749 lines
16 KiB
JSON
749 lines
16 KiB
JSON
|
|
{
|
||
|
|
"train_losses": [
|
||
|
|
{
|
||
|
|
"step": 10,
|
||
|
|
"loss": 6.137748718261719
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 20,
|
||
|
|
"loss": 5.469404220581055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 30,
|
||
|
|
"loss": 5.144061279296875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 40,
|
||
|
|
"loss": 4.876457977294922
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 50,
|
||
|
|
"loss": 4.415411376953125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 60,
|
||
|
|
"loss": 3.700760269165039
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 70,
|
||
|
|
"loss": 3.0622364044189454
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 80,
|
||
|
|
"loss": 3.438877487182617
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 90,
|
||
|
|
"loss": 2.777506637573242
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 100,
|
||
|
|
"loss": 2.799178695678711
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 110,
|
||
|
|
"loss": 2.521131706237793
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 120,
|
||
|
|
"loss": 2.195684242248535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 130,
|
||
|
|
"loss": 2.079251289367676
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 140,
|
||
|
|
"loss": 2.136846733093262
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 150,
|
||
|
|
"loss": 2.282297706604004
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 160,
|
||
|
|
"loss": 2.790775108337402
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 170,
|
||
|
|
"loss": 1.9956499099731446
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 180,
|
||
|
|
"loss": 1.890342903137207
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 190,
|
||
|
|
"loss": 1.692027473449707
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 200,
|
||
|
|
"loss": 1.9817930221557618
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 210,
|
||
|
|
"loss": 1.7466983795166016
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 220,
|
||
|
|
"loss": 2.121308135986328
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 230,
|
||
|
|
"loss": 1.948258399963379
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 240,
|
||
|
|
"loss": 1.3363015174865722
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 250,
|
||
|
|
"loss": 1.5559185028076172
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 260,
|
||
|
|
"loss": 1.568422794342041
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 270,
|
||
|
|
"loss": 1.237374210357666
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 280,
|
||
|
|
"loss": 1.8047700881958009
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 290,
|
||
|
|
"loss": 1.533273410797119
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 300,
|
||
|
|
"loss": 1.2513471603393556
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 310,
|
||
|
|
"loss": 1.269908618927002
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 320,
|
||
|
|
"loss": 1.5620304107666017
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 330,
|
||
|
|
"loss": 1.448842716217041
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 340,
|
||
|
|
"loss": 1.5316163063049317
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 350,
|
||
|
|
"loss": 1.1749078750610351
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 360,
|
||
|
|
"loss": 1.7663183212280273
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 370,
|
||
|
|
"loss": 1.4664443969726562
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 380,
|
||
|
|
"loss": 1.3086597442626953
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 390,
|
||
|
|
"loss": 1.3566680908203126
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 400,
|
||
|
|
"loss": 1.6223735809326172
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 410,
|
||
|
|
"loss": 1.3682662010192872
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 420,
|
||
|
|
"loss": 1.4399548530578614
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 430,
|
||
|
|
"loss": 1.344713306427002
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 440,
|
||
|
|
"loss": 1.2974468231201173
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 450,
|
||
|
|
"loss": 1.3712547302246094
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 460,
|
||
|
|
"loss": 1.325570011138916
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 470,
|
||
|
|
"loss": 1.1255184173583985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 480,
|
||
|
|
"loss": 1.4051344871520997
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 490,
|
||
|
|
"loss": 1.2838367462158202
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 500,
|
||
|
|
"loss": 1.6373512268066406
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 510,
|
||
|
|
"loss": 1.2228617668151855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 520,
|
||
|
|
"loss": 1.3670686721801757
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 530,
|
||
|
|
"loss": 1.3356054306030274
