5090 lines
137 KiB
JSON
5090 lines
137 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 2.270786006360745,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 2500,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.742555522918702,
|
||
|
|
"epoch": 0.004543389368468878,
|
||
|
|
"grad_norm": 5.0625,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.7779,
|
||
|
|
"mean_token_accuracy": 8.431703317910433e-05,
|
||
|
|
"num_tokens": 10156.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742563724517822,
|
||
|
|
"epoch": 0.009086778736937756,
|
||
|
|
"grad_norm": 5.25,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.7654,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 20669.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.74255313873291,
|
||
|
|
"epoch": 0.013630168105406633,
|
||
|
|
"grad_norm": 4.9375,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.7397,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 30952.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742581939697265,
|
||
|
|
"epoch": 0.01817355747387551,
|
||
|
|
"grad_norm": 5.40625,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.6785,
|
||
|
|
"mean_token_accuracy": 0.0005094278021715581,
|
||
|
|
"num_tokens": 41429.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742574501037598,
|
||
|
|
"epoch": 0.02271694684234439,
|
||
|
|
"grad_norm": 4.90625,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 10.585,
|
||
|
|
"mean_token_accuracy": 0.004951991699635982,
|
||
|
|
"num_tokens": 52166.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742272472381591,
|
||
|
|
"epoch": 0.027260336210813266,
|
||
|
|
"grad_norm": 4.0,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 10.439,
|
||
|
|
"mean_token_accuracy": 0.027590089477598667,
|
||
|
|
"num_tokens": 61670.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.741254997253417,
|
||
|
|
"epoch": 0.03180372557928214,
|
||
|
|
"grad_norm": 3.203125,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 10.2851,
|
||
|
|
"mean_token_accuracy": 0.040197663381695746,
|
||
|
|
"num_tokens": 71702.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.738425350189209,
|
||
|
|
"epoch": 0.03634711494775102,
|
||
|
|
"grad_norm": 2.734375,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 10.129,
|
||
|
|
"mean_token_accuracy": 0.04816498160362244,
|
||
|
|
"num_tokens": 82840.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.734417152404784,
|
||
|
|
"epoch": 0.0408905043162199,
|
||
|
|
"grad_norm": 2.359375,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 10.0098,
|
||
|
|
"mean_token_accuracy": 0.04295867718756199,
|
||
|
|
"num_tokens": 92290.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.731618976593017,
|
||
|
|
"epoch": 0.04543389368468878,
|
||
|
|
"grad_norm": 2.21875,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 9.9604,
|
||
|
|
"mean_token_accuracy": 0.04617781527340412,
|
||
|
|
"num_tokens": 101842.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.729147243499757,
|
||
|
|
"epoch": 0.049977283053157656,
|
||
|
|
"grad_norm": 1.875,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.9546,
|
||
|
|
"mean_token_accuracy": 0.04403300806879997,
|
||
|
|
"num_tokens": 114030.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.727308368682861,
|
||
|
|
"epoch": 0.05452067242162653,
|
||
|
|
"grad_norm": 1.890625,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.8581,
|
||
|
|
"mean_token_accuracy": 0.04366073869168759,
|
||
|
|
"num_tokens": 124349.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.726133060455322,
|
||
|
|
"epoch": 0.059064061790095414,
|
||
|
|
"grad_norm": 1.9609375,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.7412,
|
||
|
|
"mean_token_accuracy": 0.044536291435360906,
|
||
|
|
"num_tokens": 133534.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.724782562255859,
|
||
|
|
"epoch": 0.06360745115856428,
|
||
|
|
"grad_norm": 2.0625,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.6971,
|
||
|
|
"mean_token_accuracy": 0.041312586329877374,
|
||
|
|
"num_tokens": 144383.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.723019886016846,
|
||
|
|
"epoch": 0.06815084052703317,
|
||
|
|
"grad_norm": 1.8359375,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.6751,
|
||
|
|
"mean_token_accuracy": 0.04508417844772339,
|
||
|
|
"num_tokens": 155467.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.717958164215087,
|
||
|
|
"epoch": 0.07269422989550205,
|
||
|
|
"grad_norm": 1.9609375,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.5919,
|
||
|
|
"mean_token_accuracy": 0.045108040794730186,
|
||
|
|
"num_tokens": 165903.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.709596824645995,
|
||
|
|
"epoch": 0.07723761926397092,
|
||
|
|
"grad_norm": 2.125,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.511,
|
||
|
|
"mean_token_accuracy": 0.04253413174301386,
|
||
|
|
"num_tokens": 175812.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.702213764190674,
|
||
|
|
"epoch": 0.0817810086324398,
|
||
|
|
"grad_norm": 1.9140625,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.4176,
|
||
|
|
"mean_token_accuracy": 0.04180197641253471,
|
||
|
|
"num_tokens": 186357.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.6961669921875,
|
||
|
|
"epoch": 0.08632439800090867,
|
||
|
|
"grad_norm": 1.96875,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 9.3391,
|
||
|
|
"mean_token_accuracy": 0.04544849582016468,
|
||
|
|
"num_tokens": 196124.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.684025192260743,
|
||
|
|
"epoch": 0.09086778736937756,
|
||
|
|
"grad_norm": 1.9609375,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 9.2392,
|
||
|
|
"mean_token_accuracy": 0.05092858672142029,
|
||
|
|
"num_tokens": 205655.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.664148139953614,
|
||
|
|
"epoch": 0.09541117673784644,
|
||
|
|
"grad_norm": 1.875,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 9.1639,
|
||
|
|
"mean_token_accuracy": 0.05325500890612602,
|
||
|
|
"num_tokens": 215870.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.64291820526123,
|
||
|
|
"epoch": 0.09995456610631531,
|
||
|
|
"grad_norm": 1.90625,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 9.0589,
|
||
|
|
"mean_token_accuracy": 0.056853560358285905,
|
||
|
|
"num_tokens": 225027.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.60800380706787,
|
||
|
|
"epoch": 0.10449795547478419,
|
||
|
|
"grad_norm": 1.8515625,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 8.9662,
|
||
|
|
"mean_token_accuracy": 0.05881645642220974,
|
||
|
|
"num_tokens": 236352.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.564264106750489,
|
||
|
|
"epoch": 0.10904134484325306,
|
||
|
|
"grad_norm": 1.8125,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.8255,
|
||
|
|
"mean_token_accuracy": 0.06017065867781639,
|
||
|
|
"num_tokens": 246713.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.5113018989563,
|
||
|
|
"epoch": 0.11358473421172194,
|
||
|
|
"grad_norm": 1.7890625,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 8.666,
|
||
|
|
"mean_token_accuracy": 0.06393568031489849,
|
||
|
|
"num_tokens": 256950.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.445667171478272,
|
||
|
|
"epoch": 0.11812812358019083,
|
||
|
|
"grad_norm": 1.671875,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.6162,
|
||
|
|
"mean_token_accuracy": 0.06482643783092498,
|
||
|
|
"num_tokens": 267345.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.374823379516602,
|
||
|
|
"epoch": 0.1226715129486597,
|
||
|
|
"grad_norm": 1.9765625,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 8.4096,
|
||
|
|
"mean_token_accuracy": 0.07293099723756313,
|
||
|
|
"num_tokens": 276782.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.27814416885376,
|
||
|
|
"epoch": 0.12721490231712856,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 8.2813,
|
||
|
|
"mean_token_accuracy": 0.073567845672369,
|
||
|
|
"num_tokens": 287024.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.162126541137695,
|
||
|
|
"epoch": 0.13175829168559747,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 8.255,
|
||
|
|
"mean_token_accuracy": 0.07345798872411251,
|
||
|
|
"num_tokens": 296597.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.039239120483398,
|
||
|
|
"epoch": 0.13630168105406634,
|
||
|
|
"grad_norm": 1.546875,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 8.0456,
|
||
|
|
"mean_token_accuracy": 0.07541064321994781,
|
||
|
|
"num_tokens": 307709.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.879199600219726,
|
||
|
|
"epoch": 0.14084507042253522,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 8.0019,
|
||
|
|
"mean_token_accuracy": 0.07952367104589939,
|
||
|
|
"num_tokens": 317976.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.700241374969483,
|
||
|
|
"epoch": 0.1453884597910041,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 7.8309,
|
||
|
|
"mean_token_accuracy": 0.07648782916367054,
|
||
|
|
"num_tokens": 327319.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.498950004577637,
|
||
|
|
"epoch": 0.14993184915947297,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.7494,
|
||
|
|
"mean_token_accuracy": 0.07844193913042545,
|
||
|
|
"num_tokens": 337337.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.23708553314209,
|
||
|
|
"epoch": 0.15447523852794184,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.7247,
|
||
|
|
"mean_token_accuracy": 0.07220172360539437,
|
||
|
|
"num_tokens": 347779.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.071245193481445,
|
||
|
|
"epoch": 0.15901862789641072,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.6848,
|
||
|
|
"mean_token_accuracy": 0.07456069067120552,
|
||
|
|
"num_tokens": 358088.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.767854022979737,
|
||
|
|
"epoch": 0.1635620172648796,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.5652,
|
||
|
|
"mean_token_accuracy": 0.07797556966543198,
|
||
|
|
"num_tokens": 368314.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.613600921630859,
|
||
|
|
"epoch": 0.16810540663334847,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.4354,
|
||
|
|
"mean_token_accuracy": 0.08428428322076797,
|
||
|
|
"num_tokens": 378406.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.429571628570557,
|
||
|
|
"epoch": 0.17264879600181735,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.439,
|
||
|
|
"mean_token_accuracy": 0.08039730936288833,
|
||
|
|
"num_tokens": 388912.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.273902130126952,
|
||
|
|
"epoch": 0.17719218537028622,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.4157,
|
||
|
|
"mean_token_accuracy": 0.08314879797399044,
|
||
|
|
"num_tokens": 399290.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.167303562164307,
|
||
|
|
"epoch": 0.18173557473875512,
|
||
|
|
"grad_norm": 0.7421875,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.322,
|
||
|
|
"mean_token_accuracy": 0.08215823769569397,
|
||
|
|
"num_tokens": 409757.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.126931190490723,
|
||
|
|
"epoch": 0.186278964107224,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.4599,
|
||
|
|
"mean_token_accuracy": 0.08315562084317207,
|
||
|
|
"num_tokens": 420182.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.04471731185913,
|
||
|
|
"epoch": 0.19082235347569287,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.3635,
|
||
|
|
"mean_token_accuracy": 0.08014154359698296,
|
||
|
|
"num_tokens": 429897.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.973057556152344,
|
||
|
|
"epoch": 0.19536574284416175,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.2597,
|
||
|
|
"mean_token_accuracy": 0.08170034214854241,
|
||
|
|
"num_tokens": 441131.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.934465074539185,
|
||
|
|
"epoch": 0.19990913221263062,
|
||
|
|
"grad_norm": 0.76953125,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.2285,
|
||
|
|
"mean_token_accuracy": 0.08460488840937615,
|
||
|
|
"num_tokens": 451894.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.865971183776855,
|
||
|
|
"epoch": 0.2044525215810995,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 7.1586,
|
||
|
|
"mean_token_accuracy": 0.08472679629921913,
|
||
|
|
"num_tokens": 462613.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.905964708328247,
|
||
|
|
"epoch": 0.20899591094956838,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.2551,
|
||
|
|
"mean_token_accuracy": 0.08738799616694451,
|
||
|
|
"num_tokens": 471606.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.820685958862304,
|
||
|
|
"epoch": 0.21353930031803725,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.1499,
|
||
|
|
"mean_token_accuracy": 0.08987567648291588,
|
||
|
|
"num_tokens": 481559.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.777825260162354,
|
||
|
|
"epoch": 0.21808268968650613,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.1686,
|
||
|
|
"mean_token_accuracy": 0.0859978199005127,
|
||
|
|
"num_tokens": 492766.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.835345315933227,
|
||
|
|
"epoch": 0.222626079054975,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 7.2285,
|
||
|
|
"mean_token_accuracy": 0.08684551119804382,
|
||
|
|
"num_tokens": 503357.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6760852336883545,
|
||
|
|
"epoch": 0.22716946842344388,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.0637,
|
||
|
|
"mean_token_accuracy": 0.08950686678290368,
|
||
|
|
"num_tokens": 513098.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.730396175384522,
|
||
|
|
"epoch": 0.23171285779191278,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.1422,
|
||
|
|
"mean_token_accuracy": 0.08494780957698822,
|
||
|
|
"num_tokens": 522807.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.82570514678955,
|
||
|
|
"epoch": 0.23625624716038165,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.1568,
|
||
|
|
"mean_token_accuracy": 0.0862432986497879,
|
||
|
|
"num_tokens": 532670.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.713788843154907,
|
||
|
|
"epoch": 0.24079963652885053,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 7.0973,
|
||
|
|
"mean_token_accuracy": 0.0868481919169426,
|
||
|
|
"num_tokens": 543647.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.765906810760498,
|
||
|
|
"epoch": 0.2453430258973194,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 7.112,
|
||
|
|
"mean_token_accuracy": 0.09636801481246948,
|
||
|
|
"num_tokens": 553047.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.660856294631958,
|
||
|
|
"epoch": 0.24988641526578828,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.1678,
|
||
|
|
"mean_token_accuracy": 0.09444689303636551,
|
||
|
|
"num_tokens": 563413.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.606683969497681,
|
||
|
|
"epoch": 0.25442980463425713,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 7.1218,
|
||
|
|
"mean_token_accuracy": 0.089845459908247,
|
||
|
|
"num_tokens": 573790.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.731978559494019,
|
||
|
|
"epoch": 0.25897319400272606,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.0439,
|
||
|
|
"mean_token_accuracy": 0.09121683463454247,
|
||
|
|
"num_tokens": 582958.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.521587800979614,
|
||
|
|
"epoch": 0.26351658337119493,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 6.9904,
|
||
|
|
"mean_token_accuracy": 0.09767817184329033,
|
||
|
|
"num_tokens": 592886.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.548699855804443,
|
||
|
|
"epoch": 0.2680599727396638,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 7.0399,
|
||
|
|
"mean_token_accuracy": 0.09062462002038955,
|
||
|
|
"num_tokens": 603692.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.651094913482666,
|
||
|
|
"epoch": 0.2726033621081327,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 7.0823,
|
||
|
|
"mean_token_accuracy": 0.0895950011909008,
|
||
|
|
"num_tokens": 613534.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.61688346862793,
|
||
|
|
"epoch": 0.27714675147660156,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 7.0274,
|
||
|
|
"mean_token_accuracy": 0.09576684832572938,
|
||
|
|
"num_tokens": 623862.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.62919430732727,
|
||
|
|
"epoch": 0.28169014084507044,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 7.1036,
|
||
|
|
"mean_token_accuracy": 0.09453180059790611,
|
||
|
|
"num_tokens": 633759.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.475176191329956,
|
||
|
|
"epoch": 0.2862335302135393,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 6.9859,
|
||
|
|
"mean_token_accuracy": 0.09430009499192238,
|
||
|
|
"num_tokens": 643553.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.528373908996582,
|
||
|
|
"epoch": 0.2907769195820082,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 6.9115,
|
||
|
|
"mean_token_accuracy": 0.09864105582237244,
|
||
|
|
"num_tokens": 653714.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.604555463790893,
|
||
|
|
"epoch": 0.29532030895047706,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 6.9306,
|
||
|
|
"mean_token_accuracy": 0.10158697441220284,
|
||
|
|
"num_tokens": 662817.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.483990573883057,
