579,
|
|
"loss": 5.5718,
|
|
"mean_token_accuracy": 0.16380760073661804,
|
|
"num_tokens": 4643353.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.613987588882447,
|
|
"epoch": 0.21132642833277648,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998158548798687,
|
|
"loss": 5.6596,
|
|
"mean_token_accuracy": 0.1520226702094078,
|
|
"num_tokens": 4651998.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.712827730178833,
|
|
"epoch": 0.21174406949548946,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998146487263074,
|
|
"loss": 5.653,
|
|
"mean_token_accuracy": 0.16016076356172562,
|
|
"num_tokens": 4659937.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.596396350860596,
|
|
"epoch": 0.21216171065820247,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998134386370951,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.15896535590291022,
|
|
"num_tokens": 4669396.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.761886167526245,
|
|
"epoch": 0.21257935182091547,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998122246122529,
|
|
"loss": 5.706,
|
|
"mean_token_accuracy": 0.16040253043174743,
|
|
"num_tokens": 4679320.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.712255525588989,
|
|
"epoch": 0.21299699298362845,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998110066518021,
|
|
"loss": 5.6267,
|
|
"mean_token_accuracy": 0.15740251243114473,
|
|
"num_tokens": 4688807.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.680971097946167,
|
|
"epoch": 0.21341463414634146,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499809784755764,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.16529802978038788,
|
|
"num_tokens": 4697819.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.612238550186158,
|
|
"epoch": 0.21383227530905446,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049980855892416,
|
|
"loss": 5.6116,
|
|
"mean_token_accuracy": 0.16319564878940582,
|
|
"num_tokens": 4706931.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.657007837295533,
|
|
"epoch": 0.21424991647176747,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998073291570116,
|
|
"loss": 5.5977,
|
|
"mean_token_accuracy": 0.1614841639995575,
|
|
"num_tokens": 4716262.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.657294845581054,
|
|
"epoch": 0.21466755763448045,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998060954543404,
|
|
"loss": 5.641,
|
|
"mean_token_accuracy": 0.15932284742593766,
|
|
"num_tokens": 4725415.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.598384952545166,
|
|
"epoch": 0.21508519879719346,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998048578161678,
|
|
"loss": 5.6799,
|
|
"mean_token_accuracy": 0.15921542495489122,
|
|
"num_tokens": 4734580.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.70758843421936,
|
|
"epoch": 0.21550283995990646,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998036162425155,
|
|
"loss": 5.5042,
|
|
"mean_token_accuracy": 0.16997790932655335,
|
|
"num_tokens": 4742966.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.624478483200074,
|
|
"epoch": 0.21592048112261944,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998023707334055,
|
|
"loss": 5.6602,
|
|
"mean_token_accuracy": 0.15674813762307166,
|
|
"num_tokens": 4751696.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.702862167358399,
|
|
"epoch": 0.21633812228533245,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998011212888592,
|
|
"loss": 5.6996,
|
|
"mean_token_accuracy": 0.16383157521486283,
|
|
"num_tokens": 4760460.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.6970478057861325,
|
|
"epoch": 0.21675576344804545,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997998679088988,
|
|
"loss": 5.6199,
|
|
"mean_token_accuracy": 0.15811368972063064,
|
|
"num_tokens": 4769004.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.615769100189209,
|
|
"epoch": 0.21717340461075843,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997986105935461,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.16909316480159758,
|
|
"num_tokens": 4777204.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.713931846618652,
|
|
"epoch": 0.21759104577347144,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997973493428231,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.15746706277132033,
|
|
"num_tokens": 4786766.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.630015087127686,
|
|
"epoch": 0.21800868693618444,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997960841567519,
|
|
"loss": 5.6147,
|
|
"mean_token_accuracy": 0.16642356812953948,
|
|
"num_tokens": 4796676.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.836607217788696,
|
|
"epoch": 0.21842632809889742,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997948150353548,
|
|
"loss": 5.6294,
|
|
"mean_token_accuracy": 0.16387240290641786,
|
|
"num_tokens": 4805514.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.636025714874267,
|
|
"epoch": 0.21884396926161043,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997935419786537,
|
|
"loss": 5.7164,
|
|
"mean_token_accuracy": 0.1554280623793602,
|
|
"num_tokens": 4815487.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.725597667694092,
|
|
"epoch": 0.21926161042432343,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997922649866712,
|
|
"loss": 5.6606,
|
|
"mean_token_accuracy": 0.16378234028816224,
|
|
"num_tokens": 4825044.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.588494157791137,
|
|
"epoch": 0.2196792515870364,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997909840594294,
|
|
"loss": 5.4646,
|
|
"mean_token_accuracy": 0.17271657586097716,
|
|
"num_tokens": 4833875.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.5453134059906,
|
|
"epoch": 0.22009689274974942,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997896991969509,
|
|
"loss": 5.6878,
|
|
"mean_token_accuracy": 0.15461718291044235,
|
|
"num_tokens": 4843317.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.717306423187256,
|
|
"epoch": 0.22051453391246242,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997884103992581,
|
|
"loss": 5.6694,
|
|
"mean_token_accuracy": 0.1513319656252861,
|
|
"num_tokens": 4852514.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.713863706588745,
|
|
"epoch": 0.2209321750751754,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997871176663736,
|
|
"loss": 5.621,
|
|
"mean_token_accuracy": 0.16299737840890885,
|
|
"num_tokens": 4861260.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.643141365051269,
|
|
"epoch": 0.2213498162378884,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997858209983201,
|
|
"loss": 5.5676,
|
|
"mean_token_accuracy": 0.15755053833127022,
|
|
"num_tokens": 4869654.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.614552354812622,
|
|
"epoch": 0.22176745740060141,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997845203951202,
|
|
"loss": 5.632,
|
|
"mean_token_accuracy": 0.1524375632405281,
|
|
"num_tokens": 4878311.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.764042854309082,
|
|
"epoch": 0.2221850985633144,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997832158567967,
|
|
"loss": 5.6864,
|
|
"mean_token_accuracy": 0.15463019385933877,
|
|
"num_tokens": 4887251.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.66120228767395,
|
|
"epoch": 0.2226027397260274,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997819073833724,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.16053226739168167,
|
|
"num_tokens": 4896528.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.586405324935913,
|
|
"epoch": 0.2230203808887404,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997805949748702,
|
|
"loss": 5.5996,
|
|
"mean_token_accuracy": 0.15948226004838945,
|
|
"num_tokens": 4904962.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.630958700180054,
|
|
"epoch": 0.22343802205145338,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997792786313132,
|
|
"loss": 5.6198,
|
|
"mean_token_accuracy": 0.1612951412796974,
|
|
"num_tokens": 4914735.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.482047605514526,
|
|
"epoch": 0.2238556632141664,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997779583527243,
|
|
"loss": 5.4973,
|
|
"mean_token_accuracy": 0.15745694637298585,
|
|
"num_tokens": 4924271.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.763424968719482,
|
|
"epoch": 0.2242733043768794,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997766341391268,
|
|
"loss": 5.7335,
|
|
"mean_token_accuracy": 0.1580530509352684,
|
|
"num_tokens": 4933928.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.563910961151123,
|
|
"epoch": 0.22469094553959237,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997753059905437,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.1698251634836197,
|
|
"num_tokens": 4942714.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.477238178253174,
|
|
"epoch": 0.22510858670230538,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997739739069981,
|
|
"loss": 5.574,
|
|
"mean_token_accuracy": 0.16250405907630922,
|
|
"num_tokens": 4952297.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.622715759277344,
|
|
"epoch": 0.22552622786501839,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997726378885138,
|
|
"loss": 5.5178,
|
|
"mean_token_accuracy": 0.16804625689983368,
|
|
"num_tokens": 4960947.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.691080617904663,
|
|
"epoch": 0.22594386902773136,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997712979351137,
|
|
"loss": 5.6715,
|
|
"mean_token_accuracy": 0.1612107589840889,
|
|
"num_tokens": 4969705.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.678754997253418,
|
|
"epoch": 0.22636151019044437,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997699540468216,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.1642414227128029,
|
|
"num_tokens": 4979112.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.575213766098022,
|
|
"epoch": 0.22677915135315738,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997686062236609,
|
|
"loss": 5.5573,
|
|
"mean_token_accuracy": 0.16429246664047242,
|
|
"num_tokens": 4987894.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.629120254516602,
|
|
"epoch": 0.22719679251587035,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997672544656553,
|
|
"loss": 5.6969,
|
|
"mean_token_accuracy": 0.15555485635995864,
|
|
"num_tokens": 4997774.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.6939263343811035,
|
|
"epoch": 0.22761443367858336,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997658987728283,
|
|
"loss": 5.6257,
|
|
"mean_token_accuracy": 0.16721180230379104,
|
|
"num_tokens": 5006183.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.66974105834961,
|
|
"epoch": 0.22803207484129637,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997645391452035,
|
|
"loss": 5.6352,
|
|
"mean_token_accuracy": 0.15832276195287703,
|
|
"num_tokens": 5016909.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.732269906997681,
|
|
"epoch": 0.22844971600400935,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499763175582805,
|
|
"loss": 5.6664,
|
|
"mean_token_accuracy": 0.16458674222230912,
|
|
"num_tokens": 5027326.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.662186813354492,
|
|
"epoch": 0.22886735716672235,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997618080856566,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.16315631568431854,
|
|
"num_tokens": 5037043.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.532242393493652,
|
|
"epoch": 0.22928499832943536,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997604366537823,
|
|
"loss": 5.6013,
|
|
"mean_token_accuracy": 0.1606644257903099,
|
|
"num_tokens": 5045992.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.615709590911865,
|
|
"epoch": 0.22970263949214834,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997590612872058,
|
|
"loss": 5.5828,
|
|
"mean_token_accuracy": 0.16492637246847153,
|
|
"num_tokens": 5055568.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.723384141921997,
|
|
"epoch": 0.23012028065486134,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997576819859515,
|
|
"loss": 5.6511,
|
|
"mean_token_accuracy": 0.15917448103427886,
|
|
"num_tokens": 5065512.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.514522075653076,
|
|
"epoch": 0.23053792181757435,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997562987500434,
|
|
"loss": 5.5148,
|
|
"mean_token_accuracy": 0.16921254098415375,
|
|
"num_tokens": 5074776.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.603356647491455,
|
|
"epoch": 0.23095556298028733,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997549115795058,
|
|
"loss": 5.5586,
|
|
"mean_token_accuracy": 0.1597614198923111,
|
|
"num_tokens": 5084743.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.788118314743042,
|
|
"epoch": 0.23137320414300033,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499753520474363,
|
|
"loss": 5.7119,
|
|
"mean_token_accuracy": 0.15703203529119492,
|
|
"num_tokens": 5095387.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.602227401733399,
|
|
"epoch": 0.23179084530571334,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997521254346391,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.16656922772526742,
|
|
"num_tokens": 5104628.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.685851812362671,
|
|
"epoch": 0.23220848646842632,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997507264603589,
|
|
"loss": 5.5585,
|
|
"mean_token_accuracy": 0.16496562957763672,
|
|
"num_tokens": 5113169.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.598643827438354,
|
|
"epoch": 0.23262612763113932,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997493235515466,
|
|
"loss": 5.6414,
|
|
"mean_token_accuracy": 0.16375131905078888,
|
|
"num_tokens": 5122294.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.584103536605835,
|
|
"epoch": 0.23304376879385233,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997479167082269,
|
|
"loss": 5.4675,
|
|
"mean_token_accuracy": 0.17088187783956527,
|
|
"num_tokens": 5131191.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.608424329757691,
|
|
"epoch": 0.2334614099565653,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997465059304243,
|
|
"loss": 5.6914,
|
|
"mean_token_accuracy": 0.15928376764059066,
|
|
"num_tokens": 5141974.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.69712815284729,
|
|
"epoch": 0.23387905111927831,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997450912181637,
|
|
"loss": 5.6253,
|
|
"mean_token_accuracy": 0.16184188574552535,
|
|
"num_tokens": 5151412.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.600370121002197,
|
|
"epoch": 0.23429669228199132,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997436725714696,
|
|
"loss": 5.5465,
|
|
"mean_token_accuracy": 0.17141722291707992,
|
|
"num_tokens": 5160989.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.604136896133423,
|
|
"epoch": 0.2347143334447043,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997422499903671,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.1575893685221672,
|
|
"num_tokens": 5170241.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.762957906723022,
|
|
"epoch": 0.2351319746074173,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499740823474881,
|
|
"loss": 5.7537,
|
|
"mean_token_accuracy": 0.15024295151233674,
|
|
"num_tokens": 5180247.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.622417020797729,
|
|
"epoch": 0.2355496157701303,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997393930250363,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.16577300131320954,
|
|
"num_tokens": 5189144.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.687289714813232,
|
|
"epoch": 0.2359672569328433,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499737958640858,
|
|
"loss": 5.6849,
|
|
"mean_token_accuracy": 0.15777652114629745,
|
|
"num_tokens": 5199410.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.698432159423828,
|
|
"epoch": 0.2363848980955563,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997365203223711,
|
|
"loss": 5.543,
|
|
"mean_token_accuracy": 0.1669863536953926,
|
|
"num_tokens": 5209032.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.460228633880615,
|
|
"epoch": 0.2368025392582693,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499735078069601,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.17202911972999574,
|
|
"num_tokens": 5217787.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.605433750152588,
|
|
"epoch": 0.23722018042098228,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997336318825728,
|
|
"loss": 5.5649,
|
|
"mean_token_accuracy": 0.16585068553686141,
|
|
"num_tokens": 5226962.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.561488389968872,
|
|
"epoch": 0.23763782158369529,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997321817613119,
|
|
"loss": 5.54,
|
|
"mean_token_accuracy": 0.16485002040863037,
|
|
"num_tokens": 5236111.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.6743675708770756,
|
|
"epoch": 0.2380554627464083,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997307277058436,
|
|
"loss": 5.6851,
|
|
"mean_token_accuracy": 0.1568032205104828,
|
|
"num_tokens": 5246628.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.619131994247437,
|
|
"epoch": 0.23847310390912127,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997292697161935,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.16125448048114777,
|
|
"num_tokens": 5255543.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.53836874961853,
|
|
"epoch": 0.23889074507183428,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499727807792387,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.17420955300331115,
|
|
"num_tokens": 5264559.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.477006959915161,
|
|
"epoch": 0.23930838623454728,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997263419344495,
|
|
"loss": 5.5417,
|
|
"mean_token_accuracy": 0.16187895089387894,
|
|
"num_tokens": 5274599.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.608580589294434,
|
|
"epoch": 0.23972602739726026,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997248721424071,
|
|
"loss": 5.5074,
|
|
"mean_token_accuracy": 0.1679512843489647,
|
|
"num_tokens": 5283495.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.635401773452759,
|
|
"epoch": 0.24014366855997327,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997233984162853,
|
|
"loss": 5.5462,
|
|
"mean_token_accuracy": 0.17000787556171418,
|
|
"num_tokens": 5292064.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.577572917938232,
|
|
"epoch": 0.24056130972268627,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997219207561099,
|
|
"loss": 5.5791,
|
|
"mean_token_accuracy": 0.15797632038593293,
|
|
"num_tokens": 5301696.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.710454320907592,
|
|
"epoch": 0.24097895088539925,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997204391619068,
|
|
"loss": 5.6802,
|
|
"mean_token_accuracy": 0.1591041773557663,
|
|
"num_tokens": 5311427.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.741862344741821,
|
|
"epoch": 0.24139659204811226,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997189536337018,
|
|
"loss": 5.6072,
|
|
"mean_token_accuracy": 0.16055293530225753,
|
|
"num_tokens": 5321406.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.633491802215576,
|
|
"epoch": 0.24181423321082526,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997174641715211,
|
|
"loss": 5.6973,
|
|
"mean_token_accuracy": 0.15916599482297897,
|
|
"num_tokens": 5332257.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.550656461715699,
|
|
"epoch": 0.24223187437353827,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997159707753906,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.1674718514084816,
|
|
"num_tokens": 5341857.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.60410509109497,
|
|
"epoch": 0.24264951553625125,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997144734453367,
|
|
"loss": 5.5838,
|
|
"mean_token_accuracy": 0.17222851514816284,
|
|
"num_tokens": 5351367.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.458855724334716,
|
|
"epoch": 0.24306715669896425,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997129721813853,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.17036363631486892,
|
|
"num_tokens": 5360627.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.609381294250488,
|
|
"epoch": 0.24348479786167726,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997114669835629,
|
|
"loss": 5.5309,
|
|
"mean_token_accuracy": 0.1677655428647995,
|
|
"num_tokens": 5369703.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.63187084197998,
|
|
"epoch": 0.24390243902439024,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997099578518959,
|
|
"loss": 5.5813,
|
|
"mean_token_accuracy": 0.16637938767671584,
|
|
"num_tokens": 5378432.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.485184192657471,
|
|
"epoch": 0.24432008018710324,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997084447864105,
|
|
"loss": 5.4439,
|
|
"mean_token_accuracy": 0.166954642534256,
|
|
"num_tokens": 5386489.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.662143421173096,
|
|
"epoch": 0.24473772134981625,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997069277871333,
|
|
"loss": 5.6627,
|
|
"mean_token_accuracy": 0.1570824384689331,
|
|
"num_tokens": 5395908.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.712649345397949,
|
|
"epoch": 0.24515536251252923,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997054068540908,
|
|
"loss": 5.5795,
|
|
"mean_token_accuracy": 0.16576846018433572,
|
|
"num_tokens": 5404822.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.5368317604064945,
|
|
"epoch": 0.24557300367524224,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997038819873098,
|
|
"loss": 5.4965,
|
|
"mean_token_accuracy": 0.17085475027561187,
|
|
"num_tokens": 5413980.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.604154777526856,
|
|
"epoch": 0.24599064483795524,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997023531868167,
|
|
"loss": 5.5712,
|
|
"mean_token_accuracy": 0.16370426267385482,
|
|
"num_tokens": 5423538.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.5363991260528564,
|
|
"epoch": 0.24640828600066822,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997008204526386,
|
|
"loss": 5.4912,
|
|
"mean_token_accuracy": 0.16407241821289062,
|
|
"num_tokens": 5431930.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.505523586273194,
|
|
"epoch": 0.24682592716338123,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996992837848021,
|
|
"loss": 5.4793,
|
|
"mean_token_accuracy": 0.17200600057840348,
|
|
"num_tokens": 5440721.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.553699064254761,
|
|
"epoch": 0.24724356832609423,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996977431833342,
|
|
"loss": 5.5793,
|
|
"mean_token_accuracy": 0.16132830679416657,
|
|
"num_tokens": 5449617.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.643174505233764,
|
|
"epoch": 0.2476612094888072,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996961986482618,
|
|
"loss": 5.5937,
|
|
"mean_token_accuracy": 0.1634842649102211,
|
|
"num_tokens": 5458827.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.602717494964599,
|
|
"epoch": 0.24807885065152022,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996946501796119,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.16593398451805114,
|
|
"num_tokens": 5467348.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.6201794147491455,
|
|
"epoch": 0.24849649181423322,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996930977774118,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.15850166752934455,
|
|
"num_tokens": 5476645.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.603331804275513,
|
|
"epoch": 0.2489141329769462,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996915414416885,
|
|
"loss": 5.6015,
|
|
"mean_token_accuracy": 0.16163256764411926,
|
|
"num_tokens": 5486120.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.723821020126342,
|
|
"epoch": 0.2493317741396592,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996899811724693,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.16415408551692962,
|
|
"num_tokens": 5495313.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.556124019622803,
|
|
"epoch": 0.2497494153023722,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996884169697816,
|
|
"loss": 5.5648,
|
|
"mean_token_accuracy": 0.1665556788444519,
|
|
"num_tokens": 5504587.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.50765814781189,
|
|
"epoch": 0.2501670564650852,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996868488336526,
|
|
"loss": 5.5771,
|
|
"mean_token_accuracy": 0.16290449798107148,
|
|
"num_tokens": 5514188.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.618584823608399,
|
|
"epoch": 0.25058469762779817,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996852767641099,
|
|
"loss": 5.6273,
|
|
"mean_token_accuracy": 0.15422473549842836,
|
|
"num_tokens": 5524075.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.25058469762779817,
|
|
"eval_entropy": 5.509505016473965,
|
|
"eval_loss": 5.556960582733154,
|
|
"eval_mean_token_accuracy": 0.17263090768795453,
|
|
"eval_num_tokens": 5524075.0,
|
|
"eval_runtime": 27.5065,
|
|
"eval_samples_per_second": 1372.876,
|
|
"eval_steps_per_second": 171.632,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.569910383224487,
|
|
"epoch": 0.2510023387905112,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996837007611811,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.17270380705595018,
|
|
"num_tokens": 5533323.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.512850713729859,
|
|
"epoch": 0.2514199799532242,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996821208248935,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.1709403544664383,
|
|
"num_tokens": 5542288.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.643501949310303,
|
|
"epoch": 0.25183762111593716,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004996805369552749,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.16013893485069275,
|
|
"num_tokens": 5550869.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.553315210342407,
|
|
"epoch": 0.2522552622786502,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996789491523532,
|
|
"loss": 5.518,
|
|
"mean_token_accuracy": 0.17317127138376237,
|
|
"num_tokens": 5560147.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.490715360641479,
|
|
"epoch": 0.2526729034413632,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996773574161559,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.17456791847944259,
|
|
"num_tokens": 5568358.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.506763458251953,
|
|
"epoch": 0.25309054460407615,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996757617467112,
|
|
"loss": 5.5345,
|
|
"mean_token_accuracy": 0.1621170625090599,
|
|
"num_tokens": 5577755.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.613587951660156,
|
|
"epoch": 0.2535081857667892,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996741621440466,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.15454234480857848,
|
|
"num_tokens": 5587515.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.72170124053955,
|
|
"epoch": 0.25392582692950216,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996725586081906,
|
|
"loss": 5.714,
|
|
"mean_token_accuracy": 0.1539687216281891,
|
|
"num_tokens": 5597860.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.637978744506836,
|
|
"epoch": 0.25434346809221514,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996709511391709,
|
|
"loss": 5.5827,
|
|
"mean_token_accuracy": 0.1627292513847351,
|
|
"num_tokens": 5607302.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.61465163230896,
|
|
"epoch": 0.2547611092549282,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996693397370158,
|
|
"loss": 5.6451,
|
|
"mean_token_accuracy": 0.16155959963798522,
|
|
"num_tokens": 5616345.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.569490194320679,
|
|
"epoch": 0.25517875041764115,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996677244017534,
|
|
"loss": 5.4318,
|
|
"mean_token_accuracy": 0.16576905995607377,
|
|
"num_tokens": 5624745.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.563282489776611,
|
|
"epoch": 0.25559639158035413,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996661051334121,
|
|
"loss": 5.5633,
|
|
"mean_token_accuracy": 0.15848383605480193,
|
|
"num_tokens": 5634022.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.600382471084595,
|
|
"epoch": 0.25601403274306717,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996644819320201,
|
|
"loss": 5.5028,
|
|
"mean_token_accuracy": 0.1660987839102745,
|
|
"num_tokens": 5643631.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.613489151000977,
|
|
"epoch": 0.25643167390578014,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996628547976061,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.16259165555238725,
|
|
"num_tokens": 5653155.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.604352855682373,
|
|
"epoch": 0.2568493150684932,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996612237301983,
|
|
"loss": 5.6001,
|
|
"mean_token_accuracy": 0.16388349682092668,
|
|
"num_tokens": 5663091.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.540670013427734,
|
|
"epoch": 0.25726695623120616,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996595887298254,
|
|
"loss": 5.493,
|
|
"mean_token_accuracy": 0.17306645065546036,
|
|
"num_tokens": 5671885.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.618255376815796,
|
|
"epoch": 0.25768459739391913,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499657949796516,
|
|
"loss": 5.52,
|
|
"mean_token_accuracy": 0.16467965692281722,
|
|
"num_tokens": 5680225.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.434331464767456,
|
|
"epoch": 0.25810223855663217,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996563069302986,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.17379649877548217,
|
|
"num_tokens": 5689456.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.517268896102905,
|
|
"epoch": 0.25851987971934515,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996546601312023,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.16643043011426925,
|
|
"num_tokens": 5698127.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.621622753143311,
|
|
"epoch": 0.2589375208820581,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996530093992558,
|
|
"loss": 5.545,
|
|
"mean_token_accuracy": 0.17133604288101195,
|
|
"num_tokens": 5706825.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.556325244903564,
|
|
"epoch": 0.25935516204477116,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996513547344877,
|
|
"loss": 5.494,
|
|
"mean_token_accuracy": 0.1657831236720085,
|
|
"num_tokens": 5715677.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.503501224517822,
|
|
"epoch": 0.25977280320748414,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996496961369274,
|
|
"loss": 5.4165,
|
|
"mean_token_accuracy": 0.17088277041912078,
|
|
"num_tokens": 5725371.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.553598070144654,
|
|
"epoch": 0.2601904443701971,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996480336066037,
|
|
"loss": 5.521,
|
|
"mean_token_accuracy": 0.1708841696381569,
|
|
"num_tokens": 5734664.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.573401355743409,
|
|
"epoch": 0.26060808553291015,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996463671435458,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.1694071963429451,
|
|
"num_tokens": 5743870.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.507350969314575,
|
|
"epoch": 0.26102572669562313,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996446967477829,
|
|
"loss": 5.5359,
|
|
"mean_token_accuracy": 0.16690430790185928,
|
|
"num_tokens": 5752855.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.639628314971924,
|
|
"epoch": 0.2614433678583361,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996430224193441,
|
|
"loss": 5.5937,
|
|
"mean_token_accuracy": 0.1663447767496109,
|
|
"num_tokens": 5762435.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.607776641845703,
|
|
"epoch": 0.26186100902104914,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996413441582589,
|
|
"loss": 5.5813,
|
|
"mean_token_accuracy": 0.16195459812879562,
|
|
"num_tokens": 5771463.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.624371004104614,
|
|
"epoch": 0.2622786501837621,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996396619645564,
|
|
"loss": 5.5852,
|
|
"mean_token_accuracy": 0.15886165350675582,
|
|
"num_tokens": 5780530.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.553997278213501,
|
|
"epoch": 0.2626962913464751,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996379758382662,
|
|
"loss": 5.4534,
|
|
"mean_token_accuracy": 0.17759004533290862,
|
|
"num_tokens": 5789199.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.69573564529419,
|
|
"epoch": 0.26311393250918813,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499636285779418,
|
|
"loss": 5.65,
|
|
"mean_token_accuracy": 0.16340592503547668,
|
|
"num_tokens": 5799170.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.620092391967773,
|
|
"epoch": 0.2635315736719011,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996345917880412,
|
|
"loss": 5.5493,
|
|
"mean_token_accuracy": 0.16142655313014984,
|
|
"num_tokens": 5807662.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.4721107006073,
|
|
"epoch": 0.2639492148346141,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996328938641654,
|
|
"loss": 5.4585,
|
|
"mean_token_accuracy": 0.16569848209619523,
|
|
"num_tokens": 5815790.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.6283488273620605,
|
|
"epoch": 0.2643668559973271,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996311920078204,
|
|
"loss": 5.4755,
|
|
"mean_token_accuracy": 0.17084998786449432,
|
|
"num_tokens": 5824746.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.486237382888794,
|
|
"epoch": 0.2647844971600401,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996294862190361,
|
|
"loss": 5.4854,
|
|
"mean_token_accuracy": 0.1715046674013138,
|
|
"num_tokens": 5833678.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.528229284286499,
|
|
"epoch": 0.2652021383227531,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499627776497842,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.16838407665491104,
|
|
"num_tokens": 5842218.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.754685544967652,
|
|
"epoch": 0.2656197794854661,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996260628442686,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.15619731843471527,
|
|
"num_tokens": 5853250.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.566620397567749,
|
|
"epoch": 0.2660374206481791,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996243452583454,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.17067957371473313,
|
|
"num_tokens": 5862661.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.601086616516113,
|
|
"epoch": 0.26645506181089207,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996226237401028,
|
|
"loss": 5.6168,
|
|
"mean_token_accuracy": 0.1654422849416733,
|
|
"num_tokens": 5872327.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.52212347984314,
|
|
"epoch": 0.2668727029736051,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996208982895706,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.16680678874254226,
|
|
"num_tokens": 5881539.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.622729396820068,
|
|
"epoch": 0.2672903441363181,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996191689067794,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.1628652647137642,
|
|
"num_tokens": 5891602.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.5512511253356935,
|
|
"epoch": 0.26770798529903106,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996174355917591,
|
|
"loss": 5.5499,
|
|
"mean_token_accuracy": 0.1703685149550438,
|
|
"num_tokens": 5899831.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.700180721282959,
|
|
"epoch": 0.2681256264617441,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996156983445404,
|
|
"loss": 5.666,
|
|
"mean_token_accuracy": 0.15713129043579102,
|
|
"num_tokens": 5909193.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.683463907241821,
|
|
"epoch": 0.26854326762445707,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996139571651534,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.1625669240951538,
|
|
"num_tokens": 5919353.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.471538925170899,
|
|
"epoch": 0.26896090878717005,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996122120536288,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.1690175250172615,
|
|
"num_tokens": 5927853.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.503655052185058,
|
|
"epoch": 0.2693785499498831,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996104630099969,
|
|
"loss": 5.6065,
|
|
"mean_token_accuracy": 0.1630278766155243,
|
|
"num_tokens": 5937943.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.63100643157959,
|
|
"epoch": 0.26979619111259606,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996087100342885,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.17056625485420226,
|
|
"num_tokens": 5946213.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.515283298492432,
|
|
"epoch": 0.27021383227530904,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996069531265345,
|
|
"loss": 5.4122,
|
|
"mean_token_accuracy": 0.1662533089518547,
|
|
"num_tokens": 5954997.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.515188264846802,
|
|
"epoch": 0.2706314734380221,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996051922867653,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.17493584454059602,
|
|
"num_tokens": 5963947.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.549450969696045,
|
|
"epoch": 0.27104911460073505,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996034275150118,
|
|
"loss": 5.4948,
|
|
"mean_token_accuracy": 0.1700539380311966,
|
|
"num_tokens": 5972077.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.467683124542236,
|
|
"epoch": 0.27146675576344803,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499601658811305,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.1693744868040085,
|
|
"num_tokens": 5982649.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.608425951004028,
|
|
"epoch": 0.27188439692616106,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995998861756758,
|
|
"loss": 5.5166,
|
|
"mean_token_accuracy": 0.16742232888936998,
|
|
"num_tokens": 5991349.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.506754159927368,
|
|
"epoch": 0.27230203808887404,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995981096081552,
|
|
"loss": 5.4893,
|
|
"mean_token_accuracy": 0.17103740125894545,
|
|
"num_tokens": 6000555.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.731655216217041,
|
|
"epoch": 0.272719679251587,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995963291087744,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.1574689731001854,
|
|
"num_tokens": 6009554.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.605317401885986,
|
|
"epoch": 0.27313732041430006,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995945446775645,
|
|
"loss": 5.7056,
|
|
"mean_token_accuracy": 0.15773640125989913,
|
|
"num_tokens": 6019330.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.691388893127441,
|
|
"epoch": 0.27355496157701303,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995927563145566,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.16591110527515412,
|
|
"num_tokens": 6028527.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.584264707565308,
|
|
"epoch": 0.273972602739726,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995909640197825,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.17068353593349456,
|
|
"num_tokens": 6038223.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.459718418121338,
|
|
"epoch": 0.27439024390243905,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995891677932729,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.1723234698176384,
|
|
"num_tokens": 6047459.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.680184316635132,
|
|
"epoch": 0.274807885065152,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995873676350597,
|
|
"loss": 5.6245,
|
|
"mean_token_accuracy": 0.16481543332338333,
|
|
"num_tokens": 6057322.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.61651577949524,
|
|
"epoch": 0.275225526227865,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995855635451743,
|
|
"loss": 5.7453,
|
|
"mean_token_accuracy": 0.15445435047149658,
|
|
"num_tokens": 6067520.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.5944427967071535,
|
|
"epoch": 0.27564316739057804,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995837555236484,
|
|
"loss": 5.6221,
|
|
"mean_token_accuracy": 0.16172602623701096,
|
|
"num_tokens": 6076729.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.6910748958587645,
|
|
"epoch": 0.276060808553291,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995819435705133,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.1596569076180458,
|
|
"num_tokens": 6086529.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.6409749507904055,
|
|
"epoch": 0.276478449716004,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995801276858011,
|
|
"loss": 5.5777,
|
|
"mean_token_accuracy": 0.1702018052339554,
|
|
"num_tokens": 6095784.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.68081955909729,
|
|
"epoch": 0.276896090878717,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995783078695434,
|
|
"loss": 5.5926,
|
|
"mean_token_accuracy": 0.16117540150880813,
|
|
"num_tokens": 6104626.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.550822114944458,
|
|
"epoch": 0.27731373204143,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499576484121772,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.17098721265792846,
|
|
"num_tokens": 6113758.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.594186162948608,
|
|
"epoch": 0.277731373204143,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995746564425191,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.16868577748537064,
|
|
"num_tokens": 6123265.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.6335364818573,
|
|
"epoch": 0.278149014366856,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995728248318163,
|
|
"loss": 5.5909,
|
|
"mean_token_accuracy": 0.1608134001493454,
|
|
"num_tokens": 6132855.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.496687221527099,
|
|
"epoch": 0.278566655529569,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995709892896961,
|
|
"loss": 5.4769,
|
|
"mean_token_accuracy": 0.1676080346107483,
|
|
"num_tokens": 6142739.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.513911485671997,
|
|
"epoch": 0.278984296692282,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995691498161903,
|
|
"loss": 5.4272,
