5725f16527
Model: fpadovani/eus-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.26492405510420347,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.74092288017273,
|
|
"epoch": 0.0004415400918403391,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.5069,
|
|
"mean_token_accuracy": 0.0897733099758625,
|
|
"num_tokens": 9390.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.730613660812378,
|
|
"epoch": 0.0008830801836806782,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.6006,
|
|
"mean_token_accuracy": 0.09082280173897743,
|
|
"num_tokens": 18671.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.711504316329956,
|
|
"epoch": 0.0013246202755210173,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 7.5458,
|
|
"mean_token_accuracy": 0.09541130512952804,
|
|
"num_tokens": 27614.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.760569763183594,
|
|
"epoch": 0.0017661603673613563,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.6561,
|
|
"mean_token_accuracy": 0.08549572601914406,
|
|
"num_tokens": 37850.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.768425226211548,
|
|
"epoch": 0.0022077004592016957,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.5482,
|
|
"mean_token_accuracy": 0.10141252279281616,
|
|
"num_tokens": 47166.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.844929361343384,
|
|
"epoch": 0.0026492405510420347,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.5478,
|
|
"mean_token_accuracy": 0.0926934964954853,
|
|
"num_tokens": 55500.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.811486482620239,
|
|
"epoch": 0.0030907806428823736,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.5563,
|
|
"mean_token_accuracy": 0.08848847448825836,
|
|
"num_tokens": 63851.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.876116132736206,
|
|
"epoch": 0.0035323207347227126,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.5805,
|
|
"mean_token_accuracy": 0.09331603050231933,
|
|
"num_tokens": 73697.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.89044713973999,
|
|
"epoch": 0.003973860826563052,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.5408,
|
|
"mean_token_accuracy": 0.09619837477803231,
|
|
"num_tokens": 83000.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.889915847778321,
|
|
"epoch": 0.004415400918403391,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.5514,
|
|
"mean_token_accuracy": 0.09451765418052674,
|
|
"num_tokens": 92982.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.9315505027771,
|
|
"epoch": 0.00485694101024373,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.5183,
|
|
"mean_token_accuracy": 0.09080160632729531,
|
|
"num_tokens": 101455.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.839016962051391,
|
|
"epoch": 0.005298481102084069,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.5322,
|
|
"mean_token_accuracy": 0.09154317900538445,
|
|
"num_tokens": 110782.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.82890944480896,
|
|
"epoch": 0.005740021193924408,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.4277,
|
|
"mean_token_accuracy": 0.09484038800001145,
|
|
"num_tokens": 119241.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.828151416778565,
|
|
"epoch": 0.006181561285764747,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.5235,
|
|
"mean_token_accuracy": 0.08991453871130943,
|
|
"num_tokens": 127903.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.8103076934814455,
|
|
"epoch": 0.006623101377605086,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.5,
|
|
"mean_token_accuracy": 0.09334810897707939,
|
|
"num_tokens": 137370.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.8186195373535154,
|
|
"epoch": 0.007064641469445425,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.4449,
|
|
"mean_token_accuracy": 0.09487180560827255,
|
|
"num_tokens": 146582.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.844836282730102,
|
|
"epoch": 0.007506181561285765,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 7.4263,
|
|
"mean_token_accuracy": 0.10111527815461159,
|
|
"num_tokens": 154933.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.830266809463501,
|
|
"epoch": 0.007947721653126103,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.5282,
|
|
"mean_token_accuracy": 0.09698798581957817,
|
|
"num_tokens": 165157.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.830750465393066,
|
|
"epoch": 0.008389261744966443,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.4588,
|
|
"mean_token_accuracy": 0.0967378407716751,
|
|
"num_tokens": 174958.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.780857229232788,
|
|
"epoch": 0.008830801836806783,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.5012,
|
|
"mean_token_accuracy": 0.09829336479306221,
|
|
"num_tokens": 184256.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.829332780838013,
|
|
"epoch": 0.009272341928647121,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.4522,
|
|
"mean_token_accuracy": 0.09847906306385994,
|
|
"num_tokens": 192894.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.851593732833862,
|
|
"epoch": 0.00971388202048746,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.4989,
|
|
"mean_token_accuracy": 0.097539983689785,
|
|
"num_tokens": 202675.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.8246654033660885,
|
|
"epoch": 0.010155422112327799,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 7.5051,
|
|
"mean_token_accuracy": 0.09736146405339241,
|
|
"num_tokens": 212261.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.855020570755005,
|
|
"epoch": 0.010596962204168139,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.582,
|
|
"mean_token_accuracy": 0.09346140772104264,
|
|
"num_tokens": 222329.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.888062286376953,
|
|
"epoch": 0.011038502296008477,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.5076,
|
|
"mean_token_accuracy": 0.08999184891581535,
|
|
"num_tokens": 231247.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.855972003936768,
|
|
"epoch": 0.011480042387848817,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.4591,
|
|
"mean_token_accuracy": 0.10294558182358741,
|
|
"num_tokens": 239978.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.773235321044922,
|
|
"epoch": 0.011921582479689156,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.4769,
|
|
"mean_token_accuracy": 0.09530732408165932,
|
|
"num_tokens": 249735.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.8279619216918945,
|
|
"epoch": 0.012363122571529495,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.5184,
|
|
"mean_token_accuracy": 0.0965347282588482,
|
|
"num_tokens": 259369.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.942261266708374,
|
|
"epoch": 0.012804662663369834,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.5286,
|
|
"mean_token_accuracy": 0.09435783103108406,
|
|
"num_tokens": 268645.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.800592231750488,
|
|
"epoch": 0.013246202755210172,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.4194,
|
|
"mean_token_accuracy": 0.10034767463803292,
|
|
"num_tokens": 276667.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.797780895233155,
|
|
"epoch": 0.013687742847050512,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.4485,
|
|
"mean_token_accuracy": 0.1016088955104351,
|
|
"num_tokens": 286017.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.838827800750733,
|
|
"epoch": 0.01412928293889085,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.4773,
|
|
"mean_token_accuracy": 0.0957870528101921,
|
|
"num_tokens": 295631.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.811876916885376,
|
|
"epoch": 0.01457082303073119,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.4769,
|
|
"mean_token_accuracy": 0.10056489408016205,
|
|
"num_tokens": 304704.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.836099576950073,
|
|
"epoch": 0.01501236312257153,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.506,
|
|
"mean_token_accuracy": 0.09576743617653846,
|
|
"num_tokens": 314195.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.863115644454956,
|
|
"epoch": 0.015453903214411868,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.5172,
|
|
"mean_token_accuracy": 0.09137798845767975,
|
|
"num_tokens": 323379.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.841438961029053,
|
|
"epoch": 0.015895443306252206,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.4337,
|
|
"mean_token_accuracy": 0.10475980639457702,
|
|
"num_tokens": 332322.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.761782026290893,
|
|
"epoch": 0.016336983398092548,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.4066,
|
|
"mean_token_accuracy": 0.10371800139546394,
|
|
"num_tokens": 341735.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.892005348205567,
|
|
"epoch": 0.016778523489932886,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.5071,
|
|
"mean_token_accuracy": 0.09807236269116401,
|
|
"num_tokens": 351209.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.800058889389038,
|
|
"epoch": 0.017220063581773224,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.4442,
|
|
"mean_token_accuracy": 0.10099716112017632,
|
|
"num_tokens": 360467.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.8116179466247555,
|
|
"epoch": 0.017661603673613566,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.4501,
|
|
"mean_token_accuracy": 0.10495151057839394,
|
|
"num_tokens": 370361.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.931649780273437,
|
|
"epoch": 0.018103143765453904,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.496,
|
|
"mean_token_accuracy": 0.0929229848086834,
|
|
"num_tokens": 380366.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.765449905395508,
|
|
"epoch": 0.018544683857294242,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.4157,
|
|
"mean_token_accuracy": 0.1013551875948906,
|
|
"num_tokens": 390690.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.802529335021973,
|
|
"epoch": 0.01898622394913458,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.4996,
|
|
"mean_token_accuracy": 0.09649925082921981,
|
|
"num_tokens": 400722.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.8250895023345945,
|
|
"epoch": 0.01942776404097492,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.3837,
|
|
"mean_token_accuracy": 0.1022213265299797,
|
|
"num_tokens": 410223.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.719676780700683,
|
|
"epoch": 0.01986930413281526,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.4551,
|
|
"mean_token_accuracy": 0.10060659795999527,
|
|
"num_tokens": 420214.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.863075590133667,
|
|
"epoch": 0.020310844224655598,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.4203,
|
|
"mean_token_accuracy": 0.10097097754478454,
|
|
"num_tokens": 429407.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.792139530181885,
|
|
"epoch": 0.02075238431649594,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.3518,
|
|
"mean_token_accuracy": 0.0997156098484993,
|
|
"num_tokens": 438403.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.722495126724243,
|
|
"epoch": 0.021193924408336277,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.404,
|
|
"mean_token_accuracy": 0.10603894293308258,
|
|
"num_tokens": 447466.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.889057874679565,
|
|
"epoch": 0.021635464500176615,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.5207,
|
|
"mean_token_accuracy": 0.09140023961663246,
|
|
"num_tokens": 457141.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.798206424713134,
|
|
"epoch": 0.022077004592016954,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.3654,
|
|
"mean_token_accuracy": 0.10516906753182412,
|
|
"num_tokens": 465708.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.7851112365722654,
|
|
"epoch": 0.022518544683857295,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.4083,
|
|
"mean_token_accuracy": 0.10015119016170501,
|
|
"num_tokens": 475369.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.747976684570313,
|
|
"epoch": 0.022960084775697633,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.3678,
|
|
"mean_token_accuracy": 0.10004653111100197,
|
|
"num_tokens": 484249.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.840033864974975,
|
|
"epoch": 0.02340162486753797,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.4932,
|
|
"mean_token_accuracy": 0.09563242942094803,
|
|
"num_tokens": 493303.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.812006616592408,
|
|
"epoch": 0.023843164959378313,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.449,
|
|
"mean_token_accuracy": 0.10385405197739601,
|
|
"num_tokens": 501503.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.883935546875,
|
|
"epoch": 0.02428470505121865,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.3669,
|
|
"mean_token_accuracy": 0.10403206944465637,
|
|
"num_tokens": 509661.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.698855304718018,
|
|
"epoch": 0.02472624514305899,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.3695,
|
|
"mean_token_accuracy": 0.10018852427601814,
|
|
"num_tokens": 519464.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.810435962677002,
|
|
"epoch": 0.025167785234899327,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.3442,
|
|
"mean_token_accuracy": 0.10638531595468521,
|
|
"num_tokens": 527968.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.726656579971314,
|
|
"epoch": 0.02560932532673967,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.4085,
|
|
"mean_token_accuracy": 0.10700022876262665,
|
|
"num_tokens": 537234.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.8001549243927,
|
|
"epoch": 0.026050865418580007,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.3728,
|
|
"mean_token_accuracy": 0.10392982810735703,
|
|
"num_tokens": 546398.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.735007047653198,
|
|
"epoch": 0.026492405510420345,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.3857,
|
|
"mean_token_accuracy": 0.10330862030386925,
|
|
"num_tokens": 555362.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.846773290634156,
|
|
"epoch": 0.026933945602260687,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.4235,
|
|
"mean_token_accuracy": 0.09694105237722397,
|
|
"num_tokens": 564575.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.824136352539062,
|
|
"epoch": 0.027375485694101025,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.4528,
|
|
"mean_token_accuracy": 0.10274629592895508,
|
|
"num_tokens": 573915.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.747010231018066,
|
|
"epoch": 0.027817025785941363,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.3458,
|
|
"mean_token_accuracy": 0.10164012908935546,
|
|
"num_tokens": 583216.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.775792646408081,
|
|
"epoch": 0.0282585658777817,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.3946,
|
|
"mean_token_accuracy": 0.10511558204889297,
|
|
"num_tokens": 591955.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.6797911643981935,
|
|
"epoch": 0.028700105969622042,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.3672,
|
|
"mean_token_accuracy": 0.103659038990736,
|
|
"num_tokens": 600999.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.804133558273316,
|
|
"epoch": 0.02914164606146238,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.2868,
|
|
"mean_token_accuracy": 0.11126004680991172,
|
|
"num_tokens": 609478.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.633207130432129,
|
|
"epoch": 0.02958318615330272,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.3672,
|
|
"mean_token_accuracy": 0.10404063463211059,
|
|
"num_tokens": 618348.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.855530452728272,
|
|
"epoch": 0.03002472624514306,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.4232,
|
|
"mean_token_accuracy": 0.10137763321399688,
|
|
"num_tokens": 628548.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.745834493637085,
|
|
"epoch": 0.0304662663369834,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.3651,
|
|
"mean_token_accuracy": 0.10630879923701286,
|
|
"num_tokens": 637489.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.684433507919311,
|
|
"epoch": 0.030907806428823736,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.3503,
|
|
"mean_token_accuracy": 0.10281694158911706,
|
|
"num_tokens": 646715.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.803950309753418,
|
|
"epoch": 0.031349346520664075,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.3499,
|
|
"mean_token_accuracy": 0.10527043938636779,
|
|
"num_tokens": 656858.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.707482957839966,
|
|
"epoch": 0.03179088661250441,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.3208,
|
|
"mean_token_accuracy": 0.10721890702843666,
|
|
"num_tokens": 665968.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.764640760421753,
|
|
"epoch": 0.03223242670434476,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.315,
|
|
"mean_token_accuracy": 0.10370069816708564,
|
|
"num_tokens": 674295.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.695739364624023,
|
|
"epoch": 0.032673966796185096,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.2613,
|
|
"mean_token_accuracy": 0.10737213939428329,
|
|
"num_tokens": 683559.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.558203125,
|
|
"epoch": 0.033115506888025434,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.2997,
|
|
"mean_token_accuracy": 0.10474916398525239,
|
|
"num_tokens": 692402.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.85990538597107,
|
|
"epoch": 0.03355704697986577,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.4051,
|
|
"mean_token_accuracy": 0.09768549725413322,
|
|
"num_tokens": 702052.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.703890705108643,
|
|
"epoch": 0.03399858707170611,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.3332,
|
|
"mean_token_accuracy": 0.10592006072402001,
|
|
"num_tokens": 711926.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.764595699310303,
|
|
"epoch": 0.03444012716354645,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.2823,
|
|
"mean_token_accuracy": 0.09970764666795731,
|
|
"num_tokens": 720948.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.651279592514038,
|
|
"epoch": 0.034881667255386786,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.3228,
|
|
"mean_token_accuracy": 0.11015688627958298,
|
|
"num_tokens": 729611.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.79816370010376,
|
|
"epoch": 0.03532320734722713,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.3073,
|
|
"mean_token_accuracy": 0.09714326411485671,
|
|
"num_tokens": 738433.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.687422800064087,
|
|
"epoch": 0.03576474743906747,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.3504,
|
|
"mean_token_accuracy": 0.103574138879776,
|
|
"num_tokens": 747310.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.690566205978394,
