6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.29773719730051607,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.691998863220215,
|
|
"epoch": 0.0004962286621675268,
|
|
"grad_norm": 13.125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8423,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 11448.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.691888427734375,
|
|
"epoch": 0.0009924573243350536,
|
|
"grad_norm": 12.5625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7728,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 22646.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.691094398498535,
|
|
"epoch": 0.0014886859865025804,
|
|
"grad_norm": 9.0,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.5544,
|
|
"mean_token_accuracy": 0.021141647751210257,
|
|
"num_tokens": 34011.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.681868362426759,
|
|
"epoch": 0.001984914648670107,
|
|
"grad_norm": 5.90625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.2252,
|
|
"mean_token_accuracy": 0.039476046711206435,
|
|
"num_tokens": 44566.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.631160545349122,
|
|
"epoch": 0.002481143310837634,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.0163,
|
|
"mean_token_accuracy": 0.03624146841466427,
|
|
"num_tokens": 56274.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.599639701843262,
|
|
"epoch": 0.0029773719730051607,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.8244,
|
|
"mean_token_accuracy": 0.04011724218726158,
|
|
"num_tokens": 66584.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.594005584716797,
|
|
"epoch": 0.0034736006351726877,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.7609,
|
|
"mean_token_accuracy": 0.04112048838287592,
|
|
"num_tokens": 76948.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.580470752716064,
|
|
"epoch": 0.003969829297340214,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.7115,
|
|
"mean_token_accuracy": 0.03858393188565969,
|
|
"num_tokens": 87253.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.582981967926026,
|
|
"epoch": 0.004466057959507741,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.6634,
|
|
"mean_token_accuracy": 0.0404777305200696,
|
|
"num_tokens": 98273.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.553972816467285,
|
|
"epoch": 0.004962286621675268,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.5944,
|
|
"mean_token_accuracy": 0.04187291283160448,
|
|
"num_tokens": 107788.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.549640369415282,
|
|
"epoch": 0.0054585152838427945,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.5959,
|
|
"mean_token_accuracy": 0.03857453148812055,
|
|
"num_tokens": 118632.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.56945514678955,
|
|
"epoch": 0.0059547439460103215,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.4567,
|
|
"mean_token_accuracy": 0.04739701822400093,
|
|
"num_tokens": 128649.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.489003658294678,
|
|
"epoch": 0.0064509726081778485,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.4062,
|
|
"mean_token_accuracy": 0.0514289241284132,
|
|
"num_tokens": 138958.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.402282333374023,
|
|
"epoch": 0.0069472012703453755,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.3466,
|
|
"mean_token_accuracy": 0.050636925548315045,
|
|
"num_tokens": 151445.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.450450229644776,
|
|
"epoch": 0.007443429932512902,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.2601,
|
|
"mean_token_accuracy": 0.0536893866956234,
|
|
"num_tokens": 162239.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.420755386352539,
|
|
"epoch": 0.007939658594680429,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.2029,
|
|
"mean_token_accuracy": 0.047282115742564204,
|
|
"num_tokens": 173261.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.44428882598877,
|
|
"epoch": 0.008435887256847956,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.0727,
|
|
"mean_token_accuracy": 0.050180401653051376,
|
|
"num_tokens": 183857.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.376095581054688,
|
|
"epoch": 0.008932115919015483,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.0912,
|
|
"mean_token_accuracy": 0.05270495116710663,
|
|
"num_tokens": 196635.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.319845962524415,
|
|
"epoch": 0.00942834458118301,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.901,
|
|
"mean_token_accuracy": 0.05795478150248527,
|
|
"num_tokens": 208700.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.2221510887146,
|
|
"epoch": 0.009924573243350537,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.7406,
|
|
"mean_token_accuracy": 0.06187366805970669,
|
|
"num_tokens": 218915.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.15353012084961,
|
|
"epoch": 0.010420801905518062,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.6056,
|
|
"mean_token_accuracy": 0.06669228337705135,
|
|
"num_tokens": 230211.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.054761028289795,
|
|
"epoch": 0.010917030567685589,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.5184,
|
|
"mean_token_accuracy": 0.06720395609736443,
|
|
"num_tokens": 241174.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.002773189544678,
|
|
"epoch": 0.011413259229853116,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.4513,
|
|
"mean_token_accuracy": 0.06137055568397045,
|
|
"num_tokens": 251708.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.951133441925048,
|
|
"epoch": 0.011909487892020643,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.5122,
|
|
"mean_token_accuracy": 0.05963393449783325,
|
|
"num_tokens": 263287.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.863128280639648,
|
|
"epoch": 0.01240571655418817,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.3063,
|
|
"mean_token_accuracy": 0.05798467844724655,
|
|
"num_tokens": 275179.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.68651876449585,
|
|
"epoch": 0.012901945216355697,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.08,
|
|
"mean_token_accuracy": 0.06860841549932957,
|
|
"num_tokens": 287223.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.503121948242187,
|
|
"epoch": 0.013398173878523224,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.9829,
|
|
"mean_token_accuracy": 0.06533094197511673,
|
|
"num_tokens": 297868.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.286877250671386,
|
|
"epoch": 0.013894402540690751,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.9209,
|
|
"mean_token_accuracy": 0.06693189255893231,
|
|
"num_tokens": 309702.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.17711067199707,
|
|
"epoch": 0.014390631202858276,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.9296,
|
|
"mean_token_accuracy": 0.06745850630104541,
|
|
"num_tokens": 321613.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.981420612335205,
|
|
"epoch": 0.014886859865025803,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.7664,
|
|
"mean_token_accuracy": 0.06896167993545532,
|
|
"num_tokens": 332668.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.791222381591798,
|
|
"epoch": 0.01538308852719333,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.7693,
|
|
"mean_token_accuracy": 0.06417617723345756,
|
|
"num_tokens": 342579.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.651444339752198,
|
|
"epoch": 0.015879317189360857,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.6161,
|
|
"mean_token_accuracy": 0.06922528184950352,
|
|
"num_tokens": 352271.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.477163314819336,
|
|
"epoch": 0.016375545851528384,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.6478,
|
|
"mean_token_accuracy": 0.0777987513691187,
|
|
"num_tokens": 364033.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.385774326324462,
|
|
"epoch": 0.01687177451369591,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.5986,
|
|
"mean_token_accuracy": 0.06512850522994995,
|
|
"num_tokens": 373788.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.3142596244812,
|
|
"epoch": 0.01736800317586344,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.5733,
|
|
"mean_token_accuracy": 0.06904393061995506,
|
|
"num_tokens": 384883.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.242665863037109,
|
|
"epoch": 0.017864231838030965,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.4685,
|
|
"mean_token_accuracy": 0.07145911902189254,
|
|
"num_tokens": 396044.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.165802764892579,
|
|
"epoch": 0.018360460500198492,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5903,
|
|
"mean_token_accuracy": 0.07685633525252342,
|
|
"num_tokens": 406995.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.069672966003418,
|
|
"epoch": 0.01885668916236602,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.4217,
|
|
"mean_token_accuracy": 0.07526631690561772,
|
|
"num_tokens": 417238.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.172780990600586,
|
|
"epoch": 0.019352917824533546,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.4965,
|
|
"mean_token_accuracy": 0.07288087829947472,
|
|
"num_tokens": 427263.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.033447551727296,
|
|
"epoch": 0.019849146486701073,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.3851,
|
|
"mean_token_accuracy": 0.07536251321434975,
|
|
"num_tokens": 438357.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.94714241027832,
|
|
"epoch": 0.0203453751488686,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.4067,
|
|
"mean_token_accuracy": 0.0729083027690649,
|
|
"num_tokens": 448738.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.937696313858032,
|
|
"epoch": 0.020841603811036124,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.4298,
|
|
"mean_token_accuracy": 0.0836001418530941,
|
|
"num_tokens": 457873.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.968968772888184,
|
|
"epoch": 0.02133783247320365,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.3665,
|
|
"mean_token_accuracy": 0.07748601958155632,
|
|
"num_tokens": 468640.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.902806615829467,
|
|
"epoch": 0.021834061135371178,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.3699,
|
|
"mean_token_accuracy": 0.07832009121775627,
|
|
"num_tokens": 479922.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.789996480941772,
|
|
"epoch": 0.022330289797538705,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.3231,
|
|
"mean_token_accuracy": 0.07841933965682983,
|
|
"num_tokens": 491056.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.859673023223877,
|
|
"epoch": 0.022826518459706232,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.4182,
|
|
"mean_token_accuracy": 0.07705076970160007,
|
|
"num_tokens": 504365.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.791559553146362,
|
|
"epoch": 0.02332274712187376,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.2999,
|
|
"mean_token_accuracy": 0.07440029308199883,
|
|
"num_tokens": 514347.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.851759672164917,
|
|
"epoch": 0.023818975784041286,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.325,
|
|
"mean_token_accuracy": 0.08229230791330337,
|
|
"num_tokens": 525912.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.765729904174805,
|
|
"epoch": 0.024315204446208813,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.2004,
|
|
"mean_token_accuracy": 0.07634501904249191,
|
|
"num_tokens": 535566.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.780554628372192,
|
|
"epoch": 0.02481143310837634,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.2501,
|
|
"mean_token_accuracy": 0.08192761614918709,
|
|
"num_tokens": 546474.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.747992897033692,
|
|
"epoch": 0.025307661770543867,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.3489,
|
|
"mean_token_accuracy": 0.07340065240859986,
|
|
"num_tokens": 558132.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.8211634159088135,
|
|
"epoch": 0.025803890432711394,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.3332,
|
|
"mean_token_accuracy": 0.07336415946483613,
|
|
"num_tokens": 568309.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.631407022476196,
|
|
"epoch": 0.02630011909487892,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.2426,
|
|
"mean_token_accuracy": 0.07597642093896866,
|
|
"num_tokens": 579701.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.738198757171631,
|
|
"epoch": 0.026796347757046448,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.1884,
|
|
"mean_token_accuracy": 0.08395353108644485,
|
|
"num_tokens": 590832.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.638070821762085,
|
|
"epoch": 0.027292576419213975,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.1208,
|
|
"mean_token_accuracy": 0.08120987564325333,
|
|
"num_tokens": 601094.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.569035053253174,
|
|
"epoch": 0.027788805081381502,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.1377,
|
|
"mean_token_accuracy": 0.08517721891403199,
|
|
"num_tokens": 612027.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.633553075790405,
|
|
"epoch": 0.02828503374354903,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.1841,
|
|
"mean_token_accuracy": 0.08428357169032097,
|
|
"num_tokens": 623698.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.666120433807373,
|
|
"epoch": 0.028781262405716553,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.1991,
|
|
"mean_token_accuracy": 0.08183786422014236,
|
|
"num_tokens": 635631.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.63528003692627,
|
|
"epoch": 0.02927749106788408,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.1819,
|
|
"mean_token_accuracy": 0.08330717980861664,
|
|
"num_tokens": 647663.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.453550720214844,
|
|
"epoch": 0.029773719730051607,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.1489,
|
|
"mean_token_accuracy": 0.07976513430476188,
|
|
"num_tokens": 659352.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.641481256484985,
|
|
"epoch": 0.030269948392219134,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.1201,
|
|
"mean_token_accuracy": 0.08412392735481262,
|
|
"num_tokens": 669379.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.542712736129761,
|
|
"epoch": 0.03076617705438666,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.0948,
|
|
"mean_token_accuracy": 0.08485196307301521,
|
|
"num_tokens": 680144.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.560588741302491,
|
|
"epoch": 0.03126240571655419,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.0416,
|
|
"mean_token_accuracy": 0.0779119621962309,
|
|
"num_tokens": 691165.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.518430519104004,
|
|
"epoch": 0.031758634378721715,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.1409,
|
|
"mean_token_accuracy": 0.07992475032806397,
|
|
"num_tokens": 703767.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.489030599594116,
|
|
"epoch": 0.032254863040889245,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.1289,
|
|
"mean_token_accuracy": 0.08132177069783211,
|
|
"num_tokens": 714298.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.477584648132324,
|
|
"epoch": 0.03275109170305677,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.1088,
|
|
"mean_token_accuracy": 0.08670444339513779,
|
|
"num_tokens": 724135.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.487472200393677,
|
|
"epoch": 0.03324732036522429,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.1704,
|
|
"mean_token_accuracy": 0.07990842834115028,
|
|
"num_tokens": 735050.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.561232852935791,
|
|
"epoch": 0.03374354902739182,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.0652,
|
|
"mean_token_accuracy": 0.08222858682274818,
|
|
"num_tokens": 746073.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.5026990413665775,
|
|
"epoch": 0.034239777689559346,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.0587,
|
|
"mean_token_accuracy": 0.07908397540450096,
|
|
"num_tokens": 758998.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.490911149978638,
|
|
"epoch": 0.03473600635172688,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.9922,
|
|
"mean_token_accuracy": 0.08149008676409722,
|
|
"num_tokens": 771608.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.411250829696655,
|
|
"epoch": 0.0352322350138944,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.0564,
|
|
"mean_token_accuracy": 0.0840062066912651,
|
|
"num_tokens": 782394.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.412871408462524,
|
|
"epoch": 0.03572846367606193,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.9639,
|
|
"mean_token_accuracy": 0.08742633014917374,
|
|
"num_tokens": 792389.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.482435989379883,
|
|
"epoch": 0.036224692338229454,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.0042,
|
|
"mean_token_accuracy": 0.08739039152860642,
|
|
"num_tokens": 803219.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.400604963302612,
|
|
"epoch": 0.036720921000396985,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.0724,
|
|
"mean_token_accuracy": 0.08268633931875229,
|
|
"num_tokens": 814249.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.4228143215179445,
|
|
"epoch": 0.03721714966256451,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.9675,
|
|
"mean_token_accuracy": 0.09332375228404999,
|
|
"num_tokens": 825138.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.332874011993408,
|
|
"epoch": 0.03771337832473204,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.0155,
|
|
"mean_token_accuracy": 0.08916119858622551,
|
|
"num_tokens": 836024.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.422525310516358,
|
|
"epoch": 0.03820960698689956,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.0106,
|
|
"mean_token_accuracy": 0.08618483543395997,
|
|
"num_tokens": 847765.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.309659004211426,
|
|
"epoch": 0.03870583564906709,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.9978,
|
|
"mean_token_accuracy": 0.08317906334996224,
|
|
"num_tokens": 859980.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.398729848861694,
|
|
"epoch": 0.039202064311234616,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.9852,
|
|
"mean_token_accuracy": 0.08303623273968697,
|
|
"num_tokens": 871514.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.358026456832886,
|
|
"epoch": 0.03969829297340215,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.9883,
|
|
"mean_token_accuracy": 0.08641744777560234,
|
|
"num_tokens": 881984.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.339498233795166,
|
|
"epoch": 0.04019452163556967,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.9422,
|
|
"mean_token_accuracy": 0.08860462978482246,
|
|
"num_tokens": 894198.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.329129791259765,