|
|
"mean_token_accuracy": 0.17005877643823625,
|
|
"num_tokens": 6152169.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.4408985614776615,
|
|
"epoch": 0.279401937854995,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995673064113313,
|
|
"loss": 5.4454,
|
|
"mean_token_accuracy": 0.1737777844071388,
|
|
"num_tokens": 6160235.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.525840425491333,
|
|
"epoch": 0.279819579017708,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995654590751513,
|
|
"loss": 5.4355,
|
|
"mean_token_accuracy": 0.1697912961244583,
|
|
"num_tokens": 6169440.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.500869989395142,
|
|
"epoch": 0.28023722018042097,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995636078076825,
|
|
"loss": 5.4715,
|
|
"mean_token_accuracy": 0.17083757370710373,
|
|
"num_tokens": 6178456.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.51913628578186,
|
|
"epoch": 0.280654861343134,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995617526089575,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.16220356673002242,
|
|
"num_tokens": 6186844.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.555132722854614,
|
|
"epoch": 0.281072502505847,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995598934790087,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.17172517627477646,
|
|
"num_tokens": 6196117.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.563861608505249,
|
|
"epoch": 0.28149014366855996,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995580304178687,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.17228131592273713,
|
|
"num_tokens": 6204636.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.4404088973999025,
|
|
"epoch": 0.281907784831273,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995561634255701,
|
|
"loss": 5.4745,
|
|
"mean_token_accuracy": 0.16716700941324233,
|
|
"num_tokens": 6214537.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.527120113372803,
|
|
"epoch": 0.28232542599398597,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995542925021455,
|
|
"loss": 5.5406,
|
|
"mean_token_accuracy": 0.1637692406773567,
|
|
"num_tokens": 6224753.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.791276264190674,
|
|
"epoch": 0.28274306715669895,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995524176476277,
|
|
"loss": 5.7233,
|
|
"mean_token_accuracy": 0.16027000695466995,
|
|
"num_tokens": 6233842.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.6728884220123295,
|
|
"epoch": 0.283160708319412,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995505388620497,
|
|
"loss": 5.5529,
|
|
"mean_token_accuracy": 0.1680996060371399,
|
|
"num_tokens": 6243467.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.4875246524810795,
|
|
"epoch": 0.28357834948212496,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499548656145444,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.1577073633670807,
|
|
"num_tokens": 6253263.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.601888036727905,
|
|
"epoch": 0.28399599064483794,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995467694978439,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.17447730600833894,
|
|
"num_tokens": 6262249.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.494926261901855,
|
|
"epoch": 0.28441363180755097,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995448789192823,
|
|
"loss": 5.4555,
|
|
"mean_token_accuracy": 0.17069571316242219,
|
|
"num_tokens": 6271154.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.508152675628662,
|
|
"epoch": 0.28483127297026395,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995429844097922,
|
|
"loss": 5.5272,
|
|
"mean_token_accuracy": 0.174279648065567,
|
|
"num_tokens": 6280377.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.585491943359375,
|
|
"epoch": 0.2852489141329769,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995410859694071,
|
|
"loss": 5.5373,
|
|
"mean_token_accuracy": 0.1684752508997917,
|
|
"num_tokens": 6289941.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.544521903991699,
|
|
"epoch": 0.28566655529568996,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995391835981599,
|
|
"loss": 5.5944,
|
|
"mean_token_accuracy": 0.16231686770915985,
|
|
"num_tokens": 6299281.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.651609754562378,
|
|
"epoch": 0.28608419645840294,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499537277296084,
|
|
"loss": 5.5407,
|
|
"mean_token_accuracy": 0.1607593074440956,
|
|
"num_tokens": 6309408.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.559070634841919,
|
|
"epoch": 0.2865018376211159,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995353670632127,
|
|
"loss": 5.5428,
|
|
"mean_token_accuracy": 0.16397647708654403,
|
|
"num_tokens": 6318979.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.495109891891479,
|
|
"epoch": 0.28691947878382895,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995334528995797,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.18039173036813735,
|
|
"num_tokens": 6327616.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.461599111557007,
|
|
"epoch": 0.28733711994654193,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995315348052182,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.17610692828893662,
|
|
"num_tokens": 6336486.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.5086901664733885,
|
|
"epoch": 0.2877547611092549,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499529612780162,
|
|
"loss": 5.4734,
|
|
"mean_token_accuracy": 0.16618863493204117,
|
|
"num_tokens": 6345671.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.6285436153411865,
|
|
"epoch": 0.28817240227196794,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995276868244446,
|
|
"loss": 5.5721,
|
|
"mean_token_accuracy": 0.16796167194843292,
|
|
"num_tokens": 6354534.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.510032081604004,
|
|
"epoch": 0.2885900434346809,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995257569380998,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.17104145437479018,
|
|
"num_tokens": 6364052.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.539919042587281,
|
|
"epoch": 0.2890076845973939,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995238231211614,
|
|
"loss": 5.5457,
|
|
"mean_token_accuracy": 0.1703997939825058,
|
|
"num_tokens": 6373305.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.5487676620483395,
|
|
"epoch": 0.28942532576010693,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995218853736631,
|
|
"loss": 5.4752,
|
|
"mean_token_accuracy": 0.16317730098962785,
|
|
"num_tokens": 6382673.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.597512865066529,
|
|
"epoch": 0.2898429669228199,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995199436956391,
|
|
"loss": 5.5808,
|
|
"mean_token_accuracy": 0.16054316014051437,
|
|
"num_tokens": 6392122.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.643544769287109,
|
|
"epoch": 0.2902606080855329,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995179980871231,
|
|
"loss": 5.5854,
|
|
"mean_token_accuracy": 0.16072637736797332,
|
|
"num_tokens": 6401130.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.538010168075561,
|
|
"epoch": 0.2906782492482459,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995160485481493,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.16509442627429963,
|
|
"num_tokens": 6409471.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.478931093215943,
|
|
"epoch": 0.2910958904109589,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499514095078752,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.16667304188013077,
|
|
"num_tokens": 6418902.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.574909925460815,
|
|
"epoch": 0.2915135315736719,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499512137678965,
|
|
"loss": 5.5514,
|
|
"mean_token_accuracy": 0.16285862326622008,
|
|
"num_tokens": 6428529.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.5814121723175045,
|
|
"epoch": 0.2919311727363849,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995101763488229,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.1701946422457695,
|
|
"num_tokens": 6437460.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.531909990310669,
|
|
"epoch": 0.2923488138990979,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995082110883599,
|
|
"loss": 5.4605,
|
|
"mean_token_accuracy": 0.17182532101869583,
|
|
"num_tokens": 6446005.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.5357420444488525,
|
|
"epoch": 0.29276645506181087,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995062418976104,
|
|
"loss": 5.5271,
|
|
"mean_token_accuracy": 0.16687075346708297,
|
|
"num_tokens": 6455241.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.548692512512207,
|
|
"epoch": 0.2931840962245239,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995042687766089,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.1705710157752037,
|
|
"num_tokens": 6464748.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.615511178970337,
|
|
"epoch": 0.2936017373872369,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995022917253899,
|
|
"loss": 5.5552,
|
|
"mean_token_accuracy": 0.1701499566435814,
|
|
"num_tokens": 6473834.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.533133888244629,
|
|
"epoch": 0.29401937854994986,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995003107439882,
|
|
"loss": 5.4936,
|
|
"mean_token_accuracy": 0.16701297461986542,
|
|
"num_tokens": 6482169.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.459322071075439,
|
|
"epoch": 0.2944370197126629,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994983258324383,
|
|
"loss": 5.4392,
|
|
"mean_token_accuracy": 0.1680704489350319,
|
|
"num_tokens": 6491798.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.4757795333862305,
|
|
"epoch": 0.2948546608753759,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994963369907748,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.16915201246738434,
|
|
"num_tokens": 6500143.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.4345615863800045,
|
|
"epoch": 0.29527230203808885,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994943442190328,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.16544250398874283,
|
|
"num_tokens": 6509745.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.650967645645141,
|
|
"epoch": 0.2956899432008019,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994923475172471,
|
|
"loss": 5.5848,
|
|
"mean_token_accuracy": 0.15887098908424377,
|
|
"num_tokens": 6520931.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.5606303215026855,
|
|
"epoch": 0.29610758436351486,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994903468854527,
|
|
"loss": 5.5197,
|
|
"mean_token_accuracy": 0.16634719371795653,
|
|
"num_tokens": 6529774.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.544323110580445,
|
|
"epoch": 0.29652522552622784,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994883423236843,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.16737744957208633,
|
|
"num_tokens": 6538922.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.524617290496826,
|
|
"epoch": 0.2969428666889409,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994863338319775,
|
|
"loss": 5.4913,
|
|
"mean_token_accuracy": 0.17015527039766312,
|
|
"num_tokens": 6548891.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.405666828155518,
|
|
"epoch": 0.29736050785165385,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994843214103672,
|
|
"loss": 5.306,
|
|
"mean_token_accuracy": 0.17207494229078293,
|
|
"num_tokens": 6557025.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.56685996055603,
|
|
"epoch": 0.29777814901436683,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994823050588886,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.16344626247882843,
|
|
"num_tokens": 6567037.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.533381080627441,
|
|
"epoch": 0.29819579017707987,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499480284777577,
|
|
"loss": 5.5141,
|
|
"mean_token_accuracy": 0.1677533283829689,
|
|
"num_tokens": 6576766.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.5538324356079105,
|
|
"epoch": 0.29861343133979285,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994782605664677,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.16958095133304596,
|
|
"num_tokens": 6585576.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.584893608093262,
|
|
"epoch": 0.2990310725025058,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994762324255965,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.16368599086999894,
|
|
"num_tokens": 6594463.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.512655591964721,
|
|
"epoch": 0.29944871366521886,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994742003549986,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.16809990853071213,
|
|
"num_tokens": 6603651.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.561243295669556,
|
|
"epoch": 0.29986635482793184,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994721643547095,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.16976088881492615,
|
|
"num_tokens": 6612950.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.553755426406861,
|
|
"epoch": 0.3002839959906448,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499470124424765,
|
|
"loss": 5.44,
|
|
"mean_token_accuracy": 0.17298568338155745,
|
|
"num_tokens": 6622013.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.548866319656372,
|
|
"epoch": 0.30070163715335785,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994680805652008,
|
|
"loss": 5.5163,
|
|
"mean_token_accuracy": 0.16933971494436265,
|
|
"num_tokens": 6632046.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.511341762542725,
|
|
"epoch": 0.3011192783160708,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994660327760527,
|
|
"loss": 5.5702,
|
|
"mean_token_accuracy": 0.17278106957674028,
|
|
"num_tokens": 6641169.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.510961246490479,
|
|
"epoch": 0.3015369194787838,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994639810573565,
|
|
"loss": 5.3725,
|
|
"mean_token_accuracy": 0.17695365101099014,
|
|
"num_tokens": 6649663.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.623845148086548,
|
|
"epoch": 0.30195456064149684,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499461925409148,
|
|
"loss": 5.5665,
|
|
"mean_token_accuracy": 0.16110052913427353,
|
|
"num_tokens": 6659448.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.590248870849609,
|
|
"epoch": 0.3023722018042098,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994598658314634,
|
|
"loss": 5.5246,
|
|
"mean_token_accuracy": 0.16626361906528472,
|
|
"num_tokens": 6670314.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.511123561859131,
|
|
"epoch": 0.3027898429669228,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994578023243386,
|
|
"loss": 5.4871,
|
|
"mean_token_accuracy": 0.1732531487941742,
|
|
"num_tokens": 6679413.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.49867696762085,
|
|
"epoch": 0.30320748412963583,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994557348878098,
|
|
"loss": 5.4627,
|
|
"mean_token_accuracy": 0.17419134676456452,
|
|
"num_tokens": 6688439.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.5494426727294925,
|
|
"epoch": 0.3036251252923488,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994536635219133,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.17038834542036058,
|
|
"num_tokens": 6697471.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.586328601837158,
|
|
"epoch": 0.3040427664550618,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994515882266852,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.17040248662233354,
|
|
"num_tokens": 6706698.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.415295648574829,
|
|
"epoch": 0.3044604076177748,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994495090021618,
|
|
"loss": 5.4289,
|
|
"mean_token_accuracy": 0.17661873996257782,
|
|
"num_tokens": 6715676.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.427714014053345,
|
|
"epoch": 0.3048780487804878,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994474258483796,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.17413119971752167,
|
|
"num_tokens": 6723818.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.544740056991577,
|
|
"epoch": 0.3052956899432008,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994453387653751,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.1687764897942543,
|
|
"num_tokens": 6733450.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.481561374664307,
|
|
"epoch": 0.3057133311059138,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994432477531847,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.17082249820232392,
|
|
"num_tokens": 6743142.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.436155891418457,
|
|
"epoch": 0.3061309722686268,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994411528118452,
|
|
"loss": 5.3768,
|
|
"mean_token_accuracy": 0.17255899906158448,
|
|
"num_tokens": 6752185.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.477898073196411,
|
|
"epoch": 0.30654861343133977,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994390539413931,
|
|
"loss": 5.4623,
|
|
"mean_token_accuracy": 0.17468517869710923,
|
|
"num_tokens": 6761549.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.549196720123291,
|
|
"epoch": 0.3069662545940528,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994369511418652,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.17020693123340608,
|
|
"num_tokens": 6770395.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.6494293212890625,
|
|
"epoch": 0.3073838957567658,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994348444132983,
|
|
"loss": 5.5408,
|
|
"mean_token_accuracy": 0.17074840813875197,
|
|
"num_tokens": 6779154.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.391846179962158,
|
|
"epoch": 0.30780153691947876,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994327337557293,
|
|
"loss": 5.4393,
|
|
"mean_token_accuracy": 0.17821680009365082,
|
|
"num_tokens": 6789263.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.5761597633361815,
|
|
"epoch": 0.3082191780821918,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994306191691952,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.16877364367246628,
|
|
"num_tokens": 6797985.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.486738443374634,
|
|
"epoch": 0.30863681924490477,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994285006537329,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.1722109720110893,
|
|
"num_tokens": 6807566.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.487214660644531,
|
|
"epoch": 0.30905446040761775,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994263782093796,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.17012524008750915,
|
|
"num_tokens": 6815637.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.505376195907592,
|
|
"epoch": 0.3094721015703308,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994242518361723,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.17713512480258942,
|
|
"num_tokens": 6823721.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.575809669494629,
|
|
"epoch": 0.30988974273304376,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994221215341484,
|
|
"loss": 5.5168,
|
|
"mean_token_accuracy": 0.17037255465984344,
|
|
"num_tokens": 6833437.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.5108507633209225,
|
|
"epoch": 0.31030738389575674,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994199873033452,
|
|
"loss": 5.5761,
|
|
"mean_token_accuracy": 0.171338027715683,
|
|
"num_tokens": 6842287.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.590300798416138,
|
|
"epoch": 0.3107250250584698,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994178491437999,
|
|
"loss": 5.4002,
|
|
"mean_token_accuracy": 0.16826316267251967,
|
|
"num_tokens": 6851520.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.475397777557373,
|
|
"epoch": 0.31114266622118275,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994157070555501,
|
|
"loss": 5.4696,
|
|
"mean_token_accuracy": 0.17000560760498046,
|
|
"num_tokens": 6861219.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.603476238250733,
|
|
"epoch": 0.31156030738389573,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994135610386331,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.16594088822603226,
|
|
"num_tokens": 6870525.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.626299047470093,
|
|
"epoch": 0.31197794854660876,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994114110930867,
|
|
"loss": 5.52,
|
|
"mean_token_accuracy": 0.16624996811151505,
|
|
"num_tokens": 6880183.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.512535762786865,
|
|
"epoch": 0.31239558970932174,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994092572189483,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.1618015468120575,
|
|
"num_tokens": 6890442.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.511465311050415,
|
|
"epoch": 0.3128132308720348,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994070994162558,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.17312270253896714,
|
|
"num_tokens": 6900091.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.496584510803222,
|
|
"epoch": 0.31323087203474775,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994049376850471,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.16660811454057695,
|
|
"num_tokens": 6910489.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.597193670272827,
|
|
"epoch": 0.31364851319746073,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994027720253596,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.16707699447870256,
|
|
"num_tokens": 6919895.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.6900543689727785,
|
|
"epoch": 0.31406615436017377,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994006024372315,
|
|
"loss": 5.6114,
|
|
"mean_token_accuracy": 0.16193894147872925,
|
|
"num_tokens": 6929511.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.477146863937378,
|
|
"epoch": 0.31448379552288674,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993984289207007,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.1762948825955391,
|
|
"num_tokens": 6938059.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.497006607055664,
|
|
"epoch": 0.3149014366855997,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993962514758054,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.1702394813299179,
|
|
"num_tokens": 6946894.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.554160165786743,
|
|
"epoch": 0.31531907784831276,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004993940701025836,
|
|
"loss": 5.4148,
|
|
"mean_token_accuracy": 0.16560422331094743,
|
|
"num_tokens": 6955494.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.455316400527954,
|
|
"epoch": 0.31573671901102573,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993918848010734,
|
|
"loss": 5.5254,
|
|
"mean_token_accuracy": 0.16878335326910018,
|
|
"num_tokens": 6964347.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.533470582962036,
|
|
"epoch": 0.3161543601737387,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993896955713133,
|
|
"loss": 5.4786,
|
|
"mean_token_accuracy": 0.1637830153107643,
|
|
"num_tokens": 6974750.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.582107496261597,
|
|
"epoch": 0.31657200133645175,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993875024133414,
|
|
"loss": 5.4921,
|
|
"mean_token_accuracy": 0.17069665789604188,
|
|
"num_tokens": 6984228.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.4917913436889645,
|
|
"epoch": 0.3169896424991647,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993853053271962,
|
|
"loss": 5.4694,
|
|
"mean_token_accuracy": 0.16878245770931244,
|
|
"num_tokens": 6993173.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.706063556671142,
|
|
"epoch": 0.3174072836618777,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993831043129161,
|
|
"loss": 5.6669,
|
|
"mean_token_accuracy": 0.1557183623313904,
|
|
"num_tokens": 7003486.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.500661993026734,
|
|
"epoch": 0.31782492482459074,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993808993705397,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.1763479545712471,
|
|
"num_tokens": 7011985.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.481622362136841,
|
|
"epoch": 0.3182425659873037,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993786905001055,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.17533033937215806,
|
|
"num_tokens": 7021148.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.464303827285766,
|
|
"epoch": 0.3186602071500167,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993764777016524,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.16824772357940673,
|
|
"num_tokens": 7030110.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.539179086685181,
|
|
"epoch": 0.31907784831272973,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993742609752188,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.17360101789236068,
|
|
"num_tokens": 7039428.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.614913988113403,
|
|
"epoch": 0.3194954894754427,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993720403208438,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.16541504263877868,
|
|
"num_tokens": 7048703.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.552296113967896,
|
|
"epoch": 0.3199131306381557,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499369815738566,
|
|
"loss": 5.4614,
|
|
"mean_token_accuracy": 0.1668523982167244,
|
|
"num_tokens": 7057612.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.5432675838470455,
|
|
"epoch": 0.3203307718008687,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993675872284248,
|
|
"loss": 5.416,
|
|
"mean_token_accuracy": 0.17318572700023652,
|
|
"num_tokens": 7066660.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.433846664428711,
|
|
"epoch": 0.3207484129635817,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993653547904586,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.16264898627996444,
|
|
"num_tokens": 7075368.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.536958503723144,
|
|
"epoch": 0.3211660541262947,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499363118424707,
|
|
"loss": 5.5073,
|
|
"mean_token_accuracy": 0.17436618506908416,
|
|
"num_tokens": 7085276.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.533533716201783,
|
|
"epoch": 0.3215836952890077,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993608781312088,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.16549077928066253,
|
|
"num_tokens": 7094292.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.648198843002319,
|
|
"epoch": 0.3220013364517207,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993586339100035,
|
|
"loss": 5.676,
|
|
"mean_token_accuracy": 0.1579186387360096,
|
|
"num_tokens": 7104712.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.6159360885620115,
|
|
"epoch": 0.32241897761443367,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993563857611301,
|
|
"loss": 5.4774,
|
|
"mean_token_accuracy": 0.17931303083896638,
|
|
"num_tokens": 7113297.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.473030376434326,
|
|
"epoch": 0.3228366187771467,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993541336846283,
|
|
"loss": 5.4821,
|
|
"mean_token_accuracy": 0.16101839244365693,
|
|
"num_tokens": 7122706.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.521943998336792,
|
|
"epoch": 0.3232542599398597,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993518776805372,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.1689613327383995,
|
|
"num_tokens": 7131939.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.393316602706909,
|
|
"epoch": 0.32367190110257266,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993496177488965,
|
|
"loss": 5.3407,
|
|
"mean_token_accuracy": 0.1780867889523506,
|
|
"num_tokens": 7141016.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.4151207447052006,
|
|
"epoch": 0.3240895422652857,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993473538897457,
|
|
"loss": 5.2848,
|
|
"mean_token_accuracy": 0.1836669310927391,
|
|
"num_tokens": 7149177.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.486827421188354,
|
|
"epoch": 0.32450718342799867,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993450861031243,
|
|
"loss": 5.4077,
|
|
"mean_token_accuracy": 0.17718248218297958,
|
|
"num_tokens": 7157839.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.62509331703186,
|
|
"epoch": 0.32492482459071165,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993428143890722,
|
|
"loss": 5.5658,
|
|
"mean_token_accuracy": 0.1595238044857979,
|
|
"num_tokens": 7167759.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.622683382034301,
|
|
"epoch": 0.3253424657534247,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993405387476291,
|
|
"loss": 5.506,
|
|
"mean_token_accuracy": 0.16096927523612975,
|
|
"num_tokens": 7177141.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.4179102897644045,
|
|
"epoch": 0.32576010691613766,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993382591788349,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.17410117983818055,
|
|
"num_tokens": 7185350.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.40603928565979,
|
|
"epoch": 0.32617774807885064,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993359756827293,
|
|
"loss": 5.3604,
|
|
"mean_token_accuracy": 0.1728378564119339,
|
|
"num_tokens": 7194073.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.532111930847168,
|
|
"epoch": 0.32659538924156367,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993336882593524,
|
|
"loss": 5.5315,
|
|
"mean_token_accuracy": 0.16291088610887527,
|
|
"num_tokens": 7203421.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.449473905563354,
|
|
"epoch": 0.32701303040427665,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993313969087444,
|
|
"loss": 5.2971,
|
|
"mean_token_accuracy": 0.1715938299894333,
|
|
"num_tokens": 7212548.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.540735912322998,
|
|
"epoch": 0.32743067156698963,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993291016309452,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.16757371574640273,
|
|
"num_tokens": 7221668.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.507889461517334,
|
|
"epoch": 0.32784831272970266,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499326802425995,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.1652974471449852,
|
|
"num_tokens": 7231775.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.555531215667725,
|
|
"epoch": 0.32826595389241564,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993244992939342,
|
|
"loss": 5.4767,
|
|
"mean_token_accuracy": 0.16909126937389374,
|
|
"num_tokens": 7241264.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.477525520324707,
|
|
"epoch": 0.3286835950551286,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499322192234803,
|
|
"loss": 5.491,
|
|
"mean_token_accuracy": 0.16701171547174454,
|
|
"num_tokens": 7250519.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.6636481285095215,
|
|
"epoch": 0.32910123621784165,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004993198812486418,
|
|
"loss": 5.5395,
|
|
"mean_token_accuracy": 0.16968121230602265,
|
|
"num_tokens": 7259533.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.493396806716919,
|
|
"epoch": 0.32951887738055463,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499317566335491,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.17070206999778748,
|
|
"num_tokens": 7268980.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.480592918395996,
|
|
"epoch": 0.3299365185432676,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993152474953913,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.16594725996255874,
|
|
"num_tokens": 7277126.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.528022766113281,
|
|
"epoch": 0.33035415970598064,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993129247283831,
|
|
"loss": 5.4208,
|
|
"mean_token_accuracy": 0.17594209760427476,
|
|
"num_tokens": 7286223.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.486289978027344,
|
|
"epoch": 0.3307718008686936,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993105980345071,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.1727459043264389,
|
|
"num_tokens": 7295054.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.5196291446685795,
|
|
"epoch": 0.3311894420314066,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993082674138042,
|
|
"loss": 5.4602,
|
|
"mean_token_accuracy": 0.16758015602827073,
|
|
"num_tokens": 7304502.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.555356788635254,
|
|
"epoch": 0.33160708319411963,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499305932866315,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.17165492922067643,
|
|
"num_tokens": 7314093.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.50099024772644,
|
|
"epoch": 0.3320247243568326,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993035943920805,
|
|
"loss": 5.4572,
|
|
"mean_token_accuracy": 0.1696681097149849,
|
|
"num_tokens": 7323059.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.6192985534667965,
|
|
"epoch": 0.3324423655195456,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993012519911416,
|
|
"loss": 5.5943,
|
|
"mean_token_accuracy": 0.16187372356653212,
|
|
"num_tokens": 7332596.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.532523775100708,
|
|
"epoch": 0.3328600066822586,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992989056635392,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.17754316031932832,
|
|
"num_tokens": 7341671.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.4355028629302975,
|
|
"epoch": 0.3332776478449716,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992965554093146,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.16645139306783677,
|
|
"num_tokens": 7350344.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.602485799789429,
|
|
"epoch": 0.3336952890076846,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992942012285086,
|
|
"loss": 5.5326,
|
|
"mean_token_accuracy": 0.1713624395430088,
|
|
"num_tokens": 7359844.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.554539442062378,
|
|
"epoch": 0.3341129301703976,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992918431211629,
|
|
"loss": 5.459,
|
|
"mean_token_accuracy": 0.17449632287025452,
|
|
"num_tokens": 7369377.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.482081747055053,
|
|
"epoch": 0.3345305713331106,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004992894810873183,
|
|
"loss": 5.4218,
|
|
"mean_token_accuracy": 0.1696226865053177,
|
|
"num_tokens": 7378814.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.451307106018066,
|
|
"epoch": 0.33494821249582357,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992871151270165,
|
|
"loss": 5.4135,
|
|
"mean_token_accuracy": 0.17543912082910537,
|
|
"num_tokens": 7387333.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.422832012176514,
|
|
"epoch": 0.3353658536585366,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992847452402986,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.16946215331554412,
|
|
"num_tokens": 7396895.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.565013027191162,
|
|
"epoch": 0.3357834948212496,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992823714272064,
|
|
"loss": 5.4491,
|
|
"mean_token_accuracy": 0.17337892353534698,
|
|
"num_tokens": 7406430.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.513153409957885,
|
|
"epoch": 0.33620113598396256,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992799936877813,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.1838814213871956,
|
|
"num_tokens": 7415224.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.508871841430664,
|
|
"epoch": 0.3366187771466756,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004992776120220649,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.15561454445123674,
|
|
"num_tokens": 7424250.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.605917835235596,
|
|
"epoch": 0.3370364183093886,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004992752264300989,
|
|
"loss": 5.4484,
|
|
"mean_token_accuracy": 0.1740364298224449,
|
|
"num_tokens": 7433579.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.412272262573242,
|
|
"epoch": 0.33745405947210155,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004992728369119252,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.17319910526275634,
|
|
"num_tokens": 7442621.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.564623546600342,
|
|
"epoch": 0.3378717006348146,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992704434675855,
|
|
"loss": 5.5085,
|
|
"mean_token_accuracy": 0.16694118827581406,
|
|
"num_tokens": 7452077.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.461846494674683,
|
|
"epoch": 0.33828934179752757,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992680460971218,
|
|
"loss": 5.4233,
|
|
"mean_token_accuracy": 0.17070491313934327,
|
|
"num_tokens": 7461146.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.454490232467651,
|
|
"epoch": 0.33870698296024054,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992656448005758,
|
|
"loss": 5.4145,
|
|
"mean_token_accuracy": 0.1729734495282173,
|
|
"num_tokens": 7470335.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.581266927719116,
|
|
"epoch": 0.3391246241229536,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992632395779899,
|
|
"loss": 5.4225,
|
|
"mean_token_accuracy": 0.16888627856969834,
|
|
"num_tokens": 7479458.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.372164392471314,
|
|
"epoch": 0.33954226528566656,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992608304294061,
|
|
"loss": 5.3918,
|
|
"mean_token_accuracy": 0.18086428940296173,
|
|
"num_tokens": 7488005.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.390970087051391,
|
|
"epoch": 0.33995990644837953,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004992584173548664,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.17391041666269302,
|
|
"num_tokens": 7496807.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.517978620529175,
|
|
"epoch": 0.34037754761109257,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992560003544131,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.17917752861976624,
|
|
"num_tokens": 7505383.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.567019414901734,
|
|
"epoch": 0.34079518877380555,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992535794280887,
|
|
"loss": 5.4743,
|
|
"mean_token_accuracy": 0.17009843438863753,
|
|
"num_tokens": 7515093.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.514645767211914,
|
|
"epoch": 0.3412128299365185,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992511545759354,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.16668404191732406,
|
|
"num_tokens": 7524067.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.358101844787598,
|
|
"epoch": 0.34163047109923156,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992487257979958,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.16984069496393203,
|
|
"num_tokens": 7533197.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.556244897842407,
|
|
"epoch": 0.34204811226194454,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992462930943123,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.16619593650102615,
|
|
"num_tokens": 7543030.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.518676137924194,
|
|
"epoch": 0.3424657534246575,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992438564649275,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.16660134345293046,
|
|
"num_tokens": 7551556.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.500174808502197,
|
|
"epoch": 0.34288339458737055,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992414159098841,
|
|
"loss": 5.3879,
|
|
"mean_token_accuracy": 0.17086076587438584,
|
|
"num_tokens": 7559284.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.574701356887817,
|
|
"epoch": 0.3433010357500835,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992389714292247,
|
|
"loss": 5.4981,
|
|
"mean_token_accuracy": 0.17423533499240876,
|
|
"num_tokens": 7568750.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.394807052612305,
|
|
"epoch": 0.3437186769127965,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992365230229922,
|
|
"loss": 5.358,
|
|
"mean_token_accuracy": 0.17588887065649034,
|
|
"num_tokens": 7578309.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.394585037231446,
|
|
"epoch": 0.34413631807550954,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992340706912295,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.17258904576301576,
|
|
"num_tokens": 7586760.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.459982442855835,
|
|
"epoch": 0.3445539592382225,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992316144339794,
|
|
"loss": 5.3502,
|
|
"mean_token_accuracy": 0.17693475484848023,
|
|
"num_tokens": 7595472.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.509391355514526,
|
|
"epoch": 0.3449716004009355,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992291542512852,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.15762064158916472,
|
|
"num_tokens": 7605663.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.513069915771484,
|
|
"epoch": 0.34538924156364853,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992266901431895,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.16975632905960084,
|
|
"num_tokens": 7616110.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.425395250320435,
|
|
"epoch": 0.3458068827263615,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992242221097358,
|
|
"loss": 5.3798,
|
|
"mean_token_accuracy": 0.17331961393356324,
|
|
"num_tokens": 7625311.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.4703614711761475,
|
|
"epoch": 0.3462245238890745,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992217501509672,
|
|
"loss": 5.4263,
|
|
"mean_token_accuracy": 0.16921253502368927,
|
|
"num_tokens": 7634562.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.426385354995728,
|
|
"epoch": 0.3466421650517875,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499219274266927,
|
|
"loss": 5.3567,
|
|
"mean_token_accuracy": 0.1739166870713234,
|
|
"num_tokens": 7643231.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.488095760345459,
|
|
"epoch": 0.3470598062145005,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992167944576584,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.1696464702486992,
|
|
"num_tokens": 7653556.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.533686256408691,
|
|