|
|
"epoch": 0.03620628753090781,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.3092,
|
|
"mean_token_accuracy": 0.10628200694918633,
|
|
"num_tokens": 756362.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.803203916549682,
|
|
"epoch": 0.036647827622748146,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.3251,
|
|
"mean_token_accuracy": 0.09963449612259864,
|
|
"num_tokens": 764978.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.557148265838623,
|
|
"epoch": 0.037089367714588484,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.299,
|
|
"mean_token_accuracy": 0.10668339729309081,
|
|
"num_tokens": 774058.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.685351037979126,
|
|
"epoch": 0.03753090780642882,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.2881,
|
|
"mean_token_accuracy": 0.10115964189171792,
|
|
"num_tokens": 783332.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.726617670059204,
|
|
"epoch": 0.03797244789826916,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.3501,
|
|
"mean_token_accuracy": 0.10238557234406472,
|
|
"num_tokens": 792481.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.598264503479004,
|
|
"epoch": 0.038413987990109505,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.2437,
|
|
"mean_token_accuracy": 0.11149554774165153,
|
|
"num_tokens": 801396.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.771391916275024,
|
|
"epoch": 0.03885552808194984,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.3027,
|
|
"mean_token_accuracy": 0.10071089640259742,
|
|
"num_tokens": 809903.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.631546688079834,
|
|
"epoch": 0.03929706817379018,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.2639,
|
|
"mean_token_accuracy": 0.10943293869495392,
|
|
"num_tokens": 819144.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.66679310798645,
|
|
"epoch": 0.03973860826563052,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.2976,
|
|
"mean_token_accuracy": 0.10613659396767616,
|
|
"num_tokens": 828881.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.639922952651977,
|
|
"epoch": 0.04018014835747086,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.224,
|
|
"mean_token_accuracy": 0.09946361035108567,
|
|
"num_tokens": 837588.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.582935905456543,
|
|
"epoch": 0.040621688449311195,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.2197,
|
|
"mean_token_accuracy": 0.1077489398419857,
|
|
"num_tokens": 847002.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.601295232772827,
|
|
"epoch": 0.041063228541151534,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.2374,
|
|
"mean_token_accuracy": 0.10669372826814652,
|
|
"num_tokens": 855791.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.683427000045777,
|
|
"epoch": 0.04150476863299188,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.2737,
|
|
"mean_token_accuracy": 0.10692826434969901,
|
|
"num_tokens": 865392.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.632460880279541,
|
|
"epoch": 0.04194630872483222,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.3431,
|
|
"mean_token_accuracy": 0.10185316428542138,
|
|
"num_tokens": 874807.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.7053466796875,
|
|
"epoch": 0.042387848816672555,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.3151,
|
|
"mean_token_accuracy": 0.107633588463068,
|
|
"num_tokens": 883928.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.573175430297852,
|
|
"epoch": 0.04282938890851289,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.2153,
|
|
"mean_token_accuracy": 0.10783804580569267,
|
|
"num_tokens": 893047.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.575657176971435,
|
|
"epoch": 0.04327092900035323,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.2168,
|
|
"mean_token_accuracy": 0.1058282122015953,
|
|
"num_tokens": 901645.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.620817947387695,
|
|
"epoch": 0.04371246909219357,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.2325,
|
|
"mean_token_accuracy": 0.10362469628453255,
|
|
"num_tokens": 911169.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.675788545608521,
|
|
"epoch": 0.04415400918403391,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.239,
|
|
"mean_token_accuracy": 0.09903389513492585,
|
|
"num_tokens": 921382.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.509087562561035,
|
|
"epoch": 0.04459554927587425,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.1784,
|
|
"mean_token_accuracy": 0.10705869123339654,
|
|
"num_tokens": 930409.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.563630390167236,
|
|
"epoch": 0.04503708936771459,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.1437,
|
|
"mean_token_accuracy": 0.11103534623980522,
|
|
"num_tokens": 939049.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.656319618225098,
|
|
"epoch": 0.04547862945955493,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.1669,
|
|
"mean_token_accuracy": 0.10674394220113755,
|
|
"num_tokens": 947575.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.617980527877807,
|
|
"epoch": 0.045920169551395267,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.3263,
|
|
"mean_token_accuracy": 0.10124524608254433,
|
|
"num_tokens": 957848.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.594845724105835,
|
|
"epoch": 0.046361709643235605,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.1638,
|
|
"mean_token_accuracy": 0.1080893911421299,
|
|
"num_tokens": 966521.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.610377073287964,
|
|
"epoch": 0.04680324973507594,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.2181,
|
|
"mean_token_accuracy": 0.10909054726362229,
|
|
"num_tokens": 975827.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.499869298934937,
|
|
"epoch": 0.04724478982691628,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.1793,
|
|
"mean_token_accuracy": 0.11137327626347542,
|
|
"num_tokens": 985292.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.5960760593414305,
|
|
"epoch": 0.047686329918756626,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.154,
|
|
"mean_token_accuracy": 0.10950936675071717,
|
|
"num_tokens": 994791.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.469157934188843,
|
|
"epoch": 0.048127870010596964,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.1317,
|
|
"mean_token_accuracy": 0.11670516580343246,
|
|
"num_tokens": 1003700.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.523545932769776,
|
|
"epoch": 0.0485694101024373,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.1673,
|
|
"mean_token_accuracy": 0.11030299812555314,
|
|
"num_tokens": 1012682.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.583120203018188,
|
|
"epoch": 0.04901095019427764,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.1875,
|
|
"mean_token_accuracy": 0.1056957058608532,
|
|
"num_tokens": 1021018.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.558827114105225,
|
|
"epoch": 0.04945249028611798,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.0584,
|
|
"mean_token_accuracy": 0.1091762512922287,
|
|
"num_tokens": 1029744.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.384686899185181,
|
|
"epoch": 0.049894030377958316,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.1435,
|
|
"mean_token_accuracy": 0.11267905756831169,
|
|
"num_tokens": 1038805.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.607424783706665,
|
|
"epoch": 0.050335570469798654,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.1996,
|
|
"mean_token_accuracy": 0.10786581486463546,
|
|
"num_tokens": 1047656.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.606092405319214,
|
|
"epoch": 0.050777110561639,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.1792,
|
|
"mean_token_accuracy": 0.11288331896066665,
|
|
"num_tokens": 1056598.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.5449169158935545,
|
|
"epoch": 0.05121865065347934,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.1883,
|
|
"mean_token_accuracy": 0.10918098837137222,
|
|
"num_tokens": 1065226.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.479248285293579,
|
|
"epoch": 0.051660190745319676,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.1217,
|
|
"mean_token_accuracy": 0.11170855611562729,
|
|
"num_tokens": 1074661.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.5761857509613035,
|
|
"epoch": 0.052101730837160014,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.2093,
|
|
"mean_token_accuracy": 0.1055817686021328,
|
|
"num_tokens": 1083921.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.475902557373047,
|
|
"epoch": 0.05254327092900035,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.1024,
|
|
"mean_token_accuracy": 0.12069160491228104,
|
|
"num_tokens": 1093399.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.477249240875244,
|
|
"epoch": 0.05298481102084069,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.1806,
|
|
"mean_token_accuracy": 0.1091334879398346,
|
|
"num_tokens": 1104065.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.454396152496338,
|
|
"epoch": 0.05342635111268103,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.0759,
|
|
"mean_token_accuracy": 0.11466379538178444,
|
|
"num_tokens": 1112995.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.4687096118927006,
|
|
"epoch": 0.05386789120452137,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.1202,
|
|
"mean_token_accuracy": 0.10947456136345864,
|
|
"num_tokens": 1121637.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.428070116043091,
|
|
"epoch": 0.05430943129636171,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.061,
|
|
"mean_token_accuracy": 0.1107931189239025,
|
|
"num_tokens": 1131166.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.479091644287109,
|
|
"epoch": 0.05475097138820205,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.0598,
|
|
"mean_token_accuracy": 0.11267657652497291,
|
|
"num_tokens": 1140888.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.516183996200562,
|
|
"epoch": 0.05519251148004239,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.2209,
|
|
"mean_token_accuracy": 0.10797442942857742,
|
|
"num_tokens": 1150278.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.450537157058716,
|
|
"epoch": 0.055634051571882726,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.1601,
|
|
"mean_token_accuracy": 0.10592598244547843,
|
|
"num_tokens": 1159348.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.588924980163574,
|
|
"epoch": 0.056075591663723064,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.1788,
|
|
"mean_token_accuracy": 0.10933139771223069,
|
|
"num_tokens": 1168883.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.51312780380249,
|
|
"epoch": 0.0565171317555634,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.0915,
|
|
"mean_token_accuracy": 0.1159443736076355,
|
|
"num_tokens": 1178572.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.437539958953858,
|
|
"epoch": 0.05695867184740375,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.17,
|
|
"mean_token_accuracy": 0.10953533723950386,
|
|
"num_tokens": 1188909.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.465111255645752,
|
|
"epoch": 0.057400211939244085,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.0672,
|
|
"mean_token_accuracy": 0.11020829901099205,
|
|
"num_tokens": 1197705.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.397136974334717,
|
|
"epoch": 0.05784175203108442,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.9218,
|
|
"mean_token_accuracy": 0.11375543102622032,
|
|
"num_tokens": 1206351.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.38561692237854,
|
|
"epoch": 0.05828329212292476,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.0438,
|
|
"mean_token_accuracy": 0.11089925691485406,
|
|
"num_tokens": 1214984.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.4726481437683105,
|
|
"epoch": 0.0587248322147651,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.1247,
|
|
"mean_token_accuracy": 0.11059069335460663,
|
|
"num_tokens": 1224485.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.461330795288086,
|
|
"epoch": 0.05916637230660544,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.1386,
|
|
"mean_token_accuracy": 0.10253455564379692,
|
|
"num_tokens": 1233560.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.473884534835816,
|
|
"epoch": 0.05960791239844578,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.0729,
|
|
"mean_token_accuracy": 0.10994852259755135,
|
|
"num_tokens": 1242628.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.392604112625122,
|
|
"epoch": 0.06004945249028612,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.9809,
|
|
"mean_token_accuracy": 0.1146723486483097,
|
|
"num_tokens": 1251004.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.428996276855469,
|
|
"epoch": 0.06049099258212646,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.1634,
|
|
"mean_token_accuracy": 0.11115597635507583,
|
|
"num_tokens": 1260344.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.401163053512573,
|
|
"epoch": 0.0609325326739668,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.0696,
|
|
"mean_token_accuracy": 0.11442951783537865,
|
|
"num_tokens": 1269988.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.402554750442505,
|
|
"epoch": 0.061374072765807135,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.0428,
|
|
"mean_token_accuracy": 0.11391758620738983,
|
|
"num_tokens": 1280912.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.406301021575928,
|
|
"epoch": 0.06181561285764747,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.0467,
|
|
"mean_token_accuracy": 0.11682257801294327,
|
|
"num_tokens": 1289684.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.3641218662261965,
|
|
"epoch": 0.06225715294948781,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.0803,
|
|
"mean_token_accuracy": 0.10842933505773544,
|
|
"num_tokens": 1298853.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.3719359874725345,
|
|
"epoch": 0.06269869304132815,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.0386,
|
|
"mean_token_accuracy": 0.11791565641760826,
|
|
"num_tokens": 1309112.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.369606351852417,
|
|
"epoch": 0.0631402331331685,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.0135,
|
|
"mean_token_accuracy": 0.11014628857374191,
|
|
"num_tokens": 1319064.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.296480321884156,
|
|
"epoch": 0.06358177322500883,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.9938,
|
|
"mean_token_accuracy": 0.11697245836257934,
|
|
"num_tokens": 1327889.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.403489398956299,
|
|
"epoch": 0.06402331331684917,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.0083,
|
|
"mean_token_accuracy": 0.1104284293949604,
|
|
"num_tokens": 1337241.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.347339487075805,
|
|
"epoch": 0.06446485340868952,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.0718,
|
|
"mean_token_accuracy": 0.11292454376816749,
|
|
"num_tokens": 1346527.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.347748756408691,
|
|
"epoch": 0.06490639350052985,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.0639,
|
|
"mean_token_accuracy": 0.11358218491077424,
|
|
"num_tokens": 1355677.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.3271379470825195,
|
|
"epoch": 0.06534793359237019,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.0468,
|
|
"mean_token_accuracy": 0.1157820999622345,
|
|
"num_tokens": 1364874.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.400119829177856,
|
|
"epoch": 0.06578947368421052,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.9839,
|
|
"mean_token_accuracy": 0.12082682698965072,
|
|
"num_tokens": 1373717.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.417098903656006,
|
|
"epoch": 0.06623101377605087,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.9526,
|
|
"mean_token_accuracy": 0.11417729035019875,
|
|
"num_tokens": 1382767.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.194312381744385,
|
|
"epoch": 0.0666725538678912,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.9799,
|
|
"mean_token_accuracy": 0.11586436182260514,
|
|
"num_tokens": 1391190.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.339599084854126,
|
|
"epoch": 0.06711409395973154,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.9817,
|
|
"mean_token_accuracy": 0.1170587882399559,
|
|
"num_tokens": 1400722.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.400132036209106,
|
|
"epoch": 0.06755563405157189,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.0091,
|
|
"mean_token_accuracy": 0.10940207540988922,
|
|
"num_tokens": 1409328.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.115442705154419,
|
|
"epoch": 0.06799717414341222,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.8837,
|
|
"mean_token_accuracy": 0.12403405010700226,
|
|
"num_tokens": 1418504.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.437279510498047,
|
|
"epoch": 0.06843871423525257,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.0359,
|
|
"mean_token_accuracy": 0.10912163555622101,
|
|
"num_tokens": 1427690.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.26606240272522,
|
|
"epoch": 0.0688802543270929,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.0132,
|
|
"mean_token_accuracy": 0.11617867797613143,
|
|
"num_tokens": 1436798.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.26966495513916,
|
|
"epoch": 0.06932179441893324,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.01,
|
|
"mean_token_accuracy": 0.11528639197349548,
|
|
"num_tokens": 1446357.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.302881193161011,
|
|
"epoch": 0.06976333451077357,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.9315,
|
|
"mean_token_accuracy": 0.11601672917604447,
|
|
"num_tokens": 1455998.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.307020282745361,
|
|
"epoch": 0.07020487460261392,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.9813,
|
|
"mean_token_accuracy": 0.11031874865293503,
|
|
"num_tokens": 1465237.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.243889856338501,
|
|
"epoch": 0.07064641469445426,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.9248,
|
|
"mean_token_accuracy": 0.12101015448570251,
|
|
"num_tokens": 1474363.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.248915958404541,
|
|
"epoch": 0.0710879547862946,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.9906,
|
|
"mean_token_accuracy": 0.12257542759180069,
|
|
"num_tokens": 1483379.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.34154782295227,
|
|
"epoch": 0.07152949487813494,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.9828,
|
|
"mean_token_accuracy": 0.11638684496283531,
|
|
"num_tokens": 1492507.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.212753200531006,
|
|
"epoch": 0.07197103496997527,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.8604,
|
|
"mean_token_accuracy": 0.12233690097928047,
|
|