|
|
"epoch": 0.0406907502977372,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.9528,
|
|
"mean_token_accuracy": 0.08584670275449753,
|
|
"num_tokens": 905394.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.4144409656524655,
|
|
"epoch": 0.041186978959904724,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.0093,
|
|
"mean_token_accuracy": 0.08373580649495124,
|
|
"num_tokens": 917010.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.2484229564666744,
|
|
"epoch": 0.04168320762207225,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.8328,
|
|
"mean_token_accuracy": 0.09602309390902519,
|
|
"num_tokens": 926761.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.169170570373535,
|
|
"epoch": 0.04217943628423978,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.8508,
|
|
"mean_token_accuracy": 0.09352190122008323,
|
|
"num_tokens": 938385.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.252145004272461,
|
|
"epoch": 0.0426756649464073,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.8835,
|
|
"mean_token_accuracy": 0.0913587599992752,
|
|
"num_tokens": 949709.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.300234842300415,
|
|
"epoch": 0.04317189360857483,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.9009,
|
|
"mean_token_accuracy": 0.08750406205654145,
|
|
"num_tokens": 960837.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.217148399353027,
|
|
"epoch": 0.043668122270742356,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7532,
|
|
"mean_token_accuracy": 0.096002509444952,
|
|
"num_tokens": 971036.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.26617751121521,
|
|
"epoch": 0.044164350932909886,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.8966,
|
|
"mean_token_accuracy": 0.08577612191438674,
|
|
"num_tokens": 983057.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.207610130310059,
|
|
"epoch": 0.04466057959507741,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.8685,
|
|
"mean_token_accuracy": 0.09361535310745239,
|
|
"num_tokens": 994303.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.1220794200897215,
|
|
"epoch": 0.04515680825724494,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.8559,
|
|
"mean_token_accuracy": 0.09114001989364624,
|
|
"num_tokens": 1005033.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.20084171295166,
|
|
"epoch": 0.045653036919412464,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.9188,
|
|
"mean_token_accuracy": 0.09030571505427361,
|
|
"num_tokens": 1015940.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.239992237091064,
|
|
"epoch": 0.046149265581579994,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.8753,
|
|
"mean_token_accuracy": 0.09003765881061554,
|
|
"num_tokens": 1027582.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.178811550140381,
|
|
"epoch": 0.04664549424374752,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.8353,
|
|
"mean_token_accuracy": 0.08800699189305305,
|
|
"num_tokens": 1040046.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.159101486206055,
|
|
"epoch": 0.04714172290591505,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.9207,
|
|
"mean_token_accuracy": 0.07997897453606129,
|
|
"num_tokens": 1050636.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.22628493309021,
|
|
"epoch": 0.04763795156808257,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.7957,
|
|
"mean_token_accuracy": 0.09439989402890206,
|
|
"num_tokens": 1060748.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.260278987884521,
|
|
"epoch": 0.0481341802302501,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.8359,
|
|
"mean_token_accuracy": 0.08930574655532837,
|
|
"num_tokens": 1071940.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.081393527984619,
|
|
"epoch": 0.048630408892417626,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.8633,
|
|
"mean_token_accuracy": 0.09053891003131867,
|
|
"num_tokens": 1082962.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.151085042953492,
|
|
"epoch": 0.04912663755458515,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.8503,
|
|
"mean_token_accuracy": 0.093645728379488,
|
|
"num_tokens": 1093082.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.2744776725769045,
|
|
"epoch": 0.04962286621675268,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.9163,
|
|
"mean_token_accuracy": 0.0890045516192913,
|
|
"num_tokens": 1103528.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.072138071060181,
|
|
"epoch": 0.0501190948789202,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.7991,
|
|
"mean_token_accuracy": 0.08873311057686806,
|
|
"num_tokens": 1114813.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.072871494293213,
|
|
"epoch": 0.050615323541087734,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.7897,
|
|
"mean_token_accuracy": 0.08742236867547035,
|
|
"num_tokens": 1125345.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.088561058044434,
|
|
"epoch": 0.05111155220325526,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.8045,
|
|
"mean_token_accuracy": 0.09052546843886375,
|
|
"num_tokens": 1134985.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.123575067520141,
|
|
"epoch": 0.05160778086542279,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.8147,
|
|
"mean_token_accuracy": 0.09349623173475266,
|
|
"num_tokens": 1145796.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.224857807159424,
|
|
"epoch": 0.05210400952759031,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.9443,
|
|
"mean_token_accuracy": 0.08439943566918373,
|
|
"num_tokens": 1156936.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.091599845886231,
|
|
"epoch": 0.05260023818975784,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.8415,
|
|
"mean_token_accuracy": 0.09559056684374809,
|
|
"num_tokens": 1167526.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.065865850448608,
|
|
"epoch": 0.053096466851925365,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.8723,
|
|
"mean_token_accuracy": 0.08711705654859543,
|
|
"num_tokens": 1177647.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.144536447525025,
|
|
"epoch": 0.053592695514092896,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.8338,
|
|
"mean_token_accuracy": 0.0977127991616726,
|
|
"num_tokens": 1188255.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.989999294281006,
|
|
"epoch": 0.05408892417626042,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.7547,
|
|
"mean_token_accuracy": 0.09971059560775757,
|
|
"num_tokens": 1199433.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.007773780822754,
|
|
"epoch": 0.05458515283842795,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.8445,
|
|
"mean_token_accuracy": 0.09036741033196449,
|
|
"num_tokens": 1210067.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.000052261352539,
|
|
"epoch": 0.055081381500595473,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.7252,
|
|
"mean_token_accuracy": 0.09621484205126762,
|
|
"num_tokens": 1220639.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.0871340274810795,
|
|
"epoch": 0.055577610162763004,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.769,
|
|
"mean_token_accuracy": 0.09496552497148514,
|
|
"num_tokens": 1233158.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.9964536190032955,
|
|
"epoch": 0.05607383882493053,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.7508,
|
|
"mean_token_accuracy": 0.08838386237621307,
|
|
"num_tokens": 1244552.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.103402709960937,
|
|
"epoch": 0.05657006748709806,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.8534,
|
|
"mean_token_accuracy": 0.08600240871310234,
|
|
"num_tokens": 1255478.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.939698266983032,
|
|
"epoch": 0.05706629614926558,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6773,
|
|
"mean_token_accuracy": 0.10140636935830116,
|
|
"num_tokens": 1267507.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.916869688034057,
|
|
"epoch": 0.057562524811433105,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.695,
|
|
"mean_token_accuracy": 0.08891933038830757,
|
|
"num_tokens": 1279377.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.038671827316284,
|
|
"epoch": 0.058058753473600636,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.7852,
|
|
"mean_token_accuracy": 0.09897390529513359,
|
|
"num_tokens": 1290671.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.851378393173218,
|
|
"epoch": 0.05855498213576816,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.7456,
|
|
"mean_token_accuracy": 0.09530175179243087,
|
|
"num_tokens": 1302792.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.058105230331421,
|
|
"epoch": 0.05905121079793569,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6992,
|
|
"mean_token_accuracy": 0.09145391955971718,
|
|
"num_tokens": 1313315.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.8826432704925535,
|
|
"epoch": 0.05954743946010321,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.7687,
|
|
"mean_token_accuracy": 0.08865362480282783,
|
|
"num_tokens": 1326358.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.999434471130371,
|
|
"epoch": 0.060043668122270744,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.6327,
|
|
"mean_token_accuracy": 0.0945927508175373,
|
|
"num_tokens": 1336266.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.812005853652954,
|
|
"epoch": 0.06053989678443827,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.583,
|
|
"mean_token_accuracy": 0.09936992004513741,
|
|
"num_tokens": 1347610.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.810373449325562,
|
|
"epoch": 0.0610361254466058,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.5545,
|
|
"mean_token_accuracy": 0.1030762791633606,
|
|
"num_tokens": 1358317.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.903623342514038,
|
|
"epoch": 0.06153235410877332,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.6804,
|
|
"mean_token_accuracy": 0.09128398001194,
|
|
"num_tokens": 1370126.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.882534837722778,
|
|
"epoch": 0.06202858277094085,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.6464,
|
|
"mean_token_accuracy": 0.0963453158736229,
|
|
"num_tokens": 1381571.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.7741142272949215,
|
|
"epoch": 0.06252481143310838,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.6708,
|
|
"mean_token_accuracy": 0.0964869923889637,
|
|
"num_tokens": 1392486.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.902181005477905,
|
|
"epoch": 0.0630210400952759,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.68,
|
|
"mean_token_accuracy": 0.09968246370553971,
|
|
"num_tokens": 1403086.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.83144588470459,
|
|
"epoch": 0.06351726875744343,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.6507,
|
|
"mean_token_accuracy": 0.09976455271244049,
|
|
"num_tokens": 1414537.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.840048837661743,
|
|
"epoch": 0.06401349741961096,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.6542,
|
|
"mean_token_accuracy": 0.09846014603972435,
|
|
"num_tokens": 1426998.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.847141170501709,
|
|
"epoch": 0.06450972608177849,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.6781,
|
|
"mean_token_accuracy": 0.09744567275047303,
|
|
"num_tokens": 1437667.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.8108092784881595,
|
|
"epoch": 0.065005954743946,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.547,
|
|
"mean_token_accuracy": 0.10085381418466569,
|
|
"num_tokens": 1448280.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.831343030929565,
|
|
"epoch": 0.06550218340611354,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.6163,
|
|
"mean_token_accuracy": 0.09790344089269638,
|
|
"num_tokens": 1458608.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.936217546463013,
|
|
"epoch": 0.06599841206828107,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.8059,
|
|
"mean_token_accuracy": 0.08812156543135644,
|
|
"num_tokens": 1470435.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.771727180480957,
|
|
"epoch": 0.06649464073044858,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.6608,
|
|
"mean_token_accuracy": 0.09632581174373626,
|
|
"num_tokens": 1481959.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.825786304473877,
|
|
"epoch": 0.06699086939261611,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.6976,
|
|
"mean_token_accuracy": 0.0911058507859707,
|
|
"num_tokens": 1493798.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.816014671325684,
|
|
"epoch": 0.06748709805478365,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.503,
|
|
"mean_token_accuracy": 0.10050572380423546,
|
|
"num_tokens": 1502969.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.787315845489502,
|
|
"epoch": 0.06798332671695118,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.67,
|
|
"mean_token_accuracy": 0.09576347395777703,
|
|
"num_tokens": 1513825.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.755472135543823,
|
|
"epoch": 0.06847955537911869,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.5492,
|
|
"mean_token_accuracy": 0.10139472037553787,
|
|
"num_tokens": 1525328.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.805799102783203,
|
|
"epoch": 0.06897578404128622,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.5664,
|
|
"mean_token_accuracy": 0.10111717209219932,
|
|
"num_tokens": 1537383.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.773342514038086,
|
|
"epoch": 0.06947201270345375,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.6756,
|
|
"mean_token_accuracy": 0.09535346329212188,
|
|
"num_tokens": 1549671.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.707566404342652,
|
|
"epoch": 0.06996824136562128,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.55,
|
|
"mean_token_accuracy": 0.0958769753575325,
|
|
"num_tokens": 1559974.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.82678599357605,
|
|
"epoch": 0.0704644700277888,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.6602,
|
|
"mean_token_accuracy": 0.09039726406335831,
|
|
"num_tokens": 1570890.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.738782691955566,
|
|
"epoch": 0.07096069868995633,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.5641,
|
|
"mean_token_accuracy": 0.1056017056107521,
|
|
"num_tokens": 1581434.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.804084634780883,
|
|
"epoch": 0.07145692735212386,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.6318,
|
|
"mean_token_accuracy": 0.09419183582067489,
|
|
"num_tokens": 1593710.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.76332368850708,
|
|
"epoch": 0.07195315601429139,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.5919,
|
|
"mean_token_accuracy": 0.09819654747843742,
|
|
"num_tokens": 1604635.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.889756727218628,
|
|
"epoch": 0.07244938467645891,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.6595,
|
|
"mean_token_accuracy": 0.09840102568268776,
|
|
"num_tokens": 1615258.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.677707576751709,
|
|
"epoch": 0.07294561333862644,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.5582,
|
|
"mean_token_accuracy": 0.09775017052888871,
|
|
"num_tokens": 1625942.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.687536382675171,
|
|
"epoch": 0.07344184200079397,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.5459,
|
|
"mean_token_accuracy": 0.10621693730354309,
|
|
"num_tokens": 1636270.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.677185583114624,
|
|
"epoch": 0.07393807066296149,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.5294,
|
|
"mean_token_accuracy": 0.10231522172689438,
|
|
"num_tokens": 1647029.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.756840419769287,
|
|
"epoch": 0.07443429932512902,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.7135,
|
|
"mean_token_accuracy": 0.09764664024114608,
|
|
"num_tokens": 1659483.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.648179912567139,
|
|
"epoch": 0.07493052798729655,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.5518,
|
|
"mean_token_accuracy": 0.0972537100315094,
|
|
"num_tokens": 1669425.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.727893924713134,
|
|
"epoch": 0.07542675664946408,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.568,
|
|
"mean_token_accuracy": 0.09414743408560752,
|
|
"num_tokens": 1680426.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.665664148330689,
|
|
"epoch": 0.0759229853116316,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.5744,
|
|
"mean_token_accuracy": 0.0945310615003109,
|
|
"num_tokens": 1692803.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.669447755813598,
|
|
"epoch": 0.07641921397379912,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5984,
|
|
"mean_token_accuracy": 0.0979096457362175,
|
|
"num_tokens": 1703919.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.73317174911499,
|
|
"epoch": 0.07691544263596665,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.5787,
|
|
"mean_token_accuracy": 0.1017878644168377,
|
|
"num_tokens": 1714487.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.738369035720825,
|
|
"epoch": 0.07741167129813419,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.6143,
|
|
"mean_token_accuracy": 0.09932834580540657,
|
|
"num_tokens": 1726601.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.703241872787475,
|
|
"epoch": 0.0779078999603017,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.5226,
|
|
"mean_token_accuracy": 0.09681319668889046,
|
|
"num_tokens": 1738743.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.577711486816407,
|
|
"epoch": 0.07840412862246923,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.6013,
|
|
"mean_token_accuracy": 0.09930569976568222,
|
|
"num_tokens": 1748286.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.648367071151734,
|
|
"epoch": 0.07890035728463676,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.6383,
|
|
"mean_token_accuracy": 0.09991247206926346,
|
|
"num_tokens": 1758917.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.686027669906617,
|
|
"epoch": 0.0793965859468043,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.4599,
|
|
"mean_token_accuracy": 0.10187165811657906,
|
|
"num_tokens": 1769179.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.624785614013672,
|
|
"epoch": 0.07989281460897181,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.6059,
|
|
"mean_token_accuracy": 0.09910577759146691,
|
|
"num_tokens": 1782369.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.665830755233765,
|
|
"epoch": 0.08038904327113934,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.5888,
|
|
"mean_token_accuracy": 0.103836190700531,
|
|
"num_tokens": 1795992.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.596944665908813,
|
|
"epoch": 0.08088527193330687,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.491,
|
|
"mean_token_accuracy": 0.10671056434512138,