"epoch": 0.3474774473772135,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499214310723205,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.17667534947395325,
|
|
"num_tokens": 7662295.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.381580638885498,
|
|
"epoch": 0.3478950885399265,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992118230636102,
|
|
"loss": 5.4204,
|
|
"mean_token_accuracy": 0.1728316977620125,
|
|
"num_tokens": 7671429.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.365633487701416,
|
|
"epoch": 0.3483127297026395,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992093314789176,
|
|
"loss": 5.3271,
|
|
"mean_token_accuracy": 0.17085648328065872,
|
|
"num_tokens": 7680589.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.469932985305786,
|
|
"epoch": 0.34873037086535247,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992068359691707,
|
|
"loss": 5.3909,
|
|
"mean_token_accuracy": 0.17552734017372132,
|
|
"num_tokens": 7689005.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.3601926326751705,
|
|
"epoch": 0.3491480120280655,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992043365344132,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.179109425842762,
|
|
"num_tokens": 7698231.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.508357238769531,
|
|
"epoch": 0.3495656531907785,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992018331746891,
|
|
"loss": 5.4168,
|
|
"mean_token_accuracy": 0.17373043149709702,
|
|
"num_tokens": 7706678.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.527340984344482,
|
|
"epoch": 0.34998329435349146,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991993258900418,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.17227416336536408,
|
|
"num_tokens": 7715506.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.5114830493927,
|
|
"epoch": 0.3504009355162045,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991968146805156,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.17181310206651687,
|
|
"num_tokens": 7726549.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.487708234786988,
|
|
"epoch": 0.35081857667891747,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991942995461542,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.16997541934251786,
|
|
"num_tokens": 7735563.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.518128681182861,
|
|
"epoch": 0.35123621784163045,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991917804870018,
|
|
"loss": 5.4587,
|
|
"mean_token_accuracy": 0.1694946900010109,
|
|
"num_tokens": 7746144.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.485707473754883,
|
|
"epoch": 0.3516538590043435,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991892575031024,
|
|
"loss": 5.465,
|
|
"mean_token_accuracy": 0.17360012531280516,
|
|
"num_tokens": 7755394.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.425092363357544,
|
|
"epoch": 0.35207150016705646,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991867305945001,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.17738278210163116,
|
|
"num_tokens": 7764855.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.414138317108154,
|
|
"epoch": 0.35248914132976944,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991841997612394,
|
|
"loss": 5.3436,
|
|
"mean_token_accuracy": 0.17033103108406067,
|
|
"num_tokens": 7773394.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.51355562210083,
|
|
"epoch": 0.3529067824924825,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991816650033643,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.1705158069729805,
|
|
"num_tokens": 7783111.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.555590009689331,
|
|
"epoch": 0.35332442365519545,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991791263209194,
|
|
"loss": 5.5372,
|
|
"mean_token_accuracy": 0.1695098474621773,
|
|
"num_tokens": 7792569.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.462711668014526,
|
|
"epoch": 0.35374206481790843,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991765837139491,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.17686702758073808,
|
|
"num_tokens": 7801483.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.537383937835694,
|
|
"epoch": 0.35415970598062146,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991740371824977,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.1594116598367691,
|
|
"num_tokens": 7812274.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.458338975906372,
|
|
"epoch": 0.35457734714333444,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049917148672661,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.17292539179325103,
|
|
"num_tokens": 7821101.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.504837369918823,
|
|
"epoch": 0.3549949883060474,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991689323463306,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.17464094161987304,
|
|
"num_tokens": 7829805.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.426690912246704,
|
|
"epoch": 0.35541262946876045,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991663740417042,
|
|
"loss": 5.4505,
|
|
"mean_token_accuracy": 0.1664499670267105,
|
|
"num_tokens": 7839772.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.460419940948486,
|
|
"epoch": 0.35583027063147343,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991638118127757,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.1616857022047043,
|
|
"num_tokens": 7850290.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.624797105789185,
|
|
"epoch": 0.3562479117941864,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991612456595896,
|
|
"loss": 5.5243,
|
|
"mean_token_accuracy": 0.16165591925382614,
|
|
"num_tokens": 7860180.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.3619715690612795,
|
|
"epoch": 0.35666555295689945,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004991586755821913,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.18035963475704192,
|
|
"num_tokens": 7869625.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.400491714477539,
|
|
"epoch": 0.3570831941196124,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991561015806254,
|
|
"loss": 5.3234,
|
|
"mean_token_accuracy": 0.17419369220733644,
|
|
"num_tokens": 7878671.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.5154108047485355,
|
|
"epoch": 0.3575008352823254,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991535236549372,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.1769440293312073,
|
|
"num_tokens": 7887225.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.422553300857544,
|
|
"epoch": 0.35791847644503844,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991509418051718,
|
|
"loss": 5.3329,
|
|
"mean_token_accuracy": 0.17964915335178375,
|
|
"num_tokens": 7895504.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.554728364944458,
|
|
"epoch": 0.3583361176077514,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991483560313743,
|
|
"loss": 5.3973,
|
|
"mean_token_accuracy": 0.17431385666131974,
|
|
"num_tokens": 7904875.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.465934371948242,
|
|
"epoch": 0.3587537587704644,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049914576633359,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.16960846036672592,
|
|
"num_tokens": 7914747.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.4626648902893065,
|
|
"epoch": 0.3591713999331774,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991431727118643,
|
|
"loss": 5.4289,
|
|
"mean_token_accuracy": 0.17281985133886338,
|
|
"num_tokens": 7923858.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.457186269760132,
|
|
"epoch": 0.3595890410958904,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991405751662426,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.1731380209326744,
|
|
"num_tokens": 7932396.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.472230291366577,
|
|
"epoch": 0.3600066822586034,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991379736967703,
|
|
"loss": 5.3909,
|
|
"mean_token_accuracy": 0.17094642221927642,
|
|
"num_tokens": 7940763.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.391937160491944,
|
|
"epoch": 0.3604243234213164,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991353683034929,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.17015578150749205,
|
|
"num_tokens": 7949424.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.456928300857544,
|
|
"epoch": 0.3608419645840294,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991327589864563,
|
|
"loss": 5.363,
|
|
"mean_token_accuracy": 0.17916346043348313,
|
|
"num_tokens": 7958805.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.511008167266846,
|
|
"epoch": 0.3612596057467424,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004991301457457057,
|
|
"loss": 5.4862,
|
|
"mean_token_accuracy": 0.17318558990955352,
|
|
"num_tokens": 7967859.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.611777591705322,
|
|
"epoch": 0.3616772469094554,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991275285812873,
|
|
"loss": 5.6055,
|
|
"mean_token_accuracy": 0.16365025639533998,
|
|
"num_tokens": 7978357.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.593785142898559,
|
|
"epoch": 0.3620948880721684,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991249074932466,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.17306540310382842,
|
|
"num_tokens": 7986637.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.384535217285157,
|
|
"epoch": 0.36251252923488136,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991222824816296,
|
|
"loss": 5.383,
|
|
"mean_token_accuracy": 0.17511666864156722,
|
|
"num_tokens": 7995954.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.530560398101807,
|
|
"epoch": 0.3629301703975944,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991196535464824,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.1695959284901619,
|
|
"num_tokens": 8005193.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.577112483978271,
|
|
"epoch": 0.3633478115603074,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991170206878508,
|
|
"loss": 5.4548,
|
|
"mean_token_accuracy": 0.17263143956661225,
|
|
"num_tokens": 8014419.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.475562572479248,
|
|
"epoch": 0.36376545272302035,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499114383905781,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.1665061816573143,
|
|
"num_tokens": 8024133.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.413761997222901,
|
|
"epoch": 0.3641830938857334,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991117432003192,
|
|
"loss": 5.3859,
|
|
"mean_token_accuracy": 0.17992129921913147,
|
|
"num_tokens": 8033059.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.5130657196044925,
|
|
"epoch": 0.36460073504844637,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991090985715116,
|
|
"loss": 5.4517,
|
|
"mean_token_accuracy": 0.1732624128460884,
|
|
"num_tokens": 8041866.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.514360857009888,
|
|
"epoch": 0.36501837621115935,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991064500194043,
|
|
"loss": 5.4752,
|
|
"mean_token_accuracy": 0.16933687031269073,
|
|
"num_tokens": 8051541.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.554482650756836,
|
|
"epoch": 0.3654360173738724,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991037975440439,
|
|
"loss": 5.5428,
|
|
"mean_token_accuracy": 0.16507816761732103,
|
|
"num_tokens": 8061964.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.407950353622437,
|
|
"epoch": 0.36585365853658536,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991011411454769,
|
|
"loss": 5.354,
|
|
"mean_token_accuracy": 0.17312078028917313,
|
|
"num_tokens": 8071006.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.431437063217163,
|
|
"epoch": 0.36627129969929834,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990984808237495,
|
|
"loss": 5.3646,
|
|
"mean_token_accuracy": 0.1760965332388878,
|
|
"num_tokens": 8080104.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.521042060852051,
|
|
"epoch": 0.36668894086201137,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990958165789086,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.17236875146627426,
|
|
"num_tokens": 8089397.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.438767433166504,
|
|
"epoch": 0.36710658202472435,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990931484110005,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.16909443438053132,
|
|
"num_tokens": 8099055.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.532427740097046,
|
|
"epoch": 0.3675242231874373,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990904763200722,
|
|
"loss": 5.3883,
|
|
"mean_token_accuracy": 0.17435784935951232,
|
|
"num_tokens": 8107609.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.514212989807129,
|
|
"epoch": 0.36794186435015036,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990878003061705,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.17783958315849305,
|
|
"num_tokens": 8116905.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.405974292755127,
|
|
"epoch": 0.36835950551286334,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990851203693419,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.17210870534181594,
|
|
"num_tokens": 8125580.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.415756464004517,
|
|
"epoch": 0.3687771466755763,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990824365096336,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.17104125618934632,
|
|
"num_tokens": 8134568.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.375641012191773,
|
|
"epoch": 0.36919478783828935,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990797487270926,
|
|
"loss": 5.2957,
|
|
"mean_token_accuracy": 0.17495275139808655,
|
|
"num_tokens": 8143044.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.435410976409912,
|
|
"epoch": 0.36961242900100233,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004990770570217659,
|
|
"loss": 5.4167,
|
|
"mean_token_accuracy": 0.17094517052173613,
|
|
"num_tokens": 8153701.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.442280197143555,
|
|
"epoch": 0.37003007016371536,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990743613937005,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.1752011701464653,
|
|
"num_tokens": 8163264.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.401455450057983,
|
|
"epoch": 0.37044771132642834,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990716618429436,
|
|
"loss": 5.4297,
|
|
"mean_token_accuracy": 0.16744692623615265,
|
|
"num_tokens": 8173332.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.488806295394897,
|
|
"epoch": 0.3708653524891413,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004990689583695428,
|
|
"loss": 5.4233,
|
|
"mean_token_accuracy": 0.1716279938817024,
|
|
"num_tokens": 8181881.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.5240256786346436,
|
|
"epoch": 0.37128299365185435,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499066250973545,
|
|
"loss": 5.4662,
|
|
"mean_token_accuracy": 0.16734483540058137,
|
|
"num_tokens": 8190771.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.457997035980225,
|
|
"epoch": 0.37170063481456733,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990635396549978,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.1713161513209343,
|
|
"num_tokens": 8200740.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.393514347076416,
|
|
"epoch": 0.3721182759772803,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990608244139486,
|
|
"loss": 5.3827,
|
|
"mean_token_accuracy": 0.16958940178155898,
|
|
"num_tokens": 8209935.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.5158362865448,
|
|
"epoch": 0.37253591713999334,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499058105250445,
|
|
"loss": 5.4635,
|
|
"mean_token_accuracy": 0.17263396084308624,
|
|
"num_tokens": 8219137.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.583094501495362,
|
|
"epoch": 0.3729535583027063,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990553821645346,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.17537619173526764,
|
|
"num_tokens": 8228076.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.435506439208984,
|
|
"epoch": 0.3733711994654193,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499052655156265,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.17335729748010636,
|
|
"num_tokens": 8237581.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.482702732086182,
|
|
"epoch": 0.37378884062813234,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004990499242256839,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.16622574329376222,
|
|
"num_tokens": 8247384.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.519318246841431,
|
|
"epoch": 0.3742064817908453,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990471893728394,
|
|
"loss": 5.4998,
|
|
"mean_token_accuracy": 0.1719047874212265,
|
|
"num_tokens": 8256383.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.478116226196289,
|
|
"epoch": 0.3746241229535583,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499044450597779,
|
|
"loss": 5.3417,
|
|
"mean_token_accuracy": 0.1772901251912117,
|
|
"num_tokens": 8264848.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.41370005607605,
|
|
"epoch": 0.3750417641162713,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990417079005508,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.16926388293504716,
|
|
"num_tokens": 8274403.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.41335620880127,
|
|
"epoch": 0.3754594052789843,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499038961281203,
|
|
"loss": 5.3134,
|
|
"mean_token_accuracy": 0.17994887828826905,
|
|
"num_tokens": 8282700.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.394307374954224,
|
|
"epoch": 0.3758770464416973,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004990362107397834,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.18360423445701599,
|
|
"num_tokens": 8291718.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.424862241744995,
|
|
"epoch": 0.3762946876044103,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004990334562763401,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.17094081193208693,
|
|
"num_tokens": 8301113.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.578273153305053,
|
|
"epoch": 0.3767123287671233,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990306978909216,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.16932496577501296,
|
|
"num_tokens": 8310357.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.541999769210816,
|
|
"epoch": 0.3771299699298363,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990279355835761,
|
|
"loss": 5.4356,
|
|
"mean_token_accuracy": 0.1734210342168808,
|
|
"num_tokens": 8319680.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.518919038772583,
|
|
"epoch": 0.3775476110925493,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990251693543519,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.16900236755609513,
|
|
"num_tokens": 8329127.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.372347497940064,
|
|
"epoch": 0.3779652522552623,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990223992032975,
|
|
"loss": 5.2786,
|
|
"mean_token_accuracy": 0.1781455770134926,
|
|
"num_tokens": 8338308.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.426207828521728,
|
|
"epoch": 0.37838289341797526,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004990196251304612,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.17504175305366515,
|
|
"num_tokens": 8347491.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.359329080581665,
|
|
"epoch": 0.3788005345806883,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499016847135892,
|
|
"loss": 5.3347,
|
|
"mean_token_accuracy": 0.17484522759914398,
|
|
"num_tokens": 8357112.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.412172460556031,
|
|
"epoch": 0.3792181757434013,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499014065219638,
|
|
"loss": 5.3399,
|
|
"mean_token_accuracy": 0.17453625351190566,
|
|
"num_tokens": 8366285.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.40165958404541,
|
|
"epoch": 0.37963581690611425,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990112793817481,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.18874731212854384,
|
|
"num_tokens": 8374362.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.430682134628296,
|
|
"epoch": 0.3800534580688273,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990084896222713,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.16845017224550246,
|
|
"num_tokens": 8383297.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.473242664337159,
|
|
"epoch": 0.38047109923154027,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004990056959412562,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.18510000109672547,
|
|
"num_tokens": 8391926.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.49044280052185,
|
|
"epoch": 0.38088874039425324,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004990028983387517,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.17314921021461488,
|
|
"num_tokens": 8401226.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.439341115951538,
|
|
"epoch": 0.3813063815569663,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004990000968148068,
|
|
"loss": 5.3758,
|
|
"mean_token_accuracy": 0.1755836471915245,
|
|
"num_tokens": 8409966.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.357498550415039,
|
|
"epoch": 0.38172402271967926,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989972913694707,
|
|
"loss": 5.2265,
|
|
"mean_token_accuracy": 0.18585699796676636,
|
|
"num_tokens": 8418281.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.300945854187011,
|
|
"epoch": 0.38214166388239224,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989944820027923,
|
|
"loss": 5.3367,
|
|
"mean_token_accuracy": 0.181486676633358,
|
|
"num_tokens": 8427436.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.474956798553467,
|
|
"epoch": 0.38255930504510527,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989916687148209,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.1815724179148674,
|
|
"num_tokens": 8436066.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.464441156387329,
|
|
"epoch": 0.38297694620781825,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004989888515056057,
|
|
"loss": 5.3875,
|
|
"mean_token_accuracy": 0.17339179962873458,
|
|
"num_tokens": 8445572.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.505393123626709,
|
|
"epoch": 0.3833945873705312,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498986030375196,
|
|
"loss": 5.4213,
|
|
"mean_token_accuracy": 0.17482264935970307,
|
|
"num_tokens": 8454781.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.459455108642578,
|
|
"epoch": 0.38381222853324426,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004989832053236413,
|
|
"loss": 5.4976,
|
|
"mean_token_accuracy": 0.17263346761465073,
|
|
"num_tokens": 8463239.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.538398218154907,
|
|
"epoch": 0.38422986969595724,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000498980376350991,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.17584720104932786,
|
|
"num_tokens": 8472664.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.519916439056397,
|
|
"epoch": 0.3846475108586702,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989775434572945,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.16939178854227066,
|
|
"num_tokens": 8483149.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.521700716018676,
|
|
"epoch": 0.38506515202138325,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989747066426015,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.17537314295768738,
|
|
"num_tokens": 8492297.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.456653833389282,
|
|
"epoch": 0.38548279318409623,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989718659069618,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.1676836743950844,
|
|
"num_tokens": 8502092.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.502790832519532,
|
|
"epoch": 0.3859004343468092,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498969021250425,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.17625278532505034,
|
|
"num_tokens": 8510816.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.453312110900879,
|
|
"epoch": 0.38631807550952224,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989661726730407,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.17780623733997344,
|
|
"num_tokens": 8520055.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.481811618804931,
|
|
"epoch": 0.3867357166722352,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989633201748591,
|
|
"loss": 5.4122,
|
|
"mean_token_accuracy": 0.1767112836241722,
|
|
"num_tokens": 8528271.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.408877563476563,
|
|
"epoch": 0.3871533578349482,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004989604637559299,
|
|
"loss": 5.3158,
|
|
"mean_token_accuracy": 0.18203164488077164,
|
|
"num_tokens": 8537360.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.310453414916992,
|
|
"epoch": 0.38757099899766123,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989576034163033,
|
|
"loss": 5.2706,
|
|
"mean_token_accuracy": 0.18779359757900238,
|
|
"num_tokens": 8546574.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.427399921417236,
|
|
"epoch": 0.3879886401603742,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989547391560293,
|
|
"loss": 5.3793,
|
|
"mean_token_accuracy": 0.17438787817955018,
|
|
"num_tokens": 8555581.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.435323333740234,
|
|
"epoch": 0.3884062813230872,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498951870975158,
|
|
"loss": 5.4074,
|
|
"mean_token_accuracy": 0.17851884365081788,
|
|
"num_tokens": 8564539.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.462069654464722,
|
|
"epoch": 0.3888239224858002,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989489988737395,
|
|
"loss": 5.4496,
|
|
"mean_token_accuracy": 0.17168653905391693,
|
|
"num_tokens": 8573804.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.404630899429321,
|
|
"epoch": 0.3892415636485132,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989461228518243,
|
|
"loss": 5.3602,
|
|
"mean_token_accuracy": 0.18074435889720916,
|
|
"num_tokens": 8583262.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.411992454528809,
|
|
"epoch": 0.3896592048112262,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989432429094627,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.17372126281261444,
|
|
"num_tokens": 8592763.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.559574317932129,
|
|
"epoch": 0.3900768459739392,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989403590467049,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.17951521873474122,
|
|
"num_tokens": 8601884.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.382081413269043,
|
|
"epoch": 0.3904944871366522,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989374712636017,
|
|
"loss": 5.4297,
|
|
"mean_token_accuracy": 0.17157796323299407,
|
|
"num_tokens": 8611207.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.317033100128174,
|
|
"epoch": 0.39091212829936517,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989345795602036,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.19590218216180802,
|
|
"num_tokens": 8620104.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.452140617370605,
|
|
"epoch": 0.3913297694620782,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989316839365609,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.17041265070438386,
|
|
"num_tokens": 8629552.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.435151386260986,
|
|
"epoch": 0.3917474106247912,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004989287843927246,
|
|
"loss": 5.3305,
|
|
"mean_token_accuracy": 0.17590319067239762,
|
|
"num_tokens": 8638961.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.419300651550293,
|
|
"epoch": 0.39216505178750416,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989258809287455,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.17324947267770768,
|
|
"num_tokens": 8648051.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.4347825050354,
|
|
"epoch": 0.3925826929502172,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989229735446743,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.17478834241628646,
|
|
"num_tokens": 8656863.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.251941823959351,
|
|
"epoch": 0.39300033411293017,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004989200622405619,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.18895964771509172,
|
|
"num_tokens": 8665455.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.324203968048096,
|
|
"epoch": 0.39341797527564315,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989171470164592,
|
|
"loss": 5.2925,
|
|
"mean_token_accuracy": 0.18248264938592912,
|
|
"num_tokens": 8674119.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.469828939437866,
|
|
"epoch": 0.3938356164383562,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989142278724173,
|
|
"loss": 5.3925,
|
|
"mean_token_accuracy": 0.1724318742752075,
|
|
"num_tokens": 8682979.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.469657611846924,
|
|
"epoch": 0.39425325760106916,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989113048084874,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.1702787160873413,
|
|
"num_tokens": 8692392.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.318474864959716,
|
|
"epoch": 0.39467089876378214,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989083778247206,
|
|
"loss": 5.358,
|
|
"mean_token_accuracy": 0.17889411002397537,
|
|
"num_tokens": 8700932.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.550222682952881,
|
|
"epoch": 0.3950885399264952,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000498905446921168,
|
|
"loss": 5.5122,
|
|
"mean_token_accuracy": 0.1707063190639019,
|
|
"num_tokens": 8710683.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.381403684616089,
|
|
"epoch": 0.39550618108920815,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989025120978812,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.17637370228767396,
|
|
"num_tokens": 8719939.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.469001817703247,
|
|
"epoch": 0.39592382225192113,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004988995733549113,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.17335674911737442,
|
|
"num_tokens": 8729275.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.355962038040161,
|
|
"epoch": 0.39634146341463417,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004988966306923099,
|
|
"loss": 5.2687,
|
|
"mean_token_accuracy": 0.180453297495842,
|
|
"num_tokens": 8738048.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.426445722579956,
|
|
"epoch": 0.39675910457734714,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004988936841101284,
|
|
"loss": 5.3557,
|
|
"mean_token_accuracy": 0.17539500296115876,
|
|
"num_tokens": 8746967.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.358024406433105,
|
|
"epoch": 0.3971767457400601,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004988907336084186,
|
|
"loss": 5.2957,
|
|
"mean_token_accuracy": 0.18092308789491654,
|
|
"num_tokens": 8754908.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.396121072769165,
|
|
"epoch": 0.39759438690277316,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988877791872319,
|
|
"loss": 5.3433,
|
|
"mean_token_accuracy": 0.18545244336128236,
|
|
"num_tokens": 8764489.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.565548896789551,
|
|
"epoch": 0.39801202806548613,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004988848208466202,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.15702270716428757,
|
|
"num_tokens": 8774365.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.449076223373413,
|
|
"epoch": 0.3984296692281991,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004988818585866351,
|
|
"loss": 5.3008,
|
|
"mean_token_accuracy": 0.1790413498878479,
|
|
"num_tokens": 8783538.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.3570427894592285,
|
|
"epoch": 0.39884731039091215,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004988788924073288,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.17840720862150192,
|
|
"num_tokens": 8792171.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.432498550415039,
|
|
"epoch": 0.3992649515536251,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988759223087528,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.1746385797858238,
|
|
"num_tokens": 8801325.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.42991533279419,
|
|
"epoch": 0.3996825927163381,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988729482909595,
|
|
"loss": 5.3439,
|
|
"mean_token_accuracy": 0.1762702226638794,
|
|
"num_tokens": 8810566.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.296753215789795,
|
|
"epoch": 0.40010023387905114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004988699703540006,
|
|
"loss": 5.2812,
|
|
"mean_token_accuracy": 0.1823352664709091,
|
|
"num_tokens": 8819735.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.402335977554321,
|
|
"epoch": 0.4005178750417641,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988669884979284,
|
|
"loss": 5.4222,
|
|
"mean_token_accuracy": 0.1739557906985283,
|
|
"num_tokens": 8828820.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.5007377624511715,
|
|
"epoch": 0.4009355162044771,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988640027227951,
|
|
"loss": 5.3161,
|
|
"mean_token_accuracy": 0.17225112169981002,
|
|
"num_tokens": 8837858.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.402754068374634,
|
|
"epoch": 0.4013531573671901,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000498861013028653,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.18401779979467392,
|
|
"num_tokens": 8847172.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.359449672698974,
|
|
"epoch": 0.4017707985299031,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988580194155544,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.17467405050992965,
|
|
"num_tokens": 8856700.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.297247648239136,
|
|
"epoch": 0.4021884396926161,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988550218835517,
|
|
"loss": 5.2096,
|
|
"mean_token_accuracy": 0.18494719564914702,
|
|
"num_tokens": 8866108.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.347088050842285,
|
|
"epoch": 0.4026060808553291,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004988520204326975,
|
|
"loss": 5.3029,
|
|
"mean_token_accuracy": 0.18589287698268891,
|
|
"num_tokens": 8874833.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.445062351226807,
|
|
"epoch": 0.4030237220180421,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988490150630441,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.17721084058284758,
|
|
"num_tokens": 8884211.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.500857543945313,
|
|
"epoch": 0.4034413631807551,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004988460057746443,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.16921537965536118,
|
|
"num_tokens": 8893443.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.369778633117676,
|
|
"epoch": 0.4038590043434681,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004988429925675507,
|
|
"loss": 5.3515,
|
|
"mean_token_accuracy": 0.17862945795059204,
|
|
"num_tokens": 8903544.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.46190824508667,
|
|
"epoch": 0.4042766455061811,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004988399754418161,
|
|
"loss": 5.366,
|
|
"mean_token_accuracy": 0.1793976604938507,
|
|
"num_tokens": 8912270.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.537768125534058,
|
|
"epoch": 0.40469428666889407,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988369543974932,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.1689763829112053,
|
|
"num_tokens": 8922155.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.473590850830078,
|
|
"epoch": 0.4051119278316071,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988339294346351,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.17304005473852158,
|
|
"num_tokens": 8931844.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.4567924499511715,
|
|
"epoch": 0.4055295689943201,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988309005532946,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.18166026920080186,
|
|
"num_tokens": 8940874.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.412811899185181,
|
|
"epoch": 0.40594721015703306,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004988278677535247,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.18285960853099822,
|
|
"num_tokens": 8950108.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.473009872436523,
|
|
"epoch": 0.4063648513197461,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988248310353788,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.17212433815002443,
|
|
"num_tokens": 8960610.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.355665683746338,
|
|
"epoch": 0.40678249248245907,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004988217903989095,
|
|
"loss": 5.325,
|
|
"mean_token_accuracy": 0.17474715560674667,
|
|
"num_tokens": 8969853.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.465075540542602,
|
|
"epoch": 0.40720013364517205,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988187458441704,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.17334848046302795,
|
|
"num_tokens": 8979800.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.447531795501709,
|
|
"epoch": 0.4076177748078851,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004988156973712149,
|
|
"loss": 5.3784,
|
|
"mean_token_accuracy": 0.1711223915219307,
|
|
"num_tokens": 8988667.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.289280891418457,
|
|
"epoch": 0.40803541597059806,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004988126449800961,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.1802578404545784,
|
|
"num_tokens": 8997385.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.353163862228394,
|
|
"epoch": 0.40845305713331104,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004988095886708676,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.18317050039768218,
|
|
"num_tokens": 9005999.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.447890090942383,
|
|
"epoch": 0.40887069829602407,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988065284435828,
|
|
"loss": 5.4104,
|
|
"mean_token_accuracy": 0.18185970485210418,
|
|
"num_tokens": 9014837.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.505316591262817,
|
|
"epoch": 0.40928833945873705,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004988034642982954,
|
|
"loss": 5.4413,
|
|
"mean_token_accuracy": 0.1804886966943741,
|
|
"num_tokens": 9023956.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.510533952713013,
|
|
"epoch": 0.40970598062145,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988003962350589,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.16933871060609818,
|
|
"num_tokens": 9032945.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.41035795211792,
|
|
"epoch": 0.41012362178416306,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000498797324253927,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.1821726843714714,
|
|
"num_tokens": 9042109.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.327030658721924,
|
|
"epoch": 0.41054126294687604,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004987942483549537,
|
|
"loss": 5.3237,
|
|
"mean_token_accuracy": 0.17505295425653458,
|
|
"num_tokens": 9052210.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.460620880126953,
|
|
"epoch": 0.410958904109589,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004987911685381926,
|
|
"loss": 5.2838,
|
|
"mean_token_accuracy": 0.18444007337093354,
|
|
"num_tokens": 9060089.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.486596584320068,
|
|
"epoch": 0.41137654527230205,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004987880848036977,
|
|
"loss": 5.3995,
|
|
"mean_token_accuracy": 0.17101875692605972,
|
|
"num_tokens": 9069235.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.3632927417755125,
|
|
"epoch": 0.41179418643501503,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004987849971515232,
|
|
"loss": 5.3398,
|
|
"mean_token_accuracy": 0.18175618052482606,
|
|
"num_tokens": 9077509.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.4160401821136475,
|
|
"epoch": 0.412211827597728,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004987819055817227,
|
|
"loss": 5.2523,
|
|
"mean_token_accuracy": 0.18890025466680527,
|
|
"num_tokens": 9085493.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.265770339965821,
|
|
"epoch": 0.41262946876044104,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987788100943507,
|
|
"loss": 5.2334,
|
|
"mean_token_accuracy": 0.18305041491985322,
|
|
"num_tokens": 9094748.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.399051094055176,
|
|
"epoch": 0.413047109923154,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004987757106894613,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.18176668584346772,
|
|
"num_tokens": 9103678.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.412854290008545,
|
|
"epoch": 0.413464751085867,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004987726073671086,
|
|
"loss": 5.3701,
|
|
"mean_token_accuracy": 0.1806068480014801,
|
|
"num_tokens": 9112851.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.53558030128479,
|
|
"epoch": 0.41388239224858003,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987695001273471,
|
|
"loss": 5.5739,
|
|
"mean_token_accuracy": 0.16550440490245819,
|
|
"num_tokens": 9122106.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.442167043685913,
|
|
"epoch": 0.414300033411293,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004987663889702313,
|
|
"loss": 5.2991,
|
|
"mean_token_accuracy": 0.18062672168016433,
|
|
"num_tokens": 9131580.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.481163120269775,
|
|
"epoch": 0.414717674574006,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987632738958155,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.17543174624443053,
|
|
"num_tokens": 9141642.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.553693437576294,
|
|
"epoch": 0.415135315736719,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987601549041541,
|
|
"loss": 5.482,
|
|
"mean_token_accuracy": 0.16618218123912812,
|
|
"num_tokens": 9151192.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.424982213973999,
|
|
"epoch": 0.415552956899432,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004987570319953018,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.17582743167877196,
|
|