"num_tokens": 1500888.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.181662464141846,
|
|
"epoch": 0.07241257506181561,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.9234,
|
|
"mean_token_accuracy": 0.11673298925161361,
|
|
"num_tokens": 1510310.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.263974905014038,
|
|
"epoch": 0.07285411515365595,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.8977,
|
|
"mean_token_accuracy": 0.12379544451832772,
|
|
"num_tokens": 1519427.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.25563235282898,
|
|
"epoch": 0.07329565524549629,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.9332,
|
|
"mean_token_accuracy": 0.11141304299235344,
|
|
"num_tokens": 1529456.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.141549444198608,
|
|
"epoch": 0.07373719533733664,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.8617,
|
|
"mean_token_accuracy": 0.11971206367015838,
|
|
"num_tokens": 1537695.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.242198467254639,
|
|
"epoch": 0.07417873542917697,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.0075,
|
|
"mean_token_accuracy": 0.11687812730669975,
|
|
"num_tokens": 1547511.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.309858417510986,
|
|
"epoch": 0.07462027552101731,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.9839,
|
|
"mean_token_accuracy": 0.11879770755767823,
|
|
"num_tokens": 1557035.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.211091947555542,
|
|
"epoch": 0.07506181561285764,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.9346,
|
|
"mean_token_accuracy": 0.12483425140380859,
|
|
"num_tokens": 1566773.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.208451414108277,
|
|
"epoch": 0.07550335570469799,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.927,
|
|
"mean_token_accuracy": 0.11267467886209488,
|
|
"num_tokens": 1576873.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.186734676361084,
|
|
"epoch": 0.07594489579653832,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.9684,
|
|
"mean_token_accuracy": 0.11325102299451828,
|
|
"num_tokens": 1586170.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.32284631729126,
|
|
"epoch": 0.07638643588837866,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.0153,
|
|
"mean_token_accuracy": 0.11636607497930526,
|
|
"num_tokens": 1596054.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.200122261047364,
|
|
"epoch": 0.07682797598021901,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.8751,
|
|
"mean_token_accuracy": 0.1230311393737793,
|
|
"num_tokens": 1604544.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.244127464294434,
|
|
"epoch": 0.07726951607205934,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.9023,
|
|
"mean_token_accuracy": 0.12475202232599258,
|
|
"num_tokens": 1614580.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.1907594203948975,
|
|
"epoch": 0.07771105616389969,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.9948,
|
|
"mean_token_accuracy": 0.115571129322052,
|
|
"num_tokens": 1624701.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.136907148361206,
|
|
"epoch": 0.07815259625574002,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.9193,
|
|
"mean_token_accuracy": 0.11373112797737121,
|
|
"num_tokens": 1634085.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.195565986633301,
|
|
"epoch": 0.07859413634758036,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.8968,
|
|
"mean_token_accuracy": 0.11859833672642708,
|
|
"num_tokens": 1643190.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.176092052459717,
|
|
"epoch": 0.0790356764394207,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.9171,
|
|
"mean_token_accuracy": 0.11816032081842423,
|
|
"num_tokens": 1652705.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.225932455062866,
|
|
"epoch": 0.07947721653126104,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.9033,
|
|
"mean_token_accuracy": 0.11247398778796196,
|
|
"num_tokens": 1662210.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.222397232055664,
|
|
"epoch": 0.07991875662310138,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.931,
|
|
"mean_token_accuracy": 0.11510396897792816,
|
|
"num_tokens": 1671893.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.168801355361938,
|
|
"epoch": 0.08036029671494171,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.8842,
|
|
"mean_token_accuracy": 0.12047431021928787,
|
|
"num_tokens": 1681217.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.189701175689697,
|
|
"epoch": 0.08080183680678206,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.9145,
|
|
"mean_token_accuracy": 0.11493082717061043,
|
|
"num_tokens": 1690447.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.148307180404663,
|
|
"epoch": 0.08124337689862239,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.001,
|
|
"mean_token_accuracy": 0.10863983184099198,
|
|
"num_tokens": 1700355.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.2164154052734375,
|
|
"epoch": 0.08168491699046274,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.906,
|
|
"mean_token_accuracy": 0.11343243196606637,
|
|
"num_tokens": 1709449.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.191054010391236,
|
|
"epoch": 0.08212645708230307,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.9311,
|
|
"mean_token_accuracy": 0.11408023163676262,
|
|
"num_tokens": 1718838.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.111620044708252,
|
|
"epoch": 0.08256799717414341,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.8844,
|
|
"mean_token_accuracy": 0.12342581376433373,
|
|
"num_tokens": 1728594.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.233243608474732,
|
|
"epoch": 0.08300953726598376,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.9305,
|
|
"mean_token_accuracy": 0.12092314288020134,
|
|
"num_tokens": 1738814.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.168387937545776,
|
|
"epoch": 0.08345107735782409,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.8546,
|
|
"mean_token_accuracy": 0.12510684356093407,
|
|
"num_tokens": 1747644.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.201950550079346,
|
|
"epoch": 0.08389261744966443,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.9079,
|
|
"mean_token_accuracy": 0.11906211525201797,
|
|
"num_tokens": 1757489.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.130580997467041,
|
|
"epoch": 0.08433415754150476,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.8296,
|
|
"mean_token_accuracy": 0.12410564720630646,
|
|
"num_tokens": 1767546.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.093601322174072,
|
|
"epoch": 0.08477569763334511,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.8928,
|
|
"mean_token_accuracy": 0.10743151605129242,
|
|
"num_tokens": 1776035.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.145628499984741,
|
|
"epoch": 0.08521723772518544,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.953,
|
|
"mean_token_accuracy": 0.11847842559218406,
|
|
"num_tokens": 1786161.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.274262189865112,
|
|
"epoch": 0.08565877781702579,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.007,
|
|
"mean_token_accuracy": 0.11388442665338516,
|
|
"num_tokens": 1796093.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.080674505233764,
|
|
"epoch": 0.08610031790886613,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.8546,
|
|
"mean_token_accuracy": 0.11734381765127182,
|
|
"num_tokens": 1805574.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.141940927505493,
|
|
"epoch": 0.08654185800070646,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.8924,
|
|
"mean_token_accuracy": 0.11525135561823845,
|
|
"num_tokens": 1815175.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.089342260360718,
|
|
"epoch": 0.08698339809254681,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.8082,
|
|
"mean_token_accuracy": 0.12424175813794136,
|
|
"num_tokens": 1824683.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.1276007175445555,
|
|
"epoch": 0.08742493818438714,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.7918,
|
|
"mean_token_accuracy": 0.1199628159403801,
|
|
"num_tokens": 1833174.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.066866636276245,
|
|
"epoch": 0.08786647827622748,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.8796,
|
|
"mean_token_accuracy": 0.11747556179761887,
|
|
"num_tokens": 1842409.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.007741022109985,
|
|
"epoch": 0.08830801836806781,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.7861,
|
|
"mean_token_accuracy": 0.12650212571024894,
|
|
"num_tokens": 1851441.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.240553998947144,
|
|
"epoch": 0.08874955845990816,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499999998589561,
|
|
"loss": 6.9076,
|
|
"mean_token_accuracy": 0.11784921512007714,
|
|
"num_tokens": 1861188.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.046397066116333,
|
|
"epoch": 0.0891910985517485,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999999928596523,
|
|
"loss": 6.8583,
|
|
"mean_token_accuracy": 0.12223245799541474,
|
|
"num_tokens": 1870284.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.0789531707763675,
|
|
"epoch": 0.08963263864358884,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999999827221219,
|
|
"loss": 6.8283,
|
|
"mean_token_accuracy": 0.12814989313483238,
|
|
"num_tokens": 1879744.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.0941243171691895,
|
|
"epoch": 0.09007417873542918,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999681769696,
|
|
"loss": 6.8228,
|
|
"mean_token_accuracy": 0.12476407438516617,
|
|
"num_tokens": 1889241.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.043097877502442,
|
|
"epoch": 0.09051571882726951,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499999949224196,
|
|
"loss": 6.8413,
|
|
"mean_token_accuracy": 0.12211177572607994,
|
|
"num_tokens": 1898247.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.068183851242066,
|
|
"epoch": 0.09095725891910986,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999258638013,
|
|
"loss": 6.7999,
|
|
"mean_token_accuracy": 0.122597586363554,
|
|
"num_tokens": 1907559.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.042861270904541,
|
|
"epoch": 0.09139879901095019,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999998980957861,
|
|
"loss": 6.8116,
|
|
"mean_token_accuracy": 0.12296328842639923,
|
|
"num_tokens": 1917072.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.02711238861084,
|
|
"epoch": 0.09184033910279053,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999998659201508,
|
|
"loss": 6.7577,
|
|
"mean_token_accuracy": 0.1265648201107979,
|
|
"num_tokens": 1926597.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.008166885375976,
|
|
"epoch": 0.09228187919463088,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999998293368961,
|
|
"loss": 6.8148,
|
|
"mean_token_accuracy": 0.11956329345703125,
|
|
"num_tokens": 1935978.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.03216814994812,
|
|
"epoch": 0.09272341928647121,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999997883460227,
|
|
"loss": 6.7551,
|
|
"mean_token_accuracy": 0.12221006751060486,
|
|
"num_tokens": 1944424.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.016500616073609,
|
|
"epoch": 0.09316495937831155,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999997429475314,
|
|
"loss": 6.7199,
|
|
"mean_token_accuracy": 0.1299702636897564,
|
|
"num_tokens": 1953844.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.052721452713013,
|
|
"epoch": 0.09360649947015189,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999996931414232,
|
|
"loss": 6.8195,
|
|
"mean_token_accuracy": 0.12436865568161011,
|
|
"num_tokens": 1963974.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.030517196655273,
|
|
"epoch": 0.09404803956199223,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999996389276988,
|
|
"loss": 6.7732,
|
|
"mean_token_accuracy": 0.13136502131819724,
|
|
"num_tokens": 1973466.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.936943769454956,
|
|
"epoch": 0.09448957965383256,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999995803063596,
|
|
"loss": 6.7879,
|
|
"mean_token_accuracy": 0.1239612028002739,
|
|
"num_tokens": 1983478.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.092060518264771,
|
|
"epoch": 0.0949311197456729,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999995172774065,
|
|
"loss": 6.8703,
|
|
"mean_token_accuracy": 0.12069909051060676,
|
|
"num_tokens": 1992775.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.053188705444336,
|
|
"epoch": 0.09537265983751325,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999994498408408,
|
|
"loss": 6.8269,
|
|
"mean_token_accuracy": 0.11928088068962098,
|
|
"num_tokens": 2002526.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.058347511291504,
|
|
"epoch": 0.09581419992935358,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999993779966639,
|
|
"loss": 6.8484,
|
|
"mean_token_accuracy": 0.11959519013762474,
|
|
"num_tokens": 2012476.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.85009355545044,
|
|
"epoch": 0.09625574002119393,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999993017448771,
|
|
"loss": 6.6854,
|
|
"mean_token_accuracy": 0.1360420987010002,
|
|
"num_tokens": 2021252.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.145733261108399,
|
|
"epoch": 0.09669728011303426,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999992210854821,
|
|
"loss": 6.8438,
|
|
"mean_token_accuracy": 0.1258312664926052,
|
|
"num_tokens": 2031438.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.019267272949219,
|
|
"epoch": 0.0971388202048746,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999991360184801,
|
|
"loss": 6.883,
|
|
"mean_token_accuracy": 0.12097008153796196,
|
|
"num_tokens": 2041319.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.073525238037109,
|
|
"epoch": 0.09758036029671494,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999990465438731,
|
|
"loss": 6.862,
|
|
"mean_token_accuracy": 0.1219029612839222,
|
|
"num_tokens": 2052060.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.95486044883728,
|
|
"epoch": 0.09802190038855528,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999989526616628,
|
|
"loss": 6.7495,
|
|
"mean_token_accuracy": 0.12949764505028724,
|
|
"num_tokens": 2061331.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.9770708084106445,
|
|
"epoch": 0.09846344048039563,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999988543718509,
|
|
"loss": 6.7566,
|
|
"mean_token_accuracy": 0.12212359756231309,
|
|
"num_tokens": 2070006.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.0353333950042725,
|
|
"epoch": 0.09890498057223596,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999987516744394,
|
|
"loss": 6.7158,
|
|
"mean_token_accuracy": 0.13030195459723473,
|
|
"num_tokens": 2079089.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.971569681167603,
|
|
"epoch": 0.0993465206640763,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999986445694303,
|
|
"loss": 6.7236,
|
|
"mean_token_accuracy": 0.12542433887720109,
|
|
"num_tokens": 2087237.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.899944829940796,
|
|
"epoch": 0.09978806075591663,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999985330568258,
|
|
"loss": 6.6822,
|
|
"mean_token_accuracy": 0.13330597206950187,
|
|
"num_tokens": 2096598.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.01187915802002,
|
|
"epoch": 0.10022960084775698,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999984171366278,
|
|
"loss": 6.7788,
|
|
"mean_token_accuracy": 0.11807065233588218,
|
|
"num_tokens": 2106106.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.9801586151123045,
|
|
"epoch": 0.10067114093959731,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499998296808839,
|
|
"loss": 6.7582,
|
|
"mean_token_accuracy": 0.11982692703604698,
|
|
"num_tokens": 2115478.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.019436502456665,
|
|
"epoch": 0.10111268103143765,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004999981720734615,
|
|
"loss": 6.7836,
|
|
"mean_token_accuracy": 0.12526557743549346,
|
|
"num_tokens": 2124439.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.01093807220459,
|
|
"epoch": 0.101554221123278,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999980429304977,
|
|
"loss": 6.796,
|
|
"mean_token_accuracy": 0.11945406049489975,
|
|
"num_tokens": 2133718.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.833093214035034,
|
|
"epoch": 0.10199576121511833,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999979093799502,
|
|
"loss": 6.6939,
|
|
"mean_token_accuracy": 0.12498606964945794,
|
|
"num_tokens": 2142978.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.946839380264282,
|
|
"epoch": 0.10243730130695868,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999977714218217,
|
|
"loss": 6.7688,
|
|
"mean_token_accuracy": 0.12323360666632652,
|
|
"num_tokens": 2152250.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.99408917427063,
|
|
"epoch": 0.102878841398799,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999976290561147,
|
|
"loss": 6.7613,
|
|
"mean_token_accuracy": 0.12313725724816323,
|
|
"num_tokens": 2161620.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.988214206695557,
|
|
"epoch": 0.10332038149063935,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999974822828322,
|
|
"loss": 6.7814,
|
|
"mean_token_accuracy": 0.12046999335289002,
|
|
"num_tokens": 2170856.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.9620466232299805,
|
|
"epoch": 0.10376192158247968,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499997331101977,
|
|
"loss": 6.7547,
|
|
"mean_token_accuracy": 0.12075523287057877,
|
|
"num_tokens": 2180926.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.9654961109161375,
|
|
"epoch": 0.10420346167432003,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499997175513552,
|
|
"loss": 6.7462,
|
|
"mean_token_accuracy": 0.12285592630505562,
|
|
"num_tokens": 2190248.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.9309080123901365,
|
|
"epoch": 0.10464500176616037,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999970155175603,
|
|
"loss": 6.7514,
|
|
"mean_token_accuracy": 0.12348200678825379,
|
|
"num_tokens": 2199833.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.959126377105713,
|
|
"epoch": 0.1050865418580007,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499996851114005,
|
|
"loss": 6.7184,
|
|
"mean_token_accuracy": 0.12861018776893615,
|
|
"num_tokens": 2208240.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.932129383087158,
|
|
"epoch": 0.10552808194984105,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999966823028894,
|
|
"loss": 6.7618,
|
|
"mean_token_accuracy": 0.11978181153535843,
|
|
"num_tokens": 2218758.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.9820332527160645,
|
|
"epoch": 0.10596962204168138,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999965090842168,