|
|
"num_tokens": 1806938.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.592557191848755,
|
|
"epoch": 0.0813815005954744,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.4242,
|
|
"mean_token_accuracy": 0.1038404531776905,
|
|
"num_tokens": 1817663.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.645978593826294,
|
|
"epoch": 0.08187772925764192,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.577,
|
|
"mean_token_accuracy": 0.10006028190255165,
|
|
"num_tokens": 1828254.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.615597295761108,
|
|
"epoch": 0.08237395791980945,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.5017,
|
|
"mean_token_accuracy": 0.10172841027379036,
|
|
"num_tokens": 1839001.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.63342056274414,
|
|
"epoch": 0.08287018658197698,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.6031,
|
|
"mean_token_accuracy": 0.09923635870218277,
|
|
"num_tokens": 1849906.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.54316554069519,
|
|
"epoch": 0.0833664152441445,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.4851,
|
|
"mean_token_accuracy": 0.09840435534715652,
|
|
"num_tokens": 1860982.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.650843954086303,
|
|
"epoch": 0.08386264390631203,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.4543,
|
|
"mean_token_accuracy": 0.10228981822729111,
|
|
"num_tokens": 1872177.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.506167984008789,
|
|
"epoch": 0.08435887256847956,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.4298,
|
|
"mean_token_accuracy": 0.10004795640707016,
|
|
"num_tokens": 1882783.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.652998065948486,
|
|
"epoch": 0.08485510123064709,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.6083,
|
|
"mean_token_accuracy": 0.09435755014419556,
|
|
"num_tokens": 1893706.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.550818347930909,
|
|
"epoch": 0.0853513298928146,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.4819,
|
|
"mean_token_accuracy": 0.10135309919714927,
|
|
"num_tokens": 1903852.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.591495037078857,
|
|
"epoch": 0.08584755855498213,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.5065,
|
|
"mean_token_accuracy": 0.10633492544293403,
|
|
"num_tokens": 1914157.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.572027492523193,
|
|
"epoch": 0.08634378721714966,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.4494,
|
|
"mean_token_accuracy": 0.10061108618974686,
|
|
"num_tokens": 1924684.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.659038972854614,
|
|
"epoch": 0.0868400158793172,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.6039,
|
|
"mean_token_accuracy": 0.09810293242335319,
|
|
"num_tokens": 1935657.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.516001558303833,
|
|
"epoch": 0.08733624454148471,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.4699,
|
|
"mean_token_accuracy": 0.10223818272352218,
|
|
"num_tokens": 1946735.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.609535169601441,
|
|
"epoch": 0.08783247320365224,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.6563,
|
|
"mean_token_accuracy": 0.09723427742719651,
|
|
"num_tokens": 1957871.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.502126550674438,
|
|
"epoch": 0.08832870186581977,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.4901,
|
|
"mean_token_accuracy": 0.10245168954133987,
|
|
"num_tokens": 1969032.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.63283109664917,
|
|
"epoch": 0.0888249305279873,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.4947,
|
|
"mean_token_accuracy": 0.10377224013209344,
|
|
"num_tokens": 1980212.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.4811985969543455,
|
|
"epoch": 0.08932115919015482,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.4302,
|
|
"mean_token_accuracy": 0.10036835372447968,
|
|
"num_tokens": 1990333.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.624222469329834,
|
|
"epoch": 0.08981738785232235,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.5093,
|
|
"mean_token_accuracy": 0.10546329617500305,
|
|
"num_tokens": 2001486.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.498252010345459,
|
|
"epoch": 0.09031361651448988,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.4836,
|
|
"mean_token_accuracy": 0.10137376263737678,
|
|
"num_tokens": 2012535.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.448726797103882,
|
|
"epoch": 0.0908098451766574,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.4479,
|
|
"mean_token_accuracy": 0.10513061881065369,
|
|
"num_tokens": 2024116.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.52455415725708,
|
|
"epoch": 0.09130607383882493,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4937,
|
|
"mean_token_accuracy": 0.10239877849817276,
|
|
"num_tokens": 2036341.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.582788896560669,
|
|
"epoch": 0.09180230250099246,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.4589,
|
|
"mean_token_accuracy": 0.10736544132232666,
|
|
"num_tokens": 2046768.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.458439350128174,
|
|
"epoch": 0.09229853116315999,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.434,
|
|
"mean_token_accuracy": 0.10159429535269737,
|
|
"num_tokens": 2057315.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.482909297943115,
|
|
"epoch": 0.0927947598253275,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4105,
|
|
"mean_token_accuracy": 0.10489368736743927,
|
|
"num_tokens": 2068267.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.438783884048462,
|
|
"epoch": 0.09329098848749504,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.4727,
|
|
"mean_token_accuracy": 0.1056045152246952,
|
|
"num_tokens": 2078271.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.471507453918457,
|
|
"epoch": 0.09378721714966257,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.4045,
|
|
"mean_token_accuracy": 0.09843646511435508,
|
|
"num_tokens": 2088381.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.484247779846191,
|
|
"epoch": 0.0942834458118301,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.3704,
|
|
"mean_token_accuracy": 0.10096605494618416,
|
|
"num_tokens": 2098899.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.458307695388794,
|
|
"epoch": 0.09477967447399761,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.5349,
|
|
"mean_token_accuracy": 0.09965546950697898,
|
|
"num_tokens": 2110057.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.403871393203735,
|
|
"epoch": 0.09527590313616514,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.439,
|
|
"mean_token_accuracy": 0.10709322020411491,
|
|
"num_tokens": 2121758.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.51858696937561,
|
|
"epoch": 0.09577213179833267,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.4436,
|
|
"mean_token_accuracy": 0.10227768048644066,
|
|
"num_tokens": 2131840.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.40182580947876,
|
|
"epoch": 0.0962683604605002,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.4111,
|
|
"mean_token_accuracy": 0.10386593788862228,
|
|
"num_tokens": 2142084.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.511473226547241,
|
|
"epoch": 0.09676458912266772,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.4699,
|
|
"mean_token_accuracy": 0.10299977660179138,
|
|
"num_tokens": 2152785.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.500741481781006,
|
|
"epoch": 0.09726081778483525,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.4753,
|
|
"mean_token_accuracy": 0.10271376669406891,
|
|
"num_tokens": 2163774.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.387545013427735,
|
|
"epoch": 0.09775704644700278,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3898,
|
|
"mean_token_accuracy": 0.10328807160258294,
|
|
"num_tokens": 2175378.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.624388551712036,
|
|
"epoch": 0.0982532751091703,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.5951,
|
|
"mean_token_accuracy": 0.09878992438316345,
|
|
"num_tokens": 2186510.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.389967775344848,
|
|
"epoch": 0.09874950377133783,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.3943,
|
|
"mean_token_accuracy": 0.10771489515900612,
|
|
"num_tokens": 2197482.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.380904293060302,
|
|
"epoch": 0.09924573243350536,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.3707,
|
|
"mean_token_accuracy": 0.10641616210341454,
|
|
"num_tokens": 2208329.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.359027290344239,
|
|
"epoch": 0.09974196109567289,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999999982145551,
|
|
"loss": 6.2907,
|
|
"mean_token_accuracy": 0.10751227289438248,
|
|
"num_tokens": 2218632.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.3495697498321535,
|
|
"epoch": 0.1002381897578404,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999999909611855,
|
|
"loss": 6.4102,
|
|
"mean_token_accuracy": 0.09977167919278145,
|
|
"num_tokens": 2231335.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.492461919784546,
|
|
"epoch": 0.10073441842000794,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999999781283008,
|
|
"loss": 6.3835,
|
|
"mean_token_accuracy": 0.10530572384595871,
|
|
"num_tokens": 2241704.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.349406576156616,
|
|
"epoch": 0.10123064708217547,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999999597159017,
|
|
"loss": 6.4696,
|
|
"mean_token_accuracy": 0.09799574688076973,
|
|
"num_tokens": 2252310.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.513053894042969,
|
|
"epoch": 0.101726875744343,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999999357239882,
|
|
"loss": 6.3749,
|
|
"mean_token_accuracy": 0.10209976211190223,
|
|
"num_tokens": 2262270.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.457979393005371,
|
|
"epoch": 0.10222310440651051,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999999061525612,
|
|
"loss": 6.5111,
|
|
"mean_token_accuracy": 0.10106326639652252,
|
|
"num_tokens": 2273986.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.485824108123779,
|
|
"epoch": 0.10271933306867805,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999998710016214,
|
|
"loss": 6.3925,
|
|
"mean_token_accuracy": 0.10402849987149239,
|
|
"num_tokens": 2283430.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.439836835861206,
|
|
"epoch": 0.10321556173084558,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999998302711696,
|
|
"loss": 6.4099,
|
|
"mean_token_accuracy": 0.1028740145266056,
|
|
"num_tokens": 2294201.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.307459545135498,
|
|
"epoch": 0.1037117903930131,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999997839612069,
|
|
"loss": 6.3057,
|
|
"mean_token_accuracy": 0.10684936791658402,
|
|
"num_tokens": 2303876.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.308732223510742,
|
|
"epoch": 0.10420801905518062,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999997320717342,
|
|
"loss": 6.3598,
|
|
"mean_token_accuracy": 0.10919448658823967,
|
|
"num_tokens": 2313713.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.328538656234741,
|
|
"epoch": 0.10470424771734815,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999996746027531,
|
|
"loss": 6.3731,
|
|
"mean_token_accuracy": 0.10021564215421677,
|
|
"num_tokens": 2324862.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.477358341217041,
|
|
"epoch": 0.10520047637951568,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499999611554265,
|
|
"loss": 6.4335,
|
|
"mean_token_accuracy": 0.10697967633605003,
|
|
"num_tokens": 2334974.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.4058030128479,
|
|
"epoch": 0.10569670504168321,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999995429262712,
|
|
"loss": 6.478,
|
|
"mean_token_accuracy": 0.10283638387918473,
|
|
"num_tokens": 2345945.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.446000862121582,
|
|
"epoch": 0.10619293370385073,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999994687187737,
|
|
"loss": 6.401,
|
|
"mean_token_accuracy": 0.10349917486310005,
|
|
"num_tokens": 2356749.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.440154552459717,
|
|
"epoch": 0.10668916236601826,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999993889317742,
|
|
"loss": 6.4816,
|
|
"mean_token_accuracy": 0.09764729216694831,
|
|
"num_tokens": 2368181.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.341366386413574,
|
|
"epoch": 0.10718539102818579,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999993035652746,
|
|
"loss": 6.3788,
|
|
"mean_token_accuracy": 0.10620132908225059,
|
|
"num_tokens": 2377737.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.3908861637115475,
|
|
"epoch": 0.10768161969035331,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999992126192771,
|
|
"loss": 6.292,
|
|
"mean_token_accuracy": 0.1073671467602253,
|
|
"num_tokens": 2388944.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.353183174133301,
|
|
"epoch": 0.10817784835252084,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499999116093784,
|
|
"loss": 6.3801,
|
|
"mean_token_accuracy": 0.10383658036589623,
|
|
"num_tokens": 2400758.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.32312593460083,
|
|
"epoch": 0.10867407701468837,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999990139887976,
|
|
"loss": 6.375,
|
|
"mean_token_accuracy": 0.1099216289818287,
|
|
"num_tokens": 2411916.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.5799376487731935,
|
|
"epoch": 0.1091703056768559,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999989063043206,
|
|
"loss": 6.3937,
|
|
"mean_token_accuracy": 0.10351028591394425,
|
|
"num_tokens": 2423310.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.210668468475342,
|
|
"epoch": 0.10966653433902342,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999987930403555,
|
|
"loss": 6.331,
|
|
"mean_token_accuracy": 0.10480535998940468,
|
|
"num_tokens": 2432100.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.410353755950927,
|
|
"epoch": 0.11016276300119095,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999986741969051,
|
|
"loss": 6.4061,
|
|
"mean_token_accuracy": 0.10518641620874405,
|
|
"num_tokens": 2443563.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.427771806716919,
|
|
"epoch": 0.11065899166335848,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999985497739724,
|
|
"loss": 6.4161,
|
|
"mean_token_accuracy": 0.10631361752748489,
|
|
"num_tokens": 2455435.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.324798250198365,
|
|
"epoch": 0.11115522032552601,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999984197715606,
|
|
"loss": 6.3474,
|
|
"mean_token_accuracy": 0.10725902542471885,
|
|
"num_tokens": 2466173.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.336659860610962,
|
|
"epoch": 0.11165144898769352,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999982841896728,
|
|
"loss": 6.2889,
|
|
"mean_token_accuracy": 0.10596159473061562,
|
|
"num_tokens": 2476349.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.389477157592774,
|
|
"epoch": 0.11214767764986106,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999981430283123,
|
|
"loss": 6.4296,
|
|
"mean_token_accuracy": 0.11070242971181869,
|
|
"num_tokens": 2487864.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.343891382217407,
|
|
"epoch": 0.11264390631202859,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999979962874827,
|
|
"loss": 6.3521,
|
|
"mean_token_accuracy": 0.1044541135430336,
|
|
"num_tokens": 2499188.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.371397876739502,
|
|
"epoch": 0.11314013497419612,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999978439671877,
|
|
"loss": 6.3489,
|
|
"mean_token_accuracy": 0.10524334833025932,
|
|
"num_tokens": 2509813.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.323387098312378,
|
|
"epoch": 0.11363636363636363,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999976860674309,
|
|
"loss": 6.3801,
|
|
"mean_token_accuracy": 0.10332749933004379,
|
|
"num_tokens": 2520813.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.365607404708863,
|
|
"epoch": 0.11413259229853116,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999975225882164,
|
|
"loss": 6.364,
|
|
"mean_token_accuracy": 0.10385186225175858,
|
|
"num_tokens": 2531802.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.272516870498658,
|
|
"epoch": 0.1146288209606987,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499997353529548,
|
|
"loss": 6.1818,
|
|
"mean_token_accuracy": 0.11805973723530769,
|
|
"num_tokens": 2541935.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.2223155975341795,
|
|
"epoch": 0.11512504962286621,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999971788914303,
|
|
"loss": 6.2789,
|
|
"mean_token_accuracy": 0.11048080250620843,
|
|
"num_tokens": 2553224.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.273540782928467,
|
|
"epoch": 0.11562127828503374,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999969986738672,
|
|
"loss": 6.3094,
|
|
"mean_token_accuracy": 0.1041909970343113,
|
|
"num_tokens": 2565355.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.392901992797851,
|
|
"epoch": 0.11611750694720127,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999968128768634,
|
|
"loss": 6.4025,
|
|
"mean_token_accuracy": 0.10415177568793296,
|
|
"num_tokens": 2575962.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.349782133102417,
|
|
"epoch": 0.1166137356093688,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999966215004236,
|
|
"loss": 6.4036,
|
|
"mean_token_accuracy": 0.11040559411048889,
|
|
"num_tokens": 2588136.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.387732315063476,
|
|
"epoch": 0.11710996427153632,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999964245445522,
|
|
"loss": 6.2871,
|
|
"mean_token_accuracy": 0.10886711925268173,
|
|
"num_tokens": 2597785.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.262753820419311,
|
|
"epoch": 0.11760619293370385,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999962220092545,
|
|
"loss": 6.3365,
|
|
"mean_token_accuracy": 0.11655003651976585,
|
|
"num_tokens": 2609738.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.280587577819825,
|
|
"epoch": 0.11810242159587138,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999960138945351,
|
|
"loss": 6.2248,
|
|
"mean_token_accuracy": 0.11575354188680649,
|
|
"num_tokens": 2620179.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.265934133529663,
|
|
"epoch": 0.11859865025803891,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999958002003996,
|
|
"loss": 6.2575,
|
|
"mean_token_accuracy": 0.1127023346722126,
|
|
"num_tokens": 2631550.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.305636072158814,
|
|
"epoch": 0.11909487892020643,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999955809268529,