|
||
|
|
"epoch": 0.29986369831894594,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 6.9631,
|
||
|
|
"mean_token_accuracy": 0.0952290877699852,
|
||
|
|
"num_tokens": 672381.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.382349872589112,
|
||
|
|
"epoch": 0.3044070876874148,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 6.8338,
|
||
|
|
"mean_token_accuracy": 0.09701873064041137,
|
||
|
|
"num_tokens": 682525.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.496461296081543,
|
||
|
|
"epoch": 0.3089504770558837,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 6.9359,
|
||
|
|
"mean_token_accuracy": 0.09759294539690018,
|
||
|
|
"num_tokens": 691826.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.394898748397827,
|
||
|
|
"epoch": 0.31349386642435256,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 6.9089,
|
||
|
|
"mean_token_accuracy": 0.10296000391244889,
|
||
|
|
"num_tokens": 701319.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4353029251098635,
|
||
|
|
"epoch": 0.31803725579282144,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 6.998,
|
||
|
|
"mean_token_accuracy": 0.0935439720749855,
|
||
|
|
"num_tokens": 710888.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.49090256690979,
|
||
|
|
"epoch": 0.3225806451612903,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 6.9328,
|
||
|
|
"mean_token_accuracy": 0.09594348818063736,
|
||
|
|
"num_tokens": 722516.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.475078916549682,
|
||
|
|
"epoch": 0.3271240345297592,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 6.9103,
|
||
|
|
"mean_token_accuracy": 0.09800132587552071,
|
||
|
|
"num_tokens": 733058.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.39355149269104,
|
||
|
|
"epoch": 0.33166742389822806,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 6.974,
|
||
|
|
"mean_token_accuracy": 0.09975532218813896,
|
||
|
|
"num_tokens": 744832.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.496864604949951,
|
||
|
|
"epoch": 0.33621081326669694,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 6.9025,
|
||
|
|
"mean_token_accuracy": 0.09925103634595871,
|
||
|
|
"num_tokens": 755387.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3132157802581785,
|
||
|
|
"epoch": 0.3407542026351658,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 6.8349,
|
||
|
|
"mean_token_accuracy": 0.1016771987080574,
|
||
|
|
"num_tokens": 764455.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.339641284942627,
|
||
|
|
"epoch": 0.3452975920036347,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 6.8903,
|
||
|
|
"mean_token_accuracy": 0.09662013798952103,
|
||
|
|
"num_tokens": 774513.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.49444260597229,
|
||
|
|
"epoch": 0.34984098137210357,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 6.9771,
|
||
|
|
"mean_token_accuracy": 0.09587227553129196,
|
||
|
|
"num_tokens": 785540.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.336615896224975,
|
||
|
|
"epoch": 0.35438437074057244,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 6.8417,
|
||
|
|
"mean_token_accuracy": 0.09714982733130455,
|
||
|
|
"num_tokens": 795233.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.437350511550903,
|
||
|
|
"epoch": 0.35892776010904137,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 6.8975,
|
||
|
|
"mean_token_accuracy": 0.09597025141119957,
|
||
|
|
"num_tokens": 804855.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3508072853088375,
|
||
|
|
"epoch": 0.36347114947751025,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 6.8581,
|
||
|
|
"mean_token_accuracy": 0.10273054391145706,
|
||
|
|
"num_tokens": 814818.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.307885694503784,
|
||
|
|
"epoch": 0.3680145388459791,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 6.8737,
|
||
|
|
"mean_token_accuracy": 0.10590235516428947,
|
||
|
|
"num_tokens": 824622.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.379908847808838,
|
||
|
|
"epoch": 0.372557928214448,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 6.7626,
|
||
|
|
"mean_token_accuracy": 0.10957324355840684,
|
||
|
|
"num_tokens": 834813.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.205720233917236,
|
||
|
|
"epoch": 0.3771013175829169,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 6.8537,
|
||
|
|
"mean_token_accuracy": 0.10128433629870415,
|
||
|
|
"num_tokens": 844887.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.279560470581055,
|
||
|
|
"epoch": 0.38164470695138575,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 6.8512,
|
||
|
|
"mean_token_accuracy": 0.10131347700953483,
|
||
|
|
"num_tokens": 855430.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.237056398391724,
|
||
|
|
"epoch": 0.3861880963198546,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 6.6942,
|
||
|
|
"mean_token_accuracy": 0.10520395040512084,
|
||
|
|
"num_tokens": 866052.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.226158237457275,
|
||
|
|
"epoch": 0.3907314856883235,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 6.8429,
|
||
|
|
"mean_token_accuracy": 0.0950412966310978,
|
||
|
|
"num_tokens": 877961.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.291323947906494,
|
||
|
|
"epoch": 0.3952748750567924,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 6.8103,
|
||
|
|
"mean_token_accuracy": 0.10648028403520585,
|
||
|
|
"num_tokens": 888386.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.235066747665405,
|
||
|
|
"epoch": 0.39981826442526125,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 6.8563,
|
||
|
|
"mean_token_accuracy": 0.10282102078199387,
|
||
|
|
"num_tokens": 898272.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.281696557998657,
|
||
|
|
"epoch": 0.4043616537937301,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 6.8014,
|
||
|
|
"mean_token_accuracy": 0.1076163724064827,
|
||
|
|
"num_tokens": 908317.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.248809957504273,
|
||
|
|
"epoch": 0.408905043162199,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 6.7819,
|
||
|
|
"mean_token_accuracy": 0.10194819942116737,
|
||
|
|
"num_tokens": 917970.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.240721273422241,
|
||
|
|
"epoch": 0.4134484325306679,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 6.8191,
|
||
|
|
"mean_token_accuracy": 0.09906565770506859,
|
||
|
|
"num_tokens": 928132.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.241307735443115,
|
||
|
|
"epoch": 0.41799182189913675,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 6.747,
|
||
|
|
"mean_token_accuracy": 0.1059770368039608,
|
||
|
|
"num_tokens": 938092.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.299763536453247,
|
||
|
|
"epoch": 0.4225352112676056,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 6.8651,
|
||
|
|
"mean_token_accuracy": 0.10198809579014778,
|
||
|
|
"num_tokens": 948650.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.130692863464356,
|
||
|
|
"epoch": 0.4270786006360745,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 6.7675,
|
||
|
|
"mean_token_accuracy": 0.10987066626548767,
|
||
|
|
"num_tokens": 960195.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.254830408096313,
|
||
|
|
"epoch": 0.4316219900045434,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 6.7984,
|
||
|
|
"mean_token_accuracy": 0.10485964193940163,
|
||
|
|
"num_tokens": 970608.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.314376783370972,
|
||
|
|
"epoch": 0.43616537937301225,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 6.7811,
|
||
|
|
"mean_token_accuracy": 0.10285131707787513,
|
||
|
|
"num_tokens": 981053.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.066157007217408,
|
||
|
|
"epoch": 0.4407087687414811,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 6.703,
|
||
|
|
"mean_token_accuracy": 0.11324564591050149,
|
||
|
|
"num_tokens": 991560.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.167983913421631,
|
||
|
|
"epoch": 0.44525215810995,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 6.7507,
|
||
|
|
"mean_token_accuracy": 0.1001538448035717,
|
||
|
|
"num_tokens": 1002008.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.145689487457275,
|
||
|
|
"epoch": 0.4497955474784189,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 6.7502,
|
||
|
|
"mean_token_accuracy": 0.10835718214511872,
|
||
|
|
"num_tokens": 1012349.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.15342149734497,
|
||
|
|
"epoch": 0.45433893684688775,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 6.7273,
|
||
|
|
"mean_token_accuracy": 0.10544943064451218,
|
||
|
|
"num_tokens": 1022886.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.45433893684688775,
|
||
|
|
"eval_entropy": 7.164822139296421,
|
||
|
|
"eval_loss": 6.852421760559082,
|
||
|
|
"eval_mean_token_accuracy": 0.10633610026954218,
|
||
|
|
"eval_num_tokens": 1022886.0,
|
||
|
|
"eval_runtime": 2.0057,
|
||
|
|
"eval_samples_per_second": 1712.63,
|
||
|
|
"eval_steps_per_second": 214.39,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.286551141738892,
|
||
|
|
"epoch": 0.45888232621535663,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 6.783,
|
||
|
|
"mean_token_accuracy": 0.09997680187225341,
|
||
|
|
"num_tokens": 1033129.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.133803033828736,
|
||
|
|
"epoch": 0.46342571558382556,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 6.6802,
|
||
|
|
"mean_token_accuracy": 0.10805964693427086,
|
||
|
|
"num_tokens": 1043069.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.079697799682617,
|
||
|
|
"epoch": 0.46796910495229443,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 6.6994,
|
||
|
|
"mean_token_accuracy": 0.1062344878911972,
|
||
|
|
"num_tokens": 1054049.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0915602684021,
|
||
|
|
"epoch": 0.4725124943207633,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 6.6878,
|
||
|
|
"mean_token_accuracy": 0.1027360238134861,
|
||
|
|
"num_tokens": 1065155.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.116834926605224,
|
||
|
|
"epoch": 0.4770558836892322,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 6.6763,
|
||
|
|
"mean_token_accuracy": 0.1094151757657528,
|
||
|
|
"num_tokens": 1075510.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.024749040603638,
|
||
|
|
"epoch": 0.48159927305770106,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 6.6901,
|
||
|
|
"mean_token_accuracy": 0.1099021278321743,
|
||
|
|
"num_tokens": 1086494.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2192497730255125,
|
||
|
|
"epoch": 0.48614266242616994,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 6.7271,
|
||
|
|
"mean_token_accuracy": 0.10860580801963807,
|
||
|
|
"num_tokens": 1097311.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.049293804168701,
|
||
|
|
"epoch": 0.4906860517946388,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 6.6835,
|
||
|
|
"mean_token_accuracy": 0.10724506676197051,
|
||
|
|
"num_tokens": 1107757.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.006491184234619,
|
||
|
|
"epoch": 0.4952294411631077,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.5917,
|
||
|
|
"mean_token_accuracy": 0.11055039316415786,
|
||
|
|
"num_tokens": 1118889.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.137886428833008,
|
||
|
|
"epoch": 0.49977283053157656,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.7913,
|
||
|
|
"mean_token_accuracy": 0.10480824410915375,
|
||
|
|
"num_tokens": 1128951.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.029620742797851,
|
||
|
|
"epoch": 0.5043162199000454,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 6.5948,
|
||
|
|
"mean_token_accuracy": 0.11510317772626877,
|
||
|
|
"num_tokens": 1138583.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0846200466156,
|
||
|
|
"epoch": 0.5088596092685143,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.6631,
|
||
|
|
"mean_token_accuracy": 0.11140834540128708,
|
||
|
|
"num_tokens": 1149572.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.074535894393921,
|
||
|
|
"epoch": 0.5134029986369832,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.6367,
|
||
|
|
"mean_token_accuracy": 0.1094569742679596,
|
||
|
|
"num_tokens": 1160532.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.030823421478272,
|
||
|
|
"epoch": 0.5179463880054521,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 6.6299,
|
||
|
|
"mean_token_accuracy": 0.10860486924648285,
|
||
|
|
"num_tokens": 1170915.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.998789310455322,
|
||
|
|
"epoch": 0.522489777373921,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.5964,
|
||
|
|
"mean_token_accuracy": 0.11754036694765091,
|
||
|
|
"num_tokens": 1180822.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.999447011947632,
|
||
|
|
"epoch": 0.5270331667423899,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.6302,
|
||
|
|
"mean_token_accuracy": 0.11184115558862687,
|
||
|
|
"num_tokens": 1190447.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.026746368408203,
|
||
|
|
"epoch": 0.5315765561108587,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.6657,
|
||
|
|
"mean_token_accuracy": 0.11019867807626724,
|
||
|
|
"num_tokens": 1200951.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.064433956146241,
|
||
|
|
"epoch": 0.5361199454793276,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.5523,
|
||
|
|
"mean_token_accuracy": 0.1147008366882801,
|
||
|
|
"num_tokens": 1211846.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.766572427749634,
|
||
|
|
"epoch": 0.5406633348477965,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.5164,
|
||
|
|
"mean_token_accuracy": 0.11493531465530396,
|
||
|
|
"num_tokens": 1222074.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.925977277755737,
|
||
|
|
"epoch": 0.5452067242162654,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.5846,
|
||
|
|
"mean_token_accuracy": 0.11097392141819,
|
||
|
|
"num_tokens": 1231741.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0018980503082275,
|
||
|
|
"epoch": 0.5497501135847342,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.5311,
|
||
|
|
"mean_token_accuracy": 0.11044337376952171,
|
||
|
|
"num_tokens": 1241078.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9610405445098875,
|
||
|
|
"epoch": 0.5542935029532031,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.7226,
|
||
|
|
"mean_token_accuracy": 0.1040603518486023,
|
||
|
|
"num_tokens": 1251685.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.949973773956299,
|
||
|
|
"epoch": 0.558836892321672,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.562,
|
||
|
|
"mean_token_accuracy": 0.1197849079966545,
|
||
|
|
"num_tokens": 1262044.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.914613580703735,
|
||
|
|
"epoch": 0.5633802816901409,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.5713,
|
||
|
|
"mean_token_accuracy": 0.1111277848482132,
|
||
|
|
"num_tokens": 1273647.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.064757633209228,
|
||
|
|
"epoch": 0.5679236710586097,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.625,
|
||
|
|
"mean_token_accuracy": 0.10996143072843552,
|
||
|
|
"num_tokens": 1284396.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.925110483169556,
|
||
|
|
"epoch": 0.5724670604270786,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.6058,
|
||
|
|
"mean_token_accuracy": 0.1135744608938694,
|
||
|
|
"num_tokens": 1294339.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.936828088760376,
|
||
|
|
"epoch": 0.5770104497955475,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.524,
|
||
|
|
"mean_token_accuracy": 0.11486122459173202,
|
||
|
|
"num_tokens": 1304572.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9446367740631105,
|
||
|
|
"epoch": 0.5815538391640164,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.5734,
|
||
|
|
"mean_token_accuracy": 0.11208348348736763,
|
||
|
|
"num_tokens": 1314780.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.862443494796753,
|
||
|
|
"epoch": 0.5860972285324852,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.5789,
|
||
|
|
"mean_token_accuracy": 0.11142232716083526,
|
||
|
|
"num_tokens": 1325215.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.912387943267822,
|
||
|
|
"epoch": 0.5906406179009541,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.4907,
|
||
|
|
"mean_token_accuracy": 0.11991971731185913,
|
||
|
|
"num_tokens": 1334745.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.957016134262085,
|
||
|
|
"epoch": 0.595184007269423,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.6005,
|
||
|
|
"mean_token_accuracy": 0.11654155552387238,
|
||
|
|
"num_tokens": 1345150.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.955321359634399,
|
||
|
|
"epoch": 0.5997273966378919,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.554,
|
||
|
|
"mean_token_accuracy": 0.1150270789861679,
|
||
|
|
"num_tokens": 1355619.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.841307306289673,
|
||
|
|
"epoch": 0.6042707860063607,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.4846,
|
||
|
|
"mean_token_accuracy": 0.11608346402645112,
|
||
|
|
"num_tokens": 1365933.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.891475486755371,