|
|
"loss": 6.7626,
|
|
"mean_token_accuracy": 0.1300593949854374,
|
|
"num_tokens": 2228443.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.858966636657715,
|
|
"epoch": 0.10641116213352173,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999963314579905,
|
|
"loss": 6.6107,
|
|
"mean_token_accuracy": 0.1355985902249813,
|
|
"num_tokens": 2236787.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.947892761230468,
|
|
"epoch": 0.10685270222536206,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999961494242139,
|
|
"loss": 6.7746,
|
|
"mean_token_accuracy": 0.12228678241372108,
|
|
"num_tokens": 2247089.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.849541854858399,
|
|
"epoch": 0.1072942423172024,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999959629828908,
|
|
"loss": 6.7035,
|
|
"mean_token_accuracy": 0.12353255078196526,
|
|
"num_tokens": 2256045.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.002861881256104,
|
|
"epoch": 0.10773578240904275,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999957721340248,
|
|
"loss": 6.7841,
|
|
"mean_token_accuracy": 0.12372039780020713,
|
|
"num_tokens": 2265835.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.845533561706543,
|
|
"epoch": 0.10817732250088308,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999955768776195,
|
|
"loss": 6.7134,
|
|
"mean_token_accuracy": 0.12301751002669334,
|
|
"num_tokens": 2275318.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.958423137664795,
|
|
"epoch": 0.10861886259272342,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999953772136788,
|
|
"loss": 6.7049,
|
|
"mean_token_accuracy": 0.12736163064837455,
|
|
"num_tokens": 2284821.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.942495965957642,
|
|
"epoch": 0.10906040268456375,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999951731422068,
|
|
"loss": 6.6712,
|
|
"mean_token_accuracy": 0.12646759897470475,
|
|
"num_tokens": 2294013.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.917871713638306,
|
|
"epoch": 0.1095019427764041,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999949646632072,
|
|
"loss": 6.6694,
|
|
"mean_token_accuracy": 0.12900351211428643,
|
|
"num_tokens": 2302727.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.849976634979248,
|
|
"epoch": 0.10994348286824443,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999947517766842,
|
|
"loss": 6.6906,
|
|
"mean_token_accuracy": 0.12817103341221808,
|
|
"num_tokens": 2312032.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.057008552551269,
|
|
"epoch": 0.11038502296008477,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499994534482642,
|
|
"loss": 6.7819,
|
|
"mean_token_accuracy": 0.12531876042485238,
|
|
"num_tokens": 2321839.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.899663734436035,
|
|
"epoch": 0.11082656305192512,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999943127810847,
|
|
"loss": 6.7555,
|
|
"mean_token_accuracy": 0.1212481401860714,
|
|
"num_tokens": 2331255.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.816301393508911,
|
|
"epoch": 0.11126810314376545,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999940866720169,
|
|
"loss": 6.5529,
|
|
"mean_token_accuracy": 0.13424451053142547,
|
|
"num_tokens": 2340038.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.8964927196502686,
|
|
"epoch": 0.1117096432356058,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999938561554429,
|
|
"loss": 6.6959,
|
|
"mean_token_accuracy": 0.12449696063995361,
|
|
"num_tokens": 2348901.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.875371694564819,
|
|
"epoch": 0.11215118332744613,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999936212313672,
|
|
"loss": 6.7697,
|
|
"mean_token_accuracy": 0.119696693867445,
|
|
"num_tokens": 2358842.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.907081985473633,
|
|
"epoch": 0.11259272341928647,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999933818997943,
|
|
"loss": 6.6654,
|
|
"mean_token_accuracy": 0.12900050207972527,
|
|
"num_tokens": 2368650.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.866778802871704,
|
|
"epoch": 0.1130342635111268,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999931381607292,
|
|
"loss": 6.7041,
|
|
"mean_token_accuracy": 0.1312815934419632,
|
|
"num_tokens": 2377916.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.936831331253051,
|
|
"epoch": 0.11347580360296715,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999928900141764,
|
|
"loss": 6.6683,
|
|
"mean_token_accuracy": 0.12833984717726707,
|
|
"num_tokens": 2387507.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.833027648925781,
|
|
"epoch": 0.1139173436948075,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499992637460141,
|
|
"loss": 6.7166,
|
|
"mean_token_accuracy": 0.12722958698868753,
|
|
"num_tokens": 2396148.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.854029512405395,
|
|
"epoch": 0.11435888378664782,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999923804986275,
|
|
"loss": 6.5844,
|
|
"mean_token_accuracy": 0.12824990823864937,
|
|
"num_tokens": 2404891.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.922542858123779,
|
|
"epoch": 0.11480042387848817,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999921191296415,
|
|
"loss": 6.6288,
|
|
"mean_token_accuracy": 0.12811262235045434,
|
|
"num_tokens": 2414406.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.860514211654663,
|
|
"epoch": 0.1152419639703285,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999918533531877,
|
|
"loss": 6.7126,
|
|
"mean_token_accuracy": 0.12714724242687225,
|
|
"num_tokens": 2424363.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.917534399032593,
|
|
"epoch": 0.11568350406216885,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999915831692714,
|
|
"loss": 6.6534,
|
|
"mean_token_accuracy": 0.12873802334070206,
|
|
"num_tokens": 2433753.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.790404272079468,
|
|
"epoch": 0.11612504415400918,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999913085778981,
|
|
"loss": 6.6769,
|
|
"mean_token_accuracy": 0.12445072457194328,
|
|
"num_tokens": 2443275.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.909478187561035,
|
|
"epoch": 0.11656658424584952,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999910295790729,
|
|
"loss": 6.6931,
|
|
"mean_token_accuracy": 0.12268302440643311,
|
|
"num_tokens": 2452510.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.915535879135132,
|
|
"epoch": 0.11700812433768987,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999907461728014,
|
|
"loss": 6.7807,
|
|
"mean_token_accuracy": 0.1234104610979557,
|
|
"num_tokens": 2462742.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.835855340957641,
|
|
"epoch": 0.1174496644295302,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999904583590893,
|
|
"loss": 6.6549,
|
|
"mean_token_accuracy": 0.12718312442302704,
|
|
"num_tokens": 2471409.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.876492547988891,
|
|
"epoch": 0.11789120452137054,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999901661379418,
|
|
"loss": 6.6053,
|
|
"mean_token_accuracy": 0.1328142687678337,
|
|
"num_tokens": 2481011.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.79636025428772,
|
|
"epoch": 0.11833274461321087,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999898695093652,
|
|
"loss": 6.6995,
|
|
"mean_token_accuracy": 0.12458944991230965,
|
|
"num_tokens": 2490664.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.888507127761841,
|
|
"epoch": 0.11877428470505122,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999895684733648,
|
|
"loss": 6.6235,
|
|
"mean_token_accuracy": 0.13585169985890388,
|
|
"num_tokens": 2499799.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.845640707015991,
|
|
"epoch": 0.11921582479689156,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999892630299467,
|
|
"loss": 6.6025,
|
|
"mean_token_accuracy": 0.12698834463953973,
|
|
"num_tokens": 2508780.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.898168849945068,
|
|
"epoch": 0.1196573648887319,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999889531791171,
|
|
"loss": 6.6341,
|
|
"mean_token_accuracy": 0.12324970662593841,
|
|
"num_tokens": 2517741.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.750218534469605,
|
|
"epoch": 0.12009890498057224,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999886389208817,
|
|
"loss": 6.7105,
|
|
"mean_token_accuracy": 0.12327531054615974,
|
|
"num_tokens": 2528742.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.880941247940063,
|
|
"epoch": 0.12054044507241257,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999883202552468,
|
|
"loss": 6.6444,
|
|
"mean_token_accuracy": 0.1296772688627243,
|
|
"num_tokens": 2538609.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.886623859405518,
|
|
"epoch": 0.12098198516425292,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999879971822189,
|
|
"loss": 6.6274,
|
|
"mean_token_accuracy": 0.12891870513558387,
|
|
"num_tokens": 2547772.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.6913806915283205,
|
|
"epoch": 0.12142352525609325,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999876697018038,
|
|
"loss": 6.6008,
|
|
"mean_token_accuracy": 0.13324561789631845,
|
|
"num_tokens": 2556114.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.90076265335083,
|
|
"epoch": 0.1218650653479336,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999873378140085,
|
|
"loss": 6.6339,
|
|
"mean_token_accuracy": 0.12988200038671494,
|
|
"num_tokens": 2566814.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.784169101715088,
|
|
"epoch": 0.12230660543977394,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999870015188389,
|
|
"loss": 6.6031,
|
|
"mean_token_accuracy": 0.13186766728758811,
|
|
"num_tokens": 2576030.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.762492084503174,
|
|
"epoch": 0.12274814553161427,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999866608163021,
|
|
"loss": 6.6231,
|
|
"mean_token_accuracy": 0.13228361681103706,
|
|
"num_tokens": 2585756.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.82820086479187,
|
|
"epoch": 0.12318968562345461,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999863157064045,
|
|
"loss": 6.6779,
|
|
"mean_token_accuracy": 0.1298144727945328,
|
|
"num_tokens": 2595676.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.848227310180664,
|
|
"epoch": 0.12363122571529495,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999859661891529,
|
|
"loss": 6.6748,
|
|
"mean_token_accuracy": 0.1304032675921917,
|
|
"num_tokens": 2606197.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.879591560363769,
|
|
"epoch": 0.12407276580713529,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999856122645543,
|
|
"loss": 6.5967,
|
|
"mean_token_accuracy": 0.12973913177847862,
|
|
"num_tokens": 2615311.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.734095478057862,
|
|
"epoch": 0.12451430589897562,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999852539326154,
|
|
"loss": 6.5243,
|
|
"mean_token_accuracy": 0.1325017362833023,
|
|
"num_tokens": 2624074.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.758558845520019,
|
|
"epoch": 0.12495584599081597,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999848911933434,
|
|
"loss": 6.6522,
|
|
"mean_token_accuracy": 0.13497036173939705,
|
|
"num_tokens": 2633877.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.745906019210816,
|
|
"epoch": 0.1253973860826563,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999845240467453,
|
|
"loss": 6.575,
|
|
"mean_token_accuracy": 0.12966776564717292,
|
|
"num_tokens": 2643330.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.863449001312256,
|
|
"epoch": 0.12583892617449666,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999841524928282,
|
|
"loss": 6.5664,
|
|
"mean_token_accuracy": 0.13387957438826562,
|
|
"num_tokens": 2652070.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.756294584274292,
|
|
"epoch": 0.126280466266337,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999837765315997,
|
|
"loss": 6.6242,
|
|
"mean_token_accuracy": 0.12831888422369958,
|
|
"num_tokens": 2660546.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.676768016815186,
|
|
"epoch": 0.12672200635817732,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999833961630669,
|
|
"loss": 6.507,
|
|
"mean_token_accuracy": 0.13364252746105193,
|
|
"num_tokens": 2669938.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.824239492416382,
|
|
"epoch": 0.12716354645001765,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999830113872374,
|
|
"loss": 6.637,
|
|
"mean_token_accuracy": 0.13026153072714805,
|
|
"num_tokens": 2679814.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.675518751144409,
|
|
"epoch": 0.127605086541858,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999826222041186,
|
|
"loss": 6.5447,
|
|
"mean_token_accuracy": 0.13804391250014306,
|
|
"num_tokens": 2688733.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.745492744445801,
|
|
"epoch": 0.12804662663369834,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999822286137182,
|
|
"loss": 6.5346,
|
|
"mean_token_accuracy": 0.13509366363286973,
|
|
"num_tokens": 2697744.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.658346796035767,
|
|
"epoch": 0.12848816672553867,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999818306160439,
|
|
"loss": 6.4971,
|
|
"mean_token_accuracy": 0.13757269233465194,
|
|
"num_tokens": 2707037.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.859276628494262,
|
|
"epoch": 0.12892970681737903,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999814282111034,
|
|
"loss": 6.6552,
|
|
"mean_token_accuracy": 0.13125866502523423,
|
|
"num_tokens": 2717345.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.818531513214111,
|
|
"epoch": 0.12937124690921936,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999810213989047,
|
|
"loss": 6.5966,
|
|
"mean_token_accuracy": 0.13112419992685317,
|
|
"num_tokens": 2726892.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.735688495635986,
|
|
"epoch": 0.1298127870010597,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999806101794558,
|
|
"loss": 6.572,
|
|
"mean_token_accuracy": 0.13323748409748076,
|
|
"num_tokens": 2736479.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.835882139205933,
|
|
"epoch": 0.13025432709290002,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999801945527648,
|
|
"loss": 6.6304,
|
|
"mean_token_accuracy": 0.12691461741924287,
|
|
"num_tokens": 2745998.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.753359127044678,
|
|
"epoch": 0.13069586718474038,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999797745188395,
|
|
"loss": 6.6159,
|
|
"mean_token_accuracy": 0.1317651830613613,
|
|
"num_tokens": 2754346.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.801856279373169,
|
|
"epoch": 0.13113740727658071,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999793500776886,
|
|
"loss": 6.5416,
|
|
"mean_token_accuracy": 0.13924193307757377,
|
|
"num_tokens": 2763391.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.706637144088745,
|
|
"epoch": 0.13157894736842105,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999789212293201,
|
|
"loss": 6.5867,
|
|
"mean_token_accuracy": 0.13430250883102418,
|
|
"num_tokens": 2772764.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.875431776046753,
|
|
"epoch": 0.1320204874602614,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999784879737423,
|
|
"loss": 6.6781,
|
|
"mean_token_accuracy": 0.1260899782180786,
|
|
"num_tokens": 2782312.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.746471691131592,
|
|
"epoch": 0.13246202755210174,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999780503109642,
|
|
"loss": 6.5979,
|
|
"mean_token_accuracy": 0.1290306605398655,
|
|
"num_tokens": 2791159.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.704893779754639,
|
|
"epoch": 0.13290356764394207,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999776082409939,
|
|
"loss": 6.408,
|
|
"mean_token_accuracy": 0.13926204219460486,
|
|
"num_tokens": 2799319.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.6507806301116945,
|
|
"epoch": 0.1333451077357824,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999771617638401,
|
|
"loss": 6.5335,
|
|
"mean_token_accuracy": 0.13334701284766198,
|
|
"num_tokens": 2807401.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.7505804061889645,
|
|
"epoch": 0.13378664782762276,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999767108795118,
|
|
"loss": 6.6075,
|
|
"mean_token_accuracy": 0.1309545248746872,
|
|
"num_tokens": 2817734.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.790192747116089,
|
|
"epoch": 0.1342281879194631,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999762555880176,
|
|
"loss": 6.5906,
|
|
"mean_token_accuracy": 0.12997578456997871,
|
|
"num_tokens": 2828235.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.771645879745483,
|
|
"epoch": 0.13466972801130342,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999757958893666,
|
|
"loss": 6.6309,
|
|
"mean_token_accuracy": 0.1289198786020279,
|
|
"num_tokens": 2837453.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.712240839004517,
|
|
"epoch": 0.13511126810314378,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999753317835677,
|
|
"loss": 6.587,
|
|
"mean_token_accuracy": 0.12751804441213607,
|
|
"num_tokens": 2847055.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.758566999435425,
|
|
"epoch": 0.1355528081949841,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999748632706299,
|
|
"loss": 6.5597,
|
|
"mean_token_accuracy": 0.13620577305555343,
|
|
"num_tokens": 2857101.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.699764680862427,
|
|
"epoch": 0.13599434828682444,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999743903505626,
|
|
"loss": 6.4845,
|
|
"mean_token_accuracy": 0.13134869784116746,
|
|
"num_tokens": 2866685.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.813828182220459,
|
|
"epoch": 0.13643588837866477,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999739130233749,
|
|
"loss": 6.5821,
|
|
"mean_token_accuracy": 0.1299674078822136,
|
|
"num_tokens": 2876022.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.708414220809937,
|
|
"epoch": 0.13687742847050513,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999734312890761,
|
|
"loss": 6.5192,
|
|
"mean_token_accuracy": 0.12855476662516593,
|
|
"num_tokens": 2885560.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.690548992156982,
|
|
"epoch": 0.13731896856234546,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999729451476757,
|
|
"loss": 6.5568,
|
|
"mean_token_accuracy": 0.13441056087613107,
|
|
"num_tokens": 2894686.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.749054193496704,
|
|
"epoch": 0.1377605086541858,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999724545991835,
|
|
"loss": 6.5599,
|
|
"mean_token_accuracy": 0.1379253476858139,
|
|
"num_tokens": 2904390.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.715701723098755,