|
|
"loss": 6.3107,
|
|
"mean_token_accuracy": 0.10845914930105209,
|
|
"num_tokens": 2642467.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.269169902801513,
|
|
"epoch": 0.11959110758237396,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999953560739008,
|
|
"loss": 6.2755,
|
|
"mean_token_accuracy": 0.1076017014682293,
|
|
"num_tokens": 2652132.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.31046495437622,
|
|
"epoch": 0.12008733624454149,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999951256415485,
|
|
"loss": 6.3359,
|
|
"mean_token_accuracy": 0.10693469643592834,
|
|
"num_tokens": 2663336.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.4014545440673825,
|
|
"epoch": 0.12058356490670902,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499994889629802,
|
|
"loss": 6.4135,
|
|
"mean_token_accuracy": 0.10004161298274994,
|
|
"num_tokens": 2674201.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.318805313110351,
|
|
"epoch": 0.12107979356887653,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499994648038667,
|
|
"loss": 6.3365,
|
|
"mean_token_accuracy": 0.11189582347869872,
|
|
"num_tokens": 2685073.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.3630119323730465,
|
|
"epoch": 0.12157602223104406,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999944008681496,
|
|
"loss": 6.2728,
|
|
"mean_token_accuracy": 0.10747573971748352,
|
|
"num_tokens": 2695024.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.2960004806518555,
|
|
"epoch": 0.1220722508932116,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999941481182559,
|
|
"loss": 6.3667,
|
|
"mean_token_accuracy": 0.10157103613018989,
|
|
"num_tokens": 2706232.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.2944573879241945,
|
|
"epoch": 0.12256847955537911,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999938897889921,
|
|
"loss": 6.3495,
|
|
"mean_token_accuracy": 0.11251293942332267,
|
|
"num_tokens": 2715874.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.293622159957886,
|
|
"epoch": 0.12306470821754664,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999936258803647,
|
|
"loss": 6.2806,
|
|
"mean_token_accuracy": 0.11366166844964028,
|
|
"num_tokens": 2727409.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.216445827484131,
|
|
"epoch": 0.12356093687971417,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999933563923802,
|
|
"loss": 6.1902,
|
|
"mean_token_accuracy": 0.11650204434990882,
|
|
"num_tokens": 2737259.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.291175603866577,
|
|
"epoch": 0.1240571655418817,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999930813250451,
|
|
"loss": 6.3362,
|
|
"mean_token_accuracy": 0.10701057985424996,
|
|
"num_tokens": 2748416.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.2936169624328615,
|
|
"epoch": 0.12455339420404922,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999928006783667,
|
|
"loss": 6.2966,
|
|
"mean_token_accuracy": 0.11243170276284217,
|
|
"num_tokens": 2760470.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.355133771896362,
|
|
"epoch": 0.12504962286621676,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999925144523515,
|
|
"loss": 6.3282,
|
|
"mean_token_accuracy": 0.10313374847173691,
|
|
"num_tokens": 2770222.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.230967378616333,
|
|
"epoch": 0.12554585152838427,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999922226470066,
|
|
"loss": 6.2494,
|
|
"mean_token_accuracy": 0.11002011597156525,
|
|
"num_tokens": 2780212.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.241526460647583,
|
|
"epoch": 0.1260420801905518,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999919252623397,
|
|
"loss": 6.207,
|
|
"mean_token_accuracy": 0.1117776483297348,
|
|
"num_tokens": 2790239.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.312730836868286,
|
|
"epoch": 0.12653830885271933,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999916222983577,
|
|
"loss": 6.2607,
|
|
"mean_token_accuracy": 0.11156586781144143,
|
|
"num_tokens": 2801902.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.192100143432617,
|
|
"epoch": 0.12703453751488686,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999913137550682,
|
|
"loss": 6.2456,
|
|
"mean_token_accuracy": 0.11060267984867096,
|
|
"num_tokens": 2813268.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.3050133228302006,
|
|
"epoch": 0.1275307661770544,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999909996324791,
|
|
"loss": 6.3387,
|
|
"mean_token_accuracy": 0.1083206556737423,
|
|
"num_tokens": 2824506.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.242365169525146,
|
|
"epoch": 0.12802699483922192,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499990679930598,
|
|
"loss": 6.2258,
|
|
"mean_token_accuracy": 0.1135059081017971,
|
|
"num_tokens": 2835144.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.199550008773803,
|
|
"epoch": 0.12852322350138945,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999903546494327,
|
|
"loss": 6.2496,
|
|
"mean_token_accuracy": 0.10745349675416946,
|
|
"num_tokens": 2845382.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.277227210998535,
|
|
"epoch": 0.12901945216355698,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999900237889916,
|
|
"loss": 6.2721,
|
|
"mean_token_accuracy": 0.11390693038702011,
|
|
"num_tokens": 2854697.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.250763368606568,
|
|
"epoch": 0.12951568082572448,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999896873492827,
|
|
"loss": 6.2708,
|
|
"mean_token_accuracy": 0.10581153780221939,
|
|
"num_tokens": 2866216.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.232112693786621,
|
|
"epoch": 0.130011909487892,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999893453303143,
|
|
"loss": 6.2357,
|
|
"mean_token_accuracy": 0.10801640972495079,
|
|
"num_tokens": 2877734.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.268355464935302,
|
|
"epoch": 0.13050813815005954,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999889977320949,
|
|
"loss": 6.2818,
|
|
"mean_token_accuracy": 0.11378113329410552,
|
|
"num_tokens": 2889445.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.1624878406524655,
|
|
"epoch": 0.13100436681222707,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999886445546332,
|
|
"loss": 6.2205,
|
|
"mean_token_accuracy": 0.11409926936030387,
|
|
"num_tokens": 2900485.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.275825309753418,
|
|
"epoch": 0.1315005954743946,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499988285797938,
|
|
"loss": 6.2114,
|
|
"mean_token_accuracy": 0.11664246246218682,
|
|
"num_tokens": 2909795.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.141288185119629,
|
|
"epoch": 0.13199682413656214,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499987921462018,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.12180062383413315,
|
|
"num_tokens": 2920153.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.287366437911987,
|
|
"epoch": 0.13249305279872967,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999875515468825,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.11113621741533279,
|
|
"num_tokens": 2930457.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.224073600769043,
|
|
"epoch": 0.13298928146089717,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999871760525403,
|
|
"loss": 6.2823,
|
|
"mean_token_accuracy": 0.11152325570583344,
|
|
"num_tokens": 2941305.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.289729070663452,
|
|
"epoch": 0.1334855101230647,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999867949790011,
|
|
"loss": 6.2335,
|
|
"mean_token_accuracy": 0.11408303305506706,
|
|
"num_tokens": 2951798.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.166990613937378,
|
|
"epoch": 0.13398173878523223,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999864083262743,
|
|
"loss": 6.1428,
|
|
"mean_token_accuracy": 0.11790908426046372,
|
|
"num_tokens": 2962486.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.169702672958374,
|
|
"epoch": 0.13447796744739976,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999860160943691,
|
|
"loss": 6.2522,
|
|
"mean_token_accuracy": 0.11216171905398369,
|
|
"num_tokens": 2974317.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.180521392822266,
|
|
"epoch": 0.1349741961095673,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999856182832958,
|
|
"loss": 6.1615,
|
|
"mean_token_accuracy": 0.1149752452969551,
|
|
"num_tokens": 2985440.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.191335153579712,
|
|
"epoch": 0.13547042477173482,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999852148930637,
|
|
"loss": 6.2346,
|
|
"mean_token_accuracy": 0.11244972348213196,
|
|
"num_tokens": 2997044.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.225315809249878,
|
|
"epoch": 0.13596665343390235,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999848059236832,
|
|
"loss": 6.2361,
|
|
"mean_token_accuracy": 0.11013163551688195,
|
|
"num_tokens": 3005965.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.126869249343872,
|
|
"epoch": 0.13646288209606988,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999843913751643,
|
|
"loss": 6.1093,
|
|
"mean_token_accuracy": 0.1182452142238617,
|
|
"num_tokens": 3015031.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.22548999786377,
|
|
"epoch": 0.13695911075823738,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999839712475174,
|
|
"loss": 6.1845,
|
|
"mean_token_accuracy": 0.11249931305646896,
|
|
"num_tokens": 3026275.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.159559965133667,
|
|
"epoch": 0.13745533942040492,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999835455407526,
|
|
"loss": 6.2224,
|
|
"mean_token_accuracy": 0.10894647613167763,
|
|
"num_tokens": 3036778.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.311957597732544,
|
|
"epoch": 0.13795156808257245,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999831142548808,
|
|
"loss": 6.3275,
|
|
"mean_token_accuracy": 0.11298574656248092,
|
|
"num_tokens": 3048149.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.224467945098877,
|
|
"epoch": 0.13844779674473998,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999826773899124,
|
|
"loss": 6.1851,
|
|
"mean_token_accuracy": 0.10839088261127472,
|
|
"num_tokens": 3059149.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.21338529586792,
|
|
"epoch": 0.1389440254069075,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999822349458586,
|
|
"loss": 6.1999,
|
|
"mean_token_accuracy": 0.11408259272575379,
|
|
"num_tokens": 3071613.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.2782035827636715,
|
|
"epoch": 0.13944025406907504,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999817869227301,
|
|
"loss": 6.3425,
|
|
"mean_token_accuracy": 0.11115401610732079,
|
|
"num_tokens": 3084742.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.234432363510132,
|
|
"epoch": 0.13993648273124257,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999813333205381,
|
|
"loss": 6.2621,
|
|
"mean_token_accuracy": 0.11374682188034058,
|
|
"num_tokens": 3095356.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.204420900344848,
|
|
"epoch": 0.14043271139341007,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999808741392937,
|
|
"loss": 6.2371,
|
|
"mean_token_accuracy": 0.11067028492689132,
|
|
"num_tokens": 3107717.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.203734874725342,
|
|
"epoch": 0.1409289400555776,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999804093790086,
|
|
"loss": 6.2391,
|
|
"mean_token_accuracy": 0.11028466001152992,
|
|
"num_tokens": 3119205.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.267031717300415,
|
|
"epoch": 0.14142516871774513,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499979939039694,
|
|
"loss": 6.2803,
|
|
"mean_token_accuracy": 0.11363445743918418,
|
|
"num_tokens": 3130564.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.160692358016968,
|
|
"epoch": 0.14192139737991266,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999794631213618,
|
|
"loss": 6.2052,
|
|
"mean_token_accuracy": 0.10955202728509902,
|
|
"num_tokens": 3141883.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.265772008895874,
|
|
"epoch": 0.1424176260420802,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999789816240236,
|
|
"loss": 6.2202,
|
|
"mean_token_accuracy": 0.10992807522416115,
|
|
"num_tokens": 3152817.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.103646850585937,
|
|
"epoch": 0.14291385470424772,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999784945476915,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.11586950048804283,
|
|
"num_tokens": 3163546.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.2015903949737545,
|
|
"epoch": 0.14341008336641525,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999780018923775,
|
|
"loss": 6.1753,
|
|
"mean_token_accuracy": 0.10785740315914154,
|
|
"num_tokens": 3173899.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.085457897186279,
|
|
"epoch": 0.14390631202858278,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999775036580939,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.12055836096405984,
|
|
"num_tokens": 3184433.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.201753950119018,
|
|
"epoch": 0.1444025406907503,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999769998448529,
|
|
"loss": 6.2147,
|
|
"mean_token_accuracy": 0.1092314139008522,
|
|
"num_tokens": 3196077.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.093402910232544,
|
|
"epoch": 0.14489876935291782,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999764904526672,
|
|
"loss": 6.1219,
|
|
"mean_token_accuracy": 0.11739727333188058,
|
|
"num_tokens": 3206645.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.325100088119507,
|
|
"epoch": 0.14539499801508535,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999759754815492,
|
|
"loss": 6.2504,
|
|
"mean_token_accuracy": 0.11532395109534263,
|
|
"num_tokens": 3216786.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.08738226890564,
|
|
"epoch": 0.14589122667725288,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999754549315118,
|
|
"loss": 6.1654,
|
|
"mean_token_accuracy": 0.11355153918266296,
|
|
"num_tokens": 3227384.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.096103143692017,
|
|
"epoch": 0.1463874553394204,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499974928802568,
|
|
"loss": 6.0187,
|
|
"mean_token_accuracy": 0.12060984298586845,
|
|
"num_tokens": 3238800.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.12294373512268,
|
|
"epoch": 0.14688368400158794,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999743970947306,
|
|
"loss": 6.1841,
|
|
"mean_token_accuracy": 0.11260100603103637,
|
|
"num_tokens": 3248627.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.18682632446289,
|
|
"epoch": 0.14737991266375547,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499973859808013,
|
|
"loss": 6.2071,
|
|
"mean_token_accuracy": 0.11222802922129631,
|
|
"num_tokens": 3258989.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.105042552947998,
|
|
"epoch": 0.14787614132592297,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999733169424284,
|
|
"loss": 6.1819,
|
|
"mean_token_accuracy": 0.11515006572008132,
|
|
"num_tokens": 3269474.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.185284376144409,
|
|
"epoch": 0.1483723699880905,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999727684979904,
|
|
"loss": 6.1665,
|
|
"mean_token_accuracy": 0.11946634948253632,
|
|
"num_tokens": 3280453.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.12920880317688,
|
|
"epoch": 0.14886859865025803,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999722144747125,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.11274281144142151,
|
|
"num_tokens": 3290234.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.056111621856689,
|
|
"epoch": 0.14936482731242556,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999716548726085,
|
|
"loss": 6.0829,
|
|
"mean_token_accuracy": 0.12121317386627198,
|
|
"num_tokens": 3300943.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.071580934524536,
|
|
"epoch": 0.1498610559745931,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999710896916921,
|
|
"loss": 6.0445,
|
|
"mean_token_accuracy": 0.12006105631589889,
|
|
"num_tokens": 3311296.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.158681344985962,
|
|
"epoch": 0.15035728463676062,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999705189319774,
|
|
"loss": 6.1927,
|
|
"mean_token_accuracy": 0.11136121302843094,
|
|
"num_tokens": 3322310.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.132280540466309,
|
|
"epoch": 0.15085351329892815,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999699425934788,
|
|
"loss": 6.199,
|
|
"mean_token_accuracy": 0.11201063767075539,
|
|
"num_tokens": 3334176.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.151670312881469,
|
|
"epoch": 0.15134974196109569,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999693606762103,
|
|
"loss": 6.191,
|
|
"mean_token_accuracy": 0.1106182612478733,
|
|
"num_tokens": 3344839.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.192277622222901,
|
|
"epoch": 0.1518459706232632,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999687731801865,
|
|
"loss": 6.1643,
|
|
"mean_token_accuracy": 0.10991204902529716,
|
|
"num_tokens": 3357046.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.178088712692261,
|
|
"epoch": 0.15234219928543072,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999681801054217,
|
|
"loss": 6.2417,
|
|
"mean_token_accuracy": 0.11275468468666076,
|
|
"num_tokens": 3367783.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.12720513343811,
|
|
"epoch": 0.15283842794759825,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499967581451931,
|
|
"loss": 6.0922,
|
|
"mean_token_accuracy": 0.11282803192734718,
|
|
"num_tokens": 3378529.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.151979255676269,
|
|
"epoch": 0.15333465660976578,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499966977219729,
|
|
"loss": 6.3069,
|
|
"mean_token_accuracy": 0.11132591888308525,
|
|
"num_tokens": 3389318.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.220948696136475,
|
|
"epoch": 0.1538308852719333,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999663674088306,
|
|
"loss": 6.2832,
|
|
"mean_token_accuracy": 0.10738798677921295,
|
|
"num_tokens": 3400603.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.218557453155517,
|
|
"epoch": 0.15432711393410084,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999657520192511,
|
|
"loss": 6.1828,
|
|
"mean_token_accuracy": 0.11249059960246086,
|
|
"num_tokens": 3410316.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.169131898880005,
|
|
"epoch": 0.15482334259626837,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999651310510058,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.11865686550736428,
|
|
