6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.25058469762779817,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 8148212379648000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|