|
|
"epoch": 0.13820204874602615,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999719596436086,
|
|
"loss": 6.6185,
|
|
"mean_token_accuracy": 0.13158311247825621,
|
|
"num_tokens": 2913311.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.777320003509521,
|
|
"epoch": 0.13864358883786648,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999714602809611,
|
|
"loss": 6.4916,
|
|
"mean_token_accuracy": 0.13447055071592331,
|
|
"num_tokens": 2923196.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.681281852722168,
|
|
"epoch": 0.1390851289297068,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999709565112506,
|
|
"loss": 6.5513,
|
|
"mean_token_accuracy": 0.13382177129387857,
|
|
"num_tokens": 2932813.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.7223258972167965,
|
|
"epoch": 0.13952666902154715,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499970448334487,
|
|
"loss": 6.4762,
|
|
"mean_token_accuracy": 0.12845111936330794,
|
|
"num_tokens": 2942694.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.633160924911499,
|
|
"epoch": 0.1399682091133875,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999699357506803,
|
|
"loss": 6.4203,
|
|
"mean_token_accuracy": 0.14310574680566787,
|
|
"num_tokens": 2950932.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.733539772033692,
|
|
"epoch": 0.14040974920522784,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999694187598406,
|
|
"loss": 6.5208,
|
|
"mean_token_accuracy": 0.1363385871052742,
|
|
"num_tokens": 2960102.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.716689872741699,
|
|
"epoch": 0.14085128929706817,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004999688973619777,
|
|
"loss": 6.5161,
|
|
"mean_token_accuracy": 0.1320077233016491,
|
|
"num_tokens": 2969968.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.624239683151245,
|
|
"epoch": 0.14129282938890853,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999683715571022,
|
|
"loss": 6.4732,
|
|
"mean_token_accuracy": 0.14136387258768082,
|
|
"num_tokens": 2978880.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.666266059875488,
|
|
"epoch": 0.14173436948074886,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999678413452242,
|
|
"loss": 6.5087,
|
|
"mean_token_accuracy": 0.1332849942147732,
|
|
"num_tokens": 2988369.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.669563817977905,
|
|
"epoch": 0.1421759095725892,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999673067263542,
|
|
"loss": 6.5549,
|
|
"mean_token_accuracy": 0.1297246351838112,
|
|
"num_tokens": 2997070.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.7209991931915285,
|
|
"epoch": 0.14261744966442952,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999667677005026,
|
|
"loss": 6.4881,
|
|
"mean_token_accuracy": 0.1361941583454609,
|
|
"num_tokens": 3006547.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.670996856689453,
|
|
"epoch": 0.14305898975626988,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999662242676799,
|
|
"loss": 6.5007,
|
|
"mean_token_accuracy": 0.13505242466926576,
|
|
"num_tokens": 3015821.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.667819404602051,
|
|
"epoch": 0.1435005298481102,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999656764278968,
|
|
"loss": 6.4863,
|
|
"mean_token_accuracy": 0.13409159779548646,
|
|
"num_tokens": 3024750.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.699454641342163,
|
|
"epoch": 0.14394206993995054,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999651241811642,
|
|
"loss": 6.4543,
|
|
"mean_token_accuracy": 0.13378062024712561,
|
|
"num_tokens": 3033345.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.63138108253479,
|
|
"epoch": 0.1443836100317909,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999645675274925,
|
|
"loss": 6.4314,
|
|
"mean_token_accuracy": 0.1369638502597809,
|
|
"num_tokens": 3042060.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.6189075946807865,
|
|
"epoch": 0.14482515012363123,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999640064668931,
|
|
"loss": 6.584,
|
|
"mean_token_accuracy": 0.1317050538957119,
|
|
"num_tokens": 3052490.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.820568704605103,
|
|
"epoch": 0.14526669021547156,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999634409993766,
|
|
"loss": 6.5606,
|
|
"mean_token_accuracy": 0.1320354349911213,
|
|
"num_tokens": 3061934.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.609713792800903,
|
|
"epoch": 0.1457082303073119,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999628711249544,
|
|
"loss": 6.4512,
|
|
"mean_token_accuracy": 0.14322613999247552,
|
|
"num_tokens": 3070890.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.7396402835845945,
|
|
"epoch": 0.14614977039915225,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999622968436373,
|
|
"loss": 6.4715,
|
|
"mean_token_accuracy": 0.13257212415337563,
|
|
"num_tokens": 3079933.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.579079866409302,
|
|
"epoch": 0.14659131049099258,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999617181554369,
|
|
"loss": 6.5248,
|
|
"mean_token_accuracy": 0.13561063706874849,
|
|
"num_tokens": 3089910.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.757257795333862,
|
|
"epoch": 0.1470328505828329,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999611350603643,
|
|
"loss": 6.5275,
|
|
"mean_token_accuracy": 0.13599081262946128,
|
|
"num_tokens": 3098676.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.642300748825074,
|
|
"epoch": 0.14747439067467327,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499960547558431,
|
|
"loss": 6.6165,
|
|
"mean_token_accuracy": 0.13092149198055267,
|
|
"num_tokens": 3109055.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.597188997268677,
|
|
"epoch": 0.1479159307665136,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999599556496486,
|
|
"loss": 6.4706,
|
|
"mean_token_accuracy": 0.13985515162348747,
|
|
"num_tokens": 3117517.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.640227365493774,
|
|
"epoch": 0.14835747085835393,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999593593340286,
|
|
"loss": 6.463,
|
|
"mean_token_accuracy": 0.14289223924279212,
|
|
"num_tokens": 3126606.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.657995748519897,
|
|
"epoch": 0.14879901095019427,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999587586115826,
|
|
"loss": 6.4902,
|
|
"mean_token_accuracy": 0.1365136206150055,
|
|
"num_tokens": 3135444.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.682824659347534,
|
|
"epoch": 0.14924055104203462,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999581534823226,
|
|
"loss": 6.4214,
|
|
"mean_token_accuracy": 0.14298791959881782,
|
|
"num_tokens": 3144967.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.649335050582886,
|
|
"epoch": 0.14968209113387496,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999575439462601,
|
|
"loss": 6.4563,
|
|
"mean_token_accuracy": 0.13346426337957382,
|
|
"num_tokens": 3153898.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.639866065979004,
|
|
"epoch": 0.1501236312257153,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999569300034075,
|
|
"loss": 6.5099,
|
|
"mean_token_accuracy": 0.13122038245201112,
|
|
"num_tokens": 3162341.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.621887493133545,
|
|
"epoch": 0.15056517131755565,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999563116537764,
|
|
"loss": 6.3038,
|
|
"mean_token_accuracy": 0.1461081884801388,
|
|
"num_tokens": 3171420.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.58403959274292,
|
|
"epoch": 0.15100671140939598,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999556888973792,
|
|
"loss": 6.3453,
|
|
"mean_token_accuracy": 0.14070172980427742,
|
|
"num_tokens": 3180221.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.7422089099884035,
|
|
"epoch": 0.1514482515012363,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999550617342279,
|
|
"loss": 6.5005,
|
|
"mean_token_accuracy": 0.1325171984732151,
|
|
"num_tokens": 3189156.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.5561034202575685,
|
|
"epoch": 0.15188979159307664,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499954430164335,
|
|
"loss": 6.4253,
|
|
"mean_token_accuracy": 0.13670367896556854,
|
|
"num_tokens": 3199870.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.655413389205933,
|
|
"epoch": 0.152331331684917,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999537941877127,
|
|
"loss": 6.4231,
|
|
"mean_token_accuracy": 0.14037118926644326,
|
|
"num_tokens": 3208815.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.575525569915771,
|
|
"epoch": 0.15277287177675733,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999531538043735,
|
|
"loss": 6.4845,
|
|
"mean_token_accuracy": 0.137246023863554,
|
|
"num_tokens": 3218692.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.627863502502441,
|
|
"epoch": 0.15321441186859766,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999525090143298,
|
|
"loss": 6.4482,
|
|
"mean_token_accuracy": 0.14504025802016257,
|
|
"num_tokens": 3227604.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.625754451751709,
|
|
"epoch": 0.15365595196043802,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999518598175946,
|
|
"loss": 6.4675,
|
|
"mean_token_accuracy": 0.14471371322870255,
|
|
"num_tokens": 3237912.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.527244615554809,
|
|
"epoch": 0.15409749205227835,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999512062141805,
|
|
"loss": 6.3302,
|
|
"mean_token_accuracy": 0.14219417944550514,
|
|
"num_tokens": 3246003.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.632448387145996,
|
|
"epoch": 0.15453903214411868,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999505482040999,
|
|
"loss": 6.4719,
|
|
"mean_token_accuracy": 0.13460535928606987,
|
|
"num_tokens": 3256363.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.610141611099243,
|
|
"epoch": 0.154980572235959,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999498857873662,
|
|
"loss": 6.4661,
|
|
"mean_token_accuracy": 0.13534337058663368,
|
|
"num_tokens": 3265822.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.538852977752685,
|
|
"epoch": 0.15542211232779937,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999492189639921,
|
|
"loss": 6.3683,
|
|
"mean_token_accuracy": 0.14053185135126114,
|
|
"num_tokens": 3274614.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.577081727981567,
|
|
"epoch": 0.1558636524196397,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999485477339907,
|
|
"loss": 6.4384,
|
|
"mean_token_accuracy": 0.13609417378902436,
|
|
"num_tokens": 3283800.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.623507022857666,
|
|
"epoch": 0.15630519251148003,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999478720973753,
|
|
"loss": 6.3582,
|
|
"mean_token_accuracy": 0.14612039923667908,
|
|
"num_tokens": 3293221.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.631183099746704,
|
|
"epoch": 0.1567467326033204,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499947192054159,
|
|
"loss": 6.5087,
|
|
"mean_token_accuracy": 0.13212059661746026,
|
|
"num_tokens": 3302852.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.668994379043579,
|
|
"epoch": 0.15718827269516072,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499946507604355,
|
|
"loss": 6.3761,
|
|
"mean_token_accuracy": 0.14372102692723274,
|
|
"num_tokens": 3311752.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.522418546676636,
|
|
"epoch": 0.15762981278700106,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499945818747977,
|
|
"loss": 6.4622,
|
|
"mean_token_accuracy": 0.14355819597840308,
|
|
"num_tokens": 3321339.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.667537021636963,
|
|
"epoch": 0.1580713528788414,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999451254850383,
|
|
"loss": 6.4756,
|
|
"mean_token_accuracy": 0.13703957572579384,
|
|
"num_tokens": 3330269.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.634947395324707,
|
|
"epoch": 0.15851289297068175,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999444278155525,
|
|
"loss": 6.4032,
|
|
"mean_token_accuracy": 0.14509668350219726,
|
|
"num_tokens": 3340770.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.548423147201538,
|
|
"epoch": 0.15895443306252208,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999437257395333,
|
|
"loss": 6.4725,
|
|
"mean_token_accuracy": 0.1425343744456768,
|
|
"num_tokens": 3349976.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.667039012908935,
|
|
"epoch": 0.1593959731543624,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999430192569944,
|
|
"loss": 6.5242,
|
|
"mean_token_accuracy": 0.13105336651206018,
|
|
"num_tokens": 3359764.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.581896781921387,
|
|
"epoch": 0.15983751324620277,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999423083679498,
|
|
"loss": 6.405,
|
|
"mean_token_accuracy": 0.13858939930796624,
|
|
"num_tokens": 3369939.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.633963489532471,
|
|
"epoch": 0.1602790533380431,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999415930724133,
|
|
"loss": 6.5557,
|
|
"mean_token_accuracy": 0.1334507644176483,
|
|
"num_tokens": 3381326.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.706169319152832,
|
|
"epoch": 0.16072059342988343,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999408733703988,
|
|
"loss": 6.5135,
|
|
"mean_token_accuracy": 0.13054400235414504,
|
|
"num_tokens": 3391016.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.57712345123291,
|
|
"epoch": 0.16116213352172376,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999401492619207,
|
|
"loss": 6.2754,
|
|
"mean_token_accuracy": 0.14139460623264313,
|
|
"num_tokens": 3400294.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.533513784408569,
|
|
"epoch": 0.16160367361356412,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999394207469928,
|
|
"loss": 6.4737,
|
|
"mean_token_accuracy": 0.13292715698480606,
|
|
"num_tokens": 3409685.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.695759248733521,
|
|
"epoch": 0.16204521370540445,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999386878256297,
|
|
"loss": 6.3887,
|
|
"mean_token_accuracy": 0.13601208254694938,
|
|
"num_tokens": 3418946.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.4282214641571045,
|
|
"epoch": 0.16248675379724478,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999379504978457,
|
|
"loss": 6.3763,
|
|
"mean_token_accuracy": 0.13835799768567086,
|
|
"num_tokens": 3428245.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.614362144470215,
|
|
"epoch": 0.16292829388908514,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499937208763655,
|
|
"loss": 6.3958,
|
|
"mean_token_accuracy": 0.14421852231025695,
|
|
"num_tokens": 3437580.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.64262170791626,
|
|
"epoch": 0.16336983398092547,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999364626230724,
|
|
"loss": 6.3701,
|
|
"mean_token_accuracy": 0.14203060865402223,
|
|
"num_tokens": 3446393.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.477195358276367,
|
|
"epoch": 0.1638113740727658,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999357120761124,
|
|
"loss": 6.4748,
|
|
"mean_token_accuracy": 0.1370338521897793,
|
|
"num_tokens": 3455956.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.65583610534668,
|
|
"epoch": 0.16425291416460613,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999349571227898,
|
|
"loss": 6.4634,
|
|
"mean_token_accuracy": 0.1417573131620884,
|
|
"num_tokens": 3465722.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.579311370849609,
|
|
"epoch": 0.1646944542564465,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999341977631193,
|
|
"loss": 6.4233,
|
|
"mean_token_accuracy": 0.13521963283419608,
|
|
"num_tokens": 3475467.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.563374280929565,
|
|
"epoch": 0.16513599434828682,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999334339971157,
|
|
"loss": 6.3294,
|
|
"mean_token_accuracy": 0.140533210337162,
|
|
"num_tokens": 3484931.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.542880487442017,
|
|
"epoch": 0.16557753444012716,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999326658247942,
|
|
"loss": 6.4374,
|
|
"mean_token_accuracy": 0.14069321602582932,
|
|
"num_tokens": 3494001.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.596772766113281,
|
|
"epoch": 0.16601907453196751,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999318932461696,
|
|
"loss": 6.3622,
|
|
"mean_token_accuracy": 0.14485045671463012,
|
|
"num_tokens": 3503021.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.477844142913819,
|
|
"epoch": 0.16646061462380785,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999311162612571,
|
|
"loss": 6.4034,
|
|
"mean_token_accuracy": 0.1405440613627434,
|
|
"num_tokens": 3513005.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.664361810684204,
|
|
"epoch": 0.16690215471564818,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499930334870072,
|
|
"loss": 6.468,
|
|
"mean_token_accuracy": 0.14140931516885757,
|
|
"num_tokens": 3523219.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.607090282440185,
|
|
"epoch": 0.1673436948074885,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999295490726296,
|
|
"loss": 6.4475,
|
|
"mean_token_accuracy": 0.13736767545342446,
|
|
"num_tokens": 3532917.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.548594951629639,
|
|
"epoch": 0.16778523489932887,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999287588689453,
|
|
"loss": 6.4314,
|
|
"mean_token_accuracy": 0.14416549280285834,
|
|
"num_tokens": 3542845.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.615040254592896,
|
|
"epoch": 0.1682267749911692,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999279642590344,
|
|
"loss": 6.4644,
|
|
"mean_token_accuracy": 0.14099383279681205,
|
|
"num_tokens": 3552126.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.59620246887207,
|
|
"epoch": 0.16866831508300953,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999271652429127,
|
|
"loss": 6.4683,
|
|
"mean_token_accuracy": 0.13365241289138793,
|
|
"num_tokens": 3561254.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.603018665313721,
|
|
"epoch": 0.1691098551748499,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999263618205958,
|
|
"loss": 6.3064,
|
|
"mean_token_accuracy": 0.14801083952188493,
|
|
"num_tokens": 3569781.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.507657670974732,
|
|
"epoch": 0.16955139526669022,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999255539920993,
|
|
"loss": 6.4154,
|
|
"mean_token_accuracy": 0.13945700079202653,
|
|
"num_tokens": 3579664.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.607545375823975,
|
|
"epoch": 0.16999293535853055,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999247417574391,