"num_tokens": 3422155.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.150794935226441,
|
|
"epoch": 0.15531957125843587,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999645045041099,
|
|
"loss": 6.0594,
|
|
"mean_token_accuracy": 0.11627922058105469,
|
|
"num_tokens": 3432892.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.084249019622803,
|
|
"epoch": 0.1558157999206034,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999638723785791,
|
|
"loss": 6.1906,
|
|
"mean_token_accuracy": 0.11545449271798133,
|
|
"num_tokens": 3443967.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.1172302722930905,
|
|
"epoch": 0.15631202858277093,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499963234674429,
|
|
"loss": 6.0819,
|
|
"mean_token_accuracy": 0.11921455487608909,
|
|
"num_tokens": 3454354.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.014755821228027,
|
|
"epoch": 0.15680825724493846,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999625913916754,
|
|
"loss": 6.1041,
|
|
"mean_token_accuracy": 0.11667904406785964,
|
|
"num_tokens": 3465232.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.060571384429932,
|
|
"epoch": 0.157304485907106,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999619425303343,
|
|
"loss": 6.0632,
|
|
"mean_token_accuracy": 0.1209244854748249,
|
|
"num_tokens": 3475443.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.218507719039917,
|
|
"epoch": 0.15780071456927353,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999612880904219,
|
|
"loss": 6.1082,
|
|
"mean_token_accuracy": 0.11613842472434044,
|
|
"num_tokens": 3486643.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.101606178283691,
|
|
"epoch": 0.15829694323144106,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999606280719542,
|
|
"loss": 6.1576,
|
|
"mean_token_accuracy": 0.11357915550470352,
|
|
"num_tokens": 3497557.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.210038471221924,
|
|
"epoch": 0.1587931718936086,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999599624749475,
|
|
"loss": 6.1679,
|
|
"mean_token_accuracy": 0.11308549344539642,
|
|
"num_tokens": 3509790.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.055289936065674,
|
|
"epoch": 0.1592894005557761,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999592912994187,
|
|
"loss": 6.0736,
|
|
"mean_token_accuracy": 0.11441607624292374,
|
|
"num_tokens": 3521577.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.174909019470215,
|
|
"epoch": 0.15978562921794362,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999586145453842,
|
|
"loss": 6.1138,
|
|
"mean_token_accuracy": 0.11273565515875816,
|
|
"num_tokens": 3532126.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.93880524635315,
|
|
"epoch": 0.16028185788011115,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999579322128608,
|
|
"loss": 5.9598,
|
|
"mean_token_accuracy": 0.11700184866786004,
|
|
"num_tokens": 3542560.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.074759674072266,
|
|
"epoch": 0.16077808654227868,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999572443018654,
|
|
"loss": 6.1226,
|
|
"mean_token_accuracy": 0.11485312059521675,
|
|
"num_tokens": 3553863.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.075677394866943,
|
|
"epoch": 0.1612743152044462,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999565508124151,
|
|
"loss": 6.1502,
|
|
"mean_token_accuracy": 0.11331931576132774,
|
|
"num_tokens": 3564953.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.152407836914063,
|
|
"epoch": 0.16177054386661374,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499955851744527,
|
|
"loss": 6.1374,
|
|
"mean_token_accuracy": 0.11724982708692551,
|
|
"num_tokens": 3576247.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.17358717918396,
|
|
"epoch": 0.16226677252878127,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999551470982185,
|
|
"loss": 6.1659,
|
|
"mean_token_accuracy": 0.11510409265756608,
|
|
"num_tokens": 3587600.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.192458963394165,
|
|
"epoch": 0.1627630011909488,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999544368735073,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.11837180629372597,
|
|
"num_tokens": 3597727.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.070228481292725,
|
|
"epoch": 0.1632592298531163,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999537210704106,
|
|
"loss": 6.1294,
|
|
"mean_token_accuracy": 0.11915965527296066,
|
|
"num_tokens": 3608066.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.137539434432983,
|
|
"epoch": 0.16375545851528384,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999529996889463,
|
|
"loss": 6.1911,
|
|
"mean_token_accuracy": 0.11308414563536644,
|
|
"num_tokens": 3618263.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.156264162063598,
|
|
"epoch": 0.16425168717745137,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999522727291325,
|
|
"loss": 6.1235,
|
|
"mean_token_accuracy": 0.12028616815805435,
|
|
"num_tokens": 3629465.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.114594221115112,
|
|
"epoch": 0.1647479158396189,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499951540190987,
|
|
"loss": 6.1439,
|
|
"mean_token_accuracy": 0.11190734803676605,
|
|
"num_tokens": 3639657.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.203351068496704,
|
|
"epoch": 0.16524414450178643,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999508020745281,
|
|
"loss": 6.1155,
|
|
"mean_token_accuracy": 0.11490047574043274,
|
|
"num_tokens": 3652374.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.061782884597778,
|
|
"epoch": 0.16574037316395396,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999500583797739,
|
|
"loss": 6.0897,
|
|
"mean_token_accuracy": 0.1153049759566784,
|
|
"num_tokens": 3664083.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.046120309829712,
|
|
"epoch": 0.1662366018261215,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999493091067431,
|
|
"loss": 6.1311,
|
|
"mean_token_accuracy": 0.12204677686095237,
|
|
"num_tokens": 3675314.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.110049533843994,
|
|
"epoch": 0.166732830488289,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999485542554541,
|
|
"loss": 6.0837,
|
|
"mean_token_accuracy": 0.10843433886766433,
|
|
"num_tokens": 3686019.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.155540800094604,
|
|
"epoch": 0.16722905915045652,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999477938259256,
|
|
"loss": 6.1827,
|
|
"mean_token_accuracy": 0.11403719708323479,
|
|
"num_tokens": 3698170.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.084233188629151,
|
|
"epoch": 0.16772528781262405,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999470278181766,
|
|
"loss": 6.1775,
|
|
"mean_token_accuracy": 0.11221502125263214,
|
|
"num_tokens": 3709243.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.14380407333374,
|
|
"epoch": 0.16822151647479158,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999462562322261,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.11952908337116241,
|
|
"num_tokens": 3720196.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.120664167404175,
|
|
"epoch": 0.1687177451369591,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499945479068093,
|
|
"loss": 6.1849,
|
|
"mean_token_accuracy": 0.1177287794649601,
|
|
"num_tokens": 3732714.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.192463541030884,
|
|
"epoch": 0.16921397379912664,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004999446963257969,
|
|
"loss": 6.164,
|
|
"mean_token_accuracy": 0.1093910776078701,
|
|
"num_tokens": 3746474.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.031261873245239,
|
|
"epoch": 0.16971020246129417,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999439080053571,
|
|
"loss": 6.0267,
|
|
"mean_token_accuracy": 0.12488168627023696,
|
|
"num_tokens": 3757528.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.242232370376587,
|
|
"epoch": 0.1702064311234617,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999431141067928,
|
|
"loss": 6.1591,
|
|
"mean_token_accuracy": 0.11146312952041626,
|
|
"num_tokens": 3768360.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.0257631778717045,
|
|
"epoch": 0.1707026597856292,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999423146301242,
|
|
"loss": 6.0367,
|
|
"mean_token_accuracy": 0.1159180223941803,
|
|
"num_tokens": 3779809.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.9951259136199955,
|
|
"epoch": 0.17119888844779674,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999415095753709,
|
|
"loss": 6.0272,
|
|
"mean_token_accuracy": 0.11418144479393959,
|
|
"num_tokens": 3791455.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.083953142166138,
|
|
"epoch": 0.17169511710996427,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999406989425527,
|
|
"loss": 6.0646,
|
|
"mean_token_accuracy": 0.11992244198918342,
|
|
"num_tokens": 3803209.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.023218822479248,
|
|
"epoch": 0.1721913457721318,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999398827316901,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.11768920570611954,
|
|
"num_tokens": 3813553.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.128506755828857,
|
|
"epoch": 0.17268757443429933,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499939060942803,
|
|
"loss": 6.1466,
|
|
"mean_token_accuracy": 0.11251909062266349,
|
|
"num_tokens": 3824856.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.2042152881622314,
|
|
"epoch": 0.17318380309646686,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999382335759119,
|
|
"loss": 6.2169,
|
|
"mean_token_accuracy": 0.11170056387782097,
|
|
"num_tokens": 3835489.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.1185472965240475,
|
|
"epoch": 0.1736800317586344,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999374006310372,
|
|
"loss": 6.0584,
|
|
"mean_token_accuracy": 0.11355099081993103,
|
|
"num_tokens": 3844838.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.984942770004272,
|
|
"epoch": 0.1741762604208019,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999365621081999,
|
|
"loss": 6.02,
|
|
"mean_token_accuracy": 0.11664588525891303,
|
|
"num_tokens": 3855288.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.108725595474243,
|
|
"epoch": 0.17467248908296942,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999357180074204,
|
|
"loss": 6.065,
|
|
"mean_token_accuracy": 0.12154223769903183,
|
|
"num_tokens": 3865585.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.077434921264649,
|
|
"epoch": 0.17516871774513695,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999348683287199,
|
|
"loss": 6.0586,
|
|
"mean_token_accuracy": 0.11305517330765724,
|
|
"num_tokens": 3877694.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.053066635131836,
|
|
"epoch": 0.17566494640730448,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999340130721192,
|
|
"loss": 6.0273,
|
|
"mean_token_accuracy": 0.12292965203523636,
|
|
"num_tokens": 3888802.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.994657707214356,
|
|
"epoch": 0.17616117506947201,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999331522376396,
|
|
"loss": 5.9963,
|
|
"mean_token_accuracy": 0.11429235264658928,
|
|
"num_tokens": 3900294.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.0335695266723635,
|
|
"epoch": 0.17665740373163955,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999322858253027,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.11919704973697662,
|
|
"num_tokens": 3910865.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.024723052978516,
|
|
"epoch": 0.17715363239380708,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999314138351297,
|
|
"loss": 6.0896,
|
|
"mean_token_accuracy": 0.11677447333931923,
|
|
"num_tokens": 3921960.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.130808353424072,
|
|
"epoch": 0.1776498610559746,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999305362671424,
|
|
"loss": 6.1007,
|
|
"mean_token_accuracy": 0.11497491449117661,
|
|
"num_tokens": 3934085.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.012696743011475,
|
|
"epoch": 0.1781460897181421,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999296531213624,
|
|
"loss": 5.9399,
|
|
"mean_token_accuracy": 0.12995768636465072,
|
|
"num_tokens": 3944532.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.986821126937866,
|
|
"epoch": 0.17864231838030964,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999287643978117,
|
|
"loss": 5.9797,
|
|
"mean_token_accuracy": 0.1237669236958027,
|
|
"num_tokens": 3954995.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.993027114868164,
|
|
"epoch": 0.17913854704247717,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999278700965124,
|
|
"loss": 6.0469,
|
|
"mean_token_accuracy": 0.1215439960360527,
|
|
"num_tokens": 3966621.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.133916234970092,
|
|
"epoch": 0.1796347757046447,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999269702174866,
|
|
"loss": 6.1153,
|
|
"mean_token_accuracy": 0.11664739549160004,
|
|
"num_tokens": 3977568.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.023658990859985,
|
|
"epoch": 0.18013100436681223,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999260647607565,
|
|
"loss": 6.1244,
|
|
"mean_token_accuracy": 0.11225999146699905,
|
|
"num_tokens": 3988571.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.082444190979004,
|
|
"epoch": 0.18062723302897976,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999251537263448,
|
|
"loss": 5.9453,
|
|
"mean_token_accuracy": 0.12557341828942298,
|
|
"num_tokens": 3998380.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.99331431388855,
|
|
"epoch": 0.1811234616911473,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999242371142739,
|
|
"loss": 6.1229,
|
|
"mean_token_accuracy": 0.11956584751605988,
|
|
"num_tokens": 4010017.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.134469366073608,
|
|
"epoch": 0.1816196903533148,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999233149245665,
|
|
"loss": 6.0949,
|
|
"mean_token_accuracy": 0.11493808627128602,
|
|
"num_tokens": 4020922.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.083890724182129,
|
|
"epoch": 0.18211591901548232,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999223871572456,
|
|
"loss": 6.0705,
|
|
"mean_token_accuracy": 0.11875133067369462,
|
|
"num_tokens": 4030927.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.0421332836151125,
|
|
"epoch": 0.18261214767764986,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999214538123342,
|
|
"loss": 6.1447,
|
|
"mean_token_accuracy": 0.11264287009835243,
|
|
"num_tokens": 4041375.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.1017091274261475,
|
|
"epoch": 0.18310837633981739,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999205148898554,
|
|
"loss": 6.137,
|
|
"mean_token_accuracy": 0.11522981524467468,
|
|
"num_tokens": 4053213.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.06529393196106,
|
|
"epoch": 0.18360460500198492,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999195703898325,
|
|
"loss": 5.9823,
|
|
"mean_token_accuracy": 0.12415849640965462,
|
|
"num_tokens": 4064536.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.056224679946899,
|
|
"epoch": 0.18410083366415245,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999186203122889,
|
|
"loss": 6.0555,
|
|
"mean_token_accuracy": 0.12177475914359093,
|
|
"num_tokens": 4075282.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.956262111663818,
|
|
"epoch": 0.18459706232631998,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999176646572482,
|
|
"loss": 6.0447,
|
|
"mean_token_accuracy": 0.12330468744039536,
|
|
"num_tokens": 4085501.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.081436061859131,
|
|
"epoch": 0.1850932909884875,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499916703424734,
|
|
"loss": 6.0013,
|
|
"mean_token_accuracy": 0.11329571008682252,
|
|
"num_tokens": 4095697.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.003993368148803,
|
|
"epoch": 0.185589519650655,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999157366147702,
|
|
"loss": 6.0672,
|
|
"mean_token_accuracy": 0.11597673147916794,
|
|
"num_tokens": 4106459.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.079233932495117,
|
|
"epoch": 0.18608574831282254,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999147642273809,
|
|
"loss": 5.991,
|
|
"mean_token_accuracy": 0.12156878933310508,
|
|
"num_tokens": 4118320.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.973481559753418,
|
|
"epoch": 0.18658197697499007,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049991378626259,
|
|
"loss": 6.0224,
|
|
"mean_token_accuracy": 0.12918237894773482,
|
|
"num_tokens": 4131249.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.072328758239746,
|
|
"epoch": 0.1870782056371576,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999128027204219,
|
|
"loss": 6.0921,
|
|
"mean_token_accuracy": 0.11764958873391151,
|
|
"num_tokens": 4141480.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.080035591125489,
|
|
"epoch": 0.18757443429932513,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499911813600901,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.11640222296118737,
|
|
"num_tokens": 4152344.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.137289190292359,
|
|
"epoch": 0.18807066296149266,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999108189040516,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.11466791629791259,
|
|
"num_tokens": 4164772.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.027769136428833,
|
|
"epoch": 0.1885668916236602,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999098186298986,
|
|
"loss": 6.0443,
|
|
"mean_token_accuracy": 0.11440513208508492,
|
|
"num_tokens": 4175511.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.023436784744263,
|
|
"epoch": 0.1890631202858277,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999088127784667,
|
|
"loss": 6.0164,
|
|
"mean_token_accuracy": 0.11896950975060464,
|
|
"num_tokens": 4187445.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.051607608795166,
|
|
"epoch": 0.18955934894799523,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499907801349781,
|
|
"loss": 5.9987,
|
|
"mean_token_accuracy": 0.11835644766688347,
|
|
"num_tokens": 4198124.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.978174209594727,
|
|
"epoch": 0.19005557761016276,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999067843438664,
|
|
"loss": 6.047,
|
|
"mean_token_accuracy": 0.11988429352641106,
|
|
"num_tokens": 4208954.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.129126739501953,
|
|
"epoch": 0.1905518062723303,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999057617607482,
|
|
"loss": 6.1052,
|
|
"mean_token_accuracy": 0.11723098531365395,
|
|
"num_tokens": 4218896.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.979246139526367,
|
|
"epoch": 0.19104803493449782,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999047336004517,