"num_tokens": 9161316.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.487713193893432,
|
|
"epoch": 0.415970598062145,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004987539051693134,
|
|
"loss": 5.3789,
|
|
"mean_token_accuracy": 0.170578333735466,
|
|
"num_tokens": 9169535.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.433673286437989,
|
|
"epoch": 0.416388239224858,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987507744262436,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.1698138326406479,
|
|
"num_tokens": 9178187.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.338801288604737,
|
|
"epoch": 0.416805880387571,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987476397661472,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.17456402033567428,
|
|
"num_tokens": 9186342.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.470065784454346,
|
|
"epoch": 0.41722352155028397,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987445011890789,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.17456976175308228,
|
|
"num_tokens": 9196470.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.415784645080566,
|
|
"epoch": 0.417641162712997,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000498741358695094,
|
|
"loss": 5.3299,
|
|
"mean_token_accuracy": 0.17888012081384658,
|
|
"num_tokens": 9206587.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.377053928375244,
|
|
"epoch": 0.41805880387571,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000498738212284247,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.17406473457813262,
|
|
"num_tokens": 9216459.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.556557559967041,
|
|
"epoch": 0.41847644503842296,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987350619565934,
|
|
"loss": 5.44,
|
|
"mean_token_accuracy": 0.17223341315984725,
|
|
"num_tokens": 9227301.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.4989378452301025,
|
|
"epoch": 0.418894086201136,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987319077121884,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.16402043551206588,
|
|
"num_tokens": 9236577.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.350860643386841,
|
|
"epoch": 0.419311727363849,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987287495510869,
|
|
"loss": 5.362,
|
|
"mean_token_accuracy": 0.17799901366233825,
|
|
"num_tokens": 9246451.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.3903028011322025,
|
|
"epoch": 0.41972936852656195,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004987255874733444,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.1740152657032013,
|
|
"num_tokens": 9256108.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.315888261795044,
|
|
"epoch": 0.420147009689275,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004987224214790161,
|
|
"loss": 5.3004,
|
|
"mean_token_accuracy": 0.1798888012766838,
|
|
"num_tokens": 9265173.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.426610898971558,
|
|
"epoch": 0.42056465085198796,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987192515681575,
|
|
"loss": 5.4024,
|
|
"mean_token_accuracy": 0.17473443150520324,
|
|
"num_tokens": 9273979.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.392903518676758,
|
|
"epoch": 0.42098229201470094,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004987160777408243,
|
|
"loss": 5.3462,
|
|
"mean_token_accuracy": 0.17106169909238816,
|
|
"num_tokens": 9281893.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.513010692596436,
|
|
"epoch": 0.421399933177414,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004987128999970717,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.1757590688765049,
|
|
"num_tokens": 9290799.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.558505439758301,
|
|
"epoch": 0.42181757434012696,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004987097183369555,
|
|
"loss": 5.4302,
|
|
"mean_token_accuracy": 0.16776997298002244,
|
|
"num_tokens": 9300562.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.30872278213501,
|
|
"epoch": 0.42223521550283993,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987065327605315,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.18027304857969284,
|
|
"num_tokens": 9308889.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.29863543510437,
|
|
"epoch": 0.42265285666555297,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987033432678553,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.18111589998006822,
|
|
"num_tokens": 9317957.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.51900086402893,
|
|
"epoch": 0.42307049782826595,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987001498589828,
|
|
"loss": 5.4949,
|
|
"mean_token_accuracy": 0.16496727764606475,
|
|
"num_tokens": 9327849.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.506615066528321,
|
|
"epoch": 0.4234881389909789,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049869695253397,
|
|
"loss": 5.3484,
|
|
"mean_token_accuracy": 0.1687320351600647,
|
|
"num_tokens": 9337165.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.390972232818603,
|
|
"epoch": 0.42390578015369196,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004986937512928727,
|
|
"loss": 5.2594,
|
|
"mean_token_accuracy": 0.18033367842435838,
|
|
"num_tokens": 9346817.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.45494441986084,
|
|
"epoch": 0.42432342131640494,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000498690546135747,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.17511844784021377,
|
|
"num_tokens": 9356420.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.33007960319519,
|
|
"epoch": 0.4247410624791179,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004986873370626491,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.18187834471464157,
|
|
"num_tokens": 9365580.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.42194504737854,
|
|
"epoch": 0.42515870364183095,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000498684124073635,
|
|
"loss": 5.3709,
|
|
"mean_token_accuracy": 0.16973898261785508,
|
|
"num_tokens": 9375116.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.4432093620300295,
|
|
"epoch": 0.4255763448045439,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004986809071687612,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.18046289086341857,
|
|
"num_tokens": 9384129.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.370714426040649,
|
|
"epoch": 0.4259939859672569,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004986776863480838,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.17603334188461303,
|
|
"num_tokens": 9392757.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.287596130371094,
|
|
"epoch": 0.42641162712996994,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004986744616116593,
|
|
"loss": 5.2615,
|
|
"mean_token_accuracy": 0.18092862516641617,
|
|
"num_tokens": 9401753.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.397714376449585,
|
|
"epoch": 0.4268292682926829,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000498671232959544,
|
|
"loss": 5.4721,
|
|
"mean_token_accuracy": 0.166457898914814,
|
|
"num_tokens": 9411400.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.519891691207886,
|
|
"epoch": 0.42724690945539595,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004986680003917947,
|
|
"loss": 5.3158,
|
|
"mean_token_accuracy": 0.1766785129904747,
|
|
"num_tokens": 9420206.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.367687368392945,
|
|
"epoch": 0.42766455061810893,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004986647639084677,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.17577457129955293,
|
|
"num_tokens": 9428418.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.389084577560425,
|
|
"epoch": 0.4280821917808219,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00049866152350962,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.17752706706523896,
|
|
"num_tokens": 9437624.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.434055614471435,
|
|
"epoch": 0.42849983294353494,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004986582791953078,
|
|
"loss": 5.2778,
|
|
"mean_token_accuracy": 0.18143245875835418,
|
|
"num_tokens": 9446857.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.367829656600952,
|
|
"epoch": 0.4289174741062479,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004986550309655884,
|
|
"loss": 5.3738,
|
|
"mean_token_accuracy": 0.17304729223251342,
|
|
"num_tokens": 9456024.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.361046934127808,
|
|
"epoch": 0.4293351152689609,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004986517788205184,
|
|
"loss": 5.2657,
|
|
"mean_token_accuracy": 0.18356824517250062,
|
|
"num_tokens": 9464018.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.348368215560913,
|
|
"epoch": 0.42975275643167393,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004986485227601548,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.17977178692817689,
|
|
"num_tokens": 9472430.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.387197065353393,
|
|
"epoch": 0.4301703975943869,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004986452627845547,
|
|
"loss": 5.3092,
|
|
"mean_token_accuracy": 0.182216514647007,
|
|
"num_tokens": 9480592.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.368278741836548,
|
|
"epoch": 0.4305880387570999,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000498641998893775,
|
|
"loss": 5.2648,
|
|
"mean_token_accuracy": 0.1800767406821251,
|
|
"num_tokens": 9489162.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.408619976043701,
|
|
"epoch": 0.4310056799198129,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986387310878728,
|
|
"loss": 5.3317,
|
|
"mean_token_accuracy": 0.17703358680009842,
|
|
"num_tokens": 9499210.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.426770877838135,
|
|
"epoch": 0.4314233210825259,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986354593669056,
|
|
"loss": 5.3683,
|
|
"mean_token_accuracy": 0.18122825920581817,
|
|
"num_tokens": 9508062.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.43633918762207,
|
|
"epoch": 0.4318409622452389,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004986321837309304,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.18372174352407455,
|
|
"num_tokens": 9516756.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.371243238449097,
|
|
"epoch": 0.4322586034079519,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004986289041800046,
|
|
"loss": 5.3046,
|
|
"mean_token_accuracy": 0.1816995456814766,
|
|
"num_tokens": 9525305.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.390642595291138,
|
|
"epoch": 0.4326762445706649,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004986256207141857,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.18394368886947632,
|
|
"num_tokens": 9534310.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.5049614906311035,
|
|
"epoch": 0.43309388573337787,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986223333335311,
|
|
"loss": 5.3968,
|
|
"mean_token_accuracy": 0.17676397114992143,
|
|
"num_tokens": 9543648.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.33973445892334,
|
|
"epoch": 0.4335115268960909,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004986190420380985,
|
|
"loss": 5.3115,
|
|
"mean_token_accuracy": 0.1795612543821335,
|
|
"num_tokens": 9553081.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.451060962677002,
|
|
"epoch": 0.4339291680588039,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004986157468279453,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.17509184926748275,
|
|
"num_tokens": 9563184.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.426450729370117,
|
|
"epoch": 0.43434680922151686,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004986124477031293,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.17883535772562026,
|
|
"num_tokens": 9572550.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.3502343654632565,
|
|
"epoch": 0.4347644503842299,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004986091446637083,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.17619699239730835,
|
|
"num_tokens": 9580900.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.457106208801269,
|
|
"epoch": 0.4351820915469429,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00049860583770974,
|
|
"loss": 5.3515,
|
|
"mean_token_accuracy": 0.18001936376094818,
|
|
"num_tokens": 9589340.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.472261667251587,
|
|
"epoch": 0.43559973270965585,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004986025268412823,
|
|
"loss": 5.471,
|
|
"mean_token_accuracy": 0.17389730960130692,
|
|
"num_tokens": 9599316.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.452399969100952,
|
|
"epoch": 0.4360173738723689,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985992120583933,
|
|
"loss": 5.3525,
|
|
"mean_token_accuracy": 0.17356273531913757,
|
|
"num_tokens": 9609350.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.474084186553955,
|
|
"epoch": 0.43643501503508186,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000498595893361131,
|
|
"loss": 5.3968,
|
|
"mean_token_accuracy": 0.18037155270576477,
|
|
"num_tokens": 9618491.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.49598331451416,
|
|
"epoch": 0.43685265619779484,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004985925707495533,
|
|
"loss": 5.4735,
|
|
"mean_token_accuracy": 0.1682824060320854,
|
|
"num_tokens": 9629613.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.384536600112915,
|
|
"epoch": 0.4372702973605079,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004985892442237186,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.1817545160651207,
|
|
"num_tokens": 9638035.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.437534236907959,
|
|
"epoch": 0.43768793852322085,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004985859137836851,
|
|
"loss": 5.4153,
|
|
"mean_token_accuracy": 0.16965906023979188,
|
|
"num_tokens": 9647378.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.478408432006836,
|
|
"epoch": 0.43810557968593383,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004985825794295109,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.1800900012254715,
|
|
"num_tokens": 9655728.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.413166236877442,
|
|
"epoch": 0.43852322084864687,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004985792411612546,
|
|
"loss": 5.3675,
|
|
"mean_token_accuracy": 0.18087270259857177,
|
|
"num_tokens": 9665063.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.447279405593872,
|
|
"epoch": 0.43894086201135984,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004985758989789746,
|
|
"loss": 5.3492,
|
|
"mean_token_accuracy": 0.17699085175991058,
|
|
"num_tokens": 9674406.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.343826150894165,
|
|
"epoch": 0.4393585031740728,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004985725528827293,
|
|
"loss": 5.3113,
|
|
"mean_token_accuracy": 0.1798545628786087,
|
|
"num_tokens": 9683303.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.417714405059814,
|
|
"epoch": 0.43977614433678586,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004985692028725774,
|
|
"loss": 5.3111,
|
|
"mean_token_accuracy": 0.17840295135974885,
|
|
"num_tokens": 9692938.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.446576070785523,
|
|
"epoch": 0.44019378549949884,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004985658489485774,
|
|
"loss": 5.3851,
|
|
"mean_token_accuracy": 0.176699498295784,
|
|
"num_tokens": 9702192.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.409464597702026,
|
|
"epoch": 0.4406114266622118,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004985624911107882,
|
|
"loss": 5.358,
|
|
"mean_token_accuracy": 0.17101490646600723,
|
|
"num_tokens": 9711301.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.3845923900604244,
|
|
"epoch": 0.44102906782492485,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004985591293592685,
|
|
"loss": 5.3544,
|
|
"mean_token_accuracy": 0.17416053116321564,
|
|
"num_tokens": 9720768.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.47494215965271,
|
|
"epoch": 0.4414467089876378,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004985557636940771,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.17790818065404893,
|
|
"num_tokens": 9730007.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.472876501083374,
|
|
"epoch": 0.4418643501503508,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000498552394115273,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.17267797291278839,
|
|
"num_tokens": 9739546.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.391746282577515,
|
|
"epoch": 0.44228199131306384,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004985490206229151,
|
|
"loss": 5.3165,
|
|
"mean_token_accuracy": 0.18015623986721038,
|
|
"num_tokens": 9749615.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.46711368560791,
|
|
"epoch": 0.4426996324757768,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004985456432170626,
|
|
"loss": 5.4128,
|
|
"mean_token_accuracy": 0.17161605805158614,
|
|
"num_tokens": 9759285.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.372819995880127,
|
|
"epoch": 0.4431172736384898,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004985422618977744,
|
|
"loss": 5.2791,
|
|
"mean_token_accuracy": 0.17291145026683807,
|
|
"num_tokens": 9769396.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.423769426345825,
|
|
"epoch": 0.44353491480120283,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049853887666511,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.17350405901670457,
|
|
"num_tokens": 9779632.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.483930587768555,
|
|
"epoch": 0.4439525559639158,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004985354875191283,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.17986151874065398,
|
|
"num_tokens": 9788090.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.325446748733521,
|
|
"epoch": 0.4443701971266288,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004985320944598889,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.18873758614063263,
|
|
"num_tokens": 9795844.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.256659317016601,
|
|
"epoch": 0.4447878382893418,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004985286974874512,
|
|
"loss": 5.2251,
|
|
"mean_token_accuracy": 0.18810541033744813,
|
|
"num_tokens": 9805119.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.440543508529663,
|
|
"epoch": 0.4452054794520548,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004985252966018745,
|
|
"loss": 5.3417,
|
|
"mean_token_accuracy": 0.18258800655603408,
|
|
"num_tokens": 9813842.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.519575881958008,
|
|
"epoch": 0.4456231206147678,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985218918032184,
|
|
"loss": 5.3465,
|
|
"mean_token_accuracy": 0.17161140143871306,
|
|
"num_tokens": 9822872.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.438978767395019,
|
|
"epoch": 0.4460407617774808,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004985184830915426,
|
|
"loss": 5.4609,
|
|
"mean_token_accuracy": 0.1676907256245613,
|
|
"num_tokens": 9832710.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.4792500019073485,
|
|
"epoch": 0.4464584029401938,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004985150704669067,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.1726950615644455,
|
|
"num_tokens": 9841047.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.445040225982666,
|
|
"epoch": 0.44687604410290677,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004985116539293704,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.1756501317024231,
|
|
"num_tokens": 9850168.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.390517377853394,
|
|
"epoch": 0.4472936852656198,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985082334789936,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.1720145031809807,
|
|
"num_tokens": 9859550.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.530892658233642,
|
|
"epoch": 0.4477113264283328,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004985048091158361,
|
|
"loss": 5.3353,
|
|
"mean_token_accuracy": 0.17469432651996614,
|
|
"num_tokens": 9868317.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.526041316986084,
|
|
"epoch": 0.44812896759104576,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004985013808399578,
|
|
"loss": 5.5569,
|
|
"mean_token_accuracy": 0.15901562422513962,
|
|
"num_tokens": 9878421.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.395598411560059,
|
|
"epoch": 0.4485466087537588,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004984979486514189,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.1847289741039276,
|
|
"num_tokens": 9887213.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.380127382278443,
|
|
"epoch": 0.44896424991647177,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984945125502795,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.17433496117591857,
|
|
"num_tokens": 9897274.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.3499444961547855,
|
|
"epoch": 0.44938189107918475,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004984910725365994,
|
|
"loss": 5.3268,
|
|
"mean_token_accuracy": 0.17421112805604935,
|
|
"num_tokens": 9906765.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.537207746505738,
|
|
"epoch": 0.4497995322418978,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004984876286104392,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.17053734958171846,
|
|
"num_tokens": 9916149.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.396920490264892,
|
|
"epoch": 0.45021717340461076,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004984841807718591,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.17592400908470154,
|
|
"num_tokens": 9925657.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.375749349594116,
|
|
"epoch": 0.45063481456732374,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004984807290209193,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.17013389617204666,
|
|
"num_tokens": 9934740.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.54732928276062,
|
|
"epoch": 0.45105245573003677,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004984772733576803,
|
|
"loss": 5.4671,
|
|
"mean_token_accuracy": 0.1761418476700783,
|
|
"num_tokens": 9943516.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.4817307472229,
|
|
"epoch": 0.45147009689274975,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004984738137822028,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.16915766149759293,
|
|
"num_tokens": 9952998.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.393400382995606,
|
|
"epoch": 0.45188773805546273,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000498470350294547,
|
|
"loss": 5.2297,
|
|
"mean_token_accuracy": 0.1843737319111824,
|
|
"num_tokens": 9961698.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.398413372039795,
|
|
"epoch": 0.45230537921817576,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004984668828947739,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.1706392526626587,
|
|
"num_tokens": 9972015.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.426323080062867,
|
|
"epoch": 0.45272302038088874,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004984634115829439,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.1691138908267021,
|
|
"num_tokens": 9981834.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.396098852157593,
|
|
"epoch": 0.4531406615436017,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000498459936359118,
|
|
"loss": 5.3009,
|
|
"mean_token_accuracy": 0.18049199730157853,
|
|
"num_tokens": 9991113.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.384849739074707,
|
|
"epoch": 0.45355830270631475,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004984564572233568,
|
|
"loss": 5.2819,
|
|
"mean_token_accuracy": 0.17862436026334763,
|
|
"num_tokens": 10000048.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.44728536605835,
|
|
"epoch": 0.45397594386902773,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004984529741757216,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.1794531986117363,
|
|
"num_tokens": 10009389.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.303836917877197,
|
|
"epoch": 0.4543935850317407,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004984494872162728,
|
|
"loss": 5.1935,
|
|
"mean_token_accuracy": 0.1841413199901581,
|
|
"num_tokens": 10018342.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.4117495059967045,
|
|
"epoch": 0.45481122619445374,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000498445996345072,
|
|
"loss": 5.3622,
|
|
"mean_token_accuracy": 0.17776415944099427,
|
|
"num_tokens": 10027219.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.339814901351929,
|
|
"epoch": 0.4552288673571667,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004984425015621799,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.1772462785243988,
|
|
"num_tokens": 10036635.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.326971912384034,
|
|
"epoch": 0.4556465085198797,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000498439002867658,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.18105732649564743,
|
|
"num_tokens": 10045655.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.5361474514007565,
|
|
"epoch": 0.45606414968259273,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004984355002615673,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.1691015064716339,
|
|
"num_tokens": 10054366.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.434479236602783,
|
|
"epoch": 0.4564817908453057,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004984319937439693,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.18317292779684066,
|
|
"num_tokens": 10062548.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.3561845302581785,
|
|
"epoch": 0.4568994320080187,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004984284833149252,
|
|
"loss": 5.3105,
|
|
"mean_token_accuracy": 0.17571336179971694,
|
|
"num_tokens": 10071333.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.299349594116211,
|
|
"epoch": 0.4573170731707317,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004984249689744966,
|
|
"loss": 5.2155,
|
|
"mean_token_accuracy": 0.1857534885406494,
|
|
"num_tokens": 10079502.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.36715989112854,
|
|
"epoch": 0.4577347143334447,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000498421450722745,
|
|
"loss": 5.2323,
|
|
"mean_token_accuracy": 0.18540998101234435,
|
|
"num_tokens": 10088648.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.363710212707519,
|
|
"epoch": 0.4581523554961577,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000498417928559732,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.185733100771904,
|
|
"num_tokens": 10097742.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.437697315216065,
|
|
"epoch": 0.4585699966588707,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984144024855191,
|
|
"loss": 5.36,
|
|
"mean_token_accuracy": 0.17362416684627532,
|
|
"num_tokens": 10107228.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.4109265327453615,
|
|
"epoch": 0.4589876378215837,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004984108725001683,
|
|
"loss": 5.264,
|
|
"mean_token_accuracy": 0.17965881377458573,
|
|
"num_tokens": 10115488.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.276472520828247,
|
|
"epoch": 0.45940527898429667,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004984073386037413,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.18694024235010148,
|
|
"num_tokens": 10124235.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.304714584350586,
|
|
"epoch": 0.4598229201470097,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004984038007962997,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.18120416551828383,
|
|
"num_tokens": 10133208.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.3617603302001955,
|
|
"epoch": 0.4602405613097227,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004984002590779059,
|
|
"loss": 5.2291,
|
|
"mean_token_accuracy": 0.17836282253265381,
|
|
"num_tokens": 10142754.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.382237768173217,
|
|
"epoch": 0.46065820247243566,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004983967134486215,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.17632970660924913,
|
|
"num_tokens": 10152114.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.41402497291565,
|
|
"epoch": 0.4610758436351487,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004983931639085088,
|
|
"loss": 5.2544,
|
|
"mean_token_accuracy": 0.1815406411886215,
|
|
"num_tokens": 10161562.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.416577577590942,
|
|
"epoch": 0.4614934847978617,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004983896104576298,
|
|
"loss": 5.3615,
|
|
"mean_token_accuracy": 0.17958488315343857,
|
|
"num_tokens": 10170461.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.388878965377808,
|
|
"epoch": 0.46191112596057465,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000498386053096047,
|
|
"loss": 5.3639,
|
|
"mean_token_accuracy": 0.17891687750816346,
|
|
"num_tokens": 10179243.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.430717802047729,
|
|
"epoch": 0.4623287671232877,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004983824918238221,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.18487516194581985,
|
|
"num_tokens": 10187935.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.411087942123413,
|
|
"epoch": 0.46274640828600067,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000498378926641018,
|
|
"loss": 5.377,
|
|
"mean_token_accuracy": 0.17247853726148604,
|
|
"num_tokens": 10196185.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.401890468597412,
|
|
"epoch": 0.46316404944871364,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004983753575476969,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.17471231073141097,
|
|
"num_tokens": 10205373.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.46509485244751,
|
|
"epoch": 0.4635816906114267,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983717845439212,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.18027413636446,
|
|
"num_tokens": 10214464.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.4192205429077145,
|
|
"epoch": 0.46399933177413966,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983682076297536,
|
|
"loss": 5.4152,
|
|
"mean_token_accuracy": 0.17256004810333253,
|
|
"num_tokens": 10224462.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.460912370681763,
|
|
"epoch": 0.46441697293685263,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004983646268052567,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.17892708480358124,
|
|
"num_tokens": 10233123.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.3775170803070065,
|
|
"epoch": 0.46483461409956567,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983610420704931,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.18358879983425141,
|
|
"num_tokens": 10241613.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.43302698135376,
|
|
"epoch": 0.46525225526227865,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004983574534255256,
|
|
"loss": 5.5336,
|
|
"mean_token_accuracy": 0.16362907588481904,
|
|
"num_tokens": 10251809.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.384333086013794,
|
|
"epoch": 0.4656698964249916,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000498353860870417,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.17986831367015838,
|
|
"num_tokens": 10260198.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.413422966003418,
|
|
"epoch": 0.46608753758770466,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004983502644052303,
|
|
"loss": 5.2964,
|
|
"mean_token_accuracy": 0.18045338243246078,
|
|
"num_tokens": 10268906.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.293640184402466,
|
|
"epoch": 0.46650517875041764,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004983466640300282,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.17398974746465684,
|
|
"num_tokens": 10278526.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.355238723754883,
|
|
"epoch": 0.4669228199131306,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004983430597448741,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.17971521466970444,
|
|
"num_tokens": 10287428.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.497137498855591,
|
|
"epoch": 0.46734046107584365,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004983394515498308,
|
|
"loss": 5.303,
|
|
"mean_token_accuracy": 0.17363718301057815,
|
|
"num_tokens": 10297136.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.3973921775817875,
|
|
"epoch": 0.46775810223855663,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004983358394449616,
|
|
"loss": 5.3768,
|
|
"mean_token_accuracy": 0.17228453010320663,
|
|
"num_tokens": 10305678.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.335638189315796,
|
|
"epoch": 0.4681757434012696,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004983322234303297,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.18027922958135606,
|
|
"num_tokens": 10314690.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.358850812911987,
|
|
"epoch": 0.46859338456398264,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004983286035059984,
|
|
"loss": 5.2356,
|
|
"mean_token_accuracy": 0.1823755368590355,
|
|
"num_tokens": 10323521.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.38775372505188,
|
|
"epoch": 0.4690110257266956,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004983249796720311,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.18415401577949525,
|
|
"num_tokens": 10333077.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.395961093902588,
|
|
"epoch": 0.4694286668894086,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004983213519284912,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.17712220549583435,
|
|
"num_tokens": 10342194.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.370408296585083,
|
|
"epoch": 0.46984630805212163,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983177202754421,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.18557369709014893,
|
|
"num_tokens": 10351009.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.418461847305298,
|
|
"epoch": 0.4702639492148346,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004983140847129476,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.1745539128780365,
|
|
"num_tokens": 10360872.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.362072467803955,
|
|
"epoch": 0.4706815903775476,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983104452410713,
|
|
"loss": 5.2709,
|
|
"mean_token_accuracy": 0.18330505192279817,
|
|
"num_tokens": 10370159.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.361561489105225,
|
|
"epoch": 0.4710992315402606,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004983068018598768,
|
|
"loss": 5.277,
|
|
"mean_token_accuracy": 0.1826947033405304,
|
|
"num_tokens": 10379219.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.415415096282959,
|
|
"epoch": 0.4715168727029736,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000498303154569428,
|
|
"loss": 5.3165,
|
|
"mean_token_accuracy": 0.17777066081762313,
|
|
"num_tokens": 10389425.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.404468965530396,
|
|
"epoch": 0.4719345138656866,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004982995033697887,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.1823611155152321,
|
|
"num_tokens": 10398023.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.3171977519989015,
|
|
"epoch": 0.4723521550283996,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004982958482610226,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.18108674585819245,
|
|
"num_tokens": 10406578.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.324284410476684,
|
|
"epoch": 0.4727697961911126,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000498292189243194,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.18560549318790437,
|
|
"num_tokens": 10416448.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.442724084854126,
|
|
"epoch": 0.47318743735382557,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498288526316367,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.17472774982452394,
|
|
"num_tokens": 10425414.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.3667394638061525,
|
|
"epoch": 0.4736050785165386,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004982848594806054,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.18441671282052993,
|
|
"num_tokens": 10433900.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.378509855270385,
|
|
"epoch": 0.4740227196792516,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004982811887359736,
|
|
"loss": 5.4014,
|
|
"mean_token_accuracy": 0.17403701096773147,
|
|
"num_tokens": 10443077.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.416761207580566,
|
|
"epoch": 0.47444036084196456,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004982775140825359,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.1761450931429863,
|
|
"num_tokens": 10452791.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.496857118606568,
|
|
"epoch": 0.4748580020046776,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004982738355203565,
|
|
"loss": 5.4832,
|
|
"mean_token_accuracy": 0.17297002524137498,
|
|
"num_tokens": 10462087.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.523170042037964,
|
|
"epoch": 0.47527564316739057,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004982701530494998,
|
|
"loss": 5.5053,
|
|
"mean_token_accuracy": 0.16588604748249053,
|
|
"num_tokens": 10472576.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.419825744628906,
|
|
"epoch": 0.47569328433010355,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004982664666700304,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.18905199021101,
|
|
"num_tokens": 10481176.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.340116405487061,
|
|
"epoch": 0.4761109254928166,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004982627763820128,
|
|
"loss": 5.2996,
|
|
"mean_token_accuracy": 0.179258593916893,
|
|
"num_tokens": 10490558.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.399360990524292,
|
|
"epoch": 0.47652856665552956,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004982590821855115,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.17810954302549362,
|
|
"num_tokens": 10499543.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.3109029769897464,
|
|
"epoch": 0.47694620781824254,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004982553840805912,
|
|
"loss": 5.2672,
|
|
"mean_token_accuracy": 0.183368119597435,
|
|
"num_tokens": 10508162.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.337470769882202,
|
|
"epoch": 0.4773638489809556,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004982516820673167,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.18151225298643112,
|
|
"num_tokens": 10516837.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.3128574848175045,
|
|
"epoch": 0.47778149014366855,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004982479761457528,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.17841623425483705,
|
|
"num_tokens": 10526208.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.42949161529541,
|
|
"epoch": 0.47819913130638153,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004982442663159643,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.1749148890376091,
|
|
"num_tokens": 10536002.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.465812397003174,
|
|
"epoch": 0.47861677246909456,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982405525780162,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.17801699340343474,
|
|
"num_tokens": 10545861.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.3826446533203125,
|
|
"epoch": 0.47903441363180754,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004982368349319736,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.1851024940609932,
|
|
"num_tokens": 10555357.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.3701520442962645,
|
|
"epoch": 0.4794520547945205,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004982331133779014,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.1765170603990555,
|
|
"num_tokens": 10564744.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.355828952789307,
|
|
"epoch": 0.47986969595723356,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004982293879158649,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.18183653056621552,
|
|
"num_tokens": 10573736.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.376202154159546,
|
|
"epoch": 0.48028733711994653,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004982256585459293,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.17756519019603728,
|
|
"num_tokens": 10583238.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.462325572967529,
|
|
"epoch": 0.4807049782826595,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004982219252681597,
|
|
"loss": 5.3997,
|
|
"mean_token_accuracy": 0.17141326367855073,
|
|
"num_tokens": 10592316.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.41369743347168,
|
|
"epoch": 0.48112261944537255,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004982181880826218,
|
|
"loss": 5.421,
|
|
"mean_token_accuracy": 0.177415369451046,
|
|
"num_tokens": 10601418.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.3490503311157225,
|
|
"epoch": 0.4815402606080855,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982144469893807,
|
|
"loss": 5.2801,
|
|
"mean_token_accuracy": 0.18411952406167983,
|
|
"num_tokens": 10610513.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.408094787597657,
|
|
"epoch": 0.4819579017707985,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498210701988502,
|
|
"loss": 5.2443,
|
|
"mean_token_accuracy": 0.18783568739891052,
|
|
"num_tokens": 10619529.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.453507995605468,
|
|
"epoch": 0.48237554293351154,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004982069530800514,
|
|
"loss": 5.3288,
|
|
"mean_token_accuracy": 0.18438346534967423,
|
|
"num_tokens": 10628263.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.3486114025115965,
|
|
"epoch": 0.4827931840962245,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004982032002640943,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.1833382233977318,
|
|
"num_tokens": 10637605.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.416544818878174,
|
|
"epoch": 0.48321082525893755,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004981994435406965,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.17957475930452346,
|
|
"num_tokens": 10647113.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.40274977684021,