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 540,
|
||
|
|
"loss": 0.6968086242675782
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 550,
|
||
|
|
"loss": 1.4029299736022949
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 560,
|
||
|
|
"loss": 1.0916556358337401
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 570,
|
||
|
|
"loss": 1.1958709716796876
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 580,
|
||
|
|
"loss": 1.1345650672912597
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 590,
|
||
|
|
"loss": 1.4366456031799317
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 600,
|
||
|
|
"loss": 1.3605615615844726
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 610,
|
||
|
|
"loss": 1.2108879089355469
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 620,
|
||
|
|
"loss": 1.1100153923034668
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"step": 630,
|
||
|
|
"loss": 0.9917799949645996
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"eval_losses": [
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_loss": 1.2418931722640991,
|
||
|
|
"eval_runtime": 1.2417
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.0,
|
||
|
|
"eval_loss": 0.9693114161491394,
|
||
|
|
"eval_runtime": 1.1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 3.0,
|
||
|
|
"eval_loss": 0.899703323841095,
|
||
|
|
"eval_runtime": 1.1268
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"full_logs": [
|
||
|
|
{
|
||
|
|
"loss": 6.137748718261719,
|
||
|
|
"grad_norm": 23.5301456451416,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"epoch": 0.04739336492890995,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 5.469404220581055,
|
||
|
|
"grad_norm": 18.555707931518555,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"epoch": 0.0947867298578199,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 5.144061279296875,
|
||
|
|
"grad_norm": 15.515172004699707,
|
||
|
|
"learning_rate": 1.45e-05,
|
||
|
|
"epoch": 0.14218009478672985,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 4.876457977294922,
|
||
|
|
"grad_norm": 18.302534103393555,
|
||
|
|
"learning_rate": 1.9500000000000003e-05,
|
||
|
|
"epoch": 0.1895734597156398,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 4.415411376953125,
|
||
|
|
"grad_norm": 16.696500778198242,
|
||
|
|
"learning_rate": 2.45e-05,
|
||
|
|
"epoch": 0.23696682464454977,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 3.700760269165039,
|
||
|
|
"grad_norm": 16.752397537231445,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"epoch": 0.2843601895734597,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 3.0622364044189454,
|
||
|
|
"grad_norm": 15.191258430480957,
|
||
|
|
"learning_rate": 3.45e-05,
|
||
|
|
"epoch": 0.33175355450236965,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 3.438877487182617,
|
||
|
|
"grad_norm": 16.608257293701172,
|
||
|
|
"learning_rate": 3.9500000000000005e-05,
|
||
|
|
"epoch": 0.3791469194312796,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 2.777506637573242,
|
||
|
|
"grad_norm": 15.705228805541992,
|
||
|
|
"learning_rate": 4.4500000000000004e-05,
|
||
|
|
"epoch": 0.4265402843601896,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 2.799178695678711,
|
||
|
|
"grad_norm": 13.66840648651123,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"epoch": 0.47393364928909953,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 2.521131706237793,
|
||
|
|
"grad_norm": 14.546332359313965,
|
||
|
|
"learning_rate": 4.9155722326454034e-05,
|
||
|
|
"epoch": 0.5213270142180095,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 2.195684242248535,
|
||
|
|
"grad_norm": 19.163509368896484,
|
||
|
|
"learning_rate": 4.821763602251407e-05,
|
||
|
|
"epoch": 0.5687203791469194,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 2.079251289367676,
|
||
|
|
"grad_norm": 21.224340438842773,
|
||
|
|
"learning_rate": 4.727954971857411e-05,
|
||
|
|
"epoch": 0.6161137440758294,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 2.136846733093262,
|
||
|
|
"grad_norm": 15.907443046569824,
|
||
|
|
"learning_rate": 4.634146341463415e-05,
|
||
|
|
"epoch": 0.6635071090047393,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 2.282297706604004,
|
||
|
|
"grad_norm": 17.09271240234375,
|
||
|
|
"learning_rate": 4.5403377110694186e-05,
|
||
|
|
"epoch": 0.7109004739336493,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 2.790775108337402,
|
||
|
|
"grad_norm": 13.511648178100586,
|
||
|
|
"learning_rate": 4.446529080675422e-05,
|
||
|
|
"epoch": 0.7582938388625592,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.9956499099731446,
|
||
|
|
"grad_norm": 16.616485595703125,
|
||
|
|
"learning_rate": 4.3527204502814265e-05,
|
||
|
|
"epoch": 0.8056872037914692,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.890342903137207,
|
||
|
|
"grad_norm": 16.081674575805664,
|
||
|
|
"learning_rate": 4.25891181988743e-05,
|
||
|
|
"epoch": 0.8530805687203792,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.692027473449707,