|
|
"loss": 6.0138,
|
|
"mean_token_accuracy": 0.11616118773818015,
|
|
"num_tokens": 4228851.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.985688304901123,
|
|
"epoch": 0.19154426359666535,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999036998630024,
|
|
"loss": 5.977,
|
|
"mean_token_accuracy": 0.11649016365408897,
|
|
"num_tokens": 4240377.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.950987052917481,
|
|
"epoch": 0.19204049225883288,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499902660548426,
|
|
"loss": 5.9542,
|
|
"mean_token_accuracy": 0.1181262455880642,
|
|
"num_tokens": 4251341.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.056128025054932,
|
|
"epoch": 0.1925367209210004,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999016156567482,
|
|
"loss": 6.0579,
|
|
"mean_token_accuracy": 0.11999004855751991,
|
|
"num_tokens": 4261206.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.091788625717163,
|
|
"epoch": 0.1930329495831679,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499900565187995,
|
|
"loss": 6.0659,
|
|
"mean_token_accuracy": 0.11197969540953637,
|
|
"num_tokens": 4272662.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.060900783538818,
|
|
"epoch": 0.19352917824533544,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998995091421924,
|
|
"loss": 6.0496,
|
|
"mean_token_accuracy": 0.11381187662482262,
|
|
"num_tokens": 4283302.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.977718019485474,
|
|
"epoch": 0.19402540690750297,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998984475193665,
|
|
"loss": 5.9944,
|
|
"mean_token_accuracy": 0.11904016137123108,
|
|
"num_tokens": 4296087.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.980944347381592,
|
|
"epoch": 0.1945216355696705,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998973803195439,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.12316826283931732,
|
|
"num_tokens": 4305918.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.02653398513794,
|
|
"epoch": 0.19501786423183803,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998963075427508,
|
|
"loss": 6.073,
|
|
"mean_token_accuracy": 0.11951372250914574,
|
|
"num_tokens": 4316507.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.028897380828857,
|
|
"epoch": 0.19551409289400556,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998952291890138,
|
|
"loss": 6.004,
|
|
"mean_token_accuracy": 0.12352709099650383,
|
|
"num_tokens": 4329091.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.0670671463012695,
|
|
"epoch": 0.1960103215561731,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998941452583599,
|
|
"loss": 6.0668,
|
|
"mean_token_accuracy": 0.1214105449616909,
|
|
"num_tokens": 4339266.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.959065103530884,
|
|
"epoch": 0.1965065502183406,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998930557508156,
|
|
"loss": 5.9759,
|
|
"mean_token_accuracy": 0.1258009724318981,
|
|
"num_tokens": 4349300.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.941859292984009,
|
|
"epoch": 0.19700277888050813,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998919606664082,
|
|
"loss": 5.9055,
|
|
"mean_token_accuracy": 0.12807131931185722,
|
|
"num_tokens": 4360314.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.043554306030273,
|
|
"epoch": 0.19749900754267566,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998908600051648,
|
|
"loss": 5.9557,
|
|
"mean_token_accuracy": 0.12293901592493058,
|
|
"num_tokens": 4370077.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.936801719665527,
|
|
"epoch": 0.1979952362048432,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998897537671126,
|
|
"loss": 5.9691,
|
|
"mean_token_accuracy": 0.11986607536673546,
|
|
"num_tokens": 4381000.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.05441517829895,
|
|
"epoch": 0.19849146486701072,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998886419522792,
|
|
"loss": 6.183,
|
|
"mean_token_accuracy": 0.11007200106978417,
|
|
"num_tokens": 4393485.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.172304725646972,
|
|
"epoch": 0.19898769352917825,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998875245606919,
|
|
"loss": 6.0252,
|
|
"mean_token_accuracy": 0.12070057019591332,
|
|
"num_tokens": 4404354.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.957334184646607,
|
|
"epoch": 0.19948392219134578,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998864015923788,
|
|
"loss": 6.1616,
|
|
"mean_token_accuracy": 0.11959527060389519,
|
|
"num_tokens": 4414818.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.080641794204712,
|
|
"epoch": 0.1999801508535133,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998852730473674,
|
|
"loss": 6.0419,
|
|
"mean_token_accuracy": 0.11496741399168968,
|
|
"num_tokens": 4426271.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.992073965072632,
|
|
"epoch": 0.2004763795156808,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998841389256859,
|
|
"loss": 6.0961,
|
|
"mean_token_accuracy": 0.11873921528458595,
|
|
"num_tokens": 4436981.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.966401863098144,
|
|
"epoch": 0.20097260817784834,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998829992273622,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.12690763026475907,
|
|
"num_tokens": 4446494.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.971911811828614,
|
|
"epoch": 0.20146883684001587,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998818539524248,
|
|
"loss": 6.0038,
|
|
"mean_token_accuracy": 0.12495953813195229,
|
|
"num_tokens": 4458535.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.010282945632935,
|
|
"epoch": 0.2019650655021834,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499880703100902,
|
|
"loss": 5.9931,
|
|
"mean_token_accuracy": 0.12273974418640136,
|
|
"num_tokens": 4469025.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.0635312557220455,
|
|
"epoch": 0.20246129416435094,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998795466728223,
|
|
"loss": 5.9801,
|
|
"mean_token_accuracy": 0.12161237373948097,
|
|
"num_tokens": 4478431.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.947754192352295,
|
|
"epoch": 0.20295752282651847,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998783846682144,
|
|
"loss": 6.1296,
|
|
"mean_token_accuracy": 0.11572149395942688,
|
|
"num_tokens": 4490215.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.041604042053223,
|
|
"epoch": 0.203453751488686,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998772170871072,
|
|
"loss": 5.9895,
|
|
"mean_token_accuracy": 0.12096533477306366,
|
|
"num_tokens": 4502895.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.9692402362823485,
|
|
"epoch": 0.20394998015085353,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998760439295295,
|
|
"loss": 6.0113,
|
|
"mean_token_accuracy": 0.1204931080341339,
|
|
"num_tokens": 4514468.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.084046506881714,
|
|
"epoch": 0.20444620881302103,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998748651955105,
|
|
"loss": 6.0317,
|
|
"mean_token_accuracy": 0.12071766927838326,
|
|
"num_tokens": 4525787.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.992368078231811,
|
|
"epoch": 0.20494243747518856,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998736808850795,
|
|
"loss": 6.1181,
|
|
"mean_token_accuracy": 0.11842440962791442,
|
|
"num_tokens": 4537536.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.07518572807312,
|
|
"epoch": 0.2054386661373561,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998724909982656,
|
|
"loss": 6.0545,
|
|
"mean_token_accuracy": 0.12233483120799064,
|
|
"num_tokens": 4549619.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.984462881088257,
|
|
"epoch": 0.20593489479952362,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998712955350986,
|
|
"loss": 5.9774,
|
|
"mean_token_accuracy": 0.12310493364930153,
|
|
"num_tokens": 4560248.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.027503871917725,
|
|
"epoch": 0.20643112346169115,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998700944956081,
|
|
"loss": 6.0827,
|
|
"mean_token_accuracy": 0.1216159887611866,
|
|
"num_tokens": 4571888.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.05411696434021,
|
|
"epoch": 0.20692735212385868,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998688878798237,
|
|
"loss": 5.9395,
|
|
"mean_token_accuracy": 0.12731964141130447,
|
|
"num_tokens": 4583234.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.018948078155518,
|
|
"epoch": 0.2074235807860262,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998676756877753,
|
|
"loss": 6.1471,
|
|
"mean_token_accuracy": 0.11580592915415763,
|
|
"num_tokens": 4595252.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.987044811248779,
|
|
"epoch": 0.20791980944819372,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998664579194934,
|
|
"loss": 5.9279,
|
|
"mean_token_accuracy": 0.12194859310984611,
|
|
"num_tokens": 4607091.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.006628370285034,
|
|
"epoch": 0.20841603811036125,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998652345750077,
|
|
"loss": 5.8925,
|
|
"mean_token_accuracy": 0.12444933280348777,
|
|
"num_tokens": 4618003.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.890622520446778,
|
|
"epoch": 0.20891226677252878,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998640056543487,
|
|
"loss": 5.9063,
|
|
"mean_token_accuracy": 0.12009405642747879,
|
|
"num_tokens": 4628429.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.005721569061279,
|
|
"epoch": 0.2094084954346963,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998627711575469,
|
|
"loss": 5.9697,
|
|
"mean_token_accuracy": 0.1252060741186142,
|
|
"num_tokens": 4639414.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.956946802139282,
|
|
"epoch": 0.20990472409686384,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000499861531084633,
|
|
"loss": 6.0677,
|
|
"mean_token_accuracy": 0.11779648587107658,
|
|
"num_tokens": 4652594.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.9904883861541744,
|
|
"epoch": 0.21040095275903137,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998602854356376,
|
|
"loss": 5.8914,
|
|
"mean_token_accuracy": 0.1240698166191578,
|
|
"num_tokens": 4662981.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.9469305038452145,
|
|
"epoch": 0.2108971814211989,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998590342105917,
|
|
"loss": 5.9822,
|
|
"mean_token_accuracy": 0.1197172798216343,
|
|
"num_tokens": 4672469.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.015959167480469,
|
|
"epoch": 0.21139341008336643,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998577774095262,
|
|
"loss": 5.9782,
|
|
"mean_token_accuracy": 0.12201139032840728,
|
|
"num_tokens": 4683640.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.936978530883789,
|
|
"epoch": 0.21188963874553393,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998565150324724,
|
|
"loss": 5.9337,
|
|
"mean_token_accuracy": 0.1305203281342983,
|
|
"num_tokens": 4694032.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.874231004714966,
|
|
"epoch": 0.21238586740770146,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998552470794616,
|
|
"loss": 5.8023,
|
|
"mean_token_accuracy": 0.13009038046002389,
|
|
"num_tokens": 4704253.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.9205982208251955,
|
|
"epoch": 0.212882096069869,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998539735505251,
|
|
"loss": 5.9636,
|
|
"mean_token_accuracy": 0.11889011636376381,
|
|
"num_tokens": 4715327.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.089485359191895,
|
|
"epoch": 0.21337832473203652,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998526944456946,
|
|
"loss": 5.983,
|
|
"mean_token_accuracy": 0.11755810230970383,
|
|
"num_tokens": 4726450.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.928031587600708,
|
|
"epoch": 0.21387455339420405,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998514097650018,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.11683928668498993,
|
|
"num_tokens": 4736630.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.01918659210205,
|
|
"epoch": 0.21437078205637158,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998501195084786,
|
|
"loss": 5.8827,
|
|
"mean_token_accuracy": 0.1218169391155243,
|
|
"num_tokens": 4746592.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.958590841293335,
|
|
"epoch": 0.21486701071853911,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998488236761569,
|
|
"loss": 6.0581,
|
|
"mean_token_accuracy": 0.12610213384032248,
|
|
"num_tokens": 4757824.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.0240240573883055,
|
|
"epoch": 0.21536323938070662,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998475222680688,
|
|
"loss": 6.0016,
|
|
"mean_token_accuracy": 0.12206201553344727,
|
|
"num_tokens": 4768453.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.921792268753052,
|
|
"epoch": 0.21585946804287415,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998462152842468,
|
|
"loss": 5.9871,
|
|
"mean_token_accuracy": 0.11648527160286903,
|
|
"num_tokens": 4779664.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.0779510021209715,
|
|
"epoch": 0.21635569670504168,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499844902724723,
|
|
"loss": 6.0067,
|
|
"mean_token_accuracy": 0.12150592878460884,
|
|
"num_tokens": 4791012.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.887479829788208,
|
|
"epoch": 0.2168519253672092,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998435845895302,
|
|
"loss": 5.8636,
|
|
"mean_token_accuracy": 0.12329262644052505,
|
|
"num_tokens": 4800578.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.983295154571533,
|
|
"epoch": 0.21734815402937674,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499842260878701,
|
|
"loss": 5.8861,
|
|
"mean_token_accuracy": 0.12191555723547935,
|
|
"num_tokens": 4810940.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.002044200897217,
|
|
"epoch": 0.21784438269154427,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004998409315922683,
|
|
"loss": 6.0268,
|
|
"mean_token_accuracy": 0.1215096190571785,
|
|
"num_tokens": 4822696.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.937045526504517,
|
|
"epoch": 0.2183406113537118,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998395967302649,
|
|
"loss": 5.8976,
|
|
"mean_token_accuracy": 0.12619130909442902,
|
|
"num_tokens": 4833669.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.046645832061768,
|
|
"epoch": 0.21883684001587933,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499838256292724,
|
|
"loss": 6.0795,
|
|
"mean_token_accuracy": 0.12037609070539475,
|
|
"num_tokens": 4844021.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.948421573638916,
|
|
"epoch": 0.21933306867804683,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998369102796787,
|
|
"loss": 5.9532,
|
|
"mean_token_accuracy": 0.12263412401080132,
|
|
"num_tokens": 4855336.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.974256610870361,
|
|
"epoch": 0.21982929734021436,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004998355586911627,
|
|
"loss": 5.9506,
|
|
"mean_token_accuracy": 0.12540801763534545,
|
|
"num_tokens": 4867713.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.975857448577881,
|
|
"epoch": 0.2203255260023819,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998342015272093,
|
|
"loss": 5.9332,
|
|
"mean_token_accuracy": 0.12420732304453849,
|
|
"num_tokens": 4879134.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.003203201293945,
|
|
"epoch": 0.22082175466454942,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998328387878521,
|
|
"loss": 6.09,
|
|
"mean_token_accuracy": 0.11976692378520966,
|
|
"num_tokens": 4891755.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.1218338966369625,
|
|
"epoch": 0.22131798332671695,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998314704731249,
|
|
"loss": 6.0927,
|
|
"mean_token_accuracy": 0.1174064464867115,
|
|
"num_tokens": 4903264.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.947536039352417,
|
|
"epoch": 0.22181421198888449,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998300965830618,
|
|
"loss": 5.9105,
|
|
"mean_token_accuracy": 0.12291811779141426,
|
|
"num_tokens": 4912533.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.84995813369751,
|
|
"epoch": 0.22231044065105202,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998287171176968,
|
|
"loss": 5.9169,
|
|
"mean_token_accuracy": 0.12699113339185714,
|
|
"num_tokens": 4923288.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.968135643005371,
|
|
"epoch": 0.22280666931321952,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998273320770641,
|
|
"loss": 5.9355,
|
|
"mean_token_accuracy": 0.12369446530938148,
|
|
"num_tokens": 4934759.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.942650651931762,
|
|
"epoch": 0.22330289797538705,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499825941461198,
|
|
"loss": 5.9819,
|
|
"mean_token_accuracy": 0.12287837192416191,
|
|
"num_tokens": 4947024.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.953667020797729,
|
|
"epoch": 0.22379912663755458,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998245452701329,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.12497033029794694,
|
|
"num_tokens": 4959281.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.01146445274353,
|
|
"epoch": 0.2242953552997221,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998231435039036,
|
|
"loss": 5.9817,
|
|
"mean_token_accuracy": 0.11844518184661865,
|
|
"num_tokens": 4970466.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.9487926959991455,
|
|
"epoch": 0.22479158396188964,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998217361625449,
|
|
"loss": 5.9227,
|
|
"mean_token_accuracy": 0.12402417287230491,
|
|
"num_tokens": 4981135.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.973719263076783,
|
|
"epoch": 0.22528781262405717,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998203232460915,
|
|
"loss": 5.9895,
|
|
"mean_token_accuracy": 0.1295408844947815,
|
|
"num_tokens": 4991292.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.957491159439087,
|
|
"epoch": 0.2257840412862247,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998189047545785,
|
|
"loss": 5.9457,
|
|
"mean_token_accuracy": 0.12670203521847725,
|
|
"num_tokens": 5002806.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.917588376998902,
|
|
"epoch": 0.22628026994839223,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998174806880411,
|
|
"loss": 5.8916,
|
|
"mean_token_accuracy": 0.13011438325047492,
|
|
"num_tokens": 5013474.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.979103899002075,
|
|
"epoch": 0.22677649861055973,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998160510465146,
|
|
"loss": 5.934,
|
|
"mean_token_accuracy": 0.12663510590791702,
|
|