|
||
|
|
"epoch": 0.6088141753748296,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.5081,
|
||
|
|
"mean_token_accuracy": 0.11709481626749038,
|
||
|
|
"num_tokens": 1376867.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.965159177780151,
|
||
|
|
"epoch": 0.6133575647432985,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.6588,
|
||
|
|
"mean_token_accuracy": 0.1138373926281929,
|
||
|
|
"num_tokens": 1386739.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.889486598968506,
|
||
|
|
"epoch": 0.6179009541117674,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.5181,
|
||
|
|
"mean_token_accuracy": 0.116570845246315,
|
||
|
|
"num_tokens": 1397138.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.962109041213989,
|
||
|
|
"epoch": 0.6224443434802363,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.6159,
|
||
|
|
"mean_token_accuracy": 0.11419135332107544,
|
||
|
|
"num_tokens": 1408171.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.836606550216675,
|
||
|
|
"epoch": 0.6269877328487051,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.5509,
|
||
|
|
"mean_token_accuracy": 0.10746546238660812,
|
||
|
|
"num_tokens": 1418259.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8779538631439205,
|
||
|
|
"epoch": 0.631531122217174,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.5466,
|
||
|
|
"mean_token_accuracy": 0.1198190651834011,
|
||
|
|
"num_tokens": 1428080.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9482708930969235,
|
||
|
|
"epoch": 0.6360745115856429,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.5777,
|
||
|
|
"mean_token_accuracy": 0.11636564508080482,
|
||
|
|
"num_tokens": 1438502.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.803214025497437,
|
||
|
|
"epoch": 0.6406179009541118,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.5271,
|
||
|
|
"mean_token_accuracy": 0.11418517231941223,
|
||
|
|
"num_tokens": 1448396.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.889286518096924,
|
||
|
|
"epoch": 0.6451612903225806,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.581,
|
||
|
|
"mean_token_accuracy": 0.10854673013091087,
|
||
|
|
"num_tokens": 1459728.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.843706035614014,
|
||
|
|
"epoch": 0.6497046796910495,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.4748,
|
||
|
|
"mean_token_accuracy": 0.12437612041831017,
|
||
|
|
"num_tokens": 1469733.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.759375,
|
||
|
|
"epoch": 0.6542480690595184,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.4664,
|
||
|
|
"mean_token_accuracy": 0.1201399251818657,
|
||
|
|
"num_tokens": 1479004.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.855831241607666,
|
||
|
|
"epoch": 0.6587914584279873,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.4365,
|
||
|
|
"mean_token_accuracy": 0.11637238636612893,
|
||
|
|
"num_tokens": 1489848.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7456646919250485,
|
||
|
|
"epoch": 0.6633348477964561,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.4363,
|
||
|
|
"mean_token_accuracy": 0.1179615817964077,
|
||
|
|
"num_tokens": 1500877.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.931111192703247,
|
||
|
|
"epoch": 0.667878237164925,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.5786,
|
||
|
|
"mean_token_accuracy": 0.11474068090319633,
|
||
|
|
"num_tokens": 1511840.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.754684495925903,
|
||
|
|
"epoch": 0.6724216265333939,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.4844,
|
||
|
|
"mean_token_accuracy": 0.11675599068403245,
|
||
|
|
"num_tokens": 1521839.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.837312364578247,
|
||
|
|
"epoch": 0.6769650159018628,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.3889,
|
||
|
|
"mean_token_accuracy": 0.12173137590289115,
|
||
|
|
"num_tokens": 1531285.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.607749176025391,
|
||
|
|
"epoch": 0.6815084052703316,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.4363,
|
||
|
|
"mean_token_accuracy": 0.11859396696090699,
|
||
|
|
"num_tokens": 1542027.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8664957046508786,
|
||
|
|
"epoch": 0.6860517946388005,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.548,
|
||
|
|
"mean_token_accuracy": 0.11864770278334617,
|
||
|
|
"num_tokens": 1552527.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.915476655960083,
|
||
|
|
"epoch": 0.6905951840072694,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.5848,
|
||
|
|
"mean_token_accuracy": 0.11684316471219063,
|
||
|
|
"num_tokens": 1562605.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.740834951400757,
|
||
|
|
"epoch": 0.6951385733757383,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.4686,
|
||
|
|
"mean_token_accuracy": 0.11819475442171097,
|
||
|
|
"num_tokens": 1572128.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.718352746963501,
|
||
|
|
"epoch": 0.6996819627442071,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.4003,
|
||
|
|
"mean_token_accuracy": 0.11825122833251953,
|
||
|
|
"num_tokens": 1582352.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.808340549468994,
|
||
|
|
"epoch": 0.704225352112676,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.4936,
|
||
|
|
"mean_token_accuracy": 0.12305623516440392,
|
||
|
|
"num_tokens": 1592887.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.696469831466675,
|
||
|
|
"epoch": 0.7087687414811449,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.4367,
|
||
|
|
"mean_token_accuracy": 0.11979465782642365,
|
||
|
|
"num_tokens": 1603564.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.64963583946228,
|
||
|
|
"epoch": 0.7133121308496138,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.2928,
|
||
|
|
"mean_token_accuracy": 0.12856932654976844,
|
||
|
|
"num_tokens": 1613270.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.67563099861145,
|
||
|
|
"epoch": 0.7178555202180827,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.3618,
|
||
|
|
"mean_token_accuracy": 0.12818560600280762,
|
||
|
|
"num_tokens": 1623009.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.701826286315918,
|
||
|
|
"epoch": 0.7223989095865516,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.3966,
|
||
|
|
"mean_token_accuracy": 0.11920078694820405,
|
||
|
|
"num_tokens": 1633209.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.767777013778686,
|
||
|
|
"epoch": 0.7269422989550205,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.4338,
|
||
|
|
"mean_token_accuracy": 0.12207518145442009,
|
||
|
|
"num_tokens": 1643708.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.734032678604126,
|
||
|
|
"epoch": 0.7314856883234894,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.4948,
|
||
|
|
"mean_token_accuracy": 0.11701320484280586,
|
||
|
|
"num_tokens": 1653973.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.704824733734131,
|
||
|
|
"epoch": 0.7360290776919582,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.4747,
|
||
|
|
"mean_token_accuracy": 0.12068637907505035,
|
||
|
|
"num_tokens": 1664856.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.683869314193726,
|
||
|
|
"epoch": 0.7405724670604271,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.3944,
|
||
|
|
"mean_token_accuracy": 0.12224291115999222,
|
||
|
|
"num_tokens": 1675935.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7558623313903805,
|
||
|
|
"epoch": 0.745115856428896,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.4428,
|
||
|
|
"mean_token_accuracy": 0.12248818576335907,
|
||
|
|
"num_tokens": 1686597.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.610339832305908,
|
||
|
|
"epoch": 0.7496592457973649,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.3911,
|
||
|
|
"mean_token_accuracy": 0.1245286226272583,
|
||
|
|
"num_tokens": 1697385.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8567352294921875,
|
||
|
|
"epoch": 0.7542026351658337,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.4443,
|
||
|
|
"mean_token_accuracy": 0.11997077614068985,
|
||
|
|
"num_tokens": 1706680.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.645043087005615,
|
||
|
|
"epoch": 0.7587460245343026,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.4407,
|
||
|
|
"mean_token_accuracy": 0.1258401207625866,
|
||
|
|
"num_tokens": 1716130.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.69645881652832,
|
||
|
|
"epoch": 0.7632894139027715,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.3624,
|
||
|
|
"mean_token_accuracy": 0.11782209128141403,
|
||
|
|
"num_tokens": 1726835.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.711601686477661,
|
||
|
|
"epoch": 0.7678328032712404,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.3928,
|
||
|
|
"mean_token_accuracy": 0.1290561191737652,
|
||
|
|
"num_tokens": 1737708.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.639672756195068,
|
||
|
|
"epoch": 0.7723761926397092,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.3799,
|
||
|
|
"mean_token_accuracy": 0.12615877538919448,
|
||
|
|
"num_tokens": 1747649.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.673767709732056,
|
||
|
|
"epoch": 0.7769195820081781,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.4068,
|
||
|
|
"mean_token_accuracy": 0.1206041231751442,
|
||
|
|
"num_tokens": 1758327.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.613749980926514,
|
||
|
|
"epoch": 0.781462971376647,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.3619,
|
||
|
|
"mean_token_accuracy": 0.121267169713974,
|
||
|
|
"num_tokens": 1769767.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.713872861862183,
|
||
|
|
"epoch": 0.7860063607451159,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.4717,
|
||
|
|
"mean_token_accuracy": 0.1220657117664814,
|
||
|
|
"num_tokens": 1780139.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.726572799682617,
|
||
|
|
"epoch": 0.7905497501135847,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.3601,
|
||
|
|
"mean_token_accuracy": 0.12505988776683807,
|
||
|
|
"num_tokens": 1790783.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.59320387840271,
|
||
|
|
"epoch": 0.7950931394820536,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.3513,
|
||
|
|
"mean_token_accuracy": 0.12245700359344483,
|
||
|
|
"num_tokens": 1801349.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.600114583969116,
|
||
|
|
"epoch": 0.7996365288505225,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.3531,
|
||
|
|
"mean_token_accuracy": 0.1229885309934616,
|
||
|
|
"num_tokens": 1811990.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.57788610458374,
|
||
|
|
"epoch": 0.8041799182189914,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.3634,
|
||
|
|
"mean_token_accuracy": 0.13060024604201317,
|
||
|
|
"num_tokens": 1821725.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.60519003868103,
|
||
|
|
"epoch": 0.8087233075874602,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.3253,
|
||
|
|
"mean_token_accuracy": 0.11931257545948029,
|
||
|
|
"num_tokens": 1831794.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.64742259979248,
|
||
|
|
"epoch": 0.8132666969559291,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.4077,
|
||
|
|
"mean_token_accuracy": 0.12239367365837098,
|
||
|
|
"num_tokens": 1842002.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.655037879943848,
|
||
|
|
"epoch": 0.817810086324398,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.3797,
|
||
|
|
"mean_token_accuracy": 0.12452054545283317,
|
||
|
|
"num_tokens": 1852282.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.614450359344483,
|
||
|
|
"epoch": 0.8223534756928669,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.388,
|
||
|
|
"mean_token_accuracy": 0.11854704096913338,
|
||
|
|
"num_tokens": 1862830.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.592864656448365,
|
||
|
|
"epoch": 0.8268968650613358,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.3413,
|
||
|
|
"mean_token_accuracy": 0.1236710526049137,
|
||
|
|
"num_tokens": 1872746.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5772138118743895,
|
||
|
|
"epoch": 0.8314402544298046,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.3719,
|
||
|
|
"mean_token_accuracy": 0.11749232411384583,
|
||
|
|
"num_tokens": 1884353.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.676659631729126,
|
||
|
|
"epoch": 0.8359836437982735,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.4017,
|
||
|
|
"mean_token_accuracy": 0.11830696910619735,
|
||
|
|
"num_tokens": 1895719.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.629153537750244,
|
||
|
|
"epoch": 0.8405270331667424,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.3444,
|
||
|
|
"mean_token_accuracy": 0.13160407915711403,
|
||
|
|
"num_tokens": 1905905.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.659778261184693,
|
||
|
|
"epoch": 0.8450704225352113,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.4383,
|
||
|
|
"mean_token_accuracy": 0.12295959070324898,
|
||
|
|
"num_tokens": 1916010.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.56156849861145,
|
||
|
|
"epoch": 0.8496138119036801,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.3334,
|
||
|
|
"mean_token_accuracy": 0.12297626435756684,
|
||
|
|
"num_tokens": 1926429.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.445285606384277,
|
||
|
|
"epoch": 0.854157201272149,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.2646,
|
||
|
|
"mean_token_accuracy": 0.12663295194506646,
|
||
|
|
"num_tokens": 1936322.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.68843822479248,
|
||
|
|
"epoch": 0.8587005906406179,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.4278,
|
||
|
|
"mean_token_accuracy": 0.12256157100200653,
|
||
|
|
"num_tokens": 1947885.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.635422468185425,
|
||
|
|
"epoch": 0.8632439800090868,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.3923,
|
||
|
|
"mean_token_accuracy": 0.12212013304233552,
|
||
|
|
"num_tokens": 1957876.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.575307750701905,
|
||
|
|
"epoch": 0.8677873693775556,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.3884,
|
||
|
|
"mean_token_accuracy": 0.11944693848490714,
|
||
|
|
"num_tokens": 1969531.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.577566289901734,
|
||
|
|
"epoch": 0.8723307587460245,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.2501,
|
||
|
|
"mean_token_accuracy": 0.12427858263254166,
|
||
|
|
"num_tokens": 1980787.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.506700944900513,
|
||
|
|
"epoch": 0.8768741481144934,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.3301,
|
||
|
|
"mean_token_accuracy": 0.12719210535287856,
|
||
|
|
"num_tokens": 1991645.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.563048219680786,
|
||
|
|
"epoch": 0.8814175374829623,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.38,
|
||
|
|
"mean_token_accuracy": 0.12680814787745476,
|
||
|
|
"num_tokens": 2002544.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.701274681091308,
|
||
|
|
"epoch": 0.8859609268514311,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.4409,
|
||
|
|
"mean_token_accuracy": 0.12047607451677322,
|
||
|
|
"num_tokens": 2012813.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.542685174942017,
|
||
|
|
"epoch": 0.8905043162199,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.3017,
|
||
|
|
"mean_token_accuracy": 0.1271137699484825,
|
||
|
|
"num_tokens": 2023756.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.471768379211426,
|
||
|
|
"epoch": 0.8950477055883689,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.3821,
|
||
|
|
"mean_token_accuracy": 0.12684743776917456,
|
||
|
|
"num_tokens": 2034245.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.698192596435547,
|
||
|
|
"epoch": 0.8995910949568378,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.4087,
|
||
|
|
"mean_token_accuracy": 0.12129435613751412,
|
||
|
|
"num_tokens": 2045635.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.564974308013916,
|
||
|
|
"epoch": 0.9041344843253066,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.3742,
|
||
|
|
"mean_token_accuracy": 0.12397633790969849,
|
||
|
|
"num_tokens": 2056501.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.569272136688232,
|
||
|
|
"epoch": 0.9086778736937755,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.3834,
|
||
|
|
"mean_token_accuracy": 0.12595843970775605,
|
||
|
|
"num_tokens": 2066540.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9086778736937755,
|
||
|
|
"eval_entropy": 6.449487343499827,
|
||
|
|
"eval_loss": 6.4225172996521,
|
||
|
|
"eval_mean_token_accuracy": 0.12387349221768768,
|
||
|
|
"eval_num_tokens": 2066540.0,
|
||
|
|
"eval_runtime": 1.9962,
|
||
|
|
"eval_samples_per_second": 1720.779,
|
||
|
|
"eval_steps_per_second": 215.41,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.589289760589599,
|
||
|
|
"epoch": 0.9132212630622444,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999998223471442,
|
||
|
|
"loss": 6.27,
|
||
|
|
"mean_token_accuracy": 0.12683147192001343,
|
||
|
|
"num_tokens": 2077008.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.468321657180786,
|
||
|
|