|
|
"loss": 6.4491,
|
|
"mean_token_accuracy": 0.14012959450483323,
|
|
"num_tokens": 3588671.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.5801286697387695,
|
|
"epoch": 0.17043447545037088,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999239251166312,
|
|
"loss": 6.3639,
|
|
"mean_token_accuracy": 0.14608858227729798,
|
|
"num_tokens": 3597656.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.465410947799683,
|
|
"epoch": 0.17087601554221124,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999231040696914,
|
|
"loss": 6.373,
|
|
"mean_token_accuracy": 0.14378879442811013,
|
|
"num_tokens": 3608017.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.607225227355957,
|
|
"epoch": 0.17131755563405157,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999222786166361,
|
|
"loss": 6.4412,
|
|
"mean_token_accuracy": 0.14090094193816186,
|
|
"num_tokens": 3618189.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.596541976928711,
|
|
"epoch": 0.1717590957258919,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999214487574812,
|
|
"loss": 6.3977,
|
|
"mean_token_accuracy": 0.1351962171494961,
|
|
"num_tokens": 3627211.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.564425277709961,
|
|
"epoch": 0.17220063581773226,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999206144922431,
|
|
"loss": 6.331,
|
|
"mean_token_accuracy": 0.1392312839627266,
|
|
"num_tokens": 3636781.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.521996641159058,
|
|
"epoch": 0.1726421759095726,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499919775820938,
|
|
"loss": 6.4204,
|
|
"mean_token_accuracy": 0.1457922250032425,
|
|
"num_tokens": 3644891.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.611178350448609,
|
|
"epoch": 0.17308371600141292,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999189327435825,
|
|
"loss": 6.4558,
|
|
"mean_token_accuracy": 0.13934372514486312,
|
|
"num_tokens": 3655477.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.615030193328858,
|
|
"epoch": 0.17352525609325326,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999180852601929,
|
|
"loss": 6.4555,
|
|
"mean_token_accuracy": 0.1424385577440262,
|
|
"num_tokens": 3664542.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.556003856658935,
|
|
"epoch": 0.17396679618509361,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499917233370786,
|
|
"loss": 6.3637,
|
|
"mean_token_accuracy": 0.13885778263211251,
|
|
"num_tokens": 3673806.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.537166738510132,
|
|
"epoch": 0.17440833627693395,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999163770753784,
|
|
"loss": 6.3706,
|
|
"mean_token_accuracy": 0.14099680185317992,
|
|
"num_tokens": 3683238.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.504315948486328,
|
|
"epoch": 0.17484987636877428,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999155163739869,
|
|
"loss": 6.3407,
|
|
"mean_token_accuracy": 0.14536889716982843,
|
|
"num_tokens": 3692161.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.581552124023437,
|
|
"epoch": 0.17529141646061464,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999146512666284,
|
|
"loss": 6.367,
|
|
"mean_token_accuracy": 0.1379326641559601,
|
|
"num_tokens": 3701431.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.487573671340942,
|
|
"epoch": 0.17573295655245497,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999137817533197,
|
|
"loss": 6.3461,
|
|
"mean_token_accuracy": 0.14381761997938156,
|
|
"num_tokens": 3710963.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.506614542007446,
|
|
"epoch": 0.1761744966442953,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999129078340779,
|
|
"loss": 6.3353,
|
|
"mean_token_accuracy": 0.14846789166331292,
|
|
"num_tokens": 3720177.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.530578517913819,
|
|
"epoch": 0.17661603673613563,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999120295089202,
|
|
"loss": 6.2971,
|
|
"mean_token_accuracy": 0.14959900006651877,
|
|
"num_tokens": 3728123.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.542397546768188,
|
|
"epoch": 0.177057576827976,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999111467778639,
|
|
"loss": 6.4341,
|
|
"mean_token_accuracy": 0.1391107402741909,
|
|
"num_tokens": 3736869.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.53966269493103,
|
|
"epoch": 0.17749911691981632,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499910259640926,
|
|
"loss": 6.3237,
|
|
"mean_token_accuracy": 0.14294100552797318,
|
|
"num_tokens": 3745830.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.51638708114624,
|
|
"epoch": 0.17794065701165665,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499909368098124,
|
|
"loss": 6.3564,
|
|
"mean_token_accuracy": 0.13725989684462547,
|
|
"num_tokens": 3755019.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.511772108078003,
|
|
"epoch": 0.178382197103497,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999084721494754,
|
|
"loss": 6.331,
|
|
"mean_token_accuracy": 0.14094301015138627,
|
|
"num_tokens": 3764814.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.452651882171631,
|
|
"epoch": 0.17882373719533734,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999075717949978,
|
|
"loss": 6.2835,
|
|
"mean_token_accuracy": 0.14623287171125413,
|
|
"num_tokens": 3774258.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.427514886856079,
|
|
"epoch": 0.17926527728717767,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999066670347089,
|
|
"loss": 6.3158,
|
|
"mean_token_accuracy": 0.1432214617729187,
|
|
"num_tokens": 3783961.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.497758913040161,
|
|
"epoch": 0.179706817379018,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999057578686261,
|
|
"loss": 6.2899,
|
|
"mean_token_accuracy": 0.14475978389382363,
|
|
"num_tokens": 3792417.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.472495174407959,
|
|
"epoch": 0.18014835747085836,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999048442967675,
|
|
"loss": 6.2812,
|
|
"mean_token_accuracy": 0.14342265501618384,
|
|
"num_tokens": 3801479.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.572735977172852,
|
|
"epoch": 0.1805898975626987,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999039263191508,
|
|
"loss": 6.3581,
|
|
"mean_token_accuracy": 0.13960720375180244,
|
|
"num_tokens": 3810799.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.510642623901367,
|
|
"epoch": 0.18103143765453902,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999030039357943,
|
|
"loss": 6.3896,
|
|
"mean_token_accuracy": 0.13761023208498954,
|
|
"num_tokens": 3820966.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.4944600582122805,
|
|
"epoch": 0.18147297774637938,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999020771467158,
|
|
"loss": 6.3647,
|
|
"mean_token_accuracy": 0.1407288655638695,
|
|
"num_tokens": 3829247.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.609596920013428,
|
|
"epoch": 0.1819145178382197,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999011459519335,
|
|
"loss": 6.3036,
|
|
"mean_token_accuracy": 0.14792885035276412,
|
|
"num_tokens": 3838114.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.411144733428955,
|
|
"epoch": 0.18235605793006004,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999002103514655,
|
|
"loss": 6.3792,
|
|
"mean_token_accuracy": 0.142097420245409,
|
|
"num_tokens": 3848075.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.5771557807922365,
|
|
"epoch": 0.18279759802190038,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998992703453304,
|
|
"loss": 6.4163,
|
|
"mean_token_accuracy": 0.14099472612142563,
|
|
"num_tokens": 3857934.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.490412330627441,
|
|
"epoch": 0.18323913811374073,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998983259335466,
|
|
"loss": 6.2769,
|
|
"mean_token_accuracy": 0.15167167782783508,
|
|
"num_tokens": 3866707.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.511580276489258,
|
|
"epoch": 0.18368067820558107,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998973771161324,
|
|
"loss": 6.3342,
|
|
"mean_token_accuracy": 0.14083316251635553,
|
|
"num_tokens": 3875233.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.495502281188965,
|
|
"epoch": 0.1841222182974214,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998964238931065,
|
|
"loss": 6.3311,
|
|
"mean_token_accuracy": 0.1447795733809471,
|
|
"num_tokens": 3885173.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.511646032333374,
|
|
"epoch": 0.18456375838926176,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998954662644876,
|
|
"loss": 6.3103,
|
|
"mean_token_accuracy": 0.14369324892759322,
|
|
"num_tokens": 3894198.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.465791845321656,
|
|
"epoch": 0.1850052984811021,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998945042302943,
|
|
"loss": 6.3043,
|
|
"mean_token_accuracy": 0.14370952174067497,
|
|
"num_tokens": 3904076.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.529692268371582,
|
|
"epoch": 0.18544683857294242,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998935377905457,
|
|
"loss": 6.414,
|
|
"mean_token_accuracy": 0.13739102557301522,
|
|
"num_tokens": 3913204.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.59678544998169,
|
|
"epoch": 0.18588837866478275,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998925669452605,
|
|
"loss": 6.3665,
|
|
"mean_token_accuracy": 0.14387816935777664,
|
|
"num_tokens": 3922148.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.451368236541748,
|
|
"epoch": 0.1863299187566231,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998915916944579,
|
|
"loss": 6.336,
|
|
"mean_token_accuracy": 0.14496995508670807,
|
|
"num_tokens": 3931333.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.508979606628418,
|
|
"epoch": 0.18677145884846344,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998906120381568,
|
|
"loss": 6.2869,
|
|
"mean_token_accuracy": 0.14773214906454085,
|
|
"num_tokens": 3941061.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.536288022994995,
|
|
"epoch": 0.18721299894030377,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998896279763766,
|
|
"loss": 6.3841,
|
|
"mean_token_accuracy": 0.13904453590512275,
|
|
"num_tokens": 3950075.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.4915399074554445,
|
|
"epoch": 0.18765453903214413,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998886395091365,
|
|
"loss": 6.2552,
|
|
"mean_token_accuracy": 0.1421836346387863,
|
|
"num_tokens": 3958885.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.379503393173218,
|
|
"epoch": 0.18809607912398446,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998876466364559,
|
|
"loss": 6.3307,
|
|
"mean_token_accuracy": 0.1476896308362484,
|
|
"num_tokens": 3968218.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.450522613525391,
|
|
"epoch": 0.1885376192158248,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998866493583541,
|
|
"loss": 6.2918,
|
|
"mean_token_accuracy": 0.14630952328443528,
|
|
"num_tokens": 3977435.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.4365739822387695,
|
|
"epoch": 0.18897915930766512,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998856476748509,
|
|
"loss": 6.2738,
|
|
"mean_token_accuracy": 0.14805593118071556,
|
|
"num_tokens": 3986608.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.498980379104614,
|
|
"epoch": 0.18942069939950548,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998846415859656,
|
|
"loss": 6.2719,
|
|
"mean_token_accuracy": 0.14355492740869522,
|
|
"num_tokens": 3996087.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.4271481990814205,
|
|
"epoch": 0.1898622394913458,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998836310917182,
|
|
"loss": 6.3259,
|
|
"mean_token_accuracy": 0.13990697860717774,
|
|
"num_tokens": 4006257.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.432379961013794,
|
|
"epoch": 0.19030377958318614,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998826161921282,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.1525232471525669,
|
|
"num_tokens": 4015904.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.395722532272339,
|
|
"epoch": 0.1907453196750265,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998815968872157,
|
|
"loss": 6.3357,
|
|
"mean_token_accuracy": 0.14217145144939422,
|
|
"num_tokens": 4025417.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.434484338760376,
|
|
"epoch": 0.19118685976686683,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998805731770007,
|
|
"loss": 6.194,
|
|
"mean_token_accuracy": 0.16098422557115555,
|
|
"num_tokens": 4035181.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.466515350341797,
|
|
"epoch": 0.19162839985870717,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499879545061503,
|
|
"loss": 6.3656,
|
|
"mean_token_accuracy": 0.14232496544718742,
|
|
"num_tokens": 4045112.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.544062900543213,
|
|
"epoch": 0.1920699399505475,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998785125407432,
|
|
"loss": 6.468,
|
|
"mean_token_accuracy": 0.13045382052659987,
|
|
"num_tokens": 4054566.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.538053798675537,
|
|
"epoch": 0.19251148004238786,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499877475614741,
|
|
"loss": 6.2829,
|
|
"mean_token_accuracy": 0.14255435317754744,
|
|
"num_tokens": 4063960.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.318663692474365,
|
|
"epoch": 0.1929530201342282,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998764342835169,
|
|
"loss": 6.2248,
|
|
"mean_token_accuracy": 0.14946237206459045,
|
|
"num_tokens": 4072620.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.361247396469116,
|
|
"epoch": 0.19339456022606852,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998753885470915,
|
|
"loss": 6.1939,
|
|
"mean_token_accuracy": 0.15080117732286452,
|
|
"num_tokens": 4081590.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.448186588287354,
|
|
"epoch": 0.19383610031790888,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998743384054851,
|
|
"loss": 6.3243,
|
|
"mean_token_accuracy": 0.15017441809177398,
|
|
"num_tokens": 4090758.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.359209203720093,
|
|
"epoch": 0.1942776404097492,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998732838587183,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.1547905460000038,
|
|
"num_tokens": 4099281.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.484091281890869,
|
|
"epoch": 0.19471918050158954,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998722249068118,
|
|
"loss": 6.2579,
|
|
"mean_token_accuracy": 0.14498598128557205,
|
|
"num_tokens": 4108953.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.412591505050659,
|
|
"epoch": 0.19516072059342987,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998711615497863,
|
|
"loss": 6.365,
|
|
"mean_token_accuracy": 0.1421401210129261,
|
|
"num_tokens": 4118799.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.515138959884643,
|
|
"epoch": 0.19560226068527023,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998700937876626,
|
|
"loss": 6.3215,
|
|
"mean_token_accuracy": 0.14281034767627715,
|
|
"num_tokens": 4127862.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.504071760177612,
|
|
"epoch": 0.19604380077711056,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998690216204615,
|
|
"loss": 6.4025,
|
|
"mean_token_accuracy": 0.13254041969776154,
|
|
"num_tokens": 4139029.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.468188190460205,
|
|
"epoch": 0.1964853408689509,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998679450482043,
|
|
"loss": 6.2211,
|
|
"mean_token_accuracy": 0.15794688761234282,
|
|
"num_tokens": 4148257.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.399339389801026,
|
|
"epoch": 0.19692688096079125,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499866864070912,
|
|
"loss": 6.1777,
|
|
"mean_token_accuracy": 0.14184310287237167,
|
|
"num_tokens": 4157626.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.394889450073242,
|
|
"epoch": 0.19736842105263158,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998657786886056,
|
|
"loss": 6.4048,
|
|
"mean_token_accuracy": 0.1460250087082386,
|
|
"num_tokens": 4166804.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.561651229858398,
|
|
"epoch": 0.1978099611444719,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998646889013066,
|
|
"loss": 6.2711,
|
|
"mean_token_accuracy": 0.14743182435631752,
|
|
"num_tokens": 4175701.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.471790933609009,
|
|
"epoch": 0.19825150123631224,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998635947090362,
|
|
"loss": 6.3589,
|
|
"mean_token_accuracy": 0.1456327997148037,
|
|
"num_tokens": 4184711.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.440358591079712,
|
|
"epoch": 0.1986930413281526,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004998624961118158,
|
|
"loss": 6.3148,
|
|
"mean_token_accuracy": 0.1504688784480095,
|
|
"num_tokens": 4193931.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.443251514434815,
|
|
"epoch": 0.19913458141999293,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499861393109667,
|
|
"loss": 6.1933,
|
|
"mean_token_accuracy": 0.15764214992523193,
|
|
"num_tokens": 4203000.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.3125227928161625,
|
|
"epoch": 0.19957612151183327,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998602857026114,
|
|
"loss": 6.214,
|
|
"mean_token_accuracy": 0.1494602829217911,
|
|
"num_tokens": 4211977.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.4371459007263185,
|
|
"epoch": 0.20001766160367362,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998591738906708,
|
|
"loss": 6.2855,
|
|
"mean_token_accuracy": 0.15524563640356065,
|
|
"num_tokens": 4220375.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.506232404708863,
|
|
"epoch": 0.20045920169551396,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998580576738668,
|
|
"loss": 6.3022,
|
|
"mean_token_accuracy": 0.14764061123132705,
|
|
"num_tokens": 4230506.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.4268731594085695,
|
|
"epoch": 0.2009007417873543,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998569370522213,
|
|
"loss": 6.2711,
|
|
"mean_token_accuracy": 0.1487172946333885,
|
|
"num_tokens": 4240235.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.3987833023071286,
|
|
"epoch": 0.20134228187919462,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998558120257563,
|
|
"loss": 6.3105,
|
|
"mean_token_accuracy": 0.1501203641295433,
|
|
"num_tokens": 4249775.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.428017330169678,
|
|
"epoch": 0.20178382197103498,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998546825944938,
|
|
"loss": 6.2596,
|
|
"mean_token_accuracy": 0.14586075246334076,
|
|
"num_tokens": 4258523.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.456875276565552,