"num_tokens": 5025151.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.858231687545777,
|
|
"epoch": 0.22727272727272727,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998146158300345,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.12440521046519279,
|
|
"num_tokens": 5037166.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.016402339935302,
|
|
"epoch": 0.2277689559348948,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998131750386364,
|
|
"loss": 5.972,
|
|
"mean_token_accuracy": 0.12612202540040016,
|
|
"num_tokens": 5047452.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.914637041091919,
|
|
"epoch": 0.22826518459706233,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998117286723559,
|
|
"loss": 5.9791,
|
|
"mean_token_accuracy": 0.11908696666359901,
|
|
"num_tokens": 5058501.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.990808296203613,
|
|
"epoch": 0.22876141325922986,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499810276731229,
|
|
"loss": 5.9825,
|
|
"mean_token_accuracy": 0.12161915823817253,
|
|
"num_tokens": 5069716.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.073873853683471,
|
|
"epoch": 0.2292576419213974,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998088192152918,
|
|
"loss": 5.9592,
|
|
"mean_token_accuracy": 0.1198742963373661,
|
|
"num_tokens": 5078509.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.910210466384887,
|
|
"epoch": 0.22975387058356492,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998073561245801,
|
|
"loss": 6.011,
|
|
"mean_token_accuracy": 0.12116109505295754,
|
|
"num_tokens": 5090355.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.0268512725830075,
|
|
"epoch": 0.23025009924573242,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998058874591305,
|
|
"loss": 5.8952,
|
|
"mean_token_accuracy": 0.1269051119685173,
|
|
"num_tokens": 5100582.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.97053108215332,
|
|
"epoch": 0.23074632790789995,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004998044132189793,
|
|
"loss": 5.9553,
|
|
"mean_token_accuracy": 0.12131153792142868,
|
|
"num_tokens": 5112176.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.976939296722412,
|
|
"epoch": 0.23124255657006748,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499802933404163,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.12292413413524628,
|
|
"num_tokens": 5122840.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.9486147403717045,
|
|
"epoch": 0.231738785232235,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998014480147183,
|
|
"loss": 5.88,
|
|
"mean_token_accuracy": 0.1311016447842121,
|
|
"num_tokens": 5132926.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.891398763656616,
|
|
"epoch": 0.23223501389440254,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997999570506823,
|
|
"loss": 5.8679,
|
|
"mean_token_accuracy": 0.12510914131999015,
|
|
"num_tokens": 5143394.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.880256605148316,
|
|
"epoch": 0.23273124255657007,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997984605120917,
|
|
"loss": 5.8867,
|
|
"mean_token_accuracy": 0.1238784983754158,
|
|
"num_tokens": 5155710.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.813053321838379,
|
|
"epoch": 0.2332274712187376,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997969583989835,
|
|
"loss": 5.8256,
|
|
"mean_token_accuracy": 0.12075290903449058,
|
|
"num_tokens": 5167065.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.918558645248413,
|
|
"epoch": 0.23372369988090513,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997954507113952,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.1209035113453865,
|
|
"num_tokens": 5177535.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.928993511199951,
|
|
"epoch": 0.23421992854307264,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997939374493642,
|
|
"loss": 5.8424,
|
|
"mean_token_accuracy": 0.12632499486207963,
|
|
"num_tokens": 5188324.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.843468523025512,
|
|
"epoch": 0.23471615720524017,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499792418612928,
|
|
"loss": 5.9191,
|
|
"mean_token_accuracy": 0.12788572460412978,
|
|
"num_tokens": 5199223.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.968633937835693,
|
|
"epoch": 0.2352123858674077,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997908942021241,
|
|
"loss": 5.9036,
|
|
"mean_token_accuracy": 0.12390781864523888,
|
|
"num_tokens": 5210080.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.974946546554565,
|
|
"epoch": 0.23570861452957523,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997893642169904,
|
|
"loss": 6.0327,
|
|
"mean_token_accuracy": 0.12202257290482521,
|
|
"num_tokens": 5220867.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.952085304260254,
|
|
"epoch": 0.23620484319174276,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997878286575648,
|
|
"loss": 5.8665,
|
|
"mean_token_accuracy": 0.1263822741806507,
|
|
"num_tokens": 5231451.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.933335781097412,
|
|
"epoch": 0.2367010718539103,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997862875238855,
|
|
"loss": 5.9826,
|
|
"mean_token_accuracy": 0.11929206326603889,
|
|
"num_tokens": 5244643.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.931532573699951,
|
|
"epoch": 0.23719730051607782,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997847408159907,
|
|
"loss": 5.9823,
|
|
"mean_token_accuracy": 0.11998239532113075,
|
|
"num_tokens": 5256279.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.0057477951049805,
|
|
"epoch": 0.23769352917824532,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997831885339186,
|
|
"loss": 5.9682,
|
|
"mean_token_accuracy": 0.12426605671644211,
|
|
"num_tokens": 5268498.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.878379583358765,
|
|
"epoch": 0.23818975784041285,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997816306777077,
|
|
"loss": 5.9211,
|
|
"mean_token_accuracy": 0.12448853626847267,
|
|
"num_tokens": 5280869.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.116397285461426,
|
|
"epoch": 0.23868598650258038,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997800672473969,
|
|
"loss": 6.0303,
|
|
"mean_token_accuracy": 0.12171175703406334,
|
|
"num_tokens": 5293082.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.848374509811402,
|
|
"epoch": 0.2391822151647479,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997784982430247,
|
|
"loss": 5.8142,
|
|
"mean_token_accuracy": 0.13605227544903756,
|
|
"num_tokens": 5304039.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.858838510513306,
|
|
"epoch": 0.23967844382691544,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997769236646301,
|
|
"loss": 5.8998,
|
|
"mean_token_accuracy": 0.12478934675455093,
|
|
"num_tokens": 5315016.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.031330347061157,
|
|
"epoch": 0.24017467248908297,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997753435122522,
|
|
"loss": 6.0241,
|
|
"mean_token_accuracy": 0.12272524014115334,
|
|
"num_tokens": 5326090.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.902796745300293,
|
|
"epoch": 0.2406709011512505,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049977375778593,
|
|
"loss": 5.807,
|
|
"mean_token_accuracy": 0.12468553930521012,
|
|
"num_tokens": 5336423.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.924130249023437,
|
|
"epoch": 0.24116712981341804,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997721664857032,
|
|
"loss": 5.9727,
|
|
"mean_token_accuracy": 0.12364738434553146,
|
|
"num_tokens": 5346982.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.934656763076783,
|
|
"epoch": 0.24166335847558554,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997705696116108,
|
|
"loss": 5.885,
|
|
"mean_token_accuracy": 0.1343015268445015,
|
|
"num_tokens": 5359210.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.892851829528809,
|
|
"epoch": 0.24215958713775307,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997689671636926,
|
|
"loss": 5.8994,
|
|
"mean_token_accuracy": 0.11987031921744347,
|
|
"num_tokens": 5369891.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.88413896560669,
|
|
"epoch": 0.2426558157999206,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997673591419884,
|
|
"loss": 5.8828,
|
|
"mean_token_accuracy": 0.1243226870894432,
|
|
"num_tokens": 5380850.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.868440723419189,
|
|
"epoch": 0.24315204446208813,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997657455465381,
|
|
"loss": 5.9584,
|
|
"mean_token_accuracy": 0.1275911472737789,
|
|
"num_tokens": 5391903.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.989337539672851,
|
|
"epoch": 0.24364827312425566,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997641263773815,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.12448158636689186,
|
|
"num_tokens": 5402517.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.891087675094605,
|
|
"epoch": 0.2441445017864232,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499762501634559,
|
|
"loss": 5.9118,
|
|
"mean_token_accuracy": 0.12482894137501717,
|
|
"num_tokens": 5414110.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.962598514556885,
|
|
"epoch": 0.24464073044859072,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997608713181108,
|
|
"loss": 5.9243,
|
|
"mean_token_accuracy": 0.1277947887778282,
|
|
"num_tokens": 5424466.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.984759044647217,
|
|
"epoch": 0.24513695911075822,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997592354280772,
|
|
"loss": 5.9161,
|
|
"mean_token_accuracy": 0.13129449263215065,
|
|
"num_tokens": 5434461.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.84287428855896,
|
|
"epoch": 0.24563318777292575,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499757593964499,
|
|
"loss": 5.8991,
|
|
"mean_token_accuracy": 0.1189004898071289,
|
|
"num_tokens": 5445921.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.9045604228973385,
|
|
"epoch": 0.24612941643509328,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997559469274166,
|
|
"loss": 5.8835,
|
|
"mean_token_accuracy": 0.12377197816967964,
|
|
"num_tokens": 5456283.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.9440374851226805,
|
|
"epoch": 0.24662564509726081,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997542943168712,
|
|
"loss": 5.9296,
|
|
"mean_token_accuracy": 0.12799091935157775,
|
|
"num_tokens": 5467616.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.940678691864013,
|
|
"epoch": 0.24712187375942835,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997526361329035,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.13008256927132605,
|
|
"num_tokens": 5478050.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.970621490478516,
|
|
"epoch": 0.24761810242159588,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997509723755547,
|
|
"loss": 5.8866,
|
|
"mean_token_accuracy": 0.12871679589152335,
|
|
"num_tokens": 5487185.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.921407842636109,
|
|
"epoch": 0.2481143310837634,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997493030448662,
|
|
"loss": 5.9162,
|
|
"mean_token_accuracy": 0.12141515985131264,
|
|
"num_tokens": 5498802.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.850944328308105,
|
|
"epoch": 0.24861055974593094,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997476281408793,
|
|
"loss": 5.9169,
|
|
"mean_token_accuracy": 0.11781499832868576,
|
|
"num_tokens": 5510285.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.905643796920776,
|
|
"epoch": 0.24910678840809844,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997459476636354,
|
|
"loss": 5.8152,
|
|
"mean_token_accuracy": 0.13310370296239854,
|
|
"num_tokens": 5520028.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.869578409194946,
|
|
"epoch": 0.24960301707026597,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997442616131763,
|
|
"loss": 5.9188,
|
|
"mean_token_accuracy": 0.12631641551852227,
|
|
"num_tokens": 5529271.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.923573017120361,
|
|
"epoch": 0.25009924573243353,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997425699895438,
|
|
"loss": 5.8464,
|
|
"mean_token_accuracy": 0.12032231464982032,
|
|
"num_tokens": 5539396.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.949633979797364,
|
|
"epoch": 0.25059547439460106,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997408727927798,
|
|
"loss": 5.998,
|
|
"mean_token_accuracy": 0.12382508367300034,
|
|
"num_tokens": 5551674.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.928415966033936,
|
|
"epoch": 0.25109170305676853,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997391700229264,
|
|
"loss": 5.9155,
|
|
"mean_token_accuracy": 0.12471647784113885,
|
|
"num_tokens": 5562749.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.931261014938355,
|
|
"epoch": 0.25158793171893606,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499737461680026,
|
|
"loss": 5.9329,
|
|
"mean_token_accuracy": 0.12794146463274955,
|
|
"num_tokens": 5573478.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.888597440719605,
|
|
"epoch": 0.2520841603811036,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997357477641207,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.1306145206093788,
|
|
"num_tokens": 5584546.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.862578821182251,
|
|
"epoch": 0.2525803890432711,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997340282752532,
|
|
"loss": 5.7961,
|
|
"mean_token_accuracy": 0.12940113618969917,
|
|
"num_tokens": 5594004.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.944779109954834,
|
|
"epoch": 0.25307661770543866,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499732303213466,
|
|
"loss": 5.8567,
|
|
"mean_token_accuracy": 0.1197636641561985,
|
|
"num_tokens": 5606095.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.916587829589844,
|
|
"epoch": 0.2535728463676062,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997305725788019,
|
|
"loss": 5.8908,
|
|
"mean_token_accuracy": 0.12375114262104034,
|
|
"num_tokens": 5615596.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.87527642250061,
|
|
"epoch": 0.2540690750297737,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499728836371304,
|
|
"loss": 5.8512,
|
|
"mean_token_accuracy": 0.12574743628501892,
|
|
"num_tokens": 5626753.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.84861912727356,
|
|
"epoch": 0.25456530369194125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997270945910151,
|
|
"loss": 5.8587,
|
|
"mean_token_accuracy": 0.12392849400639534,
|
|
"num_tokens": 5636135.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.922877359390259,
|
|
"epoch": 0.2550615323541088,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997253472379785,
|
|
"loss": 5.9171,
|
|
"mean_token_accuracy": 0.11965455114841461,
|
|
"num_tokens": 5647074.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.952490043640137,
|
|
"epoch": 0.2555577610162763,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997235943122375,
|
|
"loss": 5.9575,
|
|
"mean_token_accuracy": 0.11915252357721329,
|
|
"num_tokens": 5658600.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.838838052749634,
|
|
"epoch": 0.25605398967844384,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997218358138356,
|
|
"loss": 5.8292,
|
|
"mean_token_accuracy": 0.12637119889259338,
|
|
"num_tokens": 5668453.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.9623559474945065,
|
|
"epoch": 0.25655021834061137,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997200717428165,
|
|
"loss": 5.9026,
|
|
"mean_token_accuracy": 0.12589198648929595,
|
|
"num_tokens": 5678855.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.920707082748413,
|
|
"epoch": 0.2570464470027789,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997183020992237,
|
|
"loss": 5.9657,
|
|
"mean_token_accuracy": 0.11761240959167481,
|
|
"num_tokens": 5690063.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.885443162918091,
|
|
"epoch": 0.25754267566494643,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997165268831014,
|
|
"loss": 5.8649,
|
|
"mean_token_accuracy": 0.12652077302336692,
|
|
"num_tokens": 5701487.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.859537076950073,
|
|
"epoch": 0.25803890432711396,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997147460944933,
|
|
"loss": 5.8464,
|
|
"mean_token_accuracy": 0.12707249894738198,
|
|
"num_tokens": 5713034.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.949060773849487,
|
|
"epoch": 0.25853513298928144,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997129597334438,
|
|
"loss": 5.8933,
|
|
"mean_token_accuracy": 0.12450260668992996,
|
|
"num_tokens": 5725469.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.900791788101197,
|
|
"epoch": 0.25903136165144897,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997111677999971,
|
|
"loss": 5.9001,
|
|
"mean_token_accuracy": 0.12473684847354889,
|
|
"num_tokens": 5737099.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.959123134613037,
|
|
"epoch": 0.2595275903136165,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997093702941976,
|
|
"loss": 5.9027,
|
|
"mean_token_accuracy": 0.12286011129617691,
|
|
"num_tokens": 5748756.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.9113915920257565,
|
|
"epoch": 0.260023818975784,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049970756721609,
|
|
"loss": 5.8852,
|
|
"mean_token_accuracy": 0.129507152736187,
|
|
"num_tokens": 5759598.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.901254463195801,
|
|
"epoch": 0.26052004763795156,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499705758565719,
|
|
"loss": 5.9362,
|
|
"mean_token_accuracy": 0.12127219662070274,
|
|
"num_tokens": 5770397.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.990640354156494,
|
|
"epoch": 0.2610162763001191,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997039443431292,
|
|
"loss": 6.0079,
|
|
"mean_token_accuracy": 0.11671988666057587,
|
|
"num_tokens": 5780935.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.943032073974609,
|
|
"epoch": 0.2615125049622866,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997021245483659,
|
|
"loss": 5.8759,
|
|
"mean_token_accuracy": 0.12639233022928237,
|
|
"num_tokens": 5791557.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.829169988632202,
|
|
"epoch": 0.26200873362445415,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499700299181474,
|
|
"loss": 5.8935,
|
|
"mean_token_accuracy": 0.1263813316822052,
|
|
"num_tokens": 5802233.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.879264640808105,
|
|
"epoch": 0.2625049622866217,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996984682424989,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.13040376976132392,
|
|
"num_tokens": 5813424.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.876601123809815,
|
|
"epoch": 0.2630011909487892,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499696631731486,