"epoch": 0.9177646524307133,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999991006328981,
|
||
|
|
"loss": 6.1974,
|
||
|
|
"mean_token_accuracy": 0.12910854443907738,
|
||
|
|
"num_tokens": 2087314.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.515331792831421,
|
||
|
|
"epoch": 0.9223080417991822,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999978237557377,
|
||
|
|
"loss": 6.365,
|
||
|
|
"mean_token_accuracy": 0.1273949436843395,
|
||
|
|
"num_tokens": 2097928.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.527489137649536,
|
||
|
|
"epoch": 0.9268514311676511,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999959917188137,
|
||
|
|
"loss": 6.2922,
|
||
|
|
"mean_token_accuracy": 0.12393052130937576,
|
||
|
|
"num_tokens": 2108662.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.452746248245239,
|
||
|
|
"epoch": 0.93139482053612,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004999936045266462,
|
||
|
|
"loss": 6.3291,
|
||
|
|
"mean_token_accuracy": 0.12396076545119286,
|
||
|
|
"num_tokens": 2118546.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.609079790115357,
|
||
|
|
"epoch": 0.9359382099045889,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999906621851255,
|
||
|
|
"loss": 6.3514,
|
||
|
|
"mean_token_accuracy": 0.1282046727836132,
|
||
|
|
"num_tokens": 2128012.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.469990539550781,
|
||
|
|
"epoch": 0.9404815992730577,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999871647015115,
|
||
|
|
"loss": 6.1834,
|
||
|
|
"mean_token_accuracy": 0.12837918177247049,
|
||
|
|
"num_tokens": 2138241.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.617193222045898,
|
||
|
|
"epoch": 0.9450249886415266,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999831120844339,
|
||
|
|
"loss": 6.3515,
|
||
|
|
"mean_token_accuracy": 0.1252776153385639,
|
||
|
|
"num_tokens": 2150780.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.467695426940918,
|
||
|
|
"epoch": 0.9495683780099955,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999785043438922,
|
||
|
|
"loss": 6.2353,
|
||
|
|
"mean_token_accuracy": 0.12729288563132285,
|
||
|
|
"num_tokens": 2161918.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.440260601043701,
|
||
|
|
"epoch": 0.9541117673784644,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999733414912555,
|
||
|
|
"loss": 6.2691,
|
||
|
|
"mean_token_accuracy": 0.12473016008734703,
|
||
|
|
"num_tokens": 2172742.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.444692325592041,
|
||
|
|
"epoch": 0.9586551567469332,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999676235392626,
|
||
|
|
"loss": 6.2628,
|
||
|
|
"mean_token_accuracy": 0.1319998823106289,
|
||
|
|
"num_tokens": 2182122.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.485652875900269,
|
||
|
|
"epoch": 0.9631985461154021,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999613505020219,
|
||
|
|
"loss": 6.3009,
|
||
|
|
"mean_token_accuracy": 0.12624281868338585,
|
||
|
|
"num_tokens": 2193703.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.477052927017212,
|
||
|
|
"epoch": 0.967741935483871,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004999545223950116,
|
||
|
|
"loss": 6.232,
|
||
|
|
"mean_token_accuracy": 0.12531697526574134,
|
||
|
|
"num_tokens": 2204041.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4596601009368895,
|
||
|
|
"epoch": 0.9722853248523399,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999471392350795,
|
||
|
|
"loss": 6.2681,
|
||
|
|
"mean_token_accuracy": 0.1249091774225235,
|
||
|
|
"num_tokens": 2214276.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.514900493621826,
|
||
|
|
"epoch": 0.9768287142208087,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999392010404426,
|
||
|
|
"loss": 6.237,
|
||
|
|
"mean_token_accuracy": 0.13163011744618416,
|
||
|
|
"num_tokens": 2225390.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.385442638397217,
|
||
|
|
"epoch": 0.9813721035892776,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999307078306876,
|
||
|
|
"loss": 6.1923,
|
||
|
|
"mean_token_accuracy": 0.13028257265686988,
|
||
|
|
"num_tokens": 2235708.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4769080638885494,
|
||
|
|
"epoch": 0.9859154929577465,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999216596267708,
|
||
|
|
"loss": 6.2303,
|
||
|
|
"mean_token_accuracy": 0.13035036474466324,
|
||
|
|
"num_tokens": 2246284.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.524853515625,
|
||
|
|
"epoch": 0.9904588823262154,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999120564510177,
|
||
|
|
"loss": 6.2358,
|
||
|
|
"mean_token_accuracy": 0.12543209120631219,
|
||
|
|
"num_tokens": 2257219.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.371940565109253,
|
||
|
|
"epoch": 0.9950022716946842,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000499901898327123,
|
||
|
|
"loss": 6.2336,
|
||
|
|
"mean_token_accuracy": 0.12906517162919046,
|
||
|
|
"num_tokens": 2268019.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.449350881576538,
|
||
|
|
"epoch": 0.9995456610631531,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004998911852801512,
|
||
|
|
"loss": 6.253,
|
||
|
|
"mean_token_accuracy": 0.12894620150327682,
|
||
|
|
"num_tokens": 2278382.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.441971778869629,
|
||
|
|
"epoch": 1.003634711494775,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998799173365355,
|
||
|
|
"loss": 6.096,
|
||
|
|
"mean_token_accuracy": 0.1329502835869789,
|
||
|
|
"num_tokens": 2288515.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.444106578826904,
|
||
|
|
"epoch": 1.008178100863244,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998680945240783,
|
||
|
|
"loss": 5.9544,
|
||
|
|
"mean_token_accuracy": 0.1410957932472229,
|
||
|
|
"num_tokens": 2298396.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.330610656738282,
|
||
|
|
"epoch": 1.0127214902317128,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998557168719513,
|
||
|
|
"loss": 6.0684,
|
||
|
|
"mean_token_accuracy": 0.12948169335722923,
|
||
|
|
"num_tokens": 2308707.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.406459140777588,
|
||
|
|
"epoch": 1.0172648796001817,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004998427844106954,
|
||
|
|
"loss": 5.98,
|
||
|
|
"mean_token_accuracy": 0.14317394495010377,
|
||
|
|
"num_tokens": 2318981.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.371292638778686,
|
||
|
|
"epoch": 1.0218082689686505,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998292971722197,
|
||
|
|
"loss": 6.072,
|
||
|
|
"mean_token_accuracy": 0.13840934932231902,
|
||
|
|
"num_tokens": 2329647.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.340481090545654,
|
||
|
|
"epoch": 1.0263516583371195,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499815255189803,
|
||
|
|
"loss": 6.0067,
|
||
|
|
"mean_token_accuracy": 0.13939314261078833,
|
||
|
|
"num_tokens": 2339449.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3922374725341795,
|
||
|
|
"epoch": 1.0308950477055883,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004998006584980922,
|
||
|
|
"loss": 6.1137,
|
||
|
|
"mean_token_accuracy": 0.13605127185583116,
|
||
|
|
"num_tokens": 2349904.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3493505954742435,
|
||
|
|
"epoch": 1.0354384370740572,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004997855071331034,
|
||
|
|
"loss": 6.0212,
|
||
|
|
"mean_token_accuracy": 0.14467629939317703,
|
||
|
|
"num_tokens": 2359833.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.463475131988526,
|
||
|
|
"epoch": 1.039981826442526,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997698011322211,
|
||
|
|
"loss": 6.0567,
|
||
|
|
"mean_token_accuracy": 0.13746307641267777,
|
||
|
|
"num_tokens": 2369857.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.399654150009155,
|
||
|
|
"epoch": 1.044525215810995,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000499753540534198,
|
||
|
|
"loss": 6.0661,
|
||
|
|
"mean_token_accuracy": 0.14009104669094086,
|
||
|
|
"num_tokens": 2380372.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.322651815414429,
|
||
|
|
"epoch": 1.049068605179464,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000499736725379156,
|
||
|
|
"loss": 6.046,
|
||
|
|
"mean_token_accuracy": 0.13437431380152703,
|
||
|
|
"num_tokens": 2391239.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3150145530700685,
|
||
|
|
"epoch": 1.0536119945479328,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004997193557085844,
|
||
|
|
"loss": 6.0224,
|
||
|
|
"mean_token_accuracy": 0.14738521873950958,
|
||
|
|
"num_tokens": 2401178.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.440890884399414,
|
||
|
|
"epoch": 1.0581553839164017,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997014315653413,
|
||
|
|
"loss": 6.115,
|
||
|
|
"mean_token_accuracy": 0.13918990567326545,
|
||
|
|
"num_tokens": 2412496.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.359582996368408,
|
||
|
|
"epoch": 1.0626987732848705,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004996829529936527,
|
||
|
|
"loss": 6.0976,
|
||
|
|
"mean_token_accuracy": 0.1375906229019165,
|
||
|
|
"num_tokens": 2423281.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.327804279327393,
|
||
|
|
"epoch": 1.0672421626533395,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004996639200391126,
|
||
|
|
"loss": 6.03,
|
||
|
|
"mean_token_accuracy": 0.14599778205156327,
|
||
|
|
"num_tokens": 2434078.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.311521911621094,
|
||
|
|
"epoch": 1.0717855520218083,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004996443327486831,
|
||
|
|
"loss": 5.9602,
|
||
|
|
"mean_token_accuracy": 0.141278412938118,
|
||
|
|
"num_tokens": 2443808.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.14685435295105,
|
||
|
|
"epoch": 1.0763289413902772,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004996241911706937,
|
||
|
|
"loss": 6.0035,
|
||
|
|
"mean_token_accuracy": 0.14571388214826583,
|
||
|
|
"num_tokens": 2453397.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.454845142364502,
|
||
|
|
"epoch": 1.080872330758746,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004996034953548418,
|
||
|
|
"loss": 6.1026,
|
||
|
|
"mean_token_accuracy": 0.13732529804110527,
|
||
|
|
"num_tokens": 2464295.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.430036211013794,
|
||
|
|
"epoch": 1.085415720127215,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004995822453521924,
|
||
|
|
"loss": 6.1424,
|
||
|
|
"mean_token_accuracy": 0.13445171639323233,
|
||
|
|
"num_tokens": 2475311.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.353321695327759,
|
||
|
|
"epoch": 1.0899591094956838,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004995604412151776,
|
||
|
|
"loss": 6.0502,
|
||
|
|
"mean_token_accuracy": 0.13472085893154145,
|
||
|
|
"num_tokens": 2485968.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.279279947280884,
|
||
|
|
"epoch": 1.0945024988641527,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000499538082997597,
|
||
|
|
"loss": 6.0794,
|
||
|
|
"mean_token_accuracy": 0.13565608412027358,
|
||
|
|
"num_tokens": 2496183.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.318364000320434,
|
||
|
|
"epoch": 1.0990458882326215,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004995151707546172,
|
||
|
|
"loss": 6.0395,
|
||
|
|
"mean_token_accuracy": 0.13798854872584343,
|
||
|
|
"num_tokens": 2506242.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.372706079483033,
|
||
|
|
"epoch": 1.1035892776010905,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004994917045427721,
|
||
|
|
"loss": 6.0423,
|
||
|
|
"mean_token_accuracy": 0.14290895834565162,
|
||
|
|
"num_tokens": 2516443.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.290970277786255,
|
||
|
|
"epoch": 1.1081326669695593,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004994676844199621,
|
||
|
|
"loss": 6.0137,
|
||
|
|
"mean_token_accuracy": 0.1438373804092407,
|
||
|
|
"num_tokens": 2525795.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2475104331970215,
|
||
|
|
"epoch": 1.1126760563380282,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004994431104454543,
|
||
|
|
"loss": 6.0515,
|
||
|
|
"mean_token_accuracy": 0.13550007790327073,
|
||
|
|
"num_tokens": 2535046.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.374474906921387,
|
||
|
|
"epoch": 1.117219445706497,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004994179826798828,
|
||
|
|
"loss": 6.0319,
|
||
|
|
"mean_token_accuracy": 0.1388425625860691,
|
||
|
|
"num_tokens": 2546489.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1246405124664305,
|
||
|
|
"epoch": 1.121762835074966,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004993923011852477,
|
||
|
|
"loss": 5.9768,
|
||
|
|
"mean_token_accuracy": 0.14362312108278275,
|
||
|
|
"num_tokens": 2556335.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.372661924362182,
|
||
|
|
"epoch": 1.1263062244434348,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004993660660249158,
|
||
|
|
"loss": 6.0025,
|
||
|
|
"mean_token_accuracy": 0.13659965619444847,
|
||
|
|
"num_tokens": 2567647.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.418256092071533,
|
||
|
|
"epoch": 1.1308496138119037,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004993392772636194,
|
||
|
|
"loss": 6.1952,
|
||
|
|
"mean_token_accuracy": 0.13226437345147132,
|
||
|
|
"num_tokens": 2578618.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.217349433898926,
|
||
|
|
"epoch": 1.1353930031803725,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004993119349674573,
|
||
|
|
"loss": 6.0181,
|
||
|
|
"mean_token_accuracy": 0.14242995530366898,
|
||
|
|
"num_tokens": 2587797.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2919868469238285,
|
||
|
|
"epoch": 1.1399363925488415,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004992840392038938,
|
||
|
|
"loss": 6.0506,
|
||
|
|
"mean_token_accuracy": 0.1346188299357891,
|
||
|
|
"num_tokens": 2598403.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.343607950210571,
|
||
|
|
"epoch": 1.1444797819173103,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499255590041759,
|
||
|
|
"loss": 6.0561,
|
||
|
|
"mean_token_accuracy": 0.13540524691343309,
|
||
|
|
"num_tokens": 2608296.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.313466644287109,
|
||
|
|
"epoch": 1.1490231712857792,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004992265875512485,
|
||
|
|
"loss": 6.0641,
|
||
|
|
"mean_token_accuracy": 0.14103504940867423,
|
||
|
|
"num_tokens": 2617906.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.25914363861084,
|
||
|
|
"epoch": 1.153566560654248,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004991970318039228,
|
||
|
|
"loss": 6.0032,
|
||
|
|
"mean_token_accuracy": 0.14189390316605568,
|
||
|
|
"num_tokens": 2627699.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.326404142379761,
|
||
|
|
"epoch": 1.158109950022717,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004991669228727078,
|
||
|
|
"loss": 5.9772,
|
||
|
|
"mean_token_accuracy": 0.14280295968055726,
|
||
|
|
"num_tokens": 2638384.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2005486488342285,
|
||
|
|
"epoch": 1.1626533393911858,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004991362608318947,
|
||
|
|
"loss": 5.9212,
|
||
|
|
"mean_token_accuracy": 0.1442661963403225,
|
||
|
|
"num_tokens": 2648279.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.234303903579712,
|
||
|
|
"epoch": 1.1671967287596547,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004991050457571384,
|
||
|
|
"loss": 6.0072,
|
||
|
|
"mean_token_accuracy": 0.12986308410763742,
|
||
|
|
"num_tokens": 2657000.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.285914278030395,
|
||
|
|
"epoch": 1.1717401181281235,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004990732777254594,
|
||
|
|
"loss": 6.0186,
|
||
|
|
"mean_token_accuracy": 0.1422954961657524,
|
||
|
|
"num_tokens": 2667760.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.256361961364746,
|
||
|
|
"epoch": 1.1762835074965925,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004990409568152422,
|
||
|
|
"loss": 5.9631,
|
||
|
|
"mean_token_accuracy": 0.14491396695375441,
|
||
|
|
"num_tokens": 2678450.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.285534238815307,
|
||
|
|
"epoch": 1.1808268968650613,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004990080831062352,
|
||
|
|
"loss": 6.0766,
|
||
|
|
"mean_token_accuracy": 0.1332152709364891,
|
||
|
|
"num_tokens": 2689695.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.358760118484497,
|
||
|
|
"epoch": 1.1853702862335302,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004989746566795512,
|
||
|
|
"loss": 6.083,
|
||
|
|
"mean_token_accuracy": 0.14606243073940278,
|
||
|
|
"num_tokens": 2700414.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.18422908782959,
|
||
|
|
"epoch": 1.189913675601999,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004989406776176665,
|
||
|
|
"loss": 5.9112,
|
||
|
|
"mean_token_accuracy": 0.1534299984574318,
|
||
|
|
"num_tokens": 2709985.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.229423856735229,
|
||
|
|