|
|
"epoch": 0.2022253620628753,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499853548758456,
|
|
"loss": 6.2549,
|
|
"mean_token_accuracy": 0.14920931309461594,
|
|
"num_tokens": 4267683.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.502974796295166,
|
|
"epoch": 0.20266690215471564,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000499852410517665,
|
|
"loss": 6.3396,
|
|
"mean_token_accuracy": 0.1415552243590355,
|
|
"num_tokens": 4276903.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.390913295745849,
|
|
"epoch": 0.203108442246556,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004998512678721431,
|
|
"loss": 6.2765,
|
|
"mean_token_accuracy": 0.14179632887244226,
|
|
"num_tokens": 4287257.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.467247819900512,
|
|
"epoch": 0.20354998233839633,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499850120821913,
|
|
"loss": 6.2994,
|
|
"mean_token_accuracy": 0.1429171495139599,
|
|
"num_tokens": 4297345.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.504390478134155,
|
|
"epoch": 0.20399152243023666,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998489693669967,
|
|
"loss": 6.2774,
|
|
"mean_token_accuracy": 0.14350235760211943,
|
|
"num_tokens": 4306533.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.430126476287842,
|
|
"epoch": 0.204433062522077,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499847813507417,
|
|
"loss": 6.3142,
|
|
"mean_token_accuracy": 0.14808136820793152,
|
|
"num_tokens": 4316338.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.418506526947022,
|
|
"epoch": 0.20487460261391735,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998466532431966,
|
|
"loss": 6.2461,
|
|
"mean_token_accuracy": 0.14408156126737595,
|
|
"num_tokens": 4326585.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.502306318283081,
|
|
"epoch": 0.20531614270575768,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998454885743581,
|
|
"loss": 6.4021,
|
|
"mean_token_accuracy": 0.1425124689936638,
|
|
"num_tokens": 4336490.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.4134602546691895,
|
|
"epoch": 0.205757682797598,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998443195009242,
|
|
"loss": 6.266,
|
|
"mean_token_accuracy": 0.14605539664626122,
|
|
"num_tokens": 4346264.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.444290590286255,
|
|
"epoch": 0.20619922288943837,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998431460229182,
|
|
"loss": 6.261,
|
|
"mean_token_accuracy": 0.14759050458669662,
|
|
"num_tokens": 4355102.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.518517303466797,
|
|
"epoch": 0.2066407629812787,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998419681403627,
|
|
"loss": 6.4309,
|
|
"mean_token_accuracy": 0.139105836302042,
|
|
"num_tokens": 4365569.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.428114986419677,
|
|
"epoch": 0.20708230307311903,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998407858532809,
|
|
"loss": 6.2633,
|
|
"mean_token_accuracy": 0.1455647498369217,
|
|
"num_tokens": 4375437.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.348156213760376,
|
|
"epoch": 0.20752384316495937,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499839599161696,
|
|
"loss": 6.2444,
|
|
"mean_token_accuracy": 0.15116954892873763,
|
|
"num_tokens": 4384420.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.430051231384278,
|
|
"epoch": 0.20796538325679972,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998384080656314,
|
|
"loss": 6.1993,
|
|
"mean_token_accuracy": 0.15055150538682938,
|
|
"num_tokens": 4393730.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.349585485458374,
|
|
"epoch": 0.20840692334864006,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00049983721256511,
|
|
"loss": 6.1842,
|
|
"mean_token_accuracy": 0.14877034425735475,
|
|
"num_tokens": 4402731.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.3974512100219725,
|
|
"epoch": 0.2088484634404804,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998360126601556,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.1482672870159149,
|
|
"num_tokens": 4411606.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.3687732219696045,
|
|
"epoch": 0.20929000353232075,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998348083507916,
|
|
"loss": 6.3177,
|
|
"mean_token_accuracy": 0.14799434095621108,
|
|
"num_tokens": 4421685.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.44785623550415,
|
|
"epoch": 0.20973154362416108,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998335996370416,
|
|
"loss": 6.2883,
|
|
"mean_token_accuracy": 0.14761801213026046,
|
|
"num_tokens": 4431765.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.392046165466309,
|
|
"epoch": 0.2101730837160014,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998323865189291,
|
|
"loss": 6.2439,
|
|
"mean_token_accuracy": 0.14551597088575363,
|
|
"num_tokens": 4441191.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.444688892364502,
|
|
"epoch": 0.21061462380784174,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998311689964781,
|
|
"loss": 6.3302,
|
|
"mean_token_accuracy": 0.138855642080307,
|
|
"num_tokens": 4450156.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.510595750808716,
|
|
"epoch": 0.2110561638996821,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998299470697125,
|
|
"loss": 6.3199,
|
|
"mean_token_accuracy": 0.15451483130455018,
|
|
"num_tokens": 4459466.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.423422145843506,
|
|
"epoch": 0.21149770399152243,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998287207386559,
|
|
"loss": 6.3232,
|
|
"mean_token_accuracy": 0.14224404096603394,
|
|
"num_tokens": 4468539.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.416548156738282,
|
|
"epoch": 0.21193924408336276,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998274900033326,
|
|
"loss": 6.2395,
|
|
"mean_token_accuracy": 0.15238402634859086,
|
|
"num_tokens": 4477579.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.291043853759765,
|
|
"epoch": 0.21238078417520312,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998262548637667,
|
|
"loss": 6.1989,
|
|
"mean_token_accuracy": 0.15245457291603087,
|
|
"num_tokens": 4486800.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.308730173110962,
|
|
"epoch": 0.21282232426704345,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998250153199822,
|
|
"loss": 6.1484,
|
|
"mean_token_accuracy": 0.15403092205524443,
|
|
"num_tokens": 4495985.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.466254568099975,
|
|
"epoch": 0.21326386435888378,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998237713720036,
|
|
"loss": 6.3239,
|
|
"mean_token_accuracy": 0.14338542893528938,
|
|
"num_tokens": 4504944.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.381775999069214,
|
|
"epoch": 0.2137054044507241,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998225230198552,
|
|
"loss": 6.1987,
|
|
"mean_token_accuracy": 0.1538494348526001,
|
|
"num_tokens": 4515402.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.330594635009765,
|
|
"epoch": 0.21414694454256447,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998212702635614,
|
|
"loss": 6.2685,
|
|
"mean_token_accuracy": 0.14354601204395295,
|
|
"num_tokens": 4525009.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.5298998832702635,
|
|
"epoch": 0.2145884846344048,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998200131031469,
|
|
"loss": 6.3256,
|
|
"mean_token_accuracy": 0.14529723376035691,
|
|
"num_tokens": 4534460.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.389695167541504,
|
|
"epoch": 0.21503002472624513,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998187515386361,
|
|
"loss": 6.1518,
|
|
"mean_token_accuracy": 0.1601933628320694,
|
|
"num_tokens": 4543748.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.282786703109741,
|
|
"epoch": 0.2154715648180855,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998174855700538,
|
|
"loss": 6.2753,
|
|
"mean_token_accuracy": 0.15319369435310365,
|
|
"num_tokens": 4552722.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.487105512619019,
|
|
"epoch": 0.21591310490992582,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998162151974248,
|
|
"loss": 6.1183,
|
|
"mean_token_accuracy": 0.15194425731897354,
|
|
"num_tokens": 4561607.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.372227382659912,
|
|
"epoch": 0.21635464500176615,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499814940420774,
|
|
"loss": 6.4008,
|
|
"mean_token_accuracy": 0.13625949174165725,
|
|
"num_tokens": 4572524.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.387830066680908,
|
|
"epoch": 0.21679618509360649,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998136612401266,
|
|
"loss": 6.2112,
|
|
"mean_token_accuracy": 0.1517648920416832,
|
|
"num_tokens": 4581601.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.404532241821289,
|
|
"epoch": 0.21723772518544684,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998123776555071,
|
|
"loss": 6.2609,
|
|
"mean_token_accuracy": 0.1447027012705803,
|
|
"num_tokens": 4591795.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.37783408164978,
|
|
"epoch": 0.21767926527728718,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998110896669412,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.14586359560489653,
|
|
"num_tokens": 4600745.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.4204151153564455,
|
|
"epoch": 0.2181208053691275,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998097972744539,
|
|
"loss": 6.2744,
|
|
"mean_token_accuracy": 0.1438829004764557,
|
|
"num_tokens": 4610490.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.344004535675049,
|
|
"epoch": 0.21856234546096787,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998085004780705,
|
|
"loss": 6.1917,
|
|
"mean_token_accuracy": 0.1555175483226776,
|
|
"num_tokens": 4619511.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.415195465087891,
|
|
"epoch": 0.2190038855528082,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998071992778164,
|
|
"loss": 6.2515,
|
|
"mean_token_accuracy": 0.14207181110978126,
|
|
"num_tokens": 4628186.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.438273286819458,
|
|
"epoch": 0.21944542564464853,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499805893673717,
|
|
"loss": 6.2691,
|
|
"mean_token_accuracy": 0.14731226563453675,
|
|
"num_tokens": 4637431.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.356544446945191,
|
|
"epoch": 0.21988696573648886,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998045836657982,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.15215693414211273,
|
|
"num_tokens": 4646627.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.363220739364624,
|
|
"epoch": 0.22032850582832922,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998032692540853,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.14926744401454925,
|
|
"num_tokens": 4656095.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.444636392593384,
|
|
"epoch": 0.22077004592016955,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998019504386044,
|
|
"loss": 6.2983,
|
|
"mean_token_accuracy": 0.1443503238260746,
|
|
"num_tokens": 4665807.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.39345760345459,
|
|
"epoch": 0.22121158601200988,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998006272193809,
|
|
"loss": 6.2515,
|
|
"mean_token_accuracy": 0.14276793897151946,
|
|
"num_tokens": 4674459.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.420822715759277,
|
|
"epoch": 0.22165312610385024,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997992995964412,
|
|
"loss": 6.3335,
|
|
"mean_token_accuracy": 0.14485810697078705,
|
|
"num_tokens": 4684063.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.430441427230835,
|
|
"epoch": 0.22209466619569057,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997979675698109,
|
|
"loss": 6.2237,
|
|
"mean_token_accuracy": 0.1505151480436325,
|
|
"num_tokens": 4692807.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.493818712234497,
|
|
"epoch": 0.2225362062875309,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997966311395164,
|
|
"loss": 6.1509,
|
|
"mean_token_accuracy": 0.15266127437353133,
|
|
"num_tokens": 4701100.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.261106777191162,
|
|
"epoch": 0.22297774637937123,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997952903055836,
|
|
"loss": 6.2014,
|
|
"mean_token_accuracy": 0.1452627256512642,
|
|
"num_tokens": 4710697.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.3538493633270265,
|
|
"epoch": 0.2234192864712116,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499793945068039,
|
|
"loss": 6.1951,
|
|
"mean_token_accuracy": 0.14937613308429717,
|
|
"num_tokens": 4718745.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.333649778366089,
|
|
"epoch": 0.22386082656305192,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997925954269088,
|
|
"loss": 6.173,
|
|
"mean_token_accuracy": 0.15181030780076982,
|
|
"num_tokens": 4728056.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.434943294525146,
|
|
"epoch": 0.22430236665489225,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997912413822196,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.15063572451472282,
|
|
"num_tokens": 4737605.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.293275022506714,
|
|
"epoch": 0.2247439067467326,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997898829339979,
|
|
"loss": 6.114,
|
|
"mean_token_accuracy": 0.16079342663288115,
|
|
"num_tokens": 4746168.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.297460889816284,
|
|
"epoch": 0.22518544683857294,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049978852008227,
|
|
"loss": 6.1821,
|
|
"mean_token_accuracy": 0.1518242985010147,
|
|
"num_tokens": 4755072.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.327752351760864,
|
|
"epoch": 0.22562698693041328,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499787152827063,
|
|
"loss": 6.192,
|
|
"mean_token_accuracy": 0.15824129432439804,
|
|
"num_tokens": 4764580.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.290549898147583,
|
|
"epoch": 0.2260685270222536,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997857811684035,
|
|
"loss": 6.2145,
|
|
"mean_token_accuracy": 0.15303274542093276,
|
|
"num_tokens": 4774135.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.410637426376343,
|
|
"epoch": 0.22651006711409397,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997844051063183,
|
|
"loss": 6.3043,
|
|
"mean_token_accuracy": 0.14438919797539712,
|
|
"num_tokens": 4784733.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.41192512512207,
|
|
"epoch": 0.2269516072059343,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997830246408346,
|
|
"loss": 6.2387,
|
|
"mean_token_accuracy": 0.15428498163819312,
|
|
"num_tokens": 4795327.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.278723859786988,
|
|
"epoch": 0.22739314729777463,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997816397719791,
|
|
"loss": 6.2157,
|
|
"mean_token_accuracy": 0.14635045304894448,
|
|
"num_tokens": 4804314.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.441279935836792,
|
|
"epoch": 0.227834687389615,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997802504997792,
|
|
"loss": 6.303,
|
|
"mean_token_accuracy": 0.14009749442338942,
|
|
"num_tokens": 4813637.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.366417980194091,
|
|
"epoch": 0.22827622748145532,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997788568242621,
|
|
"loss": 6.1695,
|
|
"mean_token_accuracy": 0.15038952380418777,
|
|
"num_tokens": 4823094.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.292829847335815,
|
|
"epoch": 0.22871776757329565,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499777458745455,
|
|
"loss": 6.1123,
|
|
"mean_token_accuracy": 0.1579282909631729,
|
|
"num_tokens": 4833199.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.3866489887237545,
|
|
"epoch": 0.22915930766513598,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997760562633853,
|
|
"loss": 6.2102,
|
|
"mean_token_accuracy": 0.15025776177644729,
|
|
"num_tokens": 4842970.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.37343578338623,
|
|
"epoch": 0.22960084775697634,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997746493780804,
|
|
"loss": 6.2792,
|
|
"mean_token_accuracy": 0.14459849298000335,
|
|
"num_tokens": 4852043.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.356409358978271,
|
|
"epoch": 0.23004238784881667,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499773238089568,
|
|
"loss": 6.1844,
|
|
"mean_token_accuracy": 0.14483380317687988,
|
|
"num_tokens": 4862232.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.343675518035889,
|
|
"epoch": 0.230483927940657,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997718223978758,
|
|
"loss": 6.1204,
|
|
"mean_token_accuracy": 0.14981301128864288,
|
|
"num_tokens": 4871186.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.302071237564087,
|
|
"epoch": 0.23092546803249736,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997704023030315,
|
|
"loss": 6.2134,
|
|
"mean_token_accuracy": 0.1568485602736473,
|
|
"num_tokens": 4879974.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.37543830871582,
|
|
"epoch": 0.2313670081243377,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997689778050627,
|
|
"loss": 6.2599,
|
|
"mean_token_accuracy": 0.15443349331617356,
|
|
"num_tokens": 4890300.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.287172794342041,
|
|
"epoch": 0.23180854821617802,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997675489039975,
|
|
"loss": 6.2494,
|
|
"mean_token_accuracy": 0.1468710109591484,
|
|
"num_tokens": 4900428.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.366749954223633,
|
|
"epoch": 0.23225008830801835,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997661155998638,
|
|
"loss": 6.2476,
|
|
"mean_token_accuracy": 0.15147435963153838,
|
|
"num_tokens": 4910092.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.374930906295776,
|
|
"epoch": 0.2326916283998587,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997646778926898,
|
|
"loss": 6.2313,
|
|
"mean_token_accuracy": 0.14748895019292832,
|
|
"num_tokens": 4919593.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.320575475692749,
|
|
"epoch": 0.23313316849169904,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997632357825035,
|
|
"loss": 6.1889,
|
|
"mean_token_accuracy": 0.15245203971862792,
|
|
"num_tokens": 4929098.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.37444224357605,
|
|
"epoch": 0.23357470858353938,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997617892693333,
|
|
"loss": 6.2685,
|
|
"mean_token_accuracy": 0.14796690195798873,
|
|
"num_tokens": 4938265.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.381702041625976,
|
|
"epoch": 0.23401624867537973,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997603383532075,