|
|
"epoch": 0.4836284664216505,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004981956829099239,
|
|
"loss": 5.1838,
|
|
"mean_token_accuracy": 0.18768427073955535,
|
|
"num_tokens": 10655464.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.359679365158081,
|
|
"epoch": 0.4840461075843635,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004981919183718422,
|
|
"loss": 5.2834,
|
|
"mean_token_accuracy": 0.18101781010627746,
|
|
"num_tokens": 10664689.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.2755897521972654,
|
|
"epoch": 0.48446374874707654,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004981881499265173,
|
|
"loss": 5.201,
|
|
"mean_token_accuracy": 0.18344079703092575,
|
|
"num_tokens": 10673440.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.342781734466553,
|
|
"epoch": 0.4848813899097895,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004981843775740151,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.1783262863755226,
|
|
"num_tokens": 10683075.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.365957736968994,
|
|
"epoch": 0.4852990310725025,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004981806013144017,
|
|
"loss": 5.2949,
|
|
"mean_token_accuracy": 0.18161205500364302,
|
|
"num_tokens": 10692663.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.356691837310791,
|
|
"epoch": 0.48571667223521553,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004981768211477434,
|
|
"loss": 5.1803,
|
|
"mean_token_accuracy": 0.18302590399980545,
|
|
"num_tokens": 10702068.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.388083744049072,
|
|
"epoch": 0.4861343133979285,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000498173037074106,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.1714998409152031,
|
|
"num_tokens": 10711230.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.2951349258422855,
|
|
"epoch": 0.4865519545606415,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004981692490935561,
|
|
"loss": 5.2956,
|
|
"mean_token_accuracy": 0.18595292121171952,
|
|
"num_tokens": 10719651.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.396548748016357,
|
|
"epoch": 0.4869695957233545,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004981654572061597,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.17995359599590302,
|
|
"num_tokens": 10729342.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.432379722595215,
|
|
"epoch": 0.4873872368860675,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004981616614119836,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.18182204365730287,
|
|
"num_tokens": 10738617.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.370879411697388,
|
|
"epoch": 0.4878048780487805,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004981578617110938,
|
|
"loss": 5.352,
|
|
"mean_token_accuracy": 0.1767614170908928,
|
|
"num_tokens": 10746881.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.33872241973877,
|
|
"epoch": 0.4882225192114935,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004981540581035571,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.18773332238197327,
|
|
"num_tokens": 10755848.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.292233085632324,
|
|
"epoch": 0.4886401603742065,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00049815025058944,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.17764829993247985,
|
|
"num_tokens": 10765519.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.328621339797974,
|
|
"epoch": 0.48905780153691947,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004981464391688092,
|
|
"loss": 5.3449,
|
|
"mean_token_accuracy": 0.17469416856765746,
|
|
"num_tokens": 10776408.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.430347108840943,
|
|
"epoch": 0.4894754426996325,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004981426238417312,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.18280997276306152,
|
|
"num_tokens": 10785499.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.363692855834961,
|
|
"epoch": 0.4898930838623455,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004981388046082731,
|
|
"loss": 5.2791,
|
|
"mean_token_accuracy": 0.17865316569805145,
|
|
"num_tokens": 10794736.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.346862268447876,
|
|
"epoch": 0.49031072502505846,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004981349814685016,
|
|
"loss": 5.3522,
|
|
"mean_token_accuracy": 0.17651747465133666,
|
|
"num_tokens": 10804125.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.457276105880737,
|
|
"epoch": 0.4907283661877715,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004981311544224838,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.17904023975133895,
|
|
"num_tokens": 10813465.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.357408809661865,
|
|
"epoch": 0.49114600735048447,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004981273234702864,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.1853638082742691,
|
|
"num_tokens": 10821550.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.320731067657471,
|
|
"epoch": 0.49156364851319745,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004981234886119767,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.18118553310632707,
|
|
"num_tokens": 10830683.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.368787336349487,
|
|
"epoch": 0.4919812896759105,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004981196498476217,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.18537646234035493,
|
|
"num_tokens": 10839492.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.318939924240112,
|
|
"epoch": 0.49239893083862346,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004981158071772887,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.18439319729804993,
|
|
"num_tokens": 10847998.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.235811233520508,
|
|
"epoch": 0.49281657200133644,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004981119606010449,
|
|
"loss": 5.2019,
|
|
"mean_token_accuracy": 0.1859842360019684,
|
|
"num_tokens": 10856438.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.2461645126342775,
|
|
"epoch": 0.4932342131640495,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004981081101189577,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.18382869511842728,
|
|
"num_tokens": 10865936.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.419135046005249,
|
|
"epoch": 0.49365185432676245,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004981042557310945,
|
|
"loss": 5.2117,
|
|
"mean_token_accuracy": 0.18635481595993042,
|
|
"num_tokens": 10874621.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.294868326187133,
|
|
"epoch": 0.49406949548947543,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004981003974375227,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.18442256897687911,
|
|
"num_tokens": 10883516.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.328514528274536,
|
|
"epoch": 0.49448713665218846,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004980965352383099,
|
|
"loss": 5.3253,
|
|
"mean_token_accuracy": 0.1761163741350174,
|
|
"num_tokens": 10892580.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.409572649002075,
|
|
"epoch": 0.49490477781490144,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004980926691335238,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.18117301613092424,
|
|
"num_tokens": 10901227.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.367732334136963,
|
|
"epoch": 0.4953224189776144,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004980887991232318,
|
|
"loss": 5.2989,
|
|
"mean_token_accuracy": 0.17467935681343078,
|
|
"num_tokens": 10909454.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.482755661010742,
|
|
"epoch": 0.49574006014032745,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000498084925207502,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.1773775488138199,
|
|
"num_tokens": 10919792.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.419538593292236,
|
|
"epoch": 0.49615770130304043,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000498081047386402,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.17599386274814605,
|
|
"num_tokens": 10930523.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.309274291992187,
|
|
"epoch": 0.4965753424657534,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004980771656599998,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.1857204556465149,
|
|
"num_tokens": 10940075.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.3744665622711185,
|
|
"epoch": 0.49699298362846644,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004980732800283633,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.18188395649194716,
|
|
"num_tokens": 10949059.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.357154750823975,
|
|
"epoch": 0.4974106247911794,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980693904915604,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.18225459307432174,
|
|
"num_tokens": 10958313.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.327280139923095,
|
|
"epoch": 0.4978282659538924,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004980654970496595,
|
|
"loss": 5.3083,
|
|
"mean_token_accuracy": 0.17470995038747789,
|
|
"num_tokens": 10967666.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.457955408096313,
|
|
"epoch": 0.49824590711660544,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004980615997027284,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.18239685744047165,
|
|
"num_tokens": 10976519.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.47369351387024,
|
|
"epoch": 0.4986635482793184,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004980576984508356,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.16856858879327774,
|
|
"num_tokens": 10987138.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.424091768264771,
|
|
"epoch": 0.4990811894420314,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004980537932940492,
|
|
"loss": 5.3092,
|
|
"mean_token_accuracy": 0.18266766965389253,
|
|
"num_tokens": 10996517.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.445526170730591,
|
|
"epoch": 0.4994988306047444,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004980498842324377,
|
|
"loss": 5.1936,
|
|
"mean_token_accuracy": 0.17778559327125548,
|
|
"num_tokens": 11006312.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.303483533859253,
|
|
"epoch": 0.4999164717674574,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004980459712660694,
|
|
"loss": 5.2982,
|
|
"mean_token_accuracy": 0.1875140354037285,
|
|
"num_tokens": 11015535.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.36759123802185,
|
|
"epoch": 0.5003341129301704,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004980420543950131,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.18209726810455323,
|
|
"num_tokens": 11024887.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.2870267868042,
|
|
"epoch": 0.5007517540928834,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004980381336193371,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.19015818387269973,
|
|
"num_tokens": 11033147.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.295065307617188,
|
|
"epoch": 0.5011693952555963,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004980342089391099,
|
|
"loss": 5.3273,
|
|
"mean_token_accuracy": 0.1844463363289833,
|
|
"num_tokens": 11042726.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5011693952555963,
|
|
"eval_entropy": 5.172037276037919,
|
|
"eval_loss": 5.286351680755615,
|
|
"eval_mean_token_accuracy": 0.19003585199226744,
|
|
"eval_num_tokens": 11042726.0,
|
|
"eval_runtime": 27.6328,
|
|
"eval_samples_per_second": 1366.6,
|
|
"eval_steps_per_second": 170.848,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.414085102081299,
|
|
"epoch": 0.5015870364183094,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980302803544006,
|
|
"loss": 5.2927,
|
|
"mean_token_accuracy": 0.18288459330797197,
|
|
"num_tokens": 11052181.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.431057929992676,
|
|
"epoch": 0.5020046775810224,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004980263478652778,
|
|
"loss": 5.3376,
|
|
"mean_token_accuracy": 0.1821412682533264,
|
|
"num_tokens": 11061586.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.46299524307251,
|
|
"epoch": 0.5024223187437353,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004980224114718102,
|
|
"loss": 5.3663,
|
|
"mean_token_accuracy": 0.18216219246387483,
|
|
"num_tokens": 11070914.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.320691680908203,
|
|
"epoch": 0.5028399599064484,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004980184711740669,
|
|
"loss": 5.1881,
|
|
"mean_token_accuracy": 0.1889343485236168,
|
|
"num_tokens": 11079836.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.273727035522461,
|
|
"epoch": 0.5032576010691614,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004980145269721168,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.18011632412672043,
|
|
"num_tokens": 11088320.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.405125617980957,
|
|
"epoch": 0.5036752422318743,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000498010578866029,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.1793920487165451,
|
|
"num_tokens": 11097803.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.513732242584228,
|
|
"epoch": 0.5040928833945874,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004980066268558726,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.17209561616182328,
|
|
"num_tokens": 11107218.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.453762054443359,
|
|
"epoch": 0.5045105245573004,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004980026709417167,
|
|
"loss": 5.2838,
|
|
"mean_token_accuracy": 0.17526641935110093,
|
|
"num_tokens": 11115599.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.254436206817627,
|
|
"epoch": 0.5049281657200133,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004979987111236306,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.1871658131480217,
|
|
"num_tokens": 11124312.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.320400142669678,
|
|
"epoch": 0.5053458068827263,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004979947474016837,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.18224723339080812,
|
|
"num_tokens": 11133117.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.485568237304688,
|
|
"epoch": 0.5057634480454394,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004979907797759453,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.18229107707738876,
|
|
"num_tokens": 11141972.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.489246559143067,
|
|
"epoch": 0.5061810892081523,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004979868082464849,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.17801129072904587,
|
|
"num_tokens": 11151416.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.368074750900268,
|
|
"epoch": 0.5065987303708653,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004979828328133719,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.1798588827252388,
|
|
"num_tokens": 11160727.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.34806489944458,
|
|
"epoch": 0.5070163715335784,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004979788534766762,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.17353069931268691,
|
|
"num_tokens": 11171350.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.359587049484253,
|
|
"epoch": 0.5074340126962913,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004979748702364672,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.18068615347146988,
|
|
"num_tokens": 11180233.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.349366998672485,
|
|
"epoch": 0.5078516538590043,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004979708830928147,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.17650825530290604,
|
|
"num_tokens": 11189269.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.3739677429199215,
|
|
"epoch": 0.5082692950217174,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004979668920457884,
|
|
"loss": 5.3131,
|
|
"mean_token_accuracy": 0.1810814157128334,
|
|
"num_tokens": 11199072.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.3011698722839355,
|
|
"epoch": 0.5086869361844303,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004979628970954584,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.18820451498031615,
|
|
"num_tokens": 11207164.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.339222431182861,
|
|
"epoch": 0.5091045773471433,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979588982418944,
|
|
"loss": 5.2644,
|
|
"mean_token_accuracy": 0.17381262183189392,
|
|
"num_tokens": 11216557.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.52068681716919,
|
|
"epoch": 0.5095222185098564,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004979548954851666,
|
|
"loss": 5.4143,
|
|
"mean_token_accuracy": 0.1751055583357811,
|
|
"num_tokens": 11227277.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.401752376556397,
|
|
"epoch": 0.5099398596725693,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000497950888825345,
|
|
"loss": 5.2005,
|
|
"mean_token_accuracy": 0.19273057878017424,
|
|
"num_tokens": 11236226.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.343244981765747,
|
|
"epoch": 0.5103575008352823,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004979468782624996,
|
|
"loss": 5.3121,
|
|
"mean_token_accuracy": 0.18312968611717223,
|
|
"num_tokens": 11245246.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.366712760925293,
|
|
"epoch": 0.5107751419979953,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004979428637967009,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.1794750526547432,
|
|
"num_tokens": 11254437.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.381765365600586,
|
|
"epoch": 0.5111927831607083,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004979388454280189,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.18831336945295335,
|
|
"num_tokens": 11262413.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.3759208679199215,
|
|
"epoch": 0.5116104243234213,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000497934823156524,
|
|
"loss": 5.4007,
|
|
"mean_token_accuracy": 0.17576018571853638,
|
|
"num_tokens": 11272061.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.353822851181031,
|
|
"epoch": 0.5120280654861343,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004979307969822869,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.1847929373383522,
|
|
"num_tokens": 11281623.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.2704144477844235,
|
|
"epoch": 0.5124457066488474,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004979267669053776,
|
|
"loss": 5.1026,
|
|
"mean_token_accuracy": 0.1965145394206047,
|
|
"num_tokens": 11290202.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.346707725524903,
|
|
"epoch": 0.5128633478115603,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004979227329258671,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.18677955716848374,
|
|
"num_tokens": 11299040.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.4291024684906,
|
|
"epoch": 0.5132809889742733,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004979186950438256,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.17737863659858705,
|
|
"num_tokens": 11307938.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.417812776565552,
|
|
"epoch": 0.5136986301369864,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004979146532593243,
|
|
"loss": 5.2973,
|
|
"mean_token_accuracy": 0.18085166364908217,
|
|
"num_tokens": 11316915.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.36984429359436,
|
|
"epoch": 0.5141162712996993,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004979106075724334,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.1764444351196289,
|
|
"num_tokens": 11326634.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.471321630477905,
|
|
"epoch": 0.5145339124624123,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004979065579832242,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.16635178923606872,
|
|
"num_tokens": 11336502.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.374242877960205,
|
|
"epoch": 0.5149515536251253,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004979025044917673,
|
|
"loss": 5.3295,
|
|
"mean_token_accuracy": 0.17512160092592238,
|
|
"num_tokens": 11346125.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.439322662353516,
|
|
"epoch": 0.5153691947878383,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004978984470981339,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.16800944954156877,
|
|
"num_tokens": 11355713.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.390084266662598,
|
|
"epoch": 0.5157868359505513,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004978943858023946,
|
|
"loss": 5.2302,
|
|
"mean_token_accuracy": 0.18250556588172911,
|
|
"num_tokens": 11364726.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.398955154418945,
|
|
"epoch": 0.5162044771132643,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497890320604621,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.1793229892849922,
|
|
"num_tokens": 11373779.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.286739683151245,
|
|
"epoch": 0.5166221182759773,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000497886251504884,
|
|
"loss": 5.2421,
|
|
"mean_token_accuracy": 0.1845567375421524,
|
|
"num_tokens": 11382641.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.2926445484161375,
|
|
"epoch": 0.5170397594386903,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004978821785032549,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.1850380316376686,
|
|
"num_tokens": 11392200.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.4064432144165036,
|
|
"epoch": 0.5174574006014033,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004978781015998048,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.16943650394678117,
|
|
"num_tokens": 11401884.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.344465208053589,
|
|
"epoch": 0.5178750417641163,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004978740207946056,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.1897432804107666,
|
|
"num_tokens": 11410710.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.275054216384888,
|
|
"epoch": 0.5182926829268293,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004978699360877281,
|
|
"loss": 5.1735,
|
|
"mean_token_accuracy": 0.18877318501472473,
|
|
"num_tokens": 11419622.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.327790784835815,
|
|
"epoch": 0.5187103240895423,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004978658474792442,
|
|
"loss": 5.1913,
|
|
"mean_token_accuracy": 0.1880590006709099,
|
|
"num_tokens": 11427631.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.373764514923096,
|
|
"epoch": 0.5191279652522552,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004978617549692253,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.18507532477378846,
|
|
"num_tokens": 11437630.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.479686069488525,
|
|
"epoch": 0.5195456064149683,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004978576585577432,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.16511390805244447,
|
|
"num_tokens": 11447962.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.501290321350098,
|
|
"epoch": 0.5199632475776813,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004978535582448695,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.1783910036087036,
|
|
"num_tokens": 11458154.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.261790037155151,
|
|
"epoch": 0.5203808887403942,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004978494540306761,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.18092765361070634,
|
|
"num_tokens": 11467449.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.3864082336425785,
|
|
"epoch": 0.5207985299031073,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004978453459152346,
|
|
"loss": 5.4549,
|
|
"mean_token_accuracy": 0.1697009190917015,
|
|
"num_tokens": 11477775.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.486942911148072,
|
|
"epoch": 0.5212161710658203,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004978412338986172,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.17945119887590408,
|
|
"num_tokens": 11486921.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.283312463760376,
|
|
"epoch": 0.5216338122285332,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004978371179808958,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.18170327991247176,
|
|
"num_tokens": 11496562.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.331500291824341,
|
|
"epoch": 0.5220514533912463,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004978329981621424,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.18204472064971924,
|
|
"num_tokens": 11504906.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.365571546554565,
|
|
"epoch": 0.5224690945539593,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000497828874442429,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.18381647765636444,
|
|
"num_tokens": 11513757.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.310463285446167,
|
|
"epoch": 0.5228867357166722,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000497824746821828,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.18171454966068268,
|
|
"num_tokens": 11523195.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.38994460105896,
|
|
"epoch": 0.5233043768793852,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004978206153004117,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.18391313403844833,
|
|
"num_tokens": 11532348.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.447969818115235,
|
|
"epoch": 0.5237220180420983,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004978164798782523,
|
|
"loss": 5.3111,
|
|
"mean_token_accuracy": 0.18087030500173568,
|
|
"num_tokens": 11542356.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.358577871322632,
|
|
"epoch": 0.5241396592048112,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004978123405554221,
|
|
"loss": 5.316,
|
|
"mean_token_accuracy": 0.18624789118766785,
|
|
"num_tokens": 11550914.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.357284021377564,
|
|
"epoch": 0.5245573003675242,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004978081973319938,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.1887720912694931,
|
|
"num_tokens": 11559314.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.298609638214112,
|
|
"epoch": 0.5249749415302373,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004978040502080398,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.18396988213062287,
|
|
"num_tokens": 11567990.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.325413465499878,
|
|
"epoch": 0.5253925826929502,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004977998991836327,
|
|
"loss": 5.2682,
|
|
"mean_token_accuracy": 0.1804572269320488,
|
|
"num_tokens": 11577133.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.404793977737427,
|
|
"epoch": 0.5258102238556632,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004977957442588451,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.18051642328500747,
|
|
"num_tokens": 11585330.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.431662559509277,
|
|
"epoch": 0.5262278650183763,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977915854337498,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.17675420343875886,
|
|
"num_tokens": 11595005.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.281835603713989,
|
|
"epoch": 0.5266455061810892,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977874227084197,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.189839705824852,
|
|
"num_tokens": 11603969.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.262091064453125,
|
|
"epoch": 0.5270631473438022,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004977832560829277,
|
|
"loss": 5.2292,
|
|
"mean_token_accuracy": 0.18192449510097503,
|
|
"num_tokens": 11613118.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.3321326732635494,
|
|
"epoch": 0.5274807885065153,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004977790855573464,
|
|
"loss": 5.1735,
|
|
"mean_token_accuracy": 0.1879858985543251,
|
|
"num_tokens": 11621799.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.27553653717041,
|
|
"epoch": 0.5278984296692282,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004977749111317492,
|
|
"loss": 5.2553,
|
|
"mean_token_accuracy": 0.18213354647159577,
|
|
"num_tokens": 11630557.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.365929841995239,
|
|
"epoch": 0.5283160708319412,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497770732806209,
|
|
"loss": 5.284,
|
|
"mean_token_accuracy": 0.18342802226543425,
|
|
"num_tokens": 11639179.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.4187873840332035,
|
|
"epoch": 0.5287337119946542,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000497766550580799,
|
|
"loss": 5.3909,
|
|
"mean_token_accuracy": 0.17303578406572342,
|
|
"num_tokens": 11648273.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.367193937301636,
|
|
"epoch": 0.5291513531573672,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004977623644555923,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.18123112320899964,
|
|
"num_tokens": 11656372.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.342953634262085,
|
|
"epoch": 0.5295689943200802,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004977581744306624,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.183183516561985,
|
|
"num_tokens": 11665007.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.353275775909424,
|
|
"epoch": 0.5299866354827932,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004977539805060824,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.17437319308519364,
|
|
"num_tokens": 11674519.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.465643739700317,
|
|
"epoch": 0.5304042766455062,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004977497826819259,
|
|
"loss": 5.2697,
|
|
"mean_token_accuracy": 0.1804721772670746,
|
|
"num_tokens": 11683705.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.33522515296936,
|
|
"epoch": 0.5308219178082192,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004977455809582664,
|
|
"loss": 5.2339,
|
|
"mean_token_accuracy": 0.18320189267396927,
|
|
"num_tokens": 11693152.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.305587673187256,
|
|
"epoch": 0.5312395589709322,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977413753351772,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.17687471807003022,
|
|
"num_tokens": 11702584.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.334028148651123,
|
|
"epoch": 0.5316572001336451,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004977371658127323,
|
|
"loss": 5.2967,
|
|
"mean_token_accuracy": 0.18502158522605897,
|
|
"num_tokens": 11711633.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.350752305984497,
|
|
"epoch": 0.5320748412963582,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004977329523910051,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.18760232329368592,
|
|
"num_tokens": 11720116.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.427316093444825,
|
|
"epoch": 0.5324924824590712,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004977287350700695,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.18175739645957947,
|
|
"num_tokens": 11729564.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.362538194656372,
|
|
"epoch": 0.5329101236217841,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004977245138499993,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.19303394705057145,
|
|
"num_tokens": 11737935.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.3124712944030765,
|
|
"epoch": 0.5333277647844972,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004977202887308684,
|
|
"loss": 5.1855,
|
|
"mean_token_accuracy": 0.19043774902820587,
|
|
"num_tokens": 11745989.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.367902755737305,
|
|
"epoch": 0.5337454059472102,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004977160597127507,
|
|
"loss": 5.3527,
|
|
"mean_token_accuracy": 0.18221916258335114,
|
|
"num_tokens": 11755530.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.382074356079102,
|
|
"epoch": 0.5341630471099231,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004977118267957204,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.17612025141716003,
|
|
"num_tokens": 11764546.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.494977712631226,
|
|
"epoch": 0.5345806882726362,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004977075899798513,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.17207112312316894,
|
|
"num_tokens": 11774117.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.417264699935913,
|
|
"epoch": 0.5349983294353492,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000497703349265218,
|
|
"loss": 5.2117,
|
|
"mean_token_accuracy": 0.18813925087451935,
|
|
"num_tokens": 11782952.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.376785326004028,
|
|
"epoch": 0.5354159705980621,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004976991046518943,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.174733866751194,
|
|
"num_tokens": 11792369.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.322673368453979,
|
|
"epoch": 0.5358336117607752,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004976948561399549,
|
|
"loss": 5.2099,
|
|
"mean_token_accuracy": 0.1901026889681816,
|
|
"num_tokens": 11801365.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.384335041046143,
|
|
"epoch": 0.5362512529234882,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004976906037294738,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.18374739438295365,
|
|
"num_tokens": 11809785.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.351803398132324,
|
|
"epoch": 0.5366688940862011,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004976863474205257,
|
|
"loss": 5.1829,
|
|
"mean_token_accuracy": 0.18223468214273453,
|
|
"num_tokens": 11817978.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.388811302185059,
|
|
"epoch": 0.5370865352489141,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004976820872131851,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.18446996659040452,
|
|
"num_tokens": 11827796.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.229735851287842,
|
|
"epoch": 0.5375041764116272,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004976778231075266,
|
|
"loss": 5.1501,
|
|
"mean_token_accuracy": 0.18932668417692183,
|
|
"num_tokens": 11836439.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.361645174026489,
|
|
"epoch": 0.5379218175743401,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004976735551036245,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.17990088164806367,
|
|
"num_tokens": 11845268.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.4373973369598385,
|
|
"epoch": 0.5383394587370531,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497669283201554,
|
|
"loss": 5.2788,
|
|
"mean_token_accuracy": 0.180202616751194,
|
|
"num_tokens": 11855185.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.31826958656311,
|
|
"epoch": 0.5387570998997662,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004976650074013895,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.1824183687567711,
|
|
"num_tokens": 11865073.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.430147266387939,
|
|
"epoch": 0.5391747410624791,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004976607277032061,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.18481045365333557,
|
|
"num_tokens": 11875004.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.382980632781982,
|
|
"epoch": 0.5395923822251921,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004976564441070788,
|
|
"loss": 5.2949,
|
|
"mean_token_accuracy": 0.17465188801288606,
|
|
"num_tokens": 11884905.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.386041259765625,
|
|
"epoch": 0.5400100233879052,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004976521566130823,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.17858238518238068,
|
|
"num_tokens": 11894669.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.501698303222656,
|
|
"epoch": 0.5404276645506181,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004976478652212918,
|
|
"loss": 5.462,
|
|
"mean_token_accuracy": 0.16954419314861296,
|
|
"num_tokens": 11904127.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.423941802978516,
|
|
"epoch": 0.5408453057133311,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004976435699317824,
|
|
"loss": 5.2784,
|
|
"mean_token_accuracy": 0.18121567368507385,
|
|
"num_tokens": 11912031.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.309411907196045,
|
|
"epoch": 0.5412629468760441,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004976392707446293,
|
|
"loss": 5.1966,
|
|
"mean_token_accuracy": 0.19244254231452942,
|
|
"num_tokens": 11920961.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.443402051925659,
|
|
"epoch": 0.5416805880387571,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004976349676599078,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.1785212427377701,
|
|
"num_tokens": 11930454.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.304493045806884,
|
|
"epoch": 0.5420982292014701,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004976306606776932,
|
|
"loss": 5.1429,
|
|
"mean_token_accuracy": 0.18634013682603837,
|
|
"num_tokens": 11938610.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.323086214065552,
|
|
"epoch": 0.5425158703641831,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004976263497980609,
|
|
"loss": 5.3255,
|
|
"mean_token_accuracy": 0.18066132068634033,
|
|
"num_tokens": 11947882.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.381497001647949,
|
|
"epoch": 0.5429335115268961,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004976220350210864,
|
|
"loss": 5.3139,
|
|
"mean_token_accuracy": 0.17742136269807815,
|
|
"num_tokens": 11957552.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.378464460372925,
|
|
"epoch": 0.5433511526896091,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004976177163468451,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.18173269033432007,
|
|
"num_tokens": 11967350.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.384993410110473,
|
|
"epoch": 0.5437687938523221,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004976133937754128,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.18130826205015182,
|
|
"num_tokens": 11976107.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.35005750656128,
|
|
"epoch": 0.544186435015035,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004976090673068651,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.18404854983091354,
|
|
"num_tokens": 11985059.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.305514287948609,
|
|
"epoch": 0.5446040761777481,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004976047369412778,
|
|
"loss": 5.2181,
|
|
"mean_token_accuracy": 0.18331118524074555,
|
|
"num_tokens": 11993453.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.250410461425782,
|
|
"epoch": 0.5450217173404611,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004976004026787266,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.1889011651277542,
|
|
"num_tokens": 12002524.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.286372709274292,
|
|
"epoch": 0.545439358503174,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004975960645192873,
|
|
"loss": 5.2366,
|
|
"mean_token_accuracy": 0.184749273955822,
|
|
"num_tokens": 12011516.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.4061259746551515,
|
|
"epoch": 0.5458569996658871,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004975917224630359,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.18020799309015273,
|
|
"num_tokens": 12020058.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.466730833053589,
|
|
"epoch": 0.5462746408286001,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004975873765100487,
|
|
"loss": 5.3838,
|
|
"mean_token_accuracy": 0.17894876897335052,
|
|
"num_tokens": 12029167.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.43693175315857,
|
|
"epoch": 0.546692281991313,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004975830266604013,
|
|
"loss": 5.3256,
|
|
"mean_token_accuracy": 0.17956264615058898,
|
|
"num_tokens": 12038298.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.384665489196777,
|
|
"epoch": 0.5471099231540261,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004975786729141702,
|
|
"loss": 5.2651,
|
|
"mean_token_accuracy": 0.17975437343120576,
|
|
"num_tokens": 12047437.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.362612628936768,
|
|
"epoch": 0.5475275643167391,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004975743152714314,
|
|
"loss": 5.2965,
|
|
"mean_token_accuracy": 0.18631380498409272,
|
|
"num_tokens": 12055821.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.327825403213501,
|
|
"epoch": 0.547945205479452,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004975699537322616,
|
|
"loss": 5.1643,
|
|
"mean_token_accuracy": 0.19042067527770995,
|
|
"num_tokens": 12064378.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.298802900314331,
|
|
"epoch": 0.5483628466421651,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004975655882967366,
|
|
"loss": 5.2241,
|
|
"mean_token_accuracy": 0.18299751430749894,
|
|
"num_tokens": 12073110.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.3863519668579105,
|
|
"epoch": 0.5487804878048781,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004975612189649331,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.18545016050338745,
|
|
"num_tokens": 12081224.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.374075174331665,
|
|
"epoch": 0.549198128967591,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004975568457369276,
|
|
"loss": 5.3135,
|
|
"mean_token_accuracy": 0.18435729891061783,
|
|
"num_tokens": 12090279.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.382840347290039,
|
|
"epoch": 0.549615770130304,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004975524686127966,
|
|
"loss": 5.3086,
|
|
"mean_token_accuracy": 0.1836516499519348,
|
|
"num_tokens": 12098818.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.343344402313233,
|
|
"epoch": 0.5500334112930171,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004975480875926168,
|
|
"loss": 5.246,
|
|
"mean_token_accuracy": 0.1891148567199707,
|
|
"num_tokens": 12107358.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.371078109741211,
|
|
"epoch": 0.55045105245573,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004975437026764648,