"epoch": 1.194457064970468,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000498906146004421,
|
||
|
|
"loss": 6.0529,
|
||
|
|
"mean_token_accuracy": 0.14144230335950853,
|
||
|
|
"num_tokens": 2720990.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.253258466720581,
|
||
|
|
"epoch": 1.1990004543389368,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004988710619250181,
|
||
|
|
"loss": 5.9568,
|
||
|
|
"mean_token_accuracy": 0.14692321121692659,
|
||
|
|
"num_tokens": 2731285.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.206444644927979,
|
||
|
|
"epoch": 1.2035438437074057,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004988354254660244,
|
||
|
|
"loss": 6.0309,
|
||
|
|
"mean_token_accuracy": 0.13927505165338516,
|
||
|
|
"num_tokens": 2741024.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2238139629364015,
|
||
|
|
"epoch": 1.2080872330758745,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004987992367153691,
|
||
|
|
"loss": 5.9787,
|
||
|
|
"mean_token_accuracy": 0.1435750648379326,
|
||
|
|
"num_tokens": 2751447.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.272238683700562,
|
||
|
|
"epoch": 1.2126306224443435,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004987624957623443,
|
||
|
|
"loss": 5.9818,
|
||
|
|
"mean_token_accuracy": 0.1429169222712517,
|
||
|
|
"num_tokens": 2761283.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.119753646850586,
|
||
|
|
"epoch": 1.2171740118128123,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004987252026976049,
|
||
|
|
"loss": 5.9119,
|
||
|
|
"mean_token_accuracy": 0.1478346861898899,
|
||
|
|
"num_tokens": 2771354.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.369901561737061,
|
||
|
|
"epoch": 1.2217174011812812,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004986873576131676,
|
||
|
|
"loss": 6.1054,
|
||
|
|
"mean_token_accuracy": 0.1408141702413559,
|
||
|
|
"num_tokens": 2781063.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.245864677429199,
|
||
|
|
"epoch": 1.22626079054975,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004986489606024116,
|
||
|
|
"loss": 6.008,
|
||
|
|
"mean_token_accuracy": 0.143255265802145,
|
||
|
|
"num_tokens": 2791103.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.304475927352906,
|
||
|
|
"epoch": 1.230804179918219,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004986100117600776,
|
||
|
|
"loss": 6.1001,
|
||
|
|
"mean_token_accuracy": 0.13890691325068474,
|
||
|
|
"num_tokens": 2802382.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.228710794448853,
|
||
|
|
"epoch": 1.235347569286688,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000498570511182268,
|
||
|
|
"loss": 5.9751,
|
||
|
|
"mean_token_accuracy": 0.14123353064060212,
|
||
|
|
"num_tokens": 2813740.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.206845951080322,
|
||
|
|
"epoch": 1.2398909586551567,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004985304589664465,
|
||
|
|
"loss": 5.9915,
|
||
|
|
"mean_token_accuracy": 0.13771087154746056,
|
||
|
|
"num_tokens": 2824121.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.323585081100464,
|
||
|
|
"epoch": 1.2444343480236255,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004984898552114381,
|
||
|
|
"loss": 6.0065,
|
||
|
|
"mean_token_accuracy": 0.1431947186589241,
|
||
|
|
"num_tokens": 2833356.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.192498970031738,
|
||
|
|
"epoch": 1.2489777373920945,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004984487000174283,
|
||
|
|
"loss": 5.9838,
|
||
|
|
"mean_token_accuracy": 0.13862482085824013,
|
||
|
|
"num_tokens": 2843839.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.203368473052978,
|
||
|
|
"epoch": 1.2535211267605635,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004984069934859637,
|
||
|
|
"loss": 5.9454,
|
||
|
|
"mean_token_accuracy": 0.1433752179145813,
|
||
|
|
"num_tokens": 2853523.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2640033721923825,
|
||
|
|
"epoch": 1.2580645161290323,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004983647357199509,
|
||
|
|
"loss": 5.9947,
|
||
|
|
"mean_token_accuracy": 0.14069052115082742,
|
||
|
|
"num_tokens": 2863226.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.273294878005982,
|
||
|
|
"epoch": 1.262607905497501,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004983219268236567,
|
||
|
|
"loss": 6.0546,
|
||
|
|
"mean_token_accuracy": 0.1447424255311489,
|
||
|
|
"num_tokens": 2873822.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.226011180877686,
|
||
|
|
"epoch": 1.26715129486597,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004982785669027079,
|
||
|
|
"loss": 5.9184,
|
||
|
|
"mean_token_accuracy": 0.14830858260393143,
|
||
|
|
"num_tokens": 2883645.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.190831136703491,
|
||
|
|
"epoch": 1.271694684234439,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004982346560640907,
|
||
|
|
"loss": 6.033,
|
||
|
|
"mean_token_accuracy": 0.13505668118596076,
|
||
|
|
"num_tokens": 2894397.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.299043893814087,
|
||
|
|
"epoch": 1.2762380736029078,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004981901944161507,
|
||
|
|
"loss": 6.0134,
|
||
|
|
"mean_token_accuracy": 0.1432926282286644,
|
||
|
|
"num_tokens": 2904947.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1759058952331545,
|
||
|
|
"epoch": 1.2807814629713765,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004981451820685928,
|
||
|
|
"loss": 5.9603,
|
||
|
|
"mean_token_accuracy": 0.1484628587961197,
|
||
|
|
"num_tokens": 2916183.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.175095415115356,
|
||
|
|
"epoch": 1.2853248523398455,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004980996191324802,
|
||
|
|
"loss": 5.8874,
|
||
|
|
"mean_token_accuracy": 0.14141177833080293,
|
||
|
|
"num_tokens": 2925429.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.246431970596314,
|
||
|
|
"epoch": 1.2898682417083145,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004980535057202351,
|
||
|
|
"loss": 5.9486,
|
||
|
|
"mean_token_accuracy": 0.1475185953080654,
|
||
|
|
"num_tokens": 2935142.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.173218536376953,
|
||
|
|
"epoch": 1.2944116310767833,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004980068419456378,
|
||
|
|
"loss": 6.0054,
|
||
|
|
"mean_token_accuracy": 0.1413328766822815,
|
||
|
|
"num_tokens": 2945151.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3213526725769045,
|
||
|
|
"epoch": 1.2989550204452522,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004979596279238265,
|
||
|
|
"loss": 6.0962,
|
||
|
|
"mean_token_accuracy": 0.14202187061309815,
|
||
|
|
"num_tokens": 2956015.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.199492073059082,
|
||
|
|
"epoch": 1.303498409813721,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004979118637712969,
|
||
|
|
"loss": 5.9377,
|
||
|
|
"mean_token_accuracy": 0.14465177059173584,
|
||
|
|
"num_tokens": 2965879.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.216682767868042,
|
||
|
|
"epoch": 1.30804179918219,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004978635496059025,
|
||
|
|
"loss": 6.0119,
|
||
|
|
"mean_token_accuracy": 0.1414727032184601,
|
||
|
|
"num_tokens": 2977021.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1556864261627195,
|
||
|
|
"epoch": 1.3125851885506588,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004978146855468537,
|
||
|
|
"loss": 5.9086,
|
||
|
|
"mean_token_accuracy": 0.14936657398939132,
|
||
|
|
"num_tokens": 2987169.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.278210592269898,
|
||
|
|
"epoch": 1.3171285779191277,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004977652717147177,
|
||
|
|
"loss": 6.0199,
|
||
|
|
"mean_token_accuracy": 0.14351356476545335,
|
||
|
|
"num_tokens": 2997666.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.191931247711182,
|
||
|
|
"epoch": 1.3216719672875965,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004977153082314182,
|
||
|
|
"loss": 5.8929,
|
||
|
|
"mean_token_accuracy": 0.14053303152322769,
|
||
|
|
"num_tokens": 3007021.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.170299625396728,
|
||
|
|
"epoch": 1.3262153566560655,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000497664795220235,
|
||
|
|
"loss": 5.952,
|
||
|
|
"mean_token_accuracy": 0.15345703661441804,
|
||
|
|
"num_tokens": 3016557.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.152959823608398,
|
||
|
|
"epoch": 1.3307587460245343,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004976137328058042,
|
||
|
|
"loss": 5.9222,
|
||
|
|
"mean_token_accuracy": 0.1459203690290451,
|
||
|
|
"num_tokens": 3026146.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.264169502258301,
|
||
|
|
"epoch": 1.3353021353930032,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000497562121114117,
|
||
|
|
"loss": 5.9734,
|
||
|
|
"mean_token_accuracy": 0.14671601578593255,
|
||
|
|
"num_tokens": 3037234.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.145901250839233,
|
||
|
|
"epoch": 1.339845524761472,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004975099602725202,
|
||
|
|
"loss": 5.9171,
|
||
|
|
"mean_token_accuracy": 0.14811089187860488,
|
||
|
|
"num_tokens": 3047282.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0958422183990475,
|
||
|
|
"epoch": 1.344388914129941,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004974572504097154,
|
||
|
|
"loss": 5.9315,
|
||
|
|
"mean_token_accuracy": 0.14823032170534134,
|
||
|
|
"num_tokens": 3058648.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.407826995849609,
|
||
|
|
"epoch": 1.3489323034984098,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004974039916557591,
|
||
|
|
"loss": 6.1211,
|
||
|
|
"mean_token_accuracy": 0.1399856761097908,
|
||
|
|
"num_tokens": 3068996.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.157318639755249,
|
||
|
|
"epoch": 1.3534756928668787,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000497350184142062,
|
||
|
|
"loss": 5.9307,
|
||
|
|
"mean_token_accuracy": 0.15413330644369125,
|
||
|
|
"num_tokens": 3078991.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.14020094871521,
|
||
|
|
"epoch": 1.3580190822353475,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004972958280013886,
|
||
|
|
"loss": 5.8893,
|
||
|
|
"mean_token_accuracy": 0.14595961272716523,
|
||
|
|
"num_tokens": 3090200.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1220416069030765,
|
||
|
|
"epoch": 1.3625624716038165,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004972409233678575,
|
||
|
|
"loss": 5.9451,
|
||
|
|
"mean_token_accuracy": 0.1446746289730072,
|
||
|
|
"num_tokens": 3101971.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.3625624716038165,
|
||
|
|
"eval_entropy": 5.998006772994995,
|
||
|
|
"eval_loss": 6.173778057098389,
|
||
|
|
"eval_mean_token_accuracy": 0.1402728841141906,
|
||
|
|
"eval_num_tokens": 3101971.0,
|
||
|
|
"eval_runtime": 2.0008,
|
||
|
|
"eval_samples_per_second": 1716.839,
|
||
|
|
"eval_steps_per_second": 214.917,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.163672637939453,
|
||
|
|
"epoch": 1.3671058609722853,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004971854703769401,
|
||
|
|
"loss": 6.0209,
|
||
|
|
"mean_token_accuracy": 0.1420085422694683,
|
||
|
|
"num_tokens": 3113381.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.293332433700561,
|
||
|
|
"epoch": 1.3716492503407542,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004971294691654616,
|
||
|
|
"loss": 5.9969,
|
||
|
|
"mean_token_accuracy": 0.1459997057914734,
|
||
|
|
"num_tokens": 3125099.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.071393442153931,
|
||
|
|
"epoch": 1.376192639709223,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000497072919871599,
|
||
|
|
"loss": 5.8885,
|
||
|
|
"mean_token_accuracy": 0.14934994727373124,
|
||
|
|
"num_tokens": 3135007.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.179635763168335,
|
||
|
|
"epoch": 1.380736029077692,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004970158226348824,
|
||
|
|
"loss": 5.9371,
|
||
|
|
"mean_token_accuracy": 0.14661285355687143,
|
||
|
|
"num_tokens": 3145031.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.185154438018799,
|
||
|
|
"epoch": 1.3852794184461608,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004969581775961932,
|
||
|
|
"loss": 5.9785,
|
||
|
|
"mean_token_accuracy": 0.14674355909228326,
|
||
|
|
"num_tokens": 3156044.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.160639667510987,
|
||
|
|
"epoch": 1.3898228078146297,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004968999848977651,
|
||
|
|
"loss": 5.8743,
|
||
|
|
"mean_token_accuracy": 0.15042117089033127,
|
||
|
|
"num_tokens": 3165124.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.065199089050293,
|
||
|
|
"epoch": 1.3943661971830985,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004968412446831827,
|
||
|
|
"loss": 5.8192,
|
||
|
|
"mean_token_accuracy": 0.15471493005752562,
|
||
|
|
"num_tokens": 3175246.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1831460952758786,
|
||
|
|
"epoch": 1.3989095865515675,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004967819570973816,
|
||
|
|
"loss": 5.9167,
|
||
|
|
"mean_token_accuracy": 0.15386194437742234,
|
||
|
|
"num_tokens": 3184817.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0874436378479,
|
||
|
|
"epoch": 1.4034529759200365,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000496722122286648,
|
||
|
|
"loss": 5.9543,
|
||
|
|
"mean_token_accuracy": 0.13574737310409546,
|
||
|
|
"num_tokens": 3195142.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.136379337310791,
|
||
|
|
"epoch": 1.4079963652885052,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004966617403986185,
|
||
|
|
"loss": 5.8976,
|
||
|
|
"mean_token_accuracy": 0.14391313940286637,
|
||
|
|
"num_tokens": 3205724.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.181877279281617,
|
||
|
|
"epoch": 1.412539754656974,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004966008115822793,
|
||
|
|
"loss": 6.0459,
|
||
|
|
"mean_token_accuracy": 0.1418856129050255,
|
||
|
|
"num_tokens": 3216919.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.292528104782105,
|
||
|
|
"epoch": 1.417083144025443,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004965393359879662,
|
||
|
|
"loss": 6.0416,
|
||
|
|
"mean_token_accuracy": 0.14282304048538208,
|
||
|
|
"num_tokens": 3228929.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.154995155334473,
|
||
|
|
"epoch": 1.421626533393912,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004964773137673641,
|
||
|
|
"loss": 5.9996,
|
||
|
|
"mean_token_accuracy": 0.14393652155995368,
|
||
|
|
"num_tokens": 3239541.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1706877708435055,
|
||
|
|
"epoch": 1.4261699227623807,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004964147450735067,
|
||
|
|
"loss": 5.8848,
|
||
|
|
"mean_token_accuracy": 0.14642009437084197,
|
||
|
|
"num_tokens": 3249527.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.04834885597229,
|
||
|
|
"epoch": 1.4307133121308495,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000496351630060776,
|
||
|
|
"loss": 5.7945,
|
||
|
|
"mean_token_accuracy": 0.14744008034467698,
|
||
|
|
"num_tokens": 3260497.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.257424974441529,
|
||
|
|
"epoch": 1.4352567014993185,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004962879688849021,
|
||
|
|
"loss": 5.9799,
|
||
|
|
"mean_token_accuracy": 0.14823087900877,
|
||
|
|
"num_tokens": 3270865.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.060004806518554,
|
||
|
|
"epoch": 1.4398000908677875,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004962237617029625,
|
||
|
|
"loss": 5.9086,
|
||
|
|
"mean_token_accuracy": 0.1426824726164341,
|
||
|
|
"num_tokens": 3281531.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.207708930969238,
|
||
|
|
"epoch": 1.4443434802362562,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004961590086733821,
|
||
|
|
"loss": 5.8779,
|
||
|
|
"mean_token_accuracy": 0.14353057891130447,
|
||
|
|
"num_tokens": 3291970.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.059498691558838,
|
||
|
|
"epoch": 1.448886869604725,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004960937099559326,
|
||
|
|
"loss": 5.9209,
|
||
|
|
"mean_token_accuracy": 0.15407329946756362,
|
||
|
|
"num_tokens": 3301638.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.249056720733643,
|
||
|
|
"epoch": 1.453430258973194,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004960278657117321,
|
||
|
|
"loss": 6.0004,
|
||
|
|
"mean_token_accuracy": 0.1454174779355526,
|
||
|
|
"num_tokens": 3311780.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.074241209030151,
|
||
|
|
"epoch": 1.457973648341663,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004959614761032446,
|
||
|
|
"loss": 5.8559,
|
||
|
|
"mean_token_accuracy": 0.14448125958442687,
|
||
|
|
"num_tokens": 3322096.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.243053770065307,
|
||
|
|
"epoch": 1.4625170377101318,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00049589454129428,
|
||
|
|