|
|
"loss": 5.8084,
|
|
"mean_token_accuracy": 0.12445717677474022,
|
|
"num_tokens": 5825652.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.923290538787842,
|
|
"epoch": 0.26349741961095674,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996947896484809,
|
|
"loss": 5.9033,
|
|
"mean_token_accuracy": 0.12721100226044654,
|
|
"num_tokens": 5836603.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.893552494049072,
|
|
"epoch": 0.26399364827312427,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499692941993529,
|
|
"loss": 5.9528,
|
|
"mean_token_accuracy": 0.12557620778679848,
|
|
"num_tokens": 5849365.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.9200966358184814,
|
|
"epoch": 0.2644898769352918,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996910887666765,
|
|
"loss": 5.8669,
|
|
"mean_token_accuracy": 0.12856241166591645,
|
|
"num_tokens": 5860305.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.83866138458252,
|
|
"epoch": 0.26498610559745933,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499689229967969,
|
|
"loss": 5.8055,
|
|
"mean_token_accuracy": 0.12650213465094567,
|
|
"num_tokens": 5872272.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.881111478805542,
|
|
"epoch": 0.26548233425962686,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996873655974529,
|
|
"loss": 5.8348,
|
|
"mean_token_accuracy": 0.12477733865380287,
|
|
"num_tokens": 5884107.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.749620342254639,
|
|
"epoch": 0.26597856292179434,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996854956551743,
|
|
"loss": 5.8186,
|
|
"mean_token_accuracy": 0.1303606040775776,
|
|
"num_tokens": 5894060.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.881046438217163,
|
|
"epoch": 0.26647479158396187,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996836201411794,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.1279796727001667,
|
|
"num_tokens": 5904804.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.954271507263184,
|
|
"epoch": 0.2669710202461294,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499681739055515,
|
|
"loss": 5.9239,
|
|
"mean_token_accuracy": 0.12369774505496026,
|
|
"num_tokens": 5916496.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.884972763061524,
|
|
"epoch": 0.26746724890829693,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996798523982276,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.12348931431770324,
|
|
"num_tokens": 5926920.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.999528169631958,
|
|
"epoch": 0.26796347757046446,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499677960169364,
|
|
"loss": 5.9731,
|
|
"mean_token_accuracy": 0.12307530716061592,
|
|
"num_tokens": 5940098.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.873397493362427,
|
|
"epoch": 0.268459706232632,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996760623689711,
|
|
"loss": 5.8108,
|
|
"mean_token_accuracy": 0.12795935273170472,
|
|
"num_tokens": 5949687.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.904886293411255,
|
|
"epoch": 0.2689559348947995,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499674158997096,
|
|
"loss": 5.9344,
|
|
"mean_token_accuracy": 0.12130291312932968,
|
|
"num_tokens": 5960777.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.976747798919678,
|
|
"epoch": 0.26945216355696705,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996722500537859,
|
|
"loss": 5.8323,
|
|
"mean_token_accuracy": 0.12468361780047417,
|
|
"num_tokens": 5972298.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.831518363952637,
|
|
"epoch": 0.2699483922191346,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996703355390881,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.11904360502958297,
|
|
"num_tokens": 5985613.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.997792959213257,
|
|
"epoch": 0.2704446208813021,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049966841545305,
|
|
"loss": 6.0036,
|
|
"mean_token_accuracy": 0.12301708981394768,
|
|
"num_tokens": 5997530.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.925682544708252,
|
|
"epoch": 0.27094084954346964,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996664897957195,
|
|
"loss": 5.8757,
|
|
"mean_token_accuracy": 0.12393735498189926,
|
|
"num_tokens": 6008123.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.934986400604248,
|
|
"epoch": 0.2714370782056372,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996645585671441,
|
|
"loss": 5.8868,
|
|
"mean_token_accuracy": 0.1257225215435028,
|
|
"num_tokens": 6020578.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.876024007797241,
|
|
"epoch": 0.2719333068678047,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996626217673717,
|
|
"loss": 5.816,
|
|
"mean_token_accuracy": 0.13031245917081832,
|
|
"num_tokens": 6031625.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.788500356674194,
|
|
"epoch": 0.27242953552997223,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996606793964504,
|
|
"loss": 5.8589,
|
|
"mean_token_accuracy": 0.12932414785027505,
|
|
"num_tokens": 6041320.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.9028442859649655,
|
|
"epoch": 0.27292576419213976,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996587314544284,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.123659198731184,
|
|
"num_tokens": 6052627.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.916861200332642,
|
|
"epoch": 0.27342199285430724,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996567779413539,
|
|
"loss": 5.8286,
|
|
"mean_token_accuracy": 0.1305013693869114,
|
|
"num_tokens": 6063468.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.808893394470215,
|
|
"epoch": 0.27391822151647477,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004996548188572755,
|
|
"loss": 5.8031,
|
|
"mean_token_accuracy": 0.13299782574176788,
|
|
"num_tokens": 6074208.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.939206218719482,
|
|
"epoch": 0.2744144501786423,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996528542022416,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.12870003804564475,
|
|
"num_tokens": 6085068.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.880002784729004,
|
|
"epoch": 0.27491067884080983,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499650883976301,
|
|
"loss": 5.8617,
|
|
"mean_token_accuracy": 0.12842236310243607,
|
|
"num_tokens": 6096445.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.792717790603637,
|
|
"epoch": 0.27540690750297736,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996489081795026,
|
|
"loss": 5.77,
|
|
"mean_token_accuracy": 0.1276902064681053,
|
|
"num_tokens": 6106527.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.80667667388916,
|
|
"epoch": 0.2759031361651449,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996469268118953,
|
|
"loss": 5.7975,
|
|
"mean_token_accuracy": 0.13269607350230217,
|
|
"num_tokens": 6115923.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.800922632217407,
|
|
"epoch": 0.2763993648273124,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004996449398735283,
|
|
"loss": 5.6777,
|
|
"mean_token_accuracy": 0.13338218480348588,
|
|
"num_tokens": 6125861.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.881807422637939,
|
|
"epoch": 0.27689559348947995,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996429473644509,
|
|
"loss": 5.8893,
|
|
"mean_token_accuracy": 0.1284797951579094,
|
|
"num_tokens": 6137189.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.898675632476807,
|
|
"epoch": 0.2773918221516475,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996409492847124,
|
|
"loss": 5.8179,
|
|
"mean_token_accuracy": 0.12720710635185242,
|
|
"num_tokens": 6147920.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.831118535995484,
|
|
"epoch": 0.277888050813815,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996389456343624,
|
|
"loss": 5.8105,
|
|
"mean_token_accuracy": 0.13541241586208344,
|
|
"num_tokens": 6159371.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.961232089996338,
|
|
"epoch": 0.27838427947598254,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996369364134507,
|
|
"loss": 6.0155,
|
|
"mean_token_accuracy": 0.1189655639231205,
|
|
"num_tokens": 6172679.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.847831535339355,
|
|
"epoch": 0.2788805081381501,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499634921622027,
|
|
"loss": 5.8821,
|
|
"mean_token_accuracy": 0.12079857736825943,
|
|
"num_tokens": 6184244.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.881469202041626,
|
|
"epoch": 0.2793767368003176,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996329012601413,
|
|
"loss": 5.7422,
|
|
"mean_token_accuracy": 0.12676719948649406,
|
|
"num_tokens": 6194826.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.890796756744384,
|
|
"epoch": 0.27987296546248513,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996308753278437,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.1250182457268238,
|
|
"num_tokens": 6206808.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.92862229347229,
|
|
"epoch": 0.28036919412465267,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996288438251843,
|
|
"loss": 5.8984,
|
|
"mean_token_accuracy": 0.12058991715312004,
|
|
"num_tokens": 6217303.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.912028837203979,
|
|
"epoch": 0.28086542278682014,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996268067522137,
|
|
"loss": 5.8827,
|
|
"mean_token_accuracy": 0.12254092544317245,
|
|
"num_tokens": 6227965.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.92435474395752,
|
|
"epoch": 0.28136165144898767,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996247641089823,
|
|
"loss": 5.9517,
|
|
"mean_token_accuracy": 0.12450585365295411,
|
|
"num_tokens": 6239011.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.813734006881714,
|
|
"epoch": 0.2818578801111552,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996227158955409,
|
|
"loss": 5.7928,
|
|
"mean_token_accuracy": 0.1279340922832489,
|
|
"num_tokens": 6249084.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.905808782577514,
|
|
"epoch": 0.28235410877332273,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049962066211194,
|
|
"loss": 5.8718,
|
|
"mean_token_accuracy": 0.1256870672106743,
|
|
"num_tokens": 6260706.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.821885061264038,
|
|
"epoch": 0.28285033743549026,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996186027582308,
|
|
"loss": 5.7954,
|
|
"mean_token_accuracy": 0.13122305497527123,
|
|
"num_tokens": 6272848.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.886135005950928,
|
|
"epoch": 0.2833465660976578,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996165378344642,
|
|
"loss": 5.8119,
|
|
"mean_token_accuracy": 0.1294620506465435,
|
|
"num_tokens": 6283820.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.8642865180969235,
|
|
"epoch": 0.2838427947598253,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996144673406914,
|
|
"loss": 5.971,
|
|
"mean_token_accuracy": 0.11893427968025208,
|
|
"num_tokens": 6294193.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.916045618057251,
|
|
"epoch": 0.28433902342199285,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996123912769639,
|
|
"loss": 5.8113,
|
|
"mean_token_accuracy": 0.13239249885082244,
|
|
"num_tokens": 6304407.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.837239408493042,
|
|
"epoch": 0.2848352520841604,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996103096433332,
|
|
"loss": 5.8682,
|
|
"mean_token_accuracy": 0.1274930603802204,
|
|
"num_tokens": 6316311.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.894733238220215,
|
|
"epoch": 0.2853314807463279,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996082224398506,
|
|
"loss": 5.8508,
|
|
"mean_token_accuracy": 0.12729406282305716,
|
|
"num_tokens": 6327248.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.829097318649292,
|
|
"epoch": 0.28582770940849545,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996061296665682,
|
|
"loss": 5.8571,
|
|
"mean_token_accuracy": 0.12545564025640488,
|
|
"num_tokens": 6338494.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.894459867477417,
|
|
"epoch": 0.286323938070663,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996040313235377,
|
|
"loss": 5.7517,
|
|
"mean_token_accuracy": 0.12818305119872092,
|
|
"num_tokens": 6349038.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.864468955993653,
|
|
"epoch": 0.2868201667328305,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996019274108112,
|
|
"loss": 5.8608,
|
|
"mean_token_accuracy": 0.12657166197896003,
|
|
"num_tokens": 6360180.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.771185398101807,
|
|
"epoch": 0.28731639539499804,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499599817928441,
|
|
"loss": 5.8005,
|
|
"mean_token_accuracy": 0.12896572723984717,
|
|
"num_tokens": 6370931.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.833103847503662,
|
|
"epoch": 0.28781262405716557,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995977028764792,
|
|
"loss": 5.7767,
|
|
"mean_token_accuracy": 0.1355249285697937,
|
|
"num_tokens": 6381810.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.802249383926392,
|
|
"epoch": 0.28830885271933304,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995955822549783,
|
|
"loss": 5.7855,
|
|
"mean_token_accuracy": 0.12975866422057153,
|
|
"num_tokens": 6392268.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.865897560119629,
|
|
"epoch": 0.2888050813815006,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995934560639909,
|
|
"loss": 5.8417,
|
|
"mean_token_accuracy": 0.13064575865864753,
|
|
"num_tokens": 6403650.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.859321403503418,
|
|
"epoch": 0.2893013100436681,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995913243035699,
|
|
"loss": 5.8183,
|
|
"mean_token_accuracy": 0.12550777047872544,
|
|
"num_tokens": 6414672.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.863259506225586,
|
|
"epoch": 0.28979753870583563,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995891869737678,
|
|
"loss": 5.8909,
|
|
"mean_token_accuracy": 0.12621842250227927,
|
|
"num_tokens": 6424916.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.932774877548217,
|
|
"epoch": 0.29029376736800316,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995870440746379,
|
|
"loss": 5.8467,
|
|
"mean_token_accuracy": 0.13387326076626777,
|
|
"num_tokens": 6435950.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.828493309020996,
|
|
"epoch": 0.2907899960301707,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995848956062333,
|
|
"loss": 5.8022,
|
|
"mean_token_accuracy": 0.12572760954499246,
|
|
"num_tokens": 6446336.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.844927358627319,
|
|
"epoch": 0.2912862246923382,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995827415686071,
|
|
"loss": 5.8729,
|
|
"mean_token_accuracy": 0.12402887716889381,
|
|
"num_tokens": 6457655.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.882878684997559,
|
|
"epoch": 0.29178245335450576,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499580581961813,
|
|
"loss": 5.7676,
|
|
"mean_token_accuracy": 0.1295201987028122,
|
|
"num_tokens": 6469627.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.810547113418579,
|
|
"epoch": 0.2922786820166733,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995784167859043,
|
|
"loss": 5.8584,
|
|
"mean_token_accuracy": 0.12580792158842086,
|
|
"num_tokens": 6480351.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.904936742782593,
|
|
"epoch": 0.2927749106788408,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995762460409349,
|
|
"loss": 5.8915,
|
|
"mean_token_accuracy": 0.1285228781402111,
|
|
"num_tokens": 6491651.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.824595022201538,
|
|
"epoch": 0.29327113934100835,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995740697269584,
|
|
"loss": 5.7323,
|
|
"mean_token_accuracy": 0.1294215962290764,
|
|
"num_tokens": 6502531.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.748151111602783,
|
|
"epoch": 0.2937673680031759,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995718878440289,
|
|
"loss": 5.7433,
|
|
"mean_token_accuracy": 0.13419339433312416,
|
|
"num_tokens": 6511938.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.907798385620117,
|
|
"epoch": 0.2942635966653434,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995697003922006,
|
|
"loss": 5.9029,
|
|
"mean_token_accuracy": 0.12496517151594162,
|
|
"num_tokens": 6522775.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.857905149459839,
|
|
"epoch": 0.29475982532751094,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995675073715274,
|
|
"loss": 5.731,
|
|
"mean_token_accuracy": 0.12566524893045425,
|
|
"num_tokens": 6534660.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.825377321243286,
|
|
"epoch": 0.29525605398967847,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995653087820641,
|
|
"loss": 5.8841,
|
|
"mean_token_accuracy": 0.12718252837657928,
|
|
"num_tokens": 6545673.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.906738996505737,
|
|
"epoch": 0.29575228265184594,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499563104623865,
|
|
"loss": 5.8274,
|
|
"mean_token_accuracy": 0.12779038175940513,
|
|
"num_tokens": 6556912.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.861005258560181,
|
|
"epoch": 0.2962485113140135,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995608948969849,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.12463748157024383,
|
|
"num_tokens": 6567532.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.91699070930481,
|
|
"epoch": 0.296744739976181,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995586796014784,
|
|
"loss": 5.8914,
|
|
"mean_token_accuracy": 0.12917492017149926,
|
|
"num_tokens": 6577830.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.8236791610717775,
|
|
"epoch": 0.29724096863834853,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995564587374005,
|
|
"loss": 5.768,
|
|
"mean_token_accuracy": 0.12926611825823783,
|
|
"num_tokens": 6587254.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.8685643672943115,
|
|
"epoch": 0.29773719730051607,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995542323048063,
|
|
"loss": 5.9674,
|
|
"mean_token_accuracy": 0.12186386585235595,
|
|
"num_tokens": 6598294.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.29773719730051607,
|
|
"eval_entropy": 5.765697889244168,
|
|
"eval_loss": 5.914527416229248,
|
|
"eval_mean_token_accuracy": 0.12812341096967877,
|
|
"eval_num_tokens": 6598294.0,
|
|
"eval_runtime": 28.0358,
|
|
"eval_samples_per_second": 1200.929,
|
|
"eval_steps_per_second": 150.129,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 100750,
|
|
"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": 1.109543952384e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|