|
|
"loss": 5.3032,
|
|
"mean_token_accuracy": 0.17587835490703582,
|
|
"num_tokens": 12116802.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.356584596633911,
|
|
"epoch": 0.550868693618443,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004975393138644175,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.18383945524692535,
|
|
"num_tokens": 12126347.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.264455652236938,
|
|
"epoch": 0.5512863347811561,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004975349211565515,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.1821246027946472,
|
|
"num_tokens": 12136138.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.329731607437134,
|
|
"epoch": 0.551703975943869,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000497530524552944,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.18586531579494475,
|
|
"num_tokens": 12146436.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.425878047943115,
|
|
"epoch": 0.552121617106582,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004975261240536716,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.18001115024089814,
|
|
"num_tokens": 12157003.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.343220472335815,
|
|
"epoch": 0.5525392582692951,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004975217196588117,
|
|
"loss": 5.2183,
|
|
"mean_token_accuracy": 0.19267099499702453,
|
|
"num_tokens": 12166671.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.276378631591797,
|
|
"epoch": 0.552956899432008,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004975173113684413,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.18465711027383805,
|
|
"num_tokens": 12176474.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.390606307983399,
|
|
"epoch": 0.553374540594721,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004975128991826374,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.19043864756822587,
|
|
"num_tokens": 12185307.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.351818180084228,
|
|
"epoch": 0.553792181757434,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004975084831014774,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.18219854831695556,
|
|
"num_tokens": 12195179.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.296496772766114,
|
|
"epoch": 0.554209822920147,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004975040631250386,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.19119415134191514,
|
|
"num_tokens": 12204083.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.29406852722168,
|
|
"epoch": 0.55462746408286,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004974996392533983,
|
|
"loss": 5.2206,
|
|
"mean_token_accuracy": 0.19135015606880187,
|
|
"num_tokens": 12213322.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.323991298675537,
|
|
"epoch": 0.555045105245573,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000497495211486634,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.18611935675144195,
|
|
"num_tokens": 12222305.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.371159934997559,
|
|
"epoch": 0.555462746408286,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004974907798248232,
|
|
"loss": 5.3233,
|
|
"mean_token_accuracy": 0.17673341184854507,
|
|
"num_tokens": 12232196.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.411021757125854,
|
|
"epoch": 0.555880387570999,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004974863442680434,
|
|
"loss": 5.2521,
|
|
"mean_token_accuracy": 0.18408025801181793,
|
|
"num_tokens": 12241914.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.189435577392578,
|
|
"epoch": 0.556298028733712,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004974819048163725,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.1912049800157547,
|
|
"num_tokens": 12250185.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.365625524520874,
|
|
"epoch": 0.556715669896425,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000497477461469888,
|
|
"loss": 5.3231,
|
|
"mean_token_accuracy": 0.17474996000528337,
|
|
"num_tokens": 12258954.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.473125267028808,
|
|
"epoch": 0.557133311059138,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004974730142286677,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.17727245539426803,
|
|
"num_tokens": 12268320.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.249721670150757,
|
|
"epoch": 0.557550952221851,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004974685630927895,
|
|
"loss": 5.2127,
|
|
"mean_token_accuracy": 0.1804267629981041,
|
|
"num_tokens": 12276804.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.442297840118409,
|
|
"epoch": 0.557968593384564,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004974641080623314,
|
|
"loss": 5.2641,
|
|
"mean_token_accuracy": 0.1770022466778755,
|
|
"num_tokens": 12286024.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.349287652969361,
|
|
"epoch": 0.558386234547277,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004974596491373711,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.18299159854650499,
|
|
"num_tokens": 12295154.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.387079477310181,
|
|
"epoch": 0.55880387570999,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004974551863179871,
|
|
"loss": 5.363,
|
|
"mean_token_accuracy": 0.17097254991531372,
|
|
"num_tokens": 12306349.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.407424402236939,
|
|
"epoch": 0.5592215168727029,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004974507196042572,
|
|
"loss": 5.3179,
|
|
"mean_token_accuracy": 0.18425286263227464,
|
|
"num_tokens": 12315496.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.2734064102172855,
|
|
"epoch": 0.559639158035416,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004974462489962597,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.1862584874033928,
|
|
"num_tokens": 12325070.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.346486568450928,
|
|
"epoch": 0.560056799198129,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004974417744940729,
|
|
"loss": 5.2523,
|
|
"mean_token_accuracy": 0.17760104089975357,
|
|
"num_tokens": 12333509.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.345494794845581,
|
|
"epoch": 0.5604744403608419,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000497437296097775,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.17850659936666488,
|
|
"num_tokens": 12342495.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.327435064315796,
|
|
"epoch": 0.560892081523555,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004974328138074445,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.18249644935131074,
|
|
"num_tokens": 12351560.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.380244398117066,
|
|
"epoch": 0.561309722686268,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004974283276231599,
|
|
"loss": 5.3262,
|
|
"mean_token_accuracy": 0.18469928950071335,
|
|
"num_tokens": 12360773.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.357887172698975,
|
|
"epoch": 0.5617273638489809,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004974238375449996,
|
|
"loss": 5.3384,
|
|
"mean_token_accuracy": 0.1726855531334877,
|
|
"num_tokens": 12370519.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.410505056381226,
|
|
"epoch": 0.562145005011694,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004974193435730424,
|
|
"loss": 5.3248,
|
|
"mean_token_accuracy": 0.17881592810153962,
|
|
"num_tokens": 12380563.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.455129098892212,
|
|
"epoch": 0.562562646174407,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004974148457073668,
|
|
"loss": 5.3182,
|
|
"mean_token_accuracy": 0.18274307399988174,
|
|
"num_tokens": 12389291.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.329137706756592,
|
|
"epoch": 0.5629802873371199,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004974103439480517,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.1844645231962204,
|
|
"num_tokens": 12399037.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.297447586059571,
|
|
"epoch": 0.563397928499833,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004974058382951757,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.19304572641849518,
|
|
"num_tokens": 12407553.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.249135494232178,
|
|
"epoch": 0.563815569662546,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004974013287488177,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.18568285256624223,
|
|
"num_tokens": 12416298.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.363959169387817,
|
|
"epoch": 0.5642332108252589,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004973968153090569,
|
|
"loss": 5.3317,
|
|
"mean_token_accuracy": 0.1737111657857895,
|
|
"num_tokens": 12425918.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.376228904724121,
|
|
"epoch": 0.5646508519879719,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004973922979759722,
|
|
"loss": 5.2656,
|
|
"mean_token_accuracy": 0.17900831997394562,
|
|
"num_tokens": 12434693.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.233968305587768,
|
|
"epoch": 0.565068493150685,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004973877767496424,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.1882891222834587,
|
|
"num_tokens": 12444055.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.2691069602966305,
|
|
"epoch": 0.5654861343133979,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004973832516301472,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.1932446539402008,
|
|
"num_tokens": 12453012.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.294369649887085,
|
|
"epoch": 0.5659037754761109,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004973787226175652,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.18431908637285233,
|
|
"num_tokens": 12462292.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.306050586700439,
|
|
"epoch": 0.566321416638824,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004973741897119761,
|
|
"loss": 5.2026,
|
|
"mean_token_accuracy": 0.19394677579402925,
|
|
"num_tokens": 12471178.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.265408897399903,
|
|
"epoch": 0.5667390578015369,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004973696529134592,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.188844895362854,
|
|
"num_tokens": 12479977.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.313236951828003,
|
|
"epoch": 0.5671566989642499,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004973651122220938,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.17963682264089584,
|
|
"num_tokens": 12489004.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.411258029937744,
|
|
"epoch": 0.567574340126963,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004973605676379595,
|
|
"loss": 5.2956,
|
|
"mean_token_accuracy": 0.18012158274650575,
|
|
"num_tokens": 12498979.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.383917236328125,
|
|
"epoch": 0.5679919812896759,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004973560191611357,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.17776286751031875,
|
|
"num_tokens": 12508293.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.49052324295044,
|
|
"epoch": 0.5684096224523889,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004973514667917021,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.17675091177225113,
|
|
"num_tokens": 12517828.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.370597171783447,
|
|
"epoch": 0.5688272636151019,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004973469105297386,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.18173562586307526,
|
|
"num_tokens": 12526569.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.390897464752197,
|
|
"epoch": 0.5692449047778149,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004973423503753247,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.18119753003120423,
|
|
"num_tokens": 12535706.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.430558538436889,
|
|
"epoch": 0.5696625459405279,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004973377863285403,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.18043635040521622,
|
|
"num_tokens": 12544689.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.304398488998413,
|
|
"epoch": 0.5700801871032409,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004973332183894653,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.18837016820907593,
|
|
"num_tokens": 12553318.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.292221403121948,
|
|
"epoch": 0.5704978282659539,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004973286465581798,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.19200338721275328,
|
|
"num_tokens": 12562009.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.388770389556885,
|
|
"epoch": 0.5709154694286669,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004973240708347637,
|
|
"loss": 5.3256,
|
|
"mean_token_accuracy": 0.19126973748207093,
|
|
"num_tokens": 12571043.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.465327453613281,
|
|
"epoch": 0.5713331105913799,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004973194912192971,
|
|
"loss": 5.2619,
|
|
"mean_token_accuracy": 0.18441184908151625,
|
|
"num_tokens": 12581151.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.317709350585938,
|
|
"epoch": 0.5717507517540928,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004973149077118602,
|
|
"loss": 5.2933,
|
|
"mean_token_accuracy": 0.1829424634575844,
|
|
"num_tokens": 12590671.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.315968370437622,
|
|
"epoch": 0.5721683929168059,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004973103203125333,
|
|
"loss": 5.3302,
|
|
"mean_token_accuracy": 0.17839666903018953,
|
|
"num_tokens": 12599693.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.390160179138183,
|
|
"epoch": 0.5725860340795189,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004973057290213965,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.1872655600309372,
|
|
"num_tokens": 12609238.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.335610485076904,
|
|
"epoch": 0.5730036752422318,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004973011338385304,
|
|
"loss": 5.2318,
|
|
"mean_token_accuracy": 0.1856747567653656,
|
|
"num_tokens": 12618273.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.321760749816894,
|
|
"epoch": 0.5734213164049449,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004972965347640154,
|
|
"loss": 5.2957,
|
|
"mean_token_accuracy": 0.18263923972845078,
|
|
"num_tokens": 12628229.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.368953704833984,
|
|
"epoch": 0.5738389575676579,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000497291931797932,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.191641004383564,
|
|
"num_tokens": 12636533.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.273049211502075,
|
|
"epoch": 0.5742565987303708,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004972873249403608,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.18528711795806885,
|
|
"num_tokens": 12645503.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.34866943359375,
|
|
"epoch": 0.5746742398930839,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004972827141913822,
|
|
"loss": 5.2341,
|
|
"mean_token_accuracy": 0.17654672712087632,
|
|
"num_tokens": 12654355.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.361291599273682,
|
|
"epoch": 0.5750918810557969,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004972780995510773,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.18175720870494844,
|
|
"num_tokens": 12663774.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.1940025806427,
|
|
"epoch": 0.5755095222185098,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004972734810195266,
|
|
"loss": 5.2585,
|
|
"mean_token_accuracy": 0.18426082879304886,
|
|
"num_tokens": 12674436.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.3957408428192135,
|
|
"epoch": 0.5759271633812229,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004972688585968112,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.18481385558843613,
|
|
"num_tokens": 12682891.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.255229520797729,
|
|
"epoch": 0.5763448045439359,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004972642322830118,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.19705357104539872,
|
|
"num_tokens": 12691170.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.273286390304565,
|
|
"epoch": 0.5767624457066488,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004972596020782096,
|
|
"loss": 5.1984,
|
|
"mean_token_accuracy": 0.18740458488464357,
|
|
"num_tokens": 12700314.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.313592338562012,
|
|
"epoch": 0.5771800868693618,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004972549679824853,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.18948954790830613,
|
|
"num_tokens": 12709418.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.333023357391357,
|
|
"epoch": 0.5775977280320749,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004972503299959204,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.18070902824401855,
|
|
"num_tokens": 12719287.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.322830009460449,
|
|
"epoch": 0.5780153691947878,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000497245688118596,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.19228754341602325,
|
|
"num_tokens": 12728836.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.353468704223633,
|
|
"epoch": 0.5784330103575008,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004972410423505932,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.17521052658557892,
|
|
"num_tokens": 12738173.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.291993188858032,
|
|
"epoch": 0.5788506515202139,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004972363926919935,
|
|
"loss": 5.2725,
|
|
"mean_token_accuracy": 0.1864841639995575,
|
|
"num_tokens": 12747428.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.403028964996338,
|
|
"epoch": 0.5792682926829268,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004972317391428782,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.17580013126134872,
|
|
"num_tokens": 12757148.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.454678773880005,
|
|
"epoch": 0.5796859338456398,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004972270817033288,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.17018143981695175,
|
|
"num_tokens": 12766820.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.429720783233643,
|
|
"epoch": 0.5801035750083529,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004972224203734269,
|
|
"loss": 5.3264,
|
|
"mean_token_accuracy": 0.17791177928447724,
|
|
"num_tokens": 12776082.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.327076101303101,
|
|
"epoch": 0.5805212161710658,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000497217755153254,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.18474810421466828,
|
|
"num_tokens": 12785057.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.308185148239136,
|
|
"epoch": 0.5809388573337788,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004972130860428918,
|
|
"loss": 5.2988,
|
|
"mean_token_accuracy": 0.190691839158535,
|
|
"num_tokens": 12793599.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.3690268993377686,
|
|
"epoch": 0.5813564984964918,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004972084130424222,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.17726799845695496,
|
|
"num_tokens": 12803775.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.348795747756958,
|
|
"epoch": 0.5817741396592048,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004972037361519267,
|
|
"loss": 5.2193,
|
|
"mean_token_accuracy": 0.1903219923377037,
|
|
"num_tokens": 12812327.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.30856499671936,
|
|
"epoch": 0.5821917808219178,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004971990553714874,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.1907658338546753,
|
|
"num_tokens": 12821218.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.371193265914917,
|
|
"epoch": 0.5826094219846308,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004971943707011861,
|
|
"loss": 5.2847,
|
|
"mean_token_accuracy": 0.1793219655752182,
|
|
"num_tokens": 12831579.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.425595474243164,
|
|
"epoch": 0.5830270631473438,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000497189682141105,
|
|
"loss": 5.3221,
|
|
"mean_token_accuracy": 0.18375834077596664,
|
|
"num_tokens": 12841026.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.297035121917725,
|
|
"epoch": 0.5834447043100568,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004971849896913259,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.17574221193790435,
|
|
"num_tokens": 12850136.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.46290545463562,
|
|
"epoch": 0.5838623454727698,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004971802933519312,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.17922402769327164,
|
|
"num_tokens": 12860345.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.307545185089111,
|
|
"epoch": 0.5842799866354828,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004971755931230031,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.18393541276454925,
|
|
"num_tokens": 12868995.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.403428411483764,
|
|
"epoch": 0.5846976277981958,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004971708890046236,
|
|
"loss": 5.415,
|
|
"mean_token_accuracy": 0.17389337867498397,
|
|
"num_tokens": 12878043.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.336083650588989,
|
|
"epoch": 0.5851152689609088,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004971661809968755,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.18721241801977156,
|
|
"num_tokens": 12887090.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.278947591781616,
|
|
"epoch": 0.5855329101236217,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004971614690998409,
|
|
"loss": 5.1714,
|
|
"mean_token_accuracy": 0.19780073016881944,
|
|
"num_tokens": 12896349.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.3414857387542725,
|
|
"epoch": 0.5859505512863348,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004971567533136024,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.17909024357795716,
|
|
"num_tokens": 12905698.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.253928852081299,
|
|
"epoch": 0.5863681924490478,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004971520336382424,
|
|
"loss": 5.2223,
|
|
"mean_token_accuracy": 0.19666144400835037,
|
|
"num_tokens": 12915146.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.181387281417846,
|
|
"epoch": 0.5867858336117607,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004971473100738437,
|
|
"loss": 5.0843,
|
|
"mean_token_accuracy": 0.1966075822710991,
|
|
"num_tokens": 12924933.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.397075414657593,
|
|
"epoch": 0.5872034747744738,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000497142582620489,
|
|
"loss": 5.331,
|
|
"mean_token_accuracy": 0.17998473197221757,
|
|
"num_tokens": 12934959.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.340605974197388,
|
|
"epoch": 0.5876211159371868,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004971378512782609,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.1947772204875946,
|
|
"num_tokens": 12943470.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.223190832138061,
|
|
"epoch": 0.5880387570998997,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004971331160472424,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.1917681023478508,
|
|
"num_tokens": 12953592.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.3833833694458,
|
|
"epoch": 0.5884563982626128,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004971283769275163,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.1722431391477585,
|
|
"num_tokens": 12962893.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.354134368896484,
|
|
"epoch": 0.5888740394253258,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004971236339191656,
|
|
"loss": 5.1945,
|
|
"mean_token_accuracy": 0.1897740438580513,
|
|
"num_tokens": 12971635.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.239306449890137,
|
|
"epoch": 0.5892916805880387,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004971188870222734,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.1947092667222023,
|
|
"num_tokens": 12981040.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.322380304336548,
|
|
"epoch": 0.5897093217507517,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004971141362369226,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.185821096599102,
|
|
"num_tokens": 12989898.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.376731729507446,
|
|
"epoch": 0.5901269629134648,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004971093815631965,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.1879758670926094,
|
|
"num_tokens": 12998584.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.234632062911987,
|
|
"epoch": 0.5905446040761777,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004971046230011783,
|
|
"loss": 5.2264,
|
|
"mean_token_accuracy": 0.18627288043498993,
|
|
"num_tokens": 13008007.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.357740354537964,
|
|
"epoch": 0.5909622452388907,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004970998605509514,
|
|
"loss": 5.3368,
|
|
"mean_token_accuracy": 0.1804517537355423,
|
|
"num_tokens": 13017034.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.495122909545898,
|
|
"epoch": 0.5913798864016038,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000497095094212599,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.16964825838804246,
|
|
"num_tokens": 13025916.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.4193336963653564,
|
|
"epoch": 0.5917975275643167,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004970903239862047,
|
|
"loss": 5.2954,
|
|
"mean_token_accuracy": 0.17611705362796784,
|
|
"num_tokens": 13035242.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.313186311721802,
|
|
"epoch": 0.5922151687270297,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004970855498718519,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.18447796553373336,
|
|
"num_tokens": 13044123.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.325734806060791,
|
|
"epoch": 0.5926328098897428,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004970807718696243,
|
|
"loss": 5.2604,
|
|
"mean_token_accuracy": 0.1772498980164528,
|
|
"num_tokens": 13053503.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.349041843414307,
|
|
"epoch": 0.5930504510524557,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004970759899796055,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.18219223469495774,
|
|
"num_tokens": 13062106.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.385118722915649,
|
|
"epoch": 0.5934680922151687,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004970712042018791,
|
|
"loss": 5.2374,
|
|
"mean_token_accuracy": 0.18351289480924607,
|
|
"num_tokens": 13071509.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.264652824401855,
|
|
"epoch": 0.5938857333778818,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004970664145365289,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.19266004711389542,
|
|
"num_tokens": 13080469.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.270586633682251,
|
|
"epoch": 0.5943033745405947,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000497061620983639,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.19512879103422165,
|
|
"num_tokens": 13089826.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.374065494537353,
|
|
"epoch": 0.5947210157033077,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004970568235432931,
|
|
"loss": 5.3253,
|
|
"mean_token_accuracy": 0.18222101777791977,
|
|
"num_tokens": 13098630.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.358995199203491,
|
|
"epoch": 0.5951386568660207,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004970520222155751,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.1871304079890251,
|
|
"num_tokens": 13106819.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.369958782196045,
|
|
"epoch": 0.5955562980287337,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004970472170005692,
|
|
"loss": 5.2379,
|
|
"mean_token_accuracy": 0.18896643668413163,
|
|
"num_tokens": 13115471.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.246409225463867,
|
|
"epoch": 0.5959739391914467,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004970424078983596,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.19780913591384888,
|
|
"num_tokens": 13124537.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.279074430465698,
|
|
"epoch": 0.5963915803541597,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004970375949090302,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.18253438025712967,
|
|
"num_tokens": 13135326.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.476173019409179,
|
|
"epoch": 0.5968092215168727,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004970327780326655,
|
|
"loss": 5.3551,
|
|
"mean_token_accuracy": 0.17697446942329406,
|
|
"num_tokens": 13145502.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.411634635925293,
|
|
"epoch": 0.5972268626795857,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004970279572693498,
|
|
"loss": 5.258,
|
|
"mean_token_accuracy": 0.18461368680000306,
|
|
"num_tokens": 13154808.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.253088760375976,
|
|
"epoch": 0.5976445038422987,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004970231326191674,
|
|
"loss": 5.3812,
|
|
"mean_token_accuracy": 0.17350238263607026,
|
|
"num_tokens": 13163982.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.361168766021729,
|
|
"epoch": 0.5980621450050116,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004970183040822029,
|
|
"loss": 5.2722,
|
|
"mean_token_accuracy": 0.18401766270399095,
|
|
"num_tokens": 13172446.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.389185571670533,
|
|
"epoch": 0.5984797861677247,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004970134716585407,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.18320017158985138,
|
|
"num_tokens": 13181671.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.250359344482422,
|
|
"epoch": 0.5988974273304377,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004970086353482654,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.1845400884747505,
|
|
"num_tokens": 13190207.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.2645087242126465,
|
|
"epoch": 0.5993150684931506,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004970037951514617,
|
|
"loss": 5.1487,
|
|
"mean_token_accuracy": 0.1919180080294609,
|
|
"num_tokens": 13198866.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.2738477230072025,
|
|
"epoch": 0.5997327096558637,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004969989510682143,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.19386524707078934,
|
|
"num_tokens": 13207921.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.441553592681885,
|
|
"epoch": 0.6001503508185767,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004969941030986082,
|
|
"loss": 5.3503,
|
|
"mean_token_accuracy": 0.1791888102889061,
|
|
"num_tokens": 13217759.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.2828004360198975,
|
|
"epoch": 0.6005679919812896,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000496989251242728,
|
|
"loss": 5.1333,
|
|
"mean_token_accuracy": 0.18978789299726487,
|
|
"num_tokens": 13226592.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.2834490776062015,
|
|
"epoch": 0.6009856331440027,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004969843955006588,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.18763985782861708,
|
|
"num_tokens": 13236123.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.330254459381104,
|
|
"epoch": 0.6014032743067157,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004969795358724855,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.1803394615650177,
|
|
"num_tokens": 13246169.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.27890911102295,
|
|
"epoch": 0.6018209154694286,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004969746723582932,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.19286707192659377,
|
|
"num_tokens": 13256141.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.371651697158813,
|
|
"epoch": 0.6022385566321417,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004969698049581672,
|
|
"loss": 5.3484,
|
|
"mean_token_accuracy": 0.18351904153823853,
|
|
"num_tokens": 13265491.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.493934679031372,
|
|
"epoch": 0.6026561977948547,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004969649336721924,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.18758141547441481,
|
|
"num_tokens": 13274805.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.403158807754517,
|
|
"epoch": 0.6030738389575676,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004969600585004544,
|
|
"loss": 5.2959,
|
|
"mean_token_accuracy": 0.1817632332444191,
|
|
"num_tokens": 13284589.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.273687744140625,
|
|
"epoch": 0.6034914801202806,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004969551794430383,
|
|
"loss": 5.1332,
|
|
"mean_token_accuracy": 0.19399268180131912,
|
|
"num_tokens": 13293370.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.3851055145263675,
|
|
"epoch": 0.6039091212829937,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004969502965000297,
|
|
"loss": 5.3173,
|
|
"mean_token_accuracy": 0.18494612872600555,
|
|
"num_tokens": 13302555.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.322985553741455,
|
|
"epoch": 0.6043267624457066,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000496945409671514,
|
|
"loss": 5.235,
|
|
"mean_token_accuracy": 0.1859142526984215,
|
|
"num_tokens": 13311632.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.3157310962677,
|
|
"epoch": 0.6047444036084196,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004969405189575768,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.19575650691986085,
|
|
"num_tokens": 13320593.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.257418537139893,
|
|
"epoch": 0.6051620447711327,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004969356243583036,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.19478675723075867,
|
|
"num_tokens": 13329095.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.25714225769043,
|
|
"epoch": 0.6055796859338456,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004969307258737802,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.189331291615963,
|
|
"num_tokens": 13338404.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.317760467529297,
|
|
"epoch": 0.6059973270965586,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004969258235040921,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.1896978050470352,
|
|
"num_tokens": 13347095.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.342493391036987,
|
|
"epoch": 0.6064149682592717,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004969209172493255,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.18658900260925293,
|
|
"num_tokens": 13356606.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.346424150466919,
|
|
"epoch": 0.6068326094219846,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004969160071095661,
|
|
"loss": 5.2473,
|
|
"mean_token_accuracy": 0.18290272057056428,
|
|
"num_tokens": 13366889.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.351289844512939,
|
|
"epoch": 0.6072502505846976,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004969110930848999,
|
|
"loss": 5.257,
|
|
"mean_token_accuracy": 0.18321869969367982,
|
|
"num_tokens": 13376761.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.319521951675415,
|
|
"epoch": 0.6076678917474106,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004969061751754129,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.19837014973163605,
|
|
"num_tokens": 13386226.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.209369802474976,
|
|
"epoch": 0.6080855329101236,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004969012533811911,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.18966408222913742,
|
|
"num_tokens": 13394243.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.3636657238006595,
|
|
"epoch": 0.6085031740728366,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004968963277023208,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.17408158481121064,
|
|
"num_tokens": 13403708.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.365334177017212,
|
|
"epoch": 0.6089208152355496,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004968913981388882,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.18925479352474212,
|
|
"num_tokens": 13412911.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.366679859161377,
|
|
"epoch": 0.6093384563982626,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004968864646909797,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.17972162812948228,
|
|
"num_tokens": 13422423.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.320084190368652,
|
|
"epoch": 0.6097560975609756,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004968815273586814,
|
|
"loss": 5.2029,
|
|
"mean_token_accuracy": 0.18353873044252395,
|
|
"num_tokens": 13430984.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.337083768844605,
|
|
"epoch": 0.6101737387236886,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004968765861420799,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.1862660065293312,
|
|
"num_tokens": 13440492.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.411310434341431,
|
|
"epoch": 0.6105913798864016,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004968716410412617,
|
|
"loss": 5.2409,
|
|
"mean_token_accuracy": 0.18004440367221833,
|
|
"num_tokens": 13449222.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.309297180175781,
|
|
"epoch": 0.6110090210491146,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004968666920563134,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.18749442845582961,
|
|
"num_tokens": 13459126.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.402968645095825,
|
|
"epoch": 0.6114266622118276,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004968617391873216,
|
|
"loss": 5.3598,
|
|
"mean_token_accuracy": 0.17306229770183562,
|
|
"num_tokens": 13468811.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.361046934127808,
|
|
"epoch": 0.6118443033745405,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004968567824343729,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.18235436379909514,
|
|
"num_tokens": 13477765.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.34081015586853,
|
|
"epoch": 0.6122619445372536,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004968518217975542,
|
|
"loss": 5.2991,
|
|
"mean_token_accuracy": 0.1704414039850235,
|
|
"num_tokens": 13487184.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.357620620727539,
|
|
"epoch": 0.6126795856999666,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004968468572769524,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.18385557383298873,
|
|
"num_tokens": 13496784.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.370666408538819,
|
|
"epoch": 0.6130972268626795,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004968418888726543,
|
|
"loss": 5.2778,
|
|
"mean_token_accuracy": 0.18444303125143052,
|
|
"num_tokens": 13505824.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.3123565196990965,
|
|
"epoch": 0.6135148680253926,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004968369165847469,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.18691591322422027,
|
|
"num_tokens": 13515111.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.236346054077148,
|
|
"epoch": 0.6139325091881056,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004968319404133173,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.19265615344047546,
|
|
"num_tokens": 13524163.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.241273498535156,
|
|
"epoch": 0.6143501503508185,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004968269603584525,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.19498640447854995,
|
|
"num_tokens": 13533368.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.320401906967163,
|
|
"epoch": 0.6147677915135316,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004968219764202397,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.1785755604505539,
|
|
"num_tokens": 13543708.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.367575216293335,
|
|
"epoch": 0.6151854326762446,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004968169885987663,
|
|
"loss": 5.2676,
|
|
"mean_token_accuracy": 0.18267862796783446,
|
|
"num_tokens": 13552561.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.4310976505279545,
|
|
"epoch": 0.6156030738389575,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004968119968941193,
|
|
"loss": 5.3533,
|
|
"mean_token_accuracy": 0.17482028156518936,
|
|
"num_tokens": 13562050.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.273569202423095,
|
|
"epoch": 0.6160207150016705,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004968070013063866,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.18400951027870177,
|
|
"num_tokens": 13571356.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.262342119216919,
|
|
"epoch": 0.6164383561643836,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004968020018356552,
|
|
"loss": 5.1844,
|
|
"mean_token_accuracy": 0.1795240670442581,
|
|
"num_tokens": 13581357.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.3235832214355465,
|
|
"epoch": 0.6168559973270965,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004967969984820128,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.18856770545244217,
|
|
"num_tokens": 13589392.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.297839641571045,
|
|
"epoch": 0.6172736384898095,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004967919912455469,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.20096796303987502,
|
|
"num_tokens": 13598376.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.174291801452637,
|
|
"epoch": 0.6176912796525226,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004967869801263454,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.1944248631596565,
|
|
"num_tokens": 13607014.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.339598274230957,