"loss": 6.0287,
|
||
|
|
"mean_token_accuracy": 0.14130257591605186,
|
||
|
|
"num_tokens": 3332324.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.052849674224854,
|
||
|
|
"epoch": 1.4670604270786005,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004958270614499932,
|
||
|
|
"loss": 5.8215,
|
||
|
|
"mean_token_accuracy": 0.15624394565820693,
|
||
|
|
"num_tokens": 3342037.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.178307437896729,
|
||
|
|
"epoch": 1.4716038164470695,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004957590367368841,
|
||
|
|
"loss": 5.9252,
|
||
|
|
"mean_token_accuracy": 0.1461096227169037,
|
||
|
|
"num_tokens": 3353047.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.08671293258667,
|
||
|
|
"epoch": 1.4761472058155385,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004956904673227968,
|
||
|
|
"loss": 5.8278,
|
||
|
|
"mean_token_accuracy": 0.14527380913496019,
|
||
|
|
"num_tokens": 3363841.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1023805141448975,
|
||
|
|
"epoch": 1.4806905951840073,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004956213533769195,
|
||
|
|
"loss": 5.9244,
|
||
|
|
"mean_token_accuracy": 0.14610948264598847,
|
||
|
|
"num_tokens": 3374086.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.123172569274902,
|
||
|
|
"epoch": 1.485233984552476,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004955516950697843,
|
||
|
|
"loss": 5.8951,
|
||
|
|
"mean_token_accuracy": 0.14830472320318222,
|
||
|
|
"num_tokens": 3384303.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.119581699371338,
|
||
|
|
"epoch": 1.489777373920945,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004954814925732657,
|
||
|
|
"loss": 5.8746,
|
||
|
|
"mean_token_accuracy": 0.14966145604848863,
|
||
|
|
"num_tokens": 3394858.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.098552131652832,
|
||
|
|
"epoch": 1.494320763289414,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004954107460605816,
|
||
|
|
"loss": 5.8808,
|
||
|
|
"mean_token_accuracy": 0.153575536608696,
|
||
|
|
"num_tokens": 3405252.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.24327540397644,
|
||
|
|
"epoch": 1.4988641526578828,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004953394557062922,
|
||
|
|
"loss": 5.9472,
|
||
|
|
"mean_token_accuracy": 0.14877036213874817,
|
||
|
|
"num_tokens": 3416007.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.228945350646972,
|
||
|
|
"epoch": 1.5034075420263515,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004952676216862989,
|
||
|
|
"loss": 5.9792,
|
||
|
|
"mean_token_accuracy": 0.14415789693593978,
|
||
|
|
"num_tokens": 3426932.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.038790559768676,
|
||
|
|
"epoch": 1.5079509313948205,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004951952441778453,
|
||
|
|
"loss": 5.8586,
|
||
|
|
"mean_token_accuracy": 0.15109123438596725,
|
||
|
|
"num_tokens": 3437262.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.09799542427063,
|
||
|
|
"epoch": 1.5124943207632895,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004951223233595158,
|
||
|
|
"loss": 5.8273,
|
||
|
|
"mean_token_accuracy": 0.15195785015821456,
|
||
|
|
"num_tokens": 3447525.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1701806545257565,
|
||
|
|
"epoch": 1.5170377101317583,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000495048859411235,
|
||
|
|
"loss": 5.9336,
|
||
|
|
"mean_token_accuracy": 0.15256594866514206,
|
||
|
|
"num_tokens": 3458198.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0774983882904055,
|
||
|
|
"epoch": 1.521581099500227,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004949748525142681,
|
||
|
|
"loss": 5.8165,
|
||
|
|
"mean_token_accuracy": 0.1567363977432251,
|
||
|
|
"num_tokens": 3468149.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.081609010696411,
|
||
|
|
"epoch": 1.526124488868696,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004949003028512195,
|
||
|
|
"loss": 5.8139,
|
||
|
|
"mean_token_accuracy": 0.14687097519636155,
|
||
|
|
"num_tokens": 3478355.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.097584533691406,
|
||
|
|
"epoch": 1.530667878237165,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004948252106060334,
|
||
|
|
"loss": 5.8428,
|
||
|
|
"mean_token_accuracy": 0.15158360898494722,
|
||
|
|
"num_tokens": 3488726.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.048998165130615,
|
||
|
|
"epoch": 1.5352112676056338,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004947495759639923,
|
||
|
|
"loss": 5.7861,
|
||
|
|
"mean_token_accuracy": 0.15492362827062606,
|
||
|
|
"num_tokens": 3498346.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.995868158340454,
|
||
|
|
"epoch": 1.5397546569741025,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004946733991117171,
|
||
|
|
"loss": 5.8739,
|
||
|
|
"mean_token_accuracy": 0.15013641715049744,
|
||
|
|
"num_tokens": 3508213.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.236345434188843,
|
||
|
|
"epoch": 1.5442980463425715,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004945966802371668,
|
||
|
|
"loss": 5.9989,
|
||
|
|
"mean_token_accuracy": 0.15021879523992537,
|
||
|
|
"num_tokens": 3518978.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.119385671615601,
|
||
|
|
"epoch": 1.5488414357110405,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004945194195296374,
|
||
|
|
"loss": 5.9327,
|
||
|
|
"mean_token_accuracy": 0.1489047683775425,
|
||
|
|
"num_tokens": 3529328.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.03963418006897,
|
||
|
|
"epoch": 1.5533848250795095,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000494441617179762,
|
||
|
|
"loss": 5.8623,
|
||
|
|
"mean_token_accuracy": 0.14225288853049278,
|
||
|
|
"num_tokens": 3539347.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.159651279449463,
|
||
|
|
"epoch": 1.5579282144479782,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004943632733795104,
|
||
|
|
"loss": 5.8838,
|
||
|
|
"mean_token_accuracy": 0.1437460221350193,
|
||
|
|
"num_tokens": 3549798.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.087096071243286,
|
||
|
|
"epoch": 1.562471603816447,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004942843883221879,
|
||
|
|
"loss": 5.978,
|
||
|
|
"mean_token_accuracy": 0.1412530466914177,
|
||
|
|
"num_tokens": 3560363.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1436097621917725,
|
||
|
|
"epoch": 1.567014993184916,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004942049622024357,
|
||
|
|
"loss": 5.9047,
|
||
|
|
"mean_token_accuracy": 0.1528037503361702,
|
||
|
|
"num_tokens": 3570080.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.058519458770752,
|
||
|
|
"epoch": 1.571558382553385,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004941249952162298,
|
||
|
|
"loss": 5.9049,
|
||
|
|
"mean_token_accuracy": 0.14703553318977355,
|
||
|
|
"num_tokens": 3580053.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.13126769065857,
|
||
|
|
"epoch": 1.5761017719218537,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004940444875608807,
|
||
|
|
"loss": 5.9875,
|
||
|
|
"mean_token_accuracy": 0.14530991315841674,
|
||
|
|
"num_tokens": 3590119.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.181125068664551,
|
||
|
|
"epoch": 1.5806451612903225,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004939634394350332,
|
||
|
|
"loss": 5.9674,
|
||
|
|
"mean_token_accuracy": 0.1385622426867485,
|
||
|
|
"num_tokens": 3601809.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.158671808242798,
|
||
|
|
"epoch": 1.5851885506587915,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004938818510386654,
|
||
|
|
"loss": 5.8219,
|
||
|
|
"mean_token_accuracy": 0.15508615523576735,
|
||
|
|
"num_tokens": 3611752.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0497949600219725,
|
||
|
|
"epoch": 1.5897319400272605,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004937997225730886,
|
||
|
|
"loss": 5.8889,
|
||
|
|
"mean_token_accuracy": 0.14583897739648818,
|
||
|
|
"num_tokens": 3621137.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.117823123931885,
|
||
|
|
"epoch": 1.5942753293957292,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004937170542409464,
|
||
|
|
"loss": 5.8594,
|
||
|
|
"mean_token_accuracy": 0.15217961221933365,
|
||
|
|
"num_tokens": 3631567.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.027679061889648,
|
||
|
|
"epoch": 1.598818718764198,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000493633846246215,
|
||
|
|
"loss": 5.8221,
|
||
|
|
"mean_token_accuracy": 0.14410740211606027,
|
||
|
|
"num_tokens": 3641145.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.09434552192688,
|
||
|
|
"epoch": 1.603362108132667,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004935500987942018,
|
||
|
|
"loss": 5.8681,
|
||
|
|
"mean_token_accuracy": 0.1448398560285568,
|
||
|
|
"num_tokens": 3651716.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.130527305603027,
|
||
|
|
"epoch": 1.607905497501136,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004934658120915452,
|
||
|
|
"loss": 5.8207,
|
||
|
|
"mean_token_accuracy": 0.15499569922685624,
|
||
|
|
"num_tokens": 3662577.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.012383270263672,
|
||
|
|
"epoch": 1.6124488868696047,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004933809863462142,
|
||
|
|
"loss": 5.8048,
|
||
|
|
"mean_token_accuracy": 0.15538352131843566,
|
||
|
|
"num_tokens": 3672984.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1079894542694095,
|
||
|
|
"epoch": 1.6169922762380735,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004932956217675082,
|
||
|
|
"loss": 5.8837,
|
||
|
|
"mean_token_accuracy": 0.15415330082178116,
|
||
|
|
"num_tokens": 3682634.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.053774452209472,
|
||
|
|
"epoch": 1.6215356656065425,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004932097185660555,
|
||
|
|
"loss": 5.8568,
|
||
|
|
"mean_token_accuracy": 0.14938003569841385,
|
||
|
|
"num_tokens": 3693022.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.923639822006225,
|
||
|
|
"epoch": 1.6260790549750115,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004931232769538138,
|
||
|
|
"loss": 5.7328,
|
||
|
|
"mean_token_accuracy": 0.15786038786172868,
|
||
|
|
"num_tokens": 3702234.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0286894798278805,
|
||
|
|
"epoch": 1.6306224443434802,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004930362971440692,
|
||
|
|
"loss": 5.9116,
|
||
|
|
"mean_token_accuracy": 0.1445778265595436,
|
||
|
|
"num_tokens": 3712235.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.143106698989868,
|
||
|
|
"epoch": 1.635165833711949,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004929487793514358,
|
||
|
|
"loss": 5.8417,
|
||
|
|
"mean_token_accuracy": 0.15846360027790068,
|
||
|
|
"num_tokens": 3722745.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9879150390625,
|
||
|
|
"epoch": 1.639709223080418,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000492860723791855,
|
||
|
|
"loss": 5.8976,
|
||
|
|
"mean_token_accuracy": 0.15017399489879607,
|
||
|
|
"num_tokens": 3732942.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.137276124954224,
|
||
|
|
"epoch": 1.644252612448887,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004927721306825952,
|
||
|
|
"loss": 5.8819,
|
||
|
|
"mean_token_accuracy": 0.1497318923473358,
|
||
|
|
"num_tokens": 3743806.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006168842315674,
|
||
|
|
"epoch": 1.6487960018173557,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004926830002422509,
|
||
|
|
"loss": 5.8719,
|
||
|
|
"mean_token_accuracy": 0.15341466218233107,
|
||
|
|
"num_tokens": 3755115.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.078045082092285,
|
||
|
|
"epoch": 1.6533393911858245,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000492593332690743,
|
||
|
|
"loss": 5.8205,
|
||
|
|
"mean_token_accuracy": 0.15602415949106216,
|
||
|
|
"num_tokens": 3765867.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.980977249145508,
|
||
|
|
"epoch": 1.6578827805542935,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004925031282493167,
|
||
|
|
"loss": 5.8035,
|
||
|
|
"mean_token_accuracy": 0.15344792902469634,
|
||
|
|
"num_tokens": 3777071.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.016601514816284,
|
||
|
|
"epoch": 1.6624261699227625,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004924123871405428,
|
||
|
|
"loss": 5.7974,
|
||
|
|
"mean_token_accuracy": 0.1537347137928009,
|
||
|
|
"num_tokens": 3786554.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.102873992919922,
|
||
|
|
"epoch": 1.6669695592912313,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004923211095883161,
|
||
|
|
"loss": 5.8517,
|
||
|
|
"mean_token_accuracy": 0.15107907652854918,
|
||
|
|
"num_tokens": 3797627.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.971213245391846,
|
||
|
|
"epoch": 1.6715129486597,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004922292958178546,
|
||
|
|
"loss": 5.8426,
|
||
|
|
"mean_token_accuracy": 0.1507897347211838,
|
||
|
|
"num_tokens": 3808841.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1389758586883545,
|
||
|
|
"epoch": 1.676056338028169,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004921369460557,
|
||
|
|
"loss": 5.8725,
|
||
|
|
"mean_token_accuracy": 0.14769963175058365,
|
||
|
|
"num_tokens": 3818995.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.062976360321045,
|
||
|
|
"epoch": 1.680599727396638,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004920440605297159,
|
||
|
|
"loss": 5.9237,
|
||
|
|
"mean_token_accuracy": 0.1460937276482582,
|
||
|
|
"num_tokens": 3828762.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.094574308395385,
|
||
|
|
"epoch": 1.6851431167651068,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000491950639469088,
|
||
|
|
"loss": 5.7671,
|
||
|
|
"mean_token_accuracy": 0.15168659314513205,
|
||
|
|
"num_tokens": 3838752.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985349941253662,
|
||
|
|
"epoch": 1.6896865061335755,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004918566831043238,
|
||
|
|
"loss": 5.8084,
|
||
|
|
"mean_token_accuracy": 0.15743009150028228,
|
||
|
|
"num_tokens": 3849664.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.03216323852539,
|
||
|
|
"epoch": 1.6942298955020445,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000491762191667251,
|
||
|
|
"loss": 5.8003,
|
||
|
|
"mean_token_accuracy": 0.1560536116361618,
|
||
|
|
"num_tokens": 3859053.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0026287078857425,
|
||
|
|
"epoch": 1.6987732848705135,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000491667165391018,
|
||
|
|
"loss": 5.8584,
|
||
|
|
"mean_token_accuracy": 0.14554656594991683,
|
||
|
|
"num_tokens": 3869654.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073776149749756,
|
||
|
|
"epoch": 1.7033166742389823,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004915716045100927,
|
||
|
|
"loss": 5.8558,
|
||
|
|
"mean_token_accuracy": 0.14700101166963578,
|
||
|
|
"num_tokens": 3879678.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.020952033996582,
|
||
|
|
"epoch": 1.707860063607451,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004914755092602621,
|
||
|
|
"loss": 5.7539,
|
||
|
|
"mean_token_accuracy": 0.15705975145101547,
|
||
|
|
"num_tokens": 3889950.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9746153354644775,
|
||
|
|
"epoch": 1.71240345297592,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004913788798786314,
|
||
|
|
"loss": 5.838,
|
||
|
|
"mean_token_accuracy": 0.15099019408226014,
|
||
|
|
"num_tokens": 3900095.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.169710397720337,
|
||
|
|
"epoch": 1.716946842344389,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004912817166036243,
|
||
|
|
"loss": 5.8931,
|
||
|
|
"mean_token_accuracy": 0.14681051373481752,
|
||
|
|
"num_tokens": 3911034.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.995103216171264,
|
||
|
|
"epoch": 1.7214902317128578,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004911840196749813,
|
||
|
|
"loss": 5.8633,
|
||
|
|
"mean_token_accuracy": 0.15044671893119813,
|
||
|
|
"num_tokens": 3922219.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01338906288147,
|
||
|
|
"epoch": 1.7260336210813265,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004910857893337602,
|
||
|
|
"loss": 5.8327,
|
||
|
|
"mean_token_accuracy": 0.15175913274288177,
|
||
|
|
"num_tokens": 3932235.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006257343292236,
|
||
|
|
"epoch": 1.7305770104497955,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004909870258223342,
|
||
|
|
"loss": 5.7738,
|
||
|
|
"mean_token_accuracy": 0.1562149293720722,
|
||
|
|
"num_tokens": 3941845.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0315406799316404,
|
||
|
|
"epoch": 1.7351203998182645,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004908877293843926,
|
||
|
|
"loss": 5.8632,
|
||
|
|
"mean_token_accuracy": 0.14723684638738632,
|
||
|
|
"num_tokens": 3953392.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0056493282318115,
|
||
|
|