|
|
"loss": 6.2157,
|
|
"mean_token_accuracy": 0.15212348997592925,
|
|
"num_tokens": 4946694.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.345135974884033,
|
|
"epoch": 0.23445778876722007,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997588830341545,
|
|
"loss": 6.2007,
|
|
"mean_token_accuracy": 0.1495561882853508,
|
|
"num_tokens": 4955296.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.262336206436157,
|
|
"epoch": 0.2348993288590604,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997574233122028,
|
|
"loss": 6.1783,
|
|
"mean_token_accuracy": 0.15376680493354797,
|
|
"num_tokens": 4964409.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.344006538391113,
|
|
"epoch": 0.23534086895090076,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997559591873809,
|
|
"loss": 6.1848,
|
|
"mean_token_accuracy": 0.15347870737314223,
|
|
"num_tokens": 4973449.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.325773239135742,
|
|
"epoch": 0.2357824090427411,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997544906597178,
|
|
"loss": 6.1774,
|
|
"mean_token_accuracy": 0.1539867863059044,
|
|
"num_tokens": 4983057.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.2636034965515135,
|
|
"epoch": 0.23622394913458142,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004997530177292418,
|
|
"loss": 6.2376,
|
|
"mean_token_accuracy": 0.14284619241952895,
|
|
"num_tokens": 4991950.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.425727081298828,
|
|
"epoch": 0.23666548922642175,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997515403959823,
|
|
"loss": 6.1908,
|
|
"mean_token_accuracy": 0.15085240155458451,
|
|
"num_tokens": 5001042.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.364514875411987,
|
|
"epoch": 0.2371070293182621,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997500586599677,
|
|
"loss": 6.1239,
|
|
"mean_token_accuracy": 0.15567631870508195,
|
|
"num_tokens": 5009827.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.238472986221313,
|
|
"epoch": 0.23754856941010244,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997485725212274,
|
|
"loss": 6.1721,
|
|
"mean_token_accuracy": 0.15332650095224382,
|
|
"num_tokens": 5018708.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.277514266967773,
|
|
"epoch": 0.23799010950194277,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997470819797903,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.1563563570380211,
|
|
"num_tokens": 5027522.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.287735462188721,
|
|
"epoch": 0.23843164959378313,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997455870356857,
|
|
"loss": 6.1948,
|
|
"mean_token_accuracy": 0.15198080092668534,
|
|
"num_tokens": 5035755.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.307868242263794,
|
|
"epoch": 0.23887318968562346,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997440876889429,
|
|
"loss": 6.1377,
|
|
"mean_token_accuracy": 0.15334794968366622,
|
|
"num_tokens": 5045289.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.278635931015015,
|
|
"epoch": 0.2393147297774638,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997425839395913,
|
|
"loss": 6.1641,
|
|
"mean_token_accuracy": 0.1568767547607422,
|
|
"num_tokens": 5053774.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.4377528667449955,
|
|
"epoch": 0.23975626986930412,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997410757876602,
|
|
"loss": 6.2444,
|
|
"mean_token_accuracy": 0.14437243491411209,
|
|
"num_tokens": 5062911.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.3234247207641605,
|
|
"epoch": 0.24019780996114448,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997395632331793,
|
|
"loss": 6.1091,
|
|
"mean_token_accuracy": 0.15637961626052857,
|
|
"num_tokens": 5072107.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.226778221130371,
|
|
"epoch": 0.2406393500529848,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997380462761781,
|
|
"loss": 6.0586,
|
|
"mean_token_accuracy": 0.15822814106941224,
|
|
"num_tokens": 5080588.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.362985134124756,
|
|
"epoch": 0.24108089014482514,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997365249166864,
|
|
"loss": 6.2812,
|
|
"mean_token_accuracy": 0.148160120844841,
|
|
"num_tokens": 5090262.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.364387369155883,
|
|
"epoch": 0.2415224302366655,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997349991547342,
|
|
"loss": 6.1672,
|
|
"mean_token_accuracy": 0.15980131253600122,
|
|
"num_tokens": 5099285.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.311175918579101,
|
|
"epoch": 0.24196397032850583,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997334689903509,
|
|
"loss": 6.2297,
|
|
"mean_token_accuracy": 0.1506420761346817,
|
|
"num_tokens": 5109115.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.381357097625733,
|
|
"epoch": 0.24240551042034617,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997319344235668,
|
|
"loss": 6.2471,
|
|
"mean_token_accuracy": 0.15130761936306952,
|
|
"num_tokens": 5117977.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.371263027191162,
|
|
"epoch": 0.2428470505121865,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499730395454412,
|
|
"loss": 6.1953,
|
|
"mean_token_accuracy": 0.15422819852828978,
|
|
"num_tokens": 5127457.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.326935291290283,
|
|
"epoch": 0.24328859060402686,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997288520829166,
|
|
"loss": 6.2614,
|
|
"mean_token_accuracy": 0.14421235620975495,
|
|
"num_tokens": 5137310.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.359060192108155,
|
|
"epoch": 0.2437301306958672,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997273043091107,
|
|
"loss": 6.1923,
|
|
"mean_token_accuracy": 0.1464222900569439,
|
|
"num_tokens": 5146963.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.268268156051636,
|
|
"epoch": 0.24417167078770752,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997257521330248,
|
|
"loss": 6.1424,
|
|
"mean_token_accuracy": 0.14788112491369249,
|
|
"num_tokens": 5155521.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.351244401931763,
|
|
"epoch": 0.24461321087954788,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997241955546892,
|
|
"loss": 6.1424,
|
|
"mean_token_accuracy": 0.1483145385980606,
|
|
"num_tokens": 5165182.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.31810302734375,
|
|
"epoch": 0.2450547509713882,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997226345741343,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.15033391118049622,
|
|
"num_tokens": 5175511.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.3378277778625485,
|
|
"epoch": 0.24549629106322854,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499721069191391,
|
|
"loss": 6.1013,
|
|
"mean_token_accuracy": 0.1578337162733078,
|
|
"num_tokens": 5184772.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.310634183883667,
|
|
"epoch": 0.24593783115506887,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997194994064896,
|
|
"loss": 6.1866,
|
|
"mean_token_accuracy": 0.1496903583407402,
|
|
"num_tokens": 5195136.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.332416534423828,
|
|
"epoch": 0.24637937124690923,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499717925219461,
|
|
"loss": 6.1167,
|
|
"mean_token_accuracy": 0.15987685918807984,
|
|
"num_tokens": 5203163.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.345263051986694,
|
|
"epoch": 0.24682091133874956,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997163466303362,
|
|
"loss": 6.2061,
|
|
"mean_token_accuracy": 0.1503751039505005,
|
|
"num_tokens": 5213233.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.292828702926636,
|
|
"epoch": 0.2472624514305899,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499714763639146,
|
|
"loss": 6.1372,
|
|
"mean_token_accuracy": 0.15086597949266434,
|
|
"num_tokens": 5222940.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.270041036605835,
|
|
"epoch": 0.24770399152243025,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997131762459211,
|
|
"loss": 6.1676,
|
|
"mean_token_accuracy": 0.15103059709072114,
|
|
"num_tokens": 5232263.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.331594228744507,
|
|
"epoch": 0.24814553161427058,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997115844506932,
|
|
"loss": 6.1405,
|
|
"mean_token_accuracy": 0.15087736994028092,
|
|
"num_tokens": 5241536.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.34823522567749,
|
|
"epoch": 0.2485870717061109,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997099882534929,
|
|
"loss": 6.1704,
|
|
"mean_token_accuracy": 0.14839458093047142,
|
|
"num_tokens": 5250702.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.377634048461914,
|
|
"epoch": 0.24902861179795124,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997083876543519,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.1505747467279434,
|
|
"num_tokens": 5259811.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.377023410797119,
|
|
"epoch": 0.2494701518897916,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997067826533014,
|
|
"loss": 6.2543,
|
|
"mean_token_accuracy": 0.1441645845770836,
|
|
"num_tokens": 5270518.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.403309440612793,
|
|
"epoch": 0.24991169198163193,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997051732503726,
|
|
"loss": 6.1311,
|
|
"mean_token_accuracy": 0.15377675592899323,
|
|
"num_tokens": 5279538.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.22372031211853,
|
|
"epoch": 0.25035323207347226,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997035594455975,
|
|
"loss": 6.1674,
|
|
"mean_token_accuracy": 0.1481279417872429,
|
|
"num_tokens": 5289633.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.387079381942749,
|
|
"epoch": 0.2507947721653126,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997019412390074,
|
|
"loss": 6.2575,
|
|
"mean_token_accuracy": 0.15361315459012986,
|
|
"num_tokens": 5299148.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.307563066482544,
|
|
"epoch": 0.2512363122571529,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499700318630634,
|
|
"loss": 6.1357,
|
|
"mean_token_accuracy": 0.15210598707199097,
|
|
"num_tokens": 5309090.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.273115110397339,
|
|
"epoch": 0.2516778523489933,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996986916205092,
|
|
"loss": 6.2278,
|
|
"mean_token_accuracy": 0.15018689632415771,
|
|
"num_tokens": 5318798.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.345541620254517,
|
|
"epoch": 0.25211939244083365,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996970602086648,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.15610066950321197,
|
|
"num_tokens": 5327915.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.211011552810669,
|
|
"epoch": 0.252560932532674,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996954243951327,
|
|
"loss": 6.1209,
|
|
"mean_token_accuracy": 0.15709759593009948,
|
|
"num_tokens": 5336970.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.323676109313965,
|
|
"epoch": 0.2530024726245143,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996937841799451,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.15997228324413298,
|
|
"num_tokens": 5345167.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.199875545501709,
|
|
"epoch": 0.25344401271635464,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996921395631342,
|
|
"loss": 6.071,
|
|
"mean_token_accuracy": 0.1565924033522606,
|
|
"num_tokens": 5353399.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.27602071762085,
|
|
"epoch": 0.25388555280819497,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499690490544732,
|
|
"loss": 6.1828,
|
|
"mean_token_accuracy": 0.1513873428106308,
|
|
"num_tokens": 5363224.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.339487314224243,
|
|
"epoch": 0.2543270929000353,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996888371247707,
|
|
"loss": 6.1923,
|
|
"mean_token_accuracy": 0.14602998048067092,
|
|
"num_tokens": 5372274.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.343375635147095,
|
|
"epoch": 0.2547686329918757,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499687179303283,
|
|
"loss": 6.1815,
|
|
"mean_token_accuracy": 0.15472851544618607,
|
|
"num_tokens": 5380240.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.228068780899048,
|
|
"epoch": 0.255210173083716,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996855170803012,
|
|
"loss": 6.0344,
|
|
"mean_token_accuracy": 0.15991738438606262,
|
|
"num_tokens": 5389390.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.28302755355835,
|
|
"epoch": 0.25565171317555635,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996838504558581,
|
|
"loss": 6.1902,
|
|
"mean_token_accuracy": 0.1521752417087555,
|
|
"num_tokens": 5399425.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.355008220672607,
|
|
"epoch": 0.2560932532673967,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499682179429986,
|
|
"loss": 6.2011,
|
|
"mean_token_accuracy": 0.1508815959095955,
|
|
"num_tokens": 5408717.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.280868196487427,
|
|
"epoch": 0.256534793359237,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996805040027178,
|
|
"loss": 6.1368,
|
|
"mean_token_accuracy": 0.14726324751973152,
|
|
"num_tokens": 5418475.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.2741169929504395,
|
|
"epoch": 0.25697633345107734,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996788241740863,
|
|
"loss": 6.1707,
|
|
"mean_token_accuracy": 0.1536627657711506,
|
|
"num_tokens": 5428403.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.269294166564942,
|
|
"epoch": 0.2574178735429177,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996771399441243,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.14502449780702592,
|
|
"num_tokens": 5437347.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.407036876678466,
|
|
"epoch": 0.25785941363475806,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996754513128652,
|
|
"loss": 6.1309,
|
|
"mean_token_accuracy": 0.15732353776693345,
|
|
"num_tokens": 5446804.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.222485494613648,
|
|
"epoch": 0.2583009537265984,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996737582803416,
|
|
"loss": 6.0819,
|
|
"mean_token_accuracy": 0.15406210720539093,
|
|
"num_tokens": 5455888.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.3086316108703615,
|
|
"epoch": 0.2587424938184387,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996720608465868,
|
|
"loss": 6.0772,
|
|
"mean_token_accuracy": 0.15540871918201446,
|
|
"num_tokens": 5463977.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.277329921722412,
|
|
"epoch": 0.25918403391027905,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996703590116342,
|
|
"loss": 6.1841,
|
|
"mean_token_accuracy": 0.14695459753274917,
|
|
"num_tokens": 5473780.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.239596223831176,
|
|
"epoch": 0.2596255740021194,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996686527755171,
|
|
"loss": 6.0776,
|
|
"mean_token_accuracy": 0.15587782710790635,
|
|
"num_tokens": 5482151.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.316288614273072,
|
|
"epoch": 0.2600671140939597,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996669421382687,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.16187871843576432,
|
|
"num_tokens": 5491103.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.257398414611816,
|
|
"epoch": 0.26050865418580005,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996652270999228,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.1524055764079094,
|
|
"num_tokens": 5500367.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.286735200881958,
|
|
"epoch": 0.26095019427764043,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996635076605128,
|
|
"loss": 6.1432,
|
|
"mean_token_accuracy": 0.15162961781024933,
|
|
"num_tokens": 5509631.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.3608544826507565,
|
|
"epoch": 0.26139173436948077,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996617838200725,
|
|
"loss": 6.1488,
|
|
"mean_token_accuracy": 0.1510395437479019,
|
|
"num_tokens": 5518635.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.2053210735321045,
|
|
"epoch": 0.2618332744613211,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996600555786357,
|
|
"loss": 6.1166,
|
|
"mean_token_accuracy": 0.1505479171872139,
|
|
"num_tokens": 5527696.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.343273687362671,
|
|
"epoch": 0.26227481455316143,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996583229362362,
|
|
"loss": 6.077,
|
|
"mean_token_accuracy": 0.15462881475687026,
|
|
"num_tokens": 5536632.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.356432819366455,
|
|
"epoch": 0.26271635464500176,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996565858929078,
|
|
"loss": 6.1634,
|
|
"mean_token_accuracy": 0.15574948489665985,
|
|
"num_tokens": 5545825.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.2175110340118405,
|
|
"epoch": 0.2631578947368421,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996548444486847,
|
|
"loss": 6.0344,
|
|
"mean_token_accuracy": 0.1576728031039238,
|
|
"num_tokens": 5555158.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.174654150009156,
|
|
"epoch": 0.2635994348286824,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996530986036008,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.16068323999643325,
|
|
"num_tokens": 5564218.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.207144069671631,
|
|
"epoch": 0.2640409749205228,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996513483576907,
|
|
"loss": 6.1208,
|
|
"mean_token_accuracy": 0.15933286994695664,
|
|
"num_tokens": 5572760.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.368608522415161,
|
|
"epoch": 0.26448251501236314,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996495937109884,
|
|
"loss": 6.1754,
|
|
"mean_token_accuracy": 0.14925839453935624,
|
|
"num_tokens": 5581660.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.248563766479492,
|
|
"epoch": 0.26492405510420347,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996478346635283,
|
|
"loss": 6.0906,
|
|
"mean_token_accuracy": 0.15518097579479218,
|
|
"num_tokens": 5590664.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.26492405510420347,
|
|
"eval_entropy": 5.978648100514914,
|
|
"eval_loss": 6.153229713439941,
|
|
"eval_mean_token_accuracy": 0.1595988018887533,
|
|
"eval_num_tokens": 5590664.0,
|
|
"eval_runtime": 20.3151,
|
|
"eval_samples_per_second": 1738.363,
|
|
"eval_steps_per_second": 217.326,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 113230,
|
|
"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": 1218962152488960.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|