|
|
"epoch": 0.6181089208152355,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004967819651244957,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.18238510191440582,
|
|
"num_tokens": 13615700.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.38496675491333,
|
|
"epoch": 0.6185265619779485,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004967769462400857,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.1903863787651062,
|
|
"num_tokens": 13625230.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.4405985355377195,
|
|
"epoch": 0.6189442031406616,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004967719234732033,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.1819121539592743,
|
|
"num_tokens": 13635258.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.270614814758301,
|
|
"epoch": 0.6193618443033745,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004967668968239365,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.1939717173576355,
|
|
"num_tokens": 13643688.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.303300952911377,
|
|
"epoch": 0.6197794854660875,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004967618662923732,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.18608999848365784,
|
|
"num_tokens": 13652894.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.313575887680054,
|
|
"epoch": 0.6201971266288006,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004967568318786016,
|
|
"loss": 5.2076,
|
|
"mean_token_accuracy": 0.18977562785148622,
|
|
"num_tokens": 13662852.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.340383863449096,
|
|
"epoch": 0.6206147677915135,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004967517935827097,
|
|
"loss": 5.1882,
|
|
"mean_token_accuracy": 0.18542782515287398,
|
|
"num_tokens": 13671457.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.351501989364624,
|
|
"epoch": 0.6210324089542265,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004967467514047856,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.18492195904254913,
|
|
"num_tokens": 13681002.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.307955884933472,
|
|
"epoch": 0.6214500501169395,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004967417053449178,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.18511720299720763,
|
|
"num_tokens": 13690677.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.227345323562622,
|
|
"epoch": 0.6218676912796525,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004967366554031945,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.19810611456632615,
|
|
"num_tokens": 13699151.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.260391616821289,
|
|
"epoch": 0.6222853324423655,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004967316015797042,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.18765032142400742,
|
|
"num_tokens": 13708105.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.3460986614227295,
|
|
"epoch": 0.6227029736050785,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004967265438745352,
|
|
"loss": 5.3876,
|
|
"mean_token_accuracy": 0.17505446076393127,
|
|
"num_tokens": 13717094.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.437796640396118,
|
|
"epoch": 0.6231206147677915,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004967214822877763,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.19002241641283035,
|
|
"num_tokens": 13726639.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.326229476928711,
|
|
"epoch": 0.6235382559305045,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004967164168195159,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.18206896185874938,
|
|
"num_tokens": 13735220.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.171748781204224,
|
|
"epoch": 0.6239558970932175,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004967113474698428,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.19392013400793076,
|
|
"num_tokens": 13743277.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.319364356994629,
|
|
"epoch": 0.6243735382559304,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004967062742388456,
|
|
"loss": 5.2173,
|
|
"mean_token_accuracy": 0.1907710313796997,
|
|
"num_tokens": 13752946.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.373605060577392,
|
|
"epoch": 0.6247911794186435,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004967011971266132,
|
|
"loss": 5.2665,
|
|
"mean_token_accuracy": 0.1872479036450386,
|
|
"num_tokens": 13761297.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.347911024093628,
|
|
"epoch": 0.6252088205813565,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004966961161332346,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.18225371241569518,
|
|
"num_tokens": 13771238.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.307698106765747,
|
|
"epoch": 0.6256264617440696,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004966910312587985,
|
|
"loss": 5.2163,
|
|
"mean_token_accuracy": 0.18507746905088424,
|
|
"num_tokens": 13781420.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.273213529586792,
|
|
"epoch": 0.6260441029067825,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004966859425033941,
|
|
"loss": 5.1881,
|
|
"mean_token_accuracy": 0.19007139801979064,
|
|
"num_tokens": 13789833.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.381387567520141,
|
|
"epoch": 0.6264617440694955,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004966808498671104,
|
|
"loss": 5.3131,
|
|
"mean_token_accuracy": 0.17912554889917373,
|
|
"num_tokens": 13799202.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.402695369720459,
|
|
"epoch": 0.6268793852322085,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004966757533500367,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.1839716613292694,
|
|
"num_tokens": 13809097.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.3216663837432865,
|
|
"epoch": 0.6272970263949215,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000496670652952262,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.19146456569433212,
|
|
"num_tokens": 13818437.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.237986040115357,
|
|
"epoch": 0.6277146675576345,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004966655486738757,
|
|
"loss": 5.2038,
|
|
"mean_token_accuracy": 0.18793047070503235,
|
|
"num_tokens": 13827083.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.285517644882202,
|
|
"epoch": 0.6281323087203475,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004966604405149672,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.18774096220731734,
|
|
"num_tokens": 13835905.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.285591888427734,
|
|
"epoch": 0.6285499498830605,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004966553284756257,
|
|
"loss": 5.1049,
|
|
"mean_token_accuracy": 0.1971011847257614,
|
|
"num_tokens": 13845136.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.212302923202515,
|
|
"epoch": 0.6289675910457735,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004966502125559411,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.1868421420454979,
|
|
"num_tokens": 13855087.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.323467683792114,
|
|
"epoch": 0.6293852322084865,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004966450927560026,
|
|
"loss": 5.2415,
|
|
"mean_token_accuracy": 0.18338870257139206,
|
|
"num_tokens": 13864077.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.360993719100952,
|
|
"epoch": 0.6298028733711994,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004966399690759,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.18297147303819655,
|
|
"num_tokens": 13873404.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.39419584274292,
|
|
"epoch": 0.6302205145339125,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000496634841515723,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.1822591856122017,
|
|
"num_tokens": 13883231.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.239055204391479,
|
|
"epoch": 0.6306381556966255,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004966297100755613,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.19852859377861024,
|
|
"num_tokens": 13892314.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.205962800979615,
|
|
"epoch": 0.6310557968593384,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004966245747555047,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.19216402918100356,
|
|
"num_tokens": 13900771.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.215718221664429,
|
|
"epoch": 0.6314734380220515,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004966194355556432,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.19043028354644775,
|
|
"num_tokens": 13909615.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.348692321777344,
|
|
"epoch": 0.6318910791847645,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004966142924760666,
|
|
"loss": 5.262,
|
|
"mean_token_accuracy": 0.1833634778857231,
|
|
"num_tokens": 13918491.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.287823867797852,
|
|
"epoch": 0.6323087203474774,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004966091455168652,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.17764877378940583,
|
|
"num_tokens": 13927935.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.289534282684326,
|
|
"epoch": 0.6327263615101905,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004966039946781289,
|
|
"loss": 5.0838,
|
|
"mean_token_accuracy": 0.19476981312036515,
|
|
"num_tokens": 13936524.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.252709674835205,
|
|
"epoch": 0.6331440026729035,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000496598839959948,
|
|
"loss": 5.1655,
|
|
"mean_token_accuracy": 0.1889199823141098,
|
|
"num_tokens": 13945544.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.272776508331299,
|
|
"epoch": 0.6335616438356164,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004965936813624126,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.19397238343954087,
|
|
"num_tokens": 13955016.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.2908196449279785,
|
|
"epoch": 0.6339792849983295,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000496588518885613,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.18109929263591767,
|
|
"num_tokens": 13964045.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.315970849990845,
|
|
"epoch": 0.6343969261610425,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004965833525296397,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.18605217188596726,
|
|
"num_tokens": 13973554.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.305334138870239,
|
|
"epoch": 0.6348145673237554,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004965781822945831,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.18150089532136918,
|
|
"num_tokens": 13982669.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.348069143295288,
|
|
"epoch": 0.6352322084864684,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004965730081805338,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.17758703529834746,
|
|
"num_tokens": 13993392.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.437088966369629,
|
|
"epoch": 0.6356498496491815,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004965678301875821,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.1790178969502449,
|
|
"num_tokens": 14002659.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.297514152526856,
|
|
"epoch": 0.6360674908118944,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000496562648315819,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.18059322685003282,
|
|
"num_tokens": 14011561.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.316247034072876,
|
|
"epoch": 0.6364851319746074,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000496557462565335,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.18654428869485856,
|
|
"num_tokens": 14021286.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.288998317718506,
|
|
"epoch": 0.6369027731373205,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004965522729362209,
|
|
"loss": 5.2223,
|
|
"mean_token_accuracy": 0.18602666407823562,
|
|
"num_tokens": 14031901.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.378972339630127,
|
|
"epoch": 0.6373204143000334,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004965470794285676,
|
|
"loss": 5.2814,
|
|
"mean_token_accuracy": 0.18820435404777527,
|
|
"num_tokens": 14041000.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.401868629455566,
|
|
"epoch": 0.6377380554627464,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000496541882042466,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.17929129302501678,
|
|
"num_tokens": 14050567.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.250955963134766,
|
|
"epoch": 0.6381556966254595,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004965366807780071,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.19183983653783798,
|
|
"num_tokens": 14059990.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.326308012008667,
|
|
"epoch": 0.6385733377881724,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004965314756352818,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.1800059974193573,
|
|
"num_tokens": 14069317.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.3463438034057615,
|
|
"epoch": 0.6389909789508854,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004965262666143816,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.1908731773495674,
|
|
"num_tokens": 14078809.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.339958190917969,
|
|
"epoch": 0.6394086201135984,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004965210537153973,
|
|
"loss": 5.2693,
|
|
"mean_token_accuracy": 0.1820810928940773,
|
|
"num_tokens": 14087660.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.369264554977417,
|
|
"epoch": 0.6398262612763114,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004965158369384204,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.1803284004330635,
|
|
"num_tokens": 14096585.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.273446750640869,
|
|
"epoch": 0.6402439024390244,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000496510616283542,
|
|
"loss": 5.1644,
|
|
"mean_token_accuracy": 0.19130808115005493,
|
|
"num_tokens": 14106079.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.353111505508423,
|
|
"epoch": 0.6406615436017374,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004965053917508537,
|
|
"loss": 5.28,
|
|
"mean_token_accuracy": 0.1832178458571434,
|
|
"num_tokens": 14115988.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.34995813369751,
|
|
"epoch": 0.6410791847644504,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004965001633404469,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.17697596102952956,
|
|
"num_tokens": 14126980.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.3710198402404785,
|
|
"epoch": 0.6414968259271634,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004964949310524131,
|
|
"loss": 5.2604,
|
|
"mean_token_accuracy": 0.18837666362524033,
|
|
"num_tokens": 14135780.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.394362115859986,
|
|
"epoch": 0.6419144670898764,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004964896948868439,
|
|
"loss": 5.2922,
|
|
"mean_token_accuracy": 0.17141007632017136,
|
|
"num_tokens": 14145655.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.345735120773315,
|
|
"epoch": 0.6423321082525894,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004964844548438311,
|
|
"loss": 5.1735,
|
|
"mean_token_accuracy": 0.18798206001520157,
|
|
"num_tokens": 14154157.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.33874135017395,
|
|
"epoch": 0.6427497494153024,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004964792109234662,
|
|
"loss": 5.3099,
|
|
"mean_token_accuracy": 0.18377748429775237,
|
|
"num_tokens": 14163749.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.312364149093628,
|
|
"epoch": 0.6431673905780154,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004964739631258411,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.18665992915630342,
|
|
"num_tokens": 14174170.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.318781089782715,
|
|
"epoch": 0.6435850317407283,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004964687114510478,
|
|
"loss": 5.2222,
|
|
"mean_token_accuracy": 0.18446299880743028,
|
|
"num_tokens": 14182625.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.336656665802002,
|
|
"epoch": 0.6440026729034414,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000496463455899178,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.18309882432222366,
|
|
"num_tokens": 14192351.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.241625595092773,
|
|
"epoch": 0.6444203140661544,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004964581964703239,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.18879476487636565,
|
|
"num_tokens": 14201107.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.292919874191284,
|
|
"epoch": 0.6448379552288673,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004964529331645776,
|
|
"loss": 5.1796,
|
|
"mean_token_accuracy": 0.18920957595109938,
|
|
"num_tokens": 14209540.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.262211751937866,
|
|
"epoch": 0.6452555963915804,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000496447665982031,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.19543268382549286,
|
|
"num_tokens": 14217944.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.246408271789551,
|
|
"epoch": 0.6456732375542934,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004964423949227765,
|
|
"loss": 5.1479,
|
|
"mean_token_accuracy": 0.1906680718064308,
|
|
"num_tokens": 14226044.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.333262348175049,
|
|
"epoch": 0.6460908787170063,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004964371199869062,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.18008633106946945,
|
|
"num_tokens": 14235566.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.31890230178833,
|
|
"epoch": 0.6465085198797194,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004964318411745127,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.19815819561481476,
|
|
"num_tokens": 14244511.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.269383287429809,
|
|
"epoch": 0.6469261610424324,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004964265584856883,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.18629941046237947,
|
|
"num_tokens": 14254299.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.215416622161865,
|
|
"epoch": 0.6473438022051453,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004964212719205254,
|
|
"loss": 5.1673,
|
|
"mean_token_accuracy": 0.18904361575841905,
|
|
"num_tokens": 14262915.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.3631199359893795,
|
|
"epoch": 0.6477614433678583,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004964159814791167,
|
|
"loss": 5.216,
|
|
"mean_token_accuracy": 0.18888179510831832,
|
|
"num_tokens": 14272606.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.312502145767212,
|
|
"epoch": 0.6481790845305714,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004964106871615547,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.1826904833316803,
|
|
"num_tokens": 14282117.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.247224283218384,
|
|
"epoch": 0.6485967256932843,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000496405388967932,
|
|
"loss": 5.2127,
|
|
"mean_token_accuracy": 0.1859871491789818,
|
|
"num_tokens": 14290421.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.446470260620117,
|
|
"epoch": 0.6490143668559973,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004964000868983416,
|
|
"loss": 5.3077,
|
|
"mean_token_accuracy": 0.18256796002388,
|
|
"num_tokens": 14299870.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.401399040222168,
|
|
"epoch": 0.6494320080187104,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004963947809528761,
|
|
"loss": 5.2342,
|
|
"mean_token_accuracy": 0.18058783560991287,
|
|
"num_tokens": 14309916.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.269759178161621,
|
|
"epoch": 0.6498496491814233,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004963894711316285,
|
|
"loss": 5.2175,
|
|
"mean_token_accuracy": 0.18339438885450363,
|
|
"num_tokens": 14319061.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.302542686462402,
|
|
"epoch": 0.6502672903441363,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004963841574346917,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.19331397712230683,
|
|
"num_tokens": 14327241.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.358416891098022,
|
|
"epoch": 0.6506849315068494,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004963788398621587,
|
|
"loss": 5.2916,
|
|
"mean_token_accuracy": 0.1789262890815735,
|
|
"num_tokens": 14336586.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.379330062866211,
|
|
"epoch": 0.6511025726695623,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004963735184141227,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.18089451193809508,
|
|
"num_tokens": 14346484.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.385251522064209,
|
|
"epoch": 0.6515202138322753,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004963681930906768,
|
|
"loss": 5.3219,
|
|
"mean_token_accuracy": 0.17985379099845886,
|
|
"num_tokens": 14356255.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.317829895019531,
|
|
"epoch": 0.6519378549949884,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004963628638919141,
|
|
"loss": 5.2595,
|
|
"mean_token_accuracy": 0.18174924701452255,
|
|
"num_tokens": 14365680.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.372163724899292,
|
|
"epoch": 0.6523554961577013,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004963575308179281,
|
|
"loss": 5.2288,
|
|
"mean_token_accuracy": 0.19130903333425522,
|
|
"num_tokens": 14374546.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.370970344543457,
|
|
"epoch": 0.6527731373204143,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004963521938688122,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.1898658886551857,
|
|
"num_tokens": 14383624.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.36236720085144,
|
|
"epoch": 0.6531907784831273,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004963468530446596,
|
|
"loss": 5.3447,
|
|
"mean_token_accuracy": 0.17924101203680037,
|
|
"num_tokens": 14392482.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.374128103256226,
|
|
"epoch": 0.6536084196458403,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004963415083455639,
|
|
"loss": 5.2385,
|
|
"mean_token_accuracy": 0.18695005774497986,
|
|
"num_tokens": 14401940.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.341295433044434,
|
|
"epoch": 0.6540260608085533,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004963361597716186,
|
|
"loss": 5.2989,
|
|
"mean_token_accuracy": 0.18396753668785096,
|
|
"num_tokens": 14411127.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.336658525466919,
|
|
"epoch": 0.6544437019712663,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004963308073229175,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.18722108751535416,
|
|
"num_tokens": 14421358.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.313114643096924,
|
|
"epoch": 0.6548613431339793,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004963254509995542,
|
|
"loss": 5.2262,
|
|
"mean_token_accuracy": 0.18385069072246552,
|
|
"num_tokens": 14430507.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.273292779922485,
|
|
"epoch": 0.6552789842966923,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004963200908016224,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.19009640514850618,
|
|
"num_tokens": 14439723.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.352698135375976,
|
|
"epoch": 0.6556966254594053,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000496314726729216,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.18810579031705857,
|
|
"num_tokens": 14449011.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.3103841781616214,
|
|
"epoch": 0.6561142666221182,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004963093587824289,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.19130851477384567,
|
|
"num_tokens": 14457676.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.342246437072754,
|
|
"epoch": 0.6565319077848313,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004963039869613551,
|
|
"loss": 5.2601,
|
|
"mean_token_accuracy": 0.18594553023576738,
|
|
"num_tokens": 14466956.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.313938426971435,
|
|
"epoch": 0.6569495489475443,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004962986112660887,
|
|
"loss": 5.1454,
|
|
"mean_token_accuracy": 0.19567489624023438,
|
|
"num_tokens": 14476083.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.365322732925415,
|
|
"epoch": 0.6573671901102572,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004962932316967237,
|
|
"loss": 5.2503,
|
|
"mean_token_accuracy": 0.18117107152938844,
|
|
"num_tokens": 14484980.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.355501651763916,
|
|
"epoch": 0.6577848312729703,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004962878482533544,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.1856757715344429,
|
|
"num_tokens": 14493965.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.350685262680054,
|
|
"epoch": 0.6582024724356833,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004962824609360748,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.1830467164516449,
|
|
"num_tokens": 14501914.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.239622974395752,
|
|
"epoch": 0.6586201135983962,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004962770697449794,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.18943492770195008,
|
|
"num_tokens": 14511447.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.301117324829102,
|
|
"epoch": 0.6590377547611093,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004962716746801625,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.18255795240402223,
|
|
"num_tokens": 14520558.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.291094636917114,
|
|
"epoch": 0.6594553959238223,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004962662757417187,
|
|
"loss": 5.1638,
|
|
"mean_token_accuracy": 0.18984782993793486,
|
|
"num_tokens": 14529995.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.3401213645935055,
|
|
"epoch": 0.6598730370865352,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004962608729297424,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.18172093480825424,
|
|
"num_tokens": 14538972.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.360935163497925,
|
|
"epoch": 0.6602906782492483,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004962554662443281,
|
|
"loss": 5.237,
|
|
"mean_token_accuracy": 0.1828315943479538,
|
|
"num_tokens": 14548255.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.304817485809326,
|
|
"epoch": 0.6607083194119613,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004962500556855706,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.1892821729183197,
|
|
"num_tokens": 14557265.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.350543355941772,
|
|
"epoch": 0.6611259605746742,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004962446412535645,
|
|
"loss": 5.2664,
|
|
"mean_token_accuracy": 0.1839459255337715,
|
|
"num_tokens": 14566650.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.32527379989624,
|
|
"epoch": 0.6615436017373872,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004962392229484046,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.19818112701177598,
|
|
"num_tokens": 14575550.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.297174882888794,
|
|
"epoch": 0.6619612429001003,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000496233800770186,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.18891645818948746,
|
|
"num_tokens": 14584459.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.371868562698364,
|
|
"epoch": 0.6623788840628132,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004962283747190033,
|
|
"loss": 5.2908,
|
|
"mean_token_accuracy": 0.1820622742176056,
|
|
"num_tokens": 14593709.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.253445720672607,
|
|
"epoch": 0.6627965252255262,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004962229447949515,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.19019092470407487,
|
|
"num_tokens": 14602071.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.417607975006104,
|
|
"epoch": 0.6632141663882393,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004962175109981259,
|
|
"loss": 5.3542,
|
|
"mean_token_accuracy": 0.17659229636192322,
|
|
"num_tokens": 14612842.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.464873266220093,
|
|
"epoch": 0.6636318075509522,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004962120733286215,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.18645621240139007,
|
|
"num_tokens": 14621645.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.294732666015625,
|
|
"epoch": 0.6640494487136652,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004962066317865334,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.18930456191301345,
|
|
"num_tokens": 14630447.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.258000373840332,
|
|
"epoch": 0.6644670898763783,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000496201186371957,
|
|
"loss": 5.2554,
|
|
"mean_token_accuracy": 0.19066265672445298,
|
|
"num_tokens": 14639371.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.372070026397705,
|
|
"epoch": 0.6648847310390912,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004961957370849875,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.18601731061935425,
|
|
"num_tokens": 14648540.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.339339542388916,
|
|
"epoch": 0.6653023722018042,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004961902839257205,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.18767533153295518,
|
|
"num_tokens": 14658130.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.403484106063843,
|
|
"epoch": 0.6657200133645172,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004961848268942513,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.1809846743941307,
|
|
"num_tokens": 14667538.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.361376237869263,
|
|
"epoch": 0.6661376545272302,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004961793659906754,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.18380988091230394,
|
|
"num_tokens": 14677115.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.355688428878784,
|
|
"epoch": 0.6665552956899432,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004961739012150885,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.19125464260578157,
|
|
"num_tokens": 14686444.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.298751592636108,
|
|
"epoch": 0.6669729368526562,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004961684325675862,
|
|
"loss": 5.1785,
|
|
"mean_token_accuracy": 0.19077081084251404,
|
|
"num_tokens": 14695951.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.2982659339904785,
|
|
"epoch": 0.6673905780153692,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004961629600482643,
|
|
"loss": 5.3024,
|
|
"mean_token_accuracy": 0.18561783134937287,
|
|
"num_tokens": 14705415.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.424433374404908,
|
|
"epoch": 0.6678082191780822,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004961574836572186,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.18185556530952454,
|
|
"num_tokens": 14714793.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.209049034118652,
|
|
"epoch": 0.6682258603407952,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004961520033945448,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.19594983905553817,
|
|
"num_tokens": 14723820.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.244827556610107,
|
|
"epoch": 0.6686435015035082,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004961465192603391,
|
|
"loss": 5.1655,
|
|
"mean_token_accuracy": 0.19469864219427108,
|
|
"num_tokens": 14733055.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.334292984008789,
|
|
"epoch": 0.6690611426662212,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004961410312546974,
|
|
"loss": 5.1865,
|
|
"mean_token_accuracy": 0.18282557129859925,
|
|
"num_tokens": 14742416.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.26261534690857,
|
|
"epoch": 0.6694787838289342,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004961355393777158,
|
|
"loss": 5.2,
|
|
"mean_token_accuracy": 0.1863041937351227,
|
|
"num_tokens": 14751384.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.2433274269104,
|
|
"epoch": 0.6698964249916471,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004961300436294902,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.18841362446546556,
|
|
"num_tokens": 14760525.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.303926610946656,
|
|
"epoch": 0.6703140661543602,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004961245440101171,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.18064588010311128,
|
|
"num_tokens": 14769405.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.225086688995361,
|
|
"epoch": 0.6707317073170732,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004961190405196928,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.19077132344245912,
|
|
"num_tokens": 14778945.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.383445405960083,
|
|
"epoch": 0.6711493484797861,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004961135331583135,
|
|
"loss": 5.285,
|
|
"mean_token_accuracy": 0.17766177356243135,
|
|
"num_tokens": 14788289.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.292051124572754,
|
|
"epoch": 0.6715669896424992,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004961080219260755,
|
|
"loss": 5.2113,
|
|
"mean_token_accuracy": 0.1816340357065201,
|
|
"num_tokens": 14797761.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.374523687362671,
|
|
"epoch": 0.6719846308052122,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004961025068230757,
|
|
"loss": 5.2663,
|
|
"mean_token_accuracy": 0.18736185282468795,
|
|
"num_tokens": 14806424.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.294801330566406,
|
|
"epoch": 0.6724022719679251,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004960969878494103,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.18426212519407273,
|
|
"num_tokens": 14815816.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.279285097122193,
|
|
"epoch": 0.6728199131306382,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004960914650051758,
|
|
"loss": 5.1966,
|
|
"mean_token_accuracy": 0.18834995329380036,
|
|
"num_tokens": 14824877.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.23910698890686,
|
|
"epoch": 0.6732375542933512,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004960859382904691,
|
|
"loss": 5.0973,
|
|
"mean_token_accuracy": 0.20258977860212327,
|
|
"num_tokens": 14833095.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.363849925994873,
|
|
"epoch": 0.6736551954560641,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000496080407705387,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.18313853591680526,
|
|
"num_tokens": 14842963.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.38482666015625,
|
|
"epoch": 0.6740728366187771,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004960748732500263,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.1805562898516655,
|
|
"num_tokens": 14851552.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.3721260070800785,
|
|
"epoch": 0.6744904777814902,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004960693349244838,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.19036448746919632,
|
|
"num_tokens": 14859997.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.288872146606446,
|
|
"epoch": 0.6749081189442031,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004960637927288566,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.18826107084751129,
|
|
"num_tokens": 14868050.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.298485517501831,
|
|
"epoch": 0.6753257601069161,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004960582466632414,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.1802084356546402,
|
|
"num_tokens": 14877774.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.231218576431274,
|
|
"epoch": 0.6757434012696292,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004960526967277356,
|
|
"loss": 5.1774,
|
|
"mean_token_accuracy": 0.19676312804222107,
|
|
"num_tokens": 14886971.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.2804406642913815,
|
|
"epoch": 0.6761610424323421,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004960471429224363,
|
|
"loss": 5.1199,
|
|
"mean_token_accuracy": 0.19002149999141693,
|
|
"num_tokens": 14895815.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.316021299362182,
|
|
"epoch": 0.6765786835950551,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004960415852474406,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.19465539008378982,
|
|
"num_tokens": 14904082.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.258999252319336,
|
|
"epoch": 0.6769963247577682,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000496036023702846,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.19023237526416778,
|
|
"num_tokens": 14913533.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.273725986480713,
|
|
"epoch": 0.6774139659204811,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004960304582887497,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.19112505614757538,
|
|
"num_tokens": 14922063.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.309419727325439,
|
|
"epoch": 0.6778316070831941,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004960248890052493,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.1919051840901375,
|
|
"num_tokens": 14930219.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.348616456985473,
|
|
"epoch": 0.6782492482459072,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000496019315852442,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.19079013168811798,
|
|
"num_tokens": 14939463.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.394223928451538,
|
|
"epoch": 0.6786668894086201,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004960137388304255,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.18611440658569336,
|
|
"num_tokens": 14948289.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.355359029769898,
|
|
"epoch": 0.6790845305713331,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004960081579392975,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.18862151056528093,
|
|
"num_tokens": 14958172.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.220905733108521,
|
|
"epoch": 0.6795021717340461,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004960025731791558,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.19197088927030564,
|
|
"num_tokens": 14967362.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.26541748046875,
|
|
"epoch": 0.6799198128967591,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004959969845500979,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.18232544213533403,
|
|
"num_tokens": 14975942.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.335718727111816,
|
|
"epoch": 0.6803374540594721,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004959913920522218,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.1935685396194458,
|
|
"num_tokens": 14985428.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.30684871673584,
|
|
"epoch": 0.6807550952221851,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004959857956856254,
|
|
"loss": 5.138,
|
|
"mean_token_accuracy": 0.18895146995782852,
|
|
"num_tokens": 14994558.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.306473255157471,
|
|
"epoch": 0.6811727363848981,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004959801954504067,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.1863776907324791,
|
|
"num_tokens": 15003674.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.312219905853271,
|
|
"epoch": 0.6815903775476111,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004959745913466635,
|
|
"loss": 5.2275,
|
|
"mean_token_accuracy": 0.1866793751716614,
|
|
"num_tokens": 15012569.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.343707275390625,
|
|
"epoch": 0.6820080187103241,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004959689833744942,
|
|
"loss": 5.2425,
|
|
"mean_token_accuracy": 0.18308268189430238,
|
|
"num_tokens": 15021863.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.386544704437256,
|
|
"epoch": 0.682425659873037,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004959633715339969,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.17785509824752807,
|
|
"num_tokens": 15032272.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.320672607421875,
|
|
"epoch": 0.6828433010357501,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004959577558252698,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.17869272232055664,
|
|
"num_tokens": 15041066.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.427869081497192,
|
|
"epoch": 0.6832609421984631,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004959521362484112,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.17796089202165605,
|
|
"num_tokens": 15050855.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.307919597625732,
|
|
"epoch": 0.683678583361176,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004959465128035195,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.19280252903699874,
|
|
"num_tokens": 15060810.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.296663665771485,
|
|
"epoch": 0.6840962245238891,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004959408854906932,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.18804777413606644,
|
|
"num_tokens": 15069761.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.285875606536865,
|
|
"epoch": 0.6845138656866021,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004959352543100306,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.18793474435806273,
|
|
"num_tokens": 15078691.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.234794330596924,
|
|
"epoch": 0.684931506849315,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004959296192616305,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.18997769951820373,
|
|
"num_tokens": 15087068.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.243432331085205,
|
|