"epoch": 1.7396637891867333,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004907879002649395,
|
||
|
|
"loss": 5.7197,
|
||
|
|
"mean_token_accuracy": 0.15770288556814194,
|
||
|
|
"num_tokens": 3963294.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.951028156280517,
|
||
|
|
"epoch": 1.744207178555202,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004906875387102935,
|
||
|
|
"loss": 5.7917,
|
||
|
|
"mean_token_accuracy": 0.1482487738132477,
|
||
|
|
"num_tokens": 3973660.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.048778867721557,
|
||
|
|
"epoch": 1.748750567923671,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004905866449680864,
|
||
|
|
"loss": 5.7858,
|
||
|
|
"mean_token_accuracy": 0.15318481773138046,
|
||
|
|
"num_tokens": 3983587.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.014044857025146,
|
||
|
|
"epoch": 1.75329395729214,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004904852192872638,
|
||
|
|
"loss": 5.8483,
|
||
|
|
"mean_token_accuracy": 0.1447431579232216,
|
||
|
|
"num_tokens": 3994346.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.030064249038697,
|
||
|
|
"epoch": 1.757837346660609,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004903832619180834,
|
||
|
|
"loss": 5.8229,
|
||
|
|
"mean_token_accuracy": 0.15561417788267135,
|
||
|
|
"num_tokens": 4005234.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.914287424087524,
|
||
|
|
"epoch": 1.7623807360290777,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004902807731121147,
|
||
|
|
"loss": 5.7382,
|
||
|
|
"mean_token_accuracy": 0.15640076696872712,
|
||
|
|
"num_tokens": 4015542.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9699568271636965,
|
||
|
|
"epoch": 1.7669241253975465,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004901777531222389,
|
||
|
|
"loss": 5.7553,
|
||
|
|
"mean_token_accuracy": 0.16071913093328477,
|
||
|
|
"num_tokens": 4024874.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.061671257019043,
|
||
|
|
"epoch": 1.7714675147660155,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004900742022026474,
|
||
|
|
"loss": 5.9002,
|
||
|
|
"mean_token_accuracy": 0.15215046256780623,
|
||
|
|
"num_tokens": 4035880.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.04217495918274,
|
||
|
|
"epoch": 1.7760109041344845,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004899701206088419,
|
||
|
|
"loss": 5.7851,
|
||
|
|
"mean_token_accuracy": 0.15591228753328323,
|
||
|
|
"num_tokens": 4046484.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0316204071044925,
|
||
|
|
"epoch": 1.7805542935029532,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004898655085976333,
|
||
|
|
"loss": 5.8441,
|
||
|
|
"mean_token_accuracy": 0.15250226184725763,
|
||
|
|
"num_tokens": 4057037.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.102791118621826,
|
||
|
|
"epoch": 1.785097682871422,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004897603664271413,
|
||
|
|
"loss": 5.9278,
|
||
|
|
"mean_token_accuracy": 0.1487814873456955,
|
||
|
|
"num_tokens": 4066169.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.98809928894043,
|
||
|
|
"epoch": 1.789641072239891,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000489654694356794,
|
||
|
|
"loss": 5.8312,
|
||
|
|
"mean_token_accuracy": 0.14956735149025918,
|
||
|
|
"num_tokens": 4076697.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.998944187164307,
|
||
|
|
"epoch": 1.79418446160836,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004895484926473265,
|
||
|
|
"loss": 5.7309,
|
||
|
|
"mean_token_accuracy": 0.15552960187196732,
|
||
|
|
"num_tokens": 4087372.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.047774410247802,
|
||
|
|
"epoch": 1.7987278509768287,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000489441761560781,
|
||
|
|
"loss": 5.8148,
|
||
|
|
"mean_token_accuracy": 0.14908257573843003,
|
||
|
|
"num_tokens": 4097653.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006575441360473,
|
||
|
|
"epoch": 1.8032712403452975,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.000489334501360506,
|
||
|
|
"loss": 5.7478,
|
||
|
|
"mean_token_accuracy": 0.15341038405895233,
|
||
|
|
"num_tokens": 4107381.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.064118814468384,
|
||
|
|
"epoch": 1.8078146297137665,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004892267123111551,
|
||
|
|
"loss": 5.8693,
|
||
|
|
"mean_token_accuracy": 0.1496926262974739,
|
||
|
|
"num_tokens": 4118762.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.946984529495239,
|
||
|
|
"epoch": 1.8123580190822355,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004891183946786873,
|
||
|
|
"loss": 5.7685,
|
||
|
|
"mean_token_accuracy": 0.15168437510728836,
|
||
|
|
"num_tokens": 4129011.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.085385131835937,
|
||
|
|
"epoch": 1.8169014084507042,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004890095487303655,
|
||
|
|
"loss": 5.8416,
|
||
|
|
"mean_token_accuracy": 0.14939511120319365,
|
||
|
|
"num_tokens": 4138975.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.8169014084507042,
|
||
|
|
"eval_entropy": 5.802581080725027,
|
||
|
|
"eval_loss": 5.989554405212402,
|
||
|
|
"eval_mean_token_accuracy": 0.15064924421698547,
|
||
|
|
"eval_num_tokens": 4138975.0,
|
||
|
|
"eval_runtime": 2.0074,
|
||
|
|
"eval_samples_per_second": 1711.137,
|
||
|
|
"eval_steps_per_second": 214.203,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.994388818740845,
|
||
|
|
"epoch": 1.821444797819173,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004889001747347562,
|
||
|
|
"loss": 5.8601,
|
||
|
|
"mean_token_accuracy": 0.14598984345793725,
|
||
|
|
"num_tokens": 4150164.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.953599166870117,
|
||
|
|
"epoch": 1.825988187187642,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.000488790272961729,
|
||
|
|
"loss": 5.762,
|
||
|
|
"mean_token_accuracy": 0.15967332124710082,
|
||
|
|
"num_tokens": 4159872.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.017344665527344,
|
||
|
|
"epoch": 1.830531576556111,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004886798436824556,
|
||
|
|
"loss": 5.8409,
|
||
|
|
"mean_token_accuracy": 0.14872767329216002,
|
||
|
|
"num_tokens": 4170665.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01618185043335,
|
||
|
|
"epoch": 1.8350749659245797,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004885688871694091,
|
||
|
|
"loss": 5.7142,
|
||
|
|
"mean_token_accuracy": 0.1626022905111313,
|
||
|
|
"num_tokens": 4180476.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.995317649841309,
|
||
|
|
"epoch": 1.8396183552930485,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004884574036963639,
|
||
|
|
"loss": 5.8566,
|
||
|
|
"mean_token_accuracy": 0.15099751204252243,
|
||
|
|
"num_tokens": 4190740.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.956916618347168,
|
||
|
|
"epoch": 1.8441617446615175,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004883453935383941,
|
||
|
|
"loss": 5.7434,
|
||
|
|
"mean_token_accuracy": 0.1571941539645195,
|
||
|
|
"num_tokens": 4201504.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.875329256057739,
|
||
|
|
"epoch": 1.8487051340299865,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004882328569718738,
|
||
|
|
"loss": 5.6753,
|
||
|
|
"mean_token_accuracy": 0.16390404999256133,
|
||
|
|
"num_tokens": 4211614.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.969325065612793,
|
||
|
|
"epoch": 1.8532485233984552,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004881197942744758,
|
||
|
|
"loss": 5.8008,
|
||
|
|
"mean_token_accuracy": 0.15329188108444214,
|
||
|
|
"num_tokens": 4221141.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.991888856887817,
|
||
|
|
"epoch": 1.857791912766924,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004880062057251711,
|
||
|
|
"loss": 5.8352,
|
||
|
|
"mean_token_accuracy": 0.15410455614328383,
|
||
|
|
"num_tokens": 4231877.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.914742946624756,
|
||
|
|
"epoch": 1.862335302135393,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000487892091604228,
|
||
|
|
"loss": 5.6553,
|
||
|
|
"mean_token_accuracy": 0.16117654740810394,
|
||
|
|
"num_tokens": 4242331.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.914829111099243,
|
||
|
|
"epoch": 1.866878691503862,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00048777745219321186,
|
||
|
|
"loss": 5.6845,
|
||
|
|
"mean_token_accuracy": 0.1546552672982216,
|
||
|
|
"num_tokens": 4252406.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.974059200286865,
|
||
|
|
"epoch": 1.8714220808723308,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00048766228777498405,
|
||
|
|
"loss": 5.7597,
|
||
|
|
"mean_token_accuracy": 0.1531647711992264,
|
||
|
|
"num_tokens": 4263036.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9508284568786625,
|
||
|
|
"epoch": 1.8759654702407995,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00048754659863370125,
|
||
|
|
"loss": 5.7335,
|
||
|
|
"mean_token_accuracy": 0.1608620196580887,
|
||
|
|
"num_tokens": 4273032.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.926699542999268,
|
||
|
|
"epoch": 1.8805088596092685,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00048743038505481503,
|
||
|
|
"loss": 5.8057,
|
||
|
|
"mean_token_accuracy": 0.1554887369275093,
|
||
|
|
"num_tokens": 4283360.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959084749221802,
|
||
|
|
"epoch": 1.8850522489777375,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004873136473250708,
|
||
|
|
"loss": 5.7423,
|
||
|
|
"mean_token_accuracy": 0.15936065316200257,
|
||
|
|
"num_tokens": 4292623.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.969320487976074,
|
||
|
|
"epoch": 1.8895956383462063,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00048719638573250715,
|
||
|
|
"loss": 5.7658,
|
||
|
|
"mean_token_accuracy": 0.1576855793595314,
|
||
|
|
"num_tokens": 4302817.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.005345106124878,
|
||
|
|
"epoch": 1.894139027714675,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004870786005664555,
|
||
|
|
"loss": 5.7671,
|
||
|
|
"mean_token_accuracy": 0.15660459101200103,
|
||
|
|
"num_tokens": 4313049.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.913744068145752,
|
||
|
|
"epoch": 1.898682417083144,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004869602921175392,
|
||
|
|
"loss": 5.6484,
|
||
|
|
"mean_token_accuracy": 0.1619171142578125,
|
||
|
|
"num_tokens": 4322873.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8904248714447025,
|
||
|
|
"epoch": 1.903225806451613,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004868414606776724,
|
||
|
|
"loss": 5.8048,
|
||
|
|
"mean_token_accuracy": 0.14883103221654892,
|
||
|
|
"num_tokens": 4333339.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.974893951416016,
|
||
|
|
"epoch": 1.9077691958200818,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00048672210654005996,
|
||
|
|
"loss": 5.7668,
|
||
|
|
"mean_token_accuracy": 0.15438382625579833,
|
||
|
|
"num_tokens": 4344917.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.866996431350708,
|
||
|
|
"epoch": 1.9123125851885505,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00048660222999919616,
|
||
|
|
"loss": 5.6211,
|
||
|
|
"mean_token_accuracy": 0.16387978196144104,
|
||
|
|
"num_tokens": 4354140.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.947313690185547,
|
||
|
|
"epoch": 1.9168559745570195,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004864818313508647,
|
||
|
|
"loss": 5.871,
|
||
|
|
"mean_token_accuracy": 0.14966592639684678,
|
||
|
|
"num_tokens": 4364976.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965764045715332,
|
||
|
|
"epoch": 1.9213993639254885,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004863609108921372,
|
||
|
|
"loss": 5.6455,
|
||
|
|
"mean_token_accuracy": 0.16220821142196656,
|
||
|
|
"num_tokens": 4376423.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96432089805603,
|
||
|
|
"epoch": 1.9259427532939573,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004862394689213728,
|
||
|
|
"loss": 5.7859,
|
||
|
|
"mean_token_accuracy": 0.15559903681278228,
|
||
|
|
"num_tokens": 4387865.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.928690385818482,
|
||
|
|
"epoch": 1.930486142662426,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004861175057382175,
|
||
|
|
"loss": 5.7782,
|
||
|
|
"mean_token_accuracy": 0.1554933860898018,
|
||
|
|
"num_tokens": 4398275.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.014926385879517,
|
||
|
|
"epoch": 1.935029532030895,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004859950216436034,
|
||
|
|
"loss": 5.705,
|
||
|
|
"mean_token_accuracy": 0.15233548432588578,
|
||
|
|
"num_tokens": 4407396.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.056639719009399,
|
||
|
|
"epoch": 1.939572921399364,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004858720169397478,
|
||
|
|
"loss": 5.9496,
|
||
|
|
"mean_token_accuracy": 0.147593604773283,
|
||
|
|
"num_tokens": 4419682.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.961567783355713,
|
||
|
|
"epoch": 1.9441163107678328,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004857484919301525,
|
||
|
|
"loss": 5.8116,
|
||
|
|
"mean_token_accuracy": 0.1537695899605751,
|
||
|
|
"num_tokens": 4430590.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9822437286376955,
|
||
|
|
"epoch": 1.9486597001363015,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004856244469196034,
|
||
|
|
"loss": 5.7355,
|
||
|
|
"mean_token_accuracy": 0.158633291721344,
|
||
|
|
"num_tokens": 4441979.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.946609210968018,
|
||
|
|
"epoch": 1.9532030895047705,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000485499882214169,
|
||
|
|
"loss": 5.7522,
|
||
|
|
"mean_token_accuracy": 0.16035017371177673,
|
||
|
|
"num_tokens": 4451975.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.85480809211731,
|
||
|
|
"epoch": 1.9577464788732395,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004853747981212003,
|
||
|
|
"loss": 5.6904,
|
||
|
|
"mean_token_accuracy": 0.1584114506840706,
|
||
|
|
"num_tokens": 4462778.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0221734046936035,
|
||
|
|
"epoch": 1.9622898682417085,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004852491949493301,
|
||
|
|
"loss": 5.7479,
|
||
|
|
"mean_token_accuracy": 0.16584970504045488,
|
||
|
|
"num_tokens": 4472461.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8947083950042725,
|
||
|
|
"epoch": 1.9668332576101772,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004851230730084716,
|
||
|
|
"loss": 5.6977,
|
||
|
|
"mean_token_accuracy": 0.15985091775655746,
|
||
|
|
"num_tokens": 4482507.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9333573341369625,
|
||
|
|
"epoch": 1.971376646978646,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00048499643260981816,
|
||
|
|
"loss": 5.72,
|
||
|
|
"mean_token_accuracy": 0.15951878279447557,
|
||
|
|
"num_tokens": 4492601.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.92025089263916,
|
||
|
|
"epoch": 1.975920036347115,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004848692740658424,
|
||
|
|
"loss": 5.8213,
|
||
|
|
"mean_token_accuracy": 0.15883293896913528,
|
||
|
|
"num_tokens": 4503696.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.95161771774292,
|
||
|
|
"epoch": 1.980463425715584,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004847415976902954,
|
||
|
|
"loss": 5.7105,
|
||
|
|
"mean_token_accuracy": 0.15256518721580506,
|
||
|
|
"num_tokens": 4513649.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.954947519302368,
|
||
|
|
"epoch": 1.9850068150840527,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00048461340379820587,
|
||
|
|
"loss": 5.733,
|
||
|
|
"mean_token_accuracy": 0.15729330182075502,
|
||
|
|
"num_tokens": 4524054.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.966910886764526,
|
||
|
|
"epoch": 1.9895502044525215,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00048448469270587945,
|
||
|
|
"loss": 5.7227,
|
||
|
|
"mean_token_accuracy": 0.15084918439388276,
|
||
|
|
"num_tokens": 4535549.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9350450992584225,
|
||
|
|
"epoch": 1.9940935938209905,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00048435546473089814,
|
||
|
|
"loss": 5.7532,
|
||
|
|
"mean_token_accuracy": 0.15482822358608245,
|
||
|
|
"num_tokens": 4545654.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.928518342971802,
|
||
|
|
"epoch": 1.9986369831894595,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00048422572019211896,
|
||
|
|
"loss": 5.757,
|
||
|
|
"mean_token_accuracy": 0.15873578190803528,
|
||
|
|
"num_tokens": 4556230.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.900713867611355,
|
||
|
|
"epoch": 2.0027260336210815,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.00048409545940967375,
|
||
|
|
"loss": 5.5157,
|
||
|
|
"mean_token_accuracy": 0.16549871199660832,
|
||
|
|
"num_tokens": 4564486.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.888030290603638,
|
||
|
|
"epoch": 2.00726942298955,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000483964682704968,
|
||
|
|