"epoch": 0.6853491480120281,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004959239803455916,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.1905503824353218,
|
|
"num_tokens": 15095962.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.2430377960205075,
|
|
"epoch": 0.6857667891747411,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004959183375620123,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.18324321359395981,
|
|
"num_tokens": 15105835.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.3210914611816404,
|
|
"epoch": 0.686184430337454,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004959126909109918,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.2020833745598793,
|
|
"num_tokens": 15114140.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.332093524932861,
|
|
"epoch": 0.686602071500167,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004959070403926286,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.18745189607143403,
|
|
"num_tokens": 15123253.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.424120044708252,
|
|
"epoch": 0.6870197126628801,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004959013860070217,
|
|
"loss": 5.3353,
|
|
"mean_token_accuracy": 0.18029178977012633,
|
|
"num_tokens": 15133699.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.366640901565551,
|
|
"epoch": 0.687437353825593,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004958957277542701,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.19338543862104415,
|
|
"num_tokens": 15142133.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.278004550933838,
|
|
"epoch": 0.687854994988306,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004958900656344731,
|
|
"loss": 5.1895,
|
|
"mean_token_accuracy": 0.18659888803958893,
|
|
"num_tokens": 15151367.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.278072834014893,
|
|
"epoch": 0.6882726361510191,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004958843996477296,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.1813654512166977,
|
|
"num_tokens": 15160938.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.383914279937744,
|
|
"epoch": 0.688690277313732,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004958787297941386,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.18058507591485978,
|
|
"num_tokens": 15170507.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.366903924942017,
|
|
"epoch": 0.689107918476445,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004958730560737998,
|
|
"loss": 5.2585,
|
|
"mean_token_accuracy": 0.18802482038736343,
|
|
"num_tokens": 15179822.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.277652025222778,
|
|
"epoch": 0.6895255596391581,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004958673784868121,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.18544214367866516,
|
|
"num_tokens": 15189353.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.358259677886963,
|
|
"epoch": 0.689943200801871,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004958616970332752,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.17864731103181838,
|
|
"num_tokens": 15197772.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.255817794799805,
|
|
"epoch": 0.690360841964584,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004958560117132884,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.19048339873552322,
|
|
"num_tokens": 15207453.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.281562089920044,
|
|
"epoch": 0.6907784831272971,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004958503225269513,
|
|
"loss": 5.1082,
|
|
"mean_token_accuracy": 0.19191768616437913,
|
|
"num_tokens": 15215787.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.367995691299439,
|
|
"epoch": 0.69119612429001,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004958446294743633,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.19048880338668822,
|
|
"num_tokens": 15225148.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.309956502914429,
|
|
"epoch": 0.691613765452723,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004958389325556245,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.18627925366163253,
|
|
"num_tokens": 15234533.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.332719612121582,
|
|
"epoch": 0.692031406615436,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004958332317708341,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.1786329224705696,
|
|
"num_tokens": 15243805.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.406910753250122,
|
|
"epoch": 0.692449047778149,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004958275271200924,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.1810326337814331,
|
|
"num_tokens": 15253298.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.297081518173218,
|
|
"epoch": 0.692866688940862,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004958218186034988,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.18782705962657928,
|
|
"num_tokens": 15261860.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.288454246520996,
|
|
"epoch": 0.693284330103575,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004958161062211537,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.18947628289461135,
|
|
"num_tokens": 15271021.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.286473751068115,
|
|
"epoch": 0.693701971266288,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004958103899731566,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.18143957555294038,
|
|
"num_tokens": 15280489.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.342685127258301,
|
|
"epoch": 0.694119612429001,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004958046698596081,
|
|
"loss": 5.2105,
|
|
"mean_token_accuracy": 0.19078896790742875,
|
|
"num_tokens": 15289387.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.334821605682373,
|
|
"epoch": 0.694537253591714,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004957989458806079,
|
|
"loss": 5.27,
|
|
"mean_token_accuracy": 0.18353917002677916,
|
|
"num_tokens": 15299334.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.3309906959533695,
|
|
"epoch": 0.694954894754427,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004957932180362564,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.18631087243556976,
|
|
"num_tokens": 15309174.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.404925775527954,
|
|
"epoch": 0.69537253591714,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004957874863266538,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.181829771399498,
|
|
"num_tokens": 15318722.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.432412815093994,
|
|
"epoch": 0.695790177079853,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004957817507519006,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.18473161309957503,
|
|
"num_tokens": 15327606.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.250016069412231,
|
|
"epoch": 0.696207818242566,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004957760113120971,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.19313850551843642,
|
|
"num_tokens": 15336520.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.380140256881714,
|
|
"epoch": 0.696625459405279,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004957702680073437,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.18560430109500886,
|
|
"num_tokens": 15345437.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.393169927597046,
|
|
"epoch": 0.697043100567992,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004957645208377411,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.1888318419456482,
|
|
"num_tokens": 15354660.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.296236753463745,
|
|
"epoch": 0.6974607417307049,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004957587698033898,
|
|
"loss": 5.2369,
|
|
"mean_token_accuracy": 0.19031170308589934,
|
|
"num_tokens": 15363958.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.281468343734741,
|
|
"epoch": 0.697878382893418,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004957530149043905,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.19381961673498155,
|
|
"num_tokens": 15373351.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.363962316513062,
|
|
"epoch": 0.698296024056131,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004957472561408438,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.1902700036764145,
|
|
"num_tokens": 15383069.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.311092233657837,
|
|
"epoch": 0.6987136652188439,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004957414935128509,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.18567148745059966,
|
|
"num_tokens": 15391394.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.295946455001831,
|
|
"epoch": 0.699131306381557,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004957357270205123,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.18772562444210053,
|
|
"num_tokens": 15399993.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.244115734100342,
|
|
"epoch": 0.69954894754427,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004957299566639292,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.18961432129144667,
|
|
"num_tokens": 15409886.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.371616411209106,
|
|
"epoch": 0.6999665887069829,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004957241824432025,
|
|
"loss": 5.1691,
|
|
"mean_token_accuracy": 0.19355978816747665,
|
|
"num_tokens": 15419772.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.338627195358276,
|
|
"epoch": 0.700384229869696,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004957184043584333,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.18718047738075255,
|
|
"num_tokens": 15429631.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.225720691680908,
|
|
"epoch": 0.700801871032409,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004957126224097227,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.19838509559631348,
|
|
"num_tokens": 15438411.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.154391050338745,
|
|
"epoch": 0.7012195121951219,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000495706836597172,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.1888429969549179,
|
|
"num_tokens": 15448943.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.331808376312256,
|
|
"epoch": 0.7016371533578349,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004957010469208825,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.19145280718803406,
|
|
"num_tokens": 15457908.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.398460102081299,
|
|
"epoch": 0.702054794520548,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004956952533809554,
|
|
"loss": 5.2188,
|
|
"mean_token_accuracy": 0.18720683008432387,
|
|
"num_tokens": 15467390.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.275925016403198,
|
|
"epoch": 0.7024724356832609,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004956894559774923,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.18277271687984467,
|
|
"num_tokens": 15476419.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.192082023620605,
|
|
"epoch": 0.7028900768459739,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004956836547105947,
|
|
"loss": 5.0608,
|
|
"mean_token_accuracy": 0.1960819587111473,
|
|
"num_tokens": 15485147.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.358620834350586,
|
|
"epoch": 0.703307718008687,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004956778495803641,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.19049345403909684,
|
|
"num_tokens": 15493816.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.339207649230957,
|
|
"epoch": 0.7037253591713999,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000495672040586902,
|
|
"loss": 5.2998,
|
|
"mean_token_accuracy": 0.18781712353229524,
|
|
"num_tokens": 15503051.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.276934671401977,
|
|
"epoch": 0.7041430003341129,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004956662277303103,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.19193120747804643,
|
|
"num_tokens": 15511854.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.303779411315918,
|
|
"epoch": 0.704560641496826,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004956604110106905,
|
|
"loss": 5.2238,
|
|
"mean_token_accuracy": 0.1936649650335312,
|
|
"num_tokens": 15521492.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.428117752075195,
|
|
"epoch": 0.7049782826595389,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004956545904281447,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.17229399383068084,
|
|
"num_tokens": 15530983.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.332515287399292,
|
|
"epoch": 0.7053959238222519,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004956487659827748,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.19503338932991027,
|
|
"num_tokens": 15539722.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.223224401473999,
|
|
"epoch": 0.705813564984965,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004956429376746825,
|
|
"loss": 5.1259,
|
|
"mean_token_accuracy": 0.1945224493741989,
|
|
"num_tokens": 15548738.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.180972003936768,
|
|
"epoch": 0.7062312061476779,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004956371055039701,
|
|
"loss": 5.1517,
|
|
"mean_token_accuracy": 0.1971757486462593,
|
|
"num_tokens": 15557520.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.419539213180542,
|
|
"epoch": 0.7066488473103909,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004956312694707395,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.1760064870119095,
|
|
"num_tokens": 15567860.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.392957305908203,
|
|
"epoch": 0.7070664884731039,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000495625429575093,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.18215364515781401,
|
|
"num_tokens": 15577174.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.215926551818848,
|
|
"epoch": 0.7074841296358169,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004956195858171327,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.19613219201564788,
|
|
"num_tokens": 15585476.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.205816268920898,
|
|
"epoch": 0.7079017707985299,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004956137381969611,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.19150867611169814,
|
|
"num_tokens": 15595422.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.343913602828979,
|
|
"epoch": 0.7083194119612429,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004956078867146805,
|
|
"loss": 5.2868,
|
|
"mean_token_accuracy": 0.18171995729207993,
|
|
"num_tokens": 15604223.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.414848661422729,
|
|
"epoch": 0.7087370531239559,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004956020313703933,
|
|
"loss": 5.264,
|
|
"mean_token_accuracy": 0.18618287444114684,
|
|
"num_tokens": 15613715.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.268935060501098,
|
|
"epoch": 0.7091546942866689,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004955961721642018,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.20129425972700118,
|
|
"num_tokens": 15623826.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.25658106803894,
|
|
"epoch": 0.7095723354493819,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000495590309096209,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.1842020645737648,
|
|
"num_tokens": 15633311.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.3058939456939695,
|
|
"epoch": 0.7099899766120948,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004955844421665171,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.19040406942367555,
|
|
"num_tokens": 15642785.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.462882614135742,
|
|
"epoch": 0.7104076177748079,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004955785713752292,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.18012833893299102,
|
|
"num_tokens": 15653009.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.327106094360351,
|
|
"epoch": 0.7108252589375209,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004955726967224479,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.19191291481256484,
|
|
"num_tokens": 15661672.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.248064231872559,
|
|
"epoch": 0.7112429001002338,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000495566818208276,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.1860044613480568,
|
|
"num_tokens": 15672186.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.253706312179565,
|
|
"epoch": 0.7116605412629469,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004955609358328163,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.19245645850896836,
|
|
"num_tokens": 15680351.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.318135833740234,
|
|
"epoch": 0.7120781824256599,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004955550495961722,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.1842174783349037,
|
|
"num_tokens": 15690140.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.296385097503662,
|
|
"epoch": 0.7124958235883728,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004955491594984462,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.18273524791002274,
|
|
"num_tokens": 15699968.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.293054294586182,
|
|
"epoch": 0.7129134647510859,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004955432655397419,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.1904730960726738,
|
|
"num_tokens": 15709061.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.354221391677856,
|
|
"epoch": 0.7133311059137989,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004955373677201621,
|
|
"loss": 5.2486,
|
|
"mean_token_accuracy": 0.18385081142187118,
|
|
"num_tokens": 15718350.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.291756105422974,
|
|
"epoch": 0.7137487470765118,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004955314660398105,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.1910427913069725,
|
|
"num_tokens": 15727120.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.2999427795410154,
|
|
"epoch": 0.7141663882392248,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004955255604987899,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.18272571116685868,
|
|
"num_tokens": 15735865.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.2988136291503904,
|
|
"epoch": 0.7145840294019379,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000495519651097204,
|
|
"loss": 5.2018,
|
|
"mean_token_accuracy": 0.18357786238193513,
|
|
"num_tokens": 15745239.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.281273698806762,
|
|
"epoch": 0.7150016705646508,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004955137378351561,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.19101595878601074,
|
|
"num_tokens": 15754418.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.2618578433990475,
|
|
"epoch": 0.7154193117273638,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004955078207127498,
|
|
"loss": 5.1739,
|
|
"mean_token_accuracy": 0.194094018638134,
|
|
"num_tokens": 15764175.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.332169723510742,
|
|
"epoch": 0.7158369528900769,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004955018997300886,
|
|
"loss": 5.1738,
|
|
"mean_token_accuracy": 0.18773175030946732,
|
|
"num_tokens": 15772766.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.241567802429199,
|
|
"epoch": 0.7162545940527898,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004954959748872764,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.19543151706457138,
|
|
"num_tokens": 15781768.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.342124986648559,
|
|
"epoch": 0.7166722352155028,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004954900461844167,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.18850684762001038,
|
|
"num_tokens": 15791706.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.349425840377807,
|
|
"epoch": 0.7170898763782159,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004954841136216132,
|
|
"loss": 5.2588,
|
|
"mean_token_accuracy": 0.18596038669347764,
|
|
"num_tokens": 15802015.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.327006816864014,
|
|
"epoch": 0.7175075175409288,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004954781771989701,
|
|
"loss": 5.2005,
|
|
"mean_token_accuracy": 0.18541175425052642,
|
|
"num_tokens": 15811116.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.367788982391358,
|
|
"epoch": 0.7179251587036418,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000495472236916591,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.18778144270181657,
|
|
"num_tokens": 15819240.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.216233777999878,
|
|
"epoch": 0.7183427998663549,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004954662927745799,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.18650583773851395,
|
|
"num_tokens": 15827740.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.233916473388672,
|
|
"epoch": 0.7187604410290678,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004954603447730411,
|
|
"loss": 5.2334,
|
|
"mean_token_accuracy": 0.18810488432645797,
|
|
"num_tokens": 15836763.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.415298748016357,
|
|
"epoch": 0.7191780821917808,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004954543929120786,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.18467582166194915,
|
|
"num_tokens": 15846624.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.328110313415527,
|
|
"epoch": 0.7195957233544938,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004954484371917967,
|
|
"loss": 5.208,
|
|
"mean_token_accuracy": 0.18547792434692384,
|
|
"num_tokens": 15855713.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.257599639892578,
|
|
"epoch": 0.7200133645172068,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004954424776122993,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.197099906206131,
|
|
"num_tokens": 15863577.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.3231040954589846,
|
|
"epoch": 0.7204310056799198,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004954365141736913,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.19211025387048722,
|
|
"num_tokens": 15872479.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.356935358047485,
|
|
"epoch": 0.7208486468426328,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004954305468760765,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.18382661193609237,
|
|
"num_tokens": 15882170.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.27643313407898,
|
|
"epoch": 0.7212662880053458,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004954245757195598,
|
|
"loss": 5.1797,
|
|
"mean_token_accuracy": 0.1908285766839981,
|
|
"num_tokens": 15891694.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.323697233200074,
|
|
"epoch": 0.7216839291680588,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004954186007042454,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.17307595759630204,
|
|
"num_tokens": 15902232.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.364664793014526,
|
|
"epoch": 0.7221015703307718,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004954126218302382,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.1835283249616623,
|
|
"num_tokens": 15912218.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.274173355102539,
|
|
"epoch": 0.7225192114934847,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004954066390976427,
|
|
"loss": 5.1159,
|
|
"mean_token_accuracy": 0.19668061137199402,
|
|
"num_tokens": 15922011.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.144522762298584,
|
|
"epoch": 0.7229368526561978,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004954006525065639,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.1925290733575821,
|
|
"num_tokens": 15930394.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.275206995010376,
|
|
"epoch": 0.7233544938189108,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004953946620571061,
|
|
"loss": 5.2164,
|
|
"mean_token_accuracy": 0.1811532571911812,
|
|
"num_tokens": 15939880.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.266812944412232,
|
|
"epoch": 0.7237721349816237,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004953886677493746,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.19883121699094772,
|
|
"num_tokens": 15948521.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.312144136428833,
|
|
"epoch": 0.7241897761443368,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004953826695834741,
|
|
"loss": 5.2031,
|
|
"mean_token_accuracy": 0.18478854596614838,
|
|
"num_tokens": 15956811.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.2990309715271,
|
|
"epoch": 0.7246074173070498,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004953766675595098,
|
|
"loss": 5.2462,
|
|
"mean_token_accuracy": 0.19069269746541978,
|
|
"num_tokens": 15967019.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.421168422698974,
|
|
"epoch": 0.7250250584697627,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004953706616775866,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.18662516474723817,
|
|
"num_tokens": 15976149.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.3284658908844,
|
|
"epoch": 0.7254426996324758,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004953646519378097,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.1943461775779724,
|
|
"num_tokens": 15986711.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.249668121337891,
|
|
"epoch": 0.7258603407951888,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004953586383402844,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.18818472623825072,
|
|
"num_tokens": 15996482.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.195931673049927,
|
|
"epoch": 0.7262779819579017,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004953526208851157,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.18975579589605332,
|
|
"num_tokens": 16005801.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.218811559677124,
|
|
"epoch": 0.7266956231206148,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004953465995724092,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.18776528388261796,
|
|
"num_tokens": 16014807.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.366499328613282,
|
|
"epoch": 0.7271132642833278,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004953405744022705,
|
|
"loss": 5.2722,
|
|
"mean_token_accuracy": 0.18139951825141906,
|
|
"num_tokens": 16023326.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.420980024337768,
|
|
"epoch": 0.7275309054460407,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004953345453748045,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.18403305411338805,
|
|
"num_tokens": 16031648.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.277630138397217,
|
|
"epoch": 0.7279485466087537,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004953285124901171,
|
|
"loss": 5.1451,
|
|
"mean_token_accuracy": 0.19288977831602097,
|
|
"num_tokens": 16040179.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.287181758880616,
|
|
"epoch": 0.7283661877714668,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000495322475748314,
|
|
"loss": 5.3103,
|
|
"mean_token_accuracy": 0.1791713386774063,
|
|
"num_tokens": 16050770.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.381537771224975,
|
|
"epoch": 0.7287838289341797,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004953164351495007,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.1909000188112259,
|
|
"num_tokens": 16060504.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.243673849105835,
|
|
"epoch": 0.7292014700968927,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004953103906937831,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.20394542068243027,
|
|
"num_tokens": 16069240.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.183630323410034,
|
|
"epoch": 0.7296191112596058,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004953043423812669,
|
|
"loss": 5.2643,
|
|
"mean_token_accuracy": 0.18672844469547273,
|
|
"num_tokens": 16079098.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.208294630050659,
|
|
"epoch": 0.7300367524223187,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004952982902120579,
|
|
"loss": 5.0756,
|
|
"mean_token_accuracy": 0.19283230602741241,
|
|
"num_tokens": 16088454.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.339796686172486,
|
|
"epoch": 0.7304543935850317,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004952922341862622,
|
|
"loss": 5.227,
|
|
"mean_token_accuracy": 0.18357341587543488,
|
|
"num_tokens": 16096985.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.436058807373047,
|
|
"epoch": 0.7308720347477448,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004952861743039858,
|
|
"loss": 5.3296,
|
|
"mean_token_accuracy": 0.18211542069911957,
|
|
"num_tokens": 16105434.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.225539636611939,
|
|
"epoch": 0.7312896759104577,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004952801105653347,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.2016468346118927,
|
|
"num_tokens": 16114933.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.321869230270385,
|
|
"epoch": 0.7317073170731707,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004952740429704152,
|
|
"loss": 5.2304,
|
|
"mean_token_accuracy": 0.18201682567596436,
|
|
"num_tokens": 16124954.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.265962553024292,
|
|
"epoch": 0.7321249582358837,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004952679715193334,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.19678904116153717,
|
|
"num_tokens": 16134442.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.26953535079956,
|
|
"epoch": 0.7325425993985967,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004952618962121956,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.1834096133708954,
|
|
"num_tokens": 16143994.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.279685401916504,
|
|
"epoch": 0.7329602405613097,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004952558170491082,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.18969169557094573,
|
|
"num_tokens": 16152931.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.301347398757935,
|
|
"epoch": 0.7333778817240227,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004952497340301776,
|
|
"loss": 5.1601,
|
|
"mean_token_accuracy": 0.1868045687675476,
|
|
"num_tokens": 16162716.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.362487745285034,
|
|
"epoch": 0.7337955228867357,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004952436471555103,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.18239102512598038,
|
|
"num_tokens": 16172371.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.304409694671631,
|
|
"epoch": 0.7342131640494487,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004952375564252128,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.1842018783092499,
|
|
"num_tokens": 16181823.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.339714431762696,
|
|
"epoch": 0.7346308052121617,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004952314618393919,
|
|
"loss": 5.1829,
|
|
"mean_token_accuracy": 0.1916033521294594,
|
|
"num_tokens": 16190720.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.296022081375122,
|
|
"epoch": 0.7350484463748747,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000495225363398154,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.1905677482485771,
|
|
"num_tokens": 16199589.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.387620830535889,
|
|
"epoch": 0.7354660875375877,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004952192611016061,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.18462697565555572,
|
|
"num_tokens": 16208800.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.334796905517578,
|
|
"epoch": 0.7358837287003007,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000495213154949855,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.18237655311822892,
|
|
"num_tokens": 16218835.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.3320722579956055,
|
|
"epoch": 0.7363013698630136,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004952070449430075,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.18262556791305543,
|
|
"num_tokens": 16228441.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.375856208801269,
|
|
"epoch": 0.7367190110257267,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004952009310811706,
|
|
"loss": 5.2163,
|
|
"mean_token_accuracy": 0.19435302913188934,
|
|
"num_tokens": 16237877.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.288750648498535,
|
|
"epoch": 0.7371366521884397,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004951948133644514,
|
|
"loss": 5.1154,
|
|
"mean_token_accuracy": 0.18971776962280273,
|
|
"num_tokens": 16246809.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.299361896514893,
|
|
"epoch": 0.7375542933511526,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000495188691792957,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.19305830895900727,
|
|
"num_tokens": 16255754.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.350617551803589,
|
|
"epoch": 0.7379719345138657,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004951825663667943,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.1851801112294197,
|
|
"num_tokens": 16264861.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.352020931243897,
|
|
"epoch": 0.7383895756765787,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000495176437086071,
|
|
"loss": 5.1803,
|
|
"mean_token_accuracy": 0.18862801939249038,
|
|
"num_tokens": 16273628.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.310912990570069,
|
|
"epoch": 0.7388072168392917,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000495170303950894,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.18131401985883713,
|
|
"num_tokens": 16282958.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.35797529220581,
|
|
"epoch": 0.7392248580020047,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004951641669613708,
|
|
"loss": 5.2065,
|
|
"mean_token_accuracy": 0.18231176137924193,
|
|
"num_tokens": 16292763.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.324119424819946,
|
|
"epoch": 0.7396424991647177,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004951580261176088,
|
|
"loss": 5.214,
|
|
"mean_token_accuracy": 0.18999577313661575,
|
|
"num_tokens": 16302216.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.216421508789063,
|
|
"epoch": 0.7400601403274307,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004951518814197156,
|
|
"loss": 5.1016,
|
|
"mean_token_accuracy": 0.1944451928138733,
|
|
"num_tokens": 16311672.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.310057544708252,
|
|
"epoch": 0.7404777814901436,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004951457328677989,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.1860945329070091,
|
|
"num_tokens": 16321027.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.338929748535156,
|
|
"epoch": 0.7408954226528567,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004951395804619659,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.1821383833885193,
|
|
"num_tokens": 16329471.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.270784616470337,
|
|
"epoch": 0.7413130638155697,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004951334242023247,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.18740254193544387,
|
|
"num_tokens": 16339085.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.4150670051574705,
|
|
"epoch": 0.7417307049782826,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004951272640889828,
|
|
"loss": 5.253,
|
|
"mean_token_accuracy": 0.1961119741201401,
|
|
"num_tokens": 16347950.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.275183629989624,
|
|
"epoch": 0.7421483461409957,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004951211001220484,
|
|
"loss": 5.0294,
|
|
"mean_token_accuracy": 0.1989552140235901,
|
|
"num_tokens": 16357129.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.217408847808838,
|
|
"epoch": 0.7425659873037087,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000495114932301629,
|
|
"loss": 5.1615,
|
|
"mean_token_accuracy": 0.19315571635961531,
|
|
"num_tokens": 16365768.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.28054986000061,
|
|
"epoch": 0.7429836284664216,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004951087606278328,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.19437289983034134,
|
|
"num_tokens": 16375548.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.317500877380371,
|
|
"epoch": 0.7434012696291347,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004951025851007678,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.1875303015112877,
|
|
"num_tokens": 16385472.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.309254741668701,
|
|
"epoch": 0.7438189107918477,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004950964057205421,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.19162075817584992,
|
|
"num_tokens": 16395048.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.354975080490112,
|
|
"epoch": 0.7442365519545606,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000495090222487264,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.18024988025426864,
|
|
"num_tokens": 16405378.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.251638317108155,
|
|
"epoch": 0.7446541931172737,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004950840354010415,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.19488231092691422,
|
|
"num_tokens": 16415206.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.326546335220337,
|
|
"epoch": 0.7450718342799867,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004950778444619831,
|
|
"loss": 5.1774,
|
|
"mean_token_accuracy": 0.19878570586442948,
|
|
"num_tokens": 16424185.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.2738865375518795,
|
|
"epoch": 0.7454894754426996,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000495071649670197,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.19145272970199584,
|
|
"num_tokens": 16433330.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.262444305419922,
|
|
"epoch": 0.7459071166054126,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000495065451025792,
|
|
"loss": 5.1727,
|
|
"mean_token_accuracy": 0.18978547155857087,
|
|
"num_tokens": 16442777.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.331970071792602,
|
|
"epoch": 0.7463247577681257,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004950592485288761,
|
|
"loss": 5.1852,
|
|
"mean_token_accuracy": 0.1919775828719139,
|
|
"num_tokens": 16451838.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.254158401489258,
|
|
"epoch": 0.7467423989308386,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004950530421795584,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.19258003830909728,
|
|
"num_tokens": 16460022.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.201046943664551,
|
|
"epoch": 0.7471600400935516,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004950468319779472,
|
|
"loss": 5.018,
|
|
"mean_token_accuracy": 0.20304833203554154,
|
|
"num_tokens": 16468891.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.206154727935791,
|
|
"epoch": 0.7475776812562647,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004950406179241515,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.19986711889505387,
|
|
"num_tokens": 16478020.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.3036723136901855,
|
|
"epoch": 0.7479953224189776,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004950344000182798,
|
|
"loss": 5.2784,
|
|
"mean_token_accuracy": 0.1881829619407654,
|
|
"num_tokens": 16487536.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.335091876983642,
|
|
"epoch": 0.7484129635816906,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004950281782604411,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.18343029022216797,
|
|
"num_tokens": 16495786.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.420146846771241,
|
|
"epoch": 0.7488306047444037,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004950219526507442,
|
|
"loss": 5.2672,
|
|
"mean_token_accuracy": 0.1825781837105751,
|
|
"num_tokens": 16505535.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.388070487976075,
|
|
"epoch": 0.7492482459071166,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004950157231892983,
|
|
"loss": 5.2654,
|
|
"mean_token_accuracy": 0.18759781122207642,
|
|
"num_tokens": 16515387.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.263113594055175,
|
|
"epoch": 0.7496658870698296,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004950094898762123,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.19486620426177978,
|
|
"num_tokens": 16524421.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.432568120956421,
|
|
"epoch": 0.7500835282325427,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004950032527115954,
|
|
"loss": 5.2024,
|
|
"mean_token_accuracy": 0.19057731330394745,
|
|
"num_tokens": 16534533.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.304015398025513,
|
|
"epoch": 0.7505011693952556,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004949970116955566,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.18082914799451827,
|
|
"num_tokens": 16543712.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.2897895812988285,
|
|
"epoch": 0.7509188105579686,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004949907668282054,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.19224326759576799,
|
|
"num_tokens": 16552475.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.33959264755249,
|
|
"epoch": 0.7513364517206816,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000494984518109651,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.18906406909227372,
|
|
"num_tokens": 16562237.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.33980073928833,
|
|
"epoch": 0.7517540928833946,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004949782655400028,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.1936530962586403,
|
|
"num_tokens": 16570508.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7517540928833946,
|
|
"eval_entropy": 5.118175612241377,
|
|
"eval_loss": 5.154400825500488,
|
|
"eval_mean_token_accuracy": 0.19930770909194723,
|
|
"eval_num_tokens": 16570508.0,
|
|
"eval_runtime": 27.4929,
|
|
"eval_samples_per_second": 1373.555,
|
|
"eval_steps_per_second": 171.717,
|
|
"step": 9000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 119720,
|
|
"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": 2.4527858651136e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|