"loss": 5.4203,
|
||
|
|
"mean_token_accuracy": 0.171760892868042,
|
||
|
|
"num_tokens": 4575026.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.825547981262207,
|
||
|
|
"epoch": 2.011812812358019,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00048383339040068024,
|
||
|
|
"loss": 5.4509,
|
||
|
|
"mean_token_accuracy": 0.16520898640155793,
|
||
|
|
"num_tokens": 4585902.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.032274007797241,
|
||
|
|
"epoch": 2.016356201726488,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004837015828207612,
|
||
|
|
"loss": 5.5558,
|
||
|
|
"mean_token_accuracy": 0.1652931973338127,
|
||
|
|
"num_tokens": 4597609.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.861545181274414,
|
||
|
|
"epoch": 2.020899591094957,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004835692602904329,
|
||
|
|
"loss": 5.4229,
|
||
|
|
"mean_token_accuracy": 0.17381911724805832,
|
||
|
|
"num_tokens": 4607531.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8608067512512205,
|
||
|
|
"epoch": 2.0254429804634255,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004834364231361882,
|
||
|
|
"loss": 5.4707,
|
||
|
|
"mean_token_accuracy": 0.16835336834192277,
|
||
|
|
"num_tokens": 4618826.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.993276453018188,
|
||
|
|
"epoch": 2.0299863698318945,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004833030716857894,
|
||
|
|
"loss": 5.4663,
|
||
|
|
"mean_token_accuracy": 0.17149772942066194,
|
||
|
|
"num_tokens": 4629526.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.863670110702515,
|
||
|
|
"epoch": 2.0345297592003635,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00048316920626826807,
|
||
|
|
"loss": 5.499,
|
||
|
|
"mean_token_accuracy": 0.17145546674728393,
|
||
|
|
"num_tokens": 4639930.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.893801164627075,
|
||
|
|
"epoch": 2.0390731485688325,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00048303482721392363,
|
||
|
|
"loss": 5.398,
|
||
|
|
"mean_token_accuracy": 0.17716680318117142,
|
||
|
|
"num_tokens": 4649661.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.778148555755616,
|
||
|
|
"epoch": 2.043616537937301,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00048289993485432325,
|
||
|
|
"loss": 5.3957,
|
||
|
|
"mean_token_accuracy": 0.17859122008085251,
|
||
|
|
"num_tokens": 4660178.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8800742626190186,
|
||
|
|
"epoch": 2.04815992730577,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00048276452952230036,
|
||
|
|
"loss": 5.4478,
|
||
|
|
"mean_token_accuracy": 0.17156661301851273,
|
||
|
|
"num_tokens": 4670417.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.827249670028687,
|
||
|
|
"epoch": 2.052703316674239,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00048262861155195407,
|
||
|
|
"loss": 5.3955,
|
||
|
|
"mean_token_accuracy": 0.18324804604053496,
|
||
|
|
"num_tokens": 4680221.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.834317541122436,
|
||
|
|
"epoch": 2.057246706042708,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004824921812786486,
|
||
|
|
"loss": 5.4471,
|
||
|
|
"mean_token_accuracy": 0.16734634935855866,
|
||
|
|
"num_tokens": 4691136.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.754065322875976,
|
||
|
|
"epoch": 2.0617900954111765,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000482355239039012,
|
||
|
|
"loss": 5.2977,
|
||
|
|
"mean_token_accuracy": 0.18202615827322005,
|
||
|
|
"num_tokens": 4700879.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.814774465560913,
|
||
|
|
"epoch": 2.0663334847796455,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004822177851709356,
|
||
|
|
"loss": 5.4785,
|
||
|
|
"mean_token_accuracy": 0.16296902894973755,
|
||
|
|
"num_tokens": 4711477.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.825762462615967,
|
||
|
|
"epoch": 2.0708768741481145,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00048207982001357327,
|
||
|
|
"loss": 5.4469,
|
||
|
|
"mean_token_accuracy": 0.17125846296548844,
|
||
|
|
"num_tokens": 4721973.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7884949207305905,
|
||
|
|
"epoch": 2.0754202635165835,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004819413439073402,
|
||
|
|
"loss": 5.4509,
|
||
|
|
"mean_token_accuracy": 0.1706570252776146,
|
||
|
|
"num_tokens": 4732425.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.817496299743652,
|
||
|
|
"epoch": 2.079963652885052,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004818023571939125,
|
||
|
|
"loss": 5.4223,
|
||
|
|
"mean_token_accuracy": 0.1764614388346672,
|
||
|
|
"num_tokens": 4743377.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.892448902130127,
|
||
|
|
"epoch": 2.084507042253521,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000481662860216226,
|
||
|
|
"loss": 5.4782,
|
||
|
|
"mean_token_accuracy": 0.17242299020290375,
|
||
|
|
"num_tokens": 4753534.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.813091564178467,
|
||
|
|
"epoch": 2.08905043162199,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00048152285331847574,
|
||
|
|
"loss": 5.425,
|
||
|
|
"mean_token_accuracy": 0.17044468671083451,
|
||
|
|
"num_tokens": 4763159.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.786837244033814,
|
||
|
|
"epoch": 2.093593820990459,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004813823368461148,
|
||
|
|
"loss": 5.3961,
|
||
|
|
"mean_token_accuracy": 0.17746685296297074,
|
||
|
|
"num_tokens": 4773497.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8038170337677,
|
||
|
|
"epoch": 2.098137210358928,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004812413111458534,
|
||
|
|
"loss": 5.4938,
|
||
|
|
"mean_token_accuracy": 0.17549572438001632,
|
||
|
|
"num_tokens": 4784291.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.802530765533447,
|
||
|
|
"epoch": 2.1026805997273965,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004810997765656587,
|
||
|
|
"loss": 5.443,
|
||
|
|
"mean_token_accuracy": 0.17139201760292053,
|
||
|
|
"num_tokens": 4794762.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9274169921875,
|
||
|
|
"epoch": 2.1072239890958655,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00048095773345475294,
|
||
|
|
"loss": 5.5627,
|
||
|
|
"mean_token_accuracy": 0.16689665615558624,
|
||
|
|
"num_tokens": 4804449.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.812848997116089,
|
||
|
|
"epoch": 2.1117673784643345,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00048081518216361367,
|
||
|
|
"loss": 5.424,
|
||
|
|
"mean_token_accuracy": 0.17251452952623367,
|
||
|
|
"num_tokens": 4814172.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.852766227722168,
|
||
|
|
"epoch": 2.1163107678328035,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004806721230439719,
|
||
|
|
"loss": 5.5253,
|
||
|
|
"mean_token_accuracy": 0.17016936093568802,
|
||
|
|
"num_tokens": 4824909.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9117193698883055,
|
||
|
|
"epoch": 2.120854157201272,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004805285564488117,
|
||
|
|
"loss": 5.5564,
|
||
|
|
"mean_token_accuracy": 0.17360106557607652,
|
||
|
|
"num_tokens": 4834546.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7922993183135985,
|
||
|
|
"epoch": 2.125397546569741,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004803844827323696,
|
||
|
|
"loss": 5.4604,
|
||
|
|
"mean_token_accuracy": 0.16917911916971207,
|
||
|
|
"num_tokens": 4844809.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.79258623123169,
|
||
|
|
"epoch": 2.12994093593821,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004802399022501329,
|
||
|
|
"loss": 5.435,
|
||
|
|
"mean_token_accuracy": 0.1720902919769287,
|
||
|
|
"num_tokens": 4855883.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.873880672454834,
|
||
|
|
"epoch": 2.134484325306679,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004800948153588397,
|
||
|
|
"loss": 5.4778,
|
||
|
|
"mean_token_accuracy": 0.17590655088424684,
|
||
|
|
"num_tokens": 4865936.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.714124965667724,
|
||
|
|
"epoch": 2.1390277146751475,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00047994922241647746,
|
||
|
|
"loss": 5.4071,
|
||
|
|
"mean_token_accuracy": 0.17288148552179336,
|
||
|
|
"num_tokens": 4876621.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.679599809646606,
|
||
|
|
"epoch": 2.1435711040436165,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00047980312378228244,
|
||
|
|
"loss": 5.37,
|
||
|
|
"mean_token_accuracy": 0.16944972723722457,
|
||
|
|
"num_tokens": 4886315.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.838567876815796,
|
||
|
|
"epoch": 2.1481144934120855,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00047965651981673823,
|
||
|
|
"loss": 5.4553,
|
||
|
|
"mean_token_accuracy": 0.1743234723806381,
|
||
|
|
"num_tokens": 4897214.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.813695907592773,
|
||
|
|
"epoch": 2.1526578827805545,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00047950941088157576,
|
||
|
|
"loss": 5.4593,
|
||
|
|
"mean_token_accuracy": 0.1741379454731941,
|
||
|
|
"num_tokens": 4907360.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7622902393341064,
|
||
|
|
"epoch": 2.157201272149023,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004793617973397715,
|
||
|
|
"loss": 5.42,
|
||
|
|
"mean_token_accuracy": 0.1762954756617546,
|
||
|
|
"num_tokens": 4917591.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8187230110168455,
|
||
|
|
"epoch": 2.161744661517492,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00047921367955554745,
|
||
|
|
"loss": 5.5005,
|
||
|
|
"mean_token_accuracy": 0.16116744875907899,
|
||
|
|
"num_tokens": 4928075.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8125792980194095,
|
||
|
|
"epoch": 2.166288050885961,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004790650578943693,
|
||
|
|
"loss": 5.3972,
|
||
|
|
"mean_token_accuracy": 0.17632868140935898,
|
||
|
|
"num_tokens": 4937898.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.751837873458863,
|
||
|
|
"epoch": 2.17083144025443,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00047891593272294636,
|
||
|
|
"loss": 5.4593,
|
||
|
|
"mean_token_accuracy": 0.16703200191259385,
|
||
|
|
"num_tokens": 4948152.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.857007837295532,
|
||
|
|
"epoch": 2.1753748296228985,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00047876630440923,
|
||
|
|
"loss": 5.4436,
|
||
|
|
"mean_token_accuracy": 0.17320962250232697,
|
||
|
|
"num_tokens": 4957973.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.687740468978882,
|
||
|
|
"epoch": 2.1799182189913675,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004786161733224134,
|
||
|
|
"loss": 5.4024,
|
||
|
|
"mean_token_accuracy": 0.17448024451732635,
|
||
|
|
"num_tokens": 4967375.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.797864818572998,
|
||
|
|
"epoch": 2.1844616083598365,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00047846553983293006,
|
||
|
|
"loss": 5.4203,
|
||
|
|
"mean_token_accuracy": 0.17751937955617905,
|
||
|
|
"num_tokens": 4977286.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.751899147033692,
|
||
|
|
"epoch": 2.1890049977283055,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00047831440431245307,
|
||
|
|
"loss": 5.4798,
|
||
|
|
"mean_token_accuracy": 0.16854800581932067,
|
||
|
|
"num_tokens": 4987930.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.89511399269104,
|
||
|
|
"epoch": 2.193548387096774,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00047816276713389424,
|
||
|
|
"loss": 5.5353,
|
||
|
|
"mean_token_accuracy": 0.16659025400876998,
|
||
|
|
"num_tokens": 4998707.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.739464187622071,
|
||
|
|
"epoch": 2.198091776465243,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004780106286714034,
|
||
|
|
"loss": 5.3842,
|
||
|
|
"mean_token_accuracy": 0.18243036270141602,
|
||
|
|
"num_tokens": 5008540.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.736773681640625,
|
||
|
|
"epoch": 2.202635165833712,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000477857989300367,
|
||
|
|
"loss": 5.4372,
|
||
|
|
"mean_token_accuracy": 0.17635186314582824,
|
||
|
|
"num_tokens": 5018199.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.849097681045532,
|
||
|
|
"epoch": 2.207178555202181,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00047770484939740757,
|
||
|
|
"loss": 5.4636,
|
||
|
|
"mean_token_accuracy": 0.1730012848973274,
|
||
|
|
"num_tokens": 5028251.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.723977041244507,
|
||
|
|
"epoch": 2.2117219445706495,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004775512093403824,
|
||
|
|
"loss": 5.4572,
|
||
|
|
"mean_token_accuracy": 0.16673808097839354,
|
||
|
|
"num_tokens": 5038290.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.776793336868286,
|
||
|
|
"epoch": 2.2162653339391185,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00047739706950838327,
|
||
|
|
"loss": 5.4156,
|
||
|
|
"mean_token_accuracy": 0.1714222863316536,
|
||
|
|
"num_tokens": 5048337.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.822423934936523,
|
||
|
|
"epoch": 2.2208087233075875,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00047724243028173484,
|
||
|
|
"loss": 5.4482,
|
||
|
|
"mean_token_accuracy": 0.16746363788843155,
|
||
|
|
"num_tokens": 5058533.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7664214134216305,
|
||
|
|
"epoch": 2.2253521126760565,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00047708729204199406,
|
||
|
|
"loss": 5.4585,
|
||
|
|
"mean_token_accuracy": 0.17420620322227479,
|
||
|
|
"num_tokens": 5068556.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.74825701713562,
|
||
|
|
"epoch": 2.229895502044525,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000476931655171949,
|
||
|
|
"loss": 5.5388,
|
||
|
|
"mean_token_accuracy": 0.1687641844153404,
|
||
|
|
"num_tokens": 5079317.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.872238731384277,
|
||
|
|
"epoch": 2.234438891412994,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004767755200556183,
|
||
|
|
"loss": 5.5164,
|
||
|
|
"mean_token_accuracy": 0.17064337730407714,
|
||
|
|
"num_tokens": 5089544.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.734923696517944,
|
||
|
|
"epoch": 2.238982280781463,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004766188870782497,
|
||
|
|
"loss": 5.503,
|
||
|
|
"mean_token_accuracy": 0.16758169382810592,
|
||
|
|
"num_tokens": 5099491.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.881393003463745,
|
||
|
|
"epoch": 2.243525670149932,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00047646175662631967,
|
||
|
|
"loss": 5.5015,
|
||
|
|
"mean_token_accuracy": 0.16988374143838883,
|
||
|
|
"num_tokens": 5109523.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.796596050262451,
|
||
|
|
"epoch": 2.2480690595184005,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00047630412908753183,
|
||
|
|
"loss": 5.4462,
|
||
|
|
"mean_token_accuracy": 0.17399886548519133,
|
||
|
|
"num_tokens": 5119940.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.754668188095093,
|
||
|
|
"epoch": 2.2526124488868695,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00047614600485081657,
|
||
|
|
"loss": 5.4222,
|
||
|
|
"mean_token_accuracy": 0.1754487484693527,
|
||
|
|
"num_tokens": 5129789.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7520379543304445,
|
||
|
|
"epoch": 2.2571558382553385,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00047598738430632963,
|
||
|
|
"loss": 5.4475,
|
||
|
|
"mean_token_accuracy": 0.167902871966362,
|
||
|
|
"num_tokens": 5139570.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.700397777557373,
|
||
|
|
"epoch": 2.2616992276238075,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00047582826784545146,
|
||
|
|
"loss": 5.4177,
|
||
|
|
"mean_token_accuracy": 0.1686418280005455,
|
||
|
|
"num_tokens": 5150526.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7402173519134525,
|
||
|
|
"epoch": 2.266242616992276,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00047566865586078615,
|
||
|
|
"loss": 5.3691,
|
||
|
|
"mean_token_accuracy": 0.1707841008901596,
|
||
|
|
"num_tokens": 5160895.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.727770662307739,
|
||
|
|
"epoch": 2.270786006360745,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00047550854874616047,
|
||
|
|
"loss": 5.3712,
|
||
|
|
"mean_token_accuracy": 0.17329805642366408,
|
||
|
|
"num_tokens": 5171054.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.270786006360745,
|
||
|
|
"eval_entropy": 5.57227717111277,
|
||
|
|
"eval_loss": 5.902021408081055,
|
||
|
|
"eval_mean_token_accuracy": 0.1561654274720092,
|
||
|
|
"eval_num_tokens": 5171054.0,
|
||
|
|
"eval_runtime": 2.0014,
|
||
|
|
"eval_samples_per_second": 1716.327,
|
||
|
|
"eval_steps_per_second": 214.853,
|
||
|
|
"step": 2500
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 11000,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 10,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 1113086866821120.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|