|
||
|
|
"grad_norm": 13.304547309875488,
|
||
|
|
"learning_rate": 4.165103189493433e-05,
|
||
|
|
"epoch": 0.9004739336492891,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.9817930221557618,
|
||
|
|
"grad_norm": 18.04024887084961,
|
||
|
|
"learning_rate": 4.071294559099437e-05,
|
||
|
|
"epoch": 0.9478672985781991,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.7466983795166016,
|
||
|
|
"grad_norm": 15.37869644165039,
|
||
|
|
"learning_rate": 3.977485928705441e-05,
|
||
|
|
"epoch": 0.995260663507109,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"eval_loss": 1.2418931722640991,
|
||
|
|
"eval_runtime": 1.2417,
|
||
|
|
"eval_samples_per_second": 75.705,
|
||
|
|
"eval_steps_per_second": 37.853,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"step": 211
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 2.121308135986328,
|
||
|
|
"grad_norm": 13.085193634033203,
|
||
|
|
"learning_rate": 3.883677298311445e-05,
|
||
|
|
"epoch": 1.042654028436019,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.948258399963379,
|
||
|
|
"grad_norm": 12.731958389282227,
|
||
|
|
"learning_rate": 3.789868667917448e-05,
|
||
|
|
"epoch": 1.0900473933649288,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.3363015174865722,
|
||
|
|
"grad_norm": 16.21705436706543,
|
||
|
|
"learning_rate": 3.6960600375234525e-05,
|
||
|
|
"epoch": 1.1374407582938388,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.5559185028076172,
|
||
|
|
"grad_norm": 14.514242172241211,
|
||
|
|
"learning_rate": 3.602251407129456e-05,
|
||
|
|
"epoch": 1.1848341232227488,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.568422794342041,
|
||
|
|
"grad_norm": 12.71330738067627,
|
||
|
|
"learning_rate": 3.50844277673546e-05,
|
||
|
|
"epoch": 1.2322274881516588,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.237374210357666,
|
||
|
|
"grad_norm": 14.786351203918457,
|
||
|
|
"learning_rate": 3.414634146341464e-05,
|
||
|
|
"epoch": 1.2796208530805688,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.8047700881958009,
|
||
|
|
"grad_norm": 16.485517501831055,
|
||
|
|
"learning_rate": 3.320825515947467e-05,
|
||
|
|
"epoch": 1.3270142180094786,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.533273410797119,
|
||
|
|
"grad_norm": 14.662726402282715,
|
||
|
|
"learning_rate": 3.227016885553471e-05,
|
||
|
|
"epoch": 1.3744075829383886,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.2513471603393556,
|
||
|
|
"grad_norm": 14.021987915039062,
|
||
|
|
"learning_rate": 3.133208255159475e-05,
|
||
|
|
"epoch": 1.4218009478672986,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.269908618927002,
|
||
|
|
"grad_norm": 15.776110649108887,
|
||
|
|
"learning_rate": 3.0393996247654788e-05,
|
||
|
|
"epoch": 1.4691943127962086,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.5620304107666017,
|
||
|
|
"grad_norm": 14.94189453125,
|
||
|
|
"learning_rate": 2.945590994371482e-05,
|
||
|
|
"epoch": 1.5165876777251186,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.448842716217041,
|
||
|
|
"grad_norm": 17.744874954223633,
|
||
|
|
"learning_rate": 2.851782363977486e-05,
|
||
|
|
"epoch": 1.5639810426540284,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.5316163063049317,
|
||
|
|
"grad_norm": 16.207765579223633,
|
||
|
|
"learning_rate": 2.75797373358349e-05,
|
||
|
|
"epoch": 1.6113744075829384,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.1749078750610351,
|
||
|
|
"grad_norm": 12.924609184265137,
|
||
|
|
"learning_rate": 2.6641651031894936e-05,
|
||
|
|
"epoch": 1.6587677725118484,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.7663183212280273,
|
||
|
|
"grad_norm": 11.12903881072998,
|
||
|
|
"learning_rate": 2.5703564727954972e-05,
|
||
|
|
"epoch": 1.7061611374407581,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.4664443969726562,
|
||
|
|
"grad_norm": 16.2852783203125,
|
||
|
|
"learning_rate": 2.476547842401501e-05,
|
||
|
|
"epoch": 1.7535545023696684,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.3086597442626953,
|
||
|
|
"grad_norm": 15.057639122009277,
|
||
|
|
"learning_rate": 2.3827392120075048e-05,
|
||
|
|
"epoch": 1.8009478672985781,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.3566680908203126,
|
||
|
|
"grad_norm": 14.29211139678955,
|
||
|
|
"learning_rate": 2.2889305816135084e-05,
|
||
|
|
"epoch": 1.8483412322274881,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.6223735809326172,
|
||
|
|
"grad_norm": 11.776235580444336,
|
||
|
|
"learning_rate": 2.1951219512195124e-05,
|
||
|
|
"epoch": 1.8957345971563981,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.3682662010192872,
|
||
|
|
"grad_norm": 13.214008331298828,
|
||
|
|
"learning_rate": 2.1013133208255163e-05,
|
||
|
|
"epoch": 1.943127962085308,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.4399548530578614,
|
||
|
|
"grad_norm": 15.142778396606445,
|
||
|
|
"learning_rate": 2.0075046904315196e-05,
|
||
|
|
"epoch": 1.9905213270142181,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"eval_loss": 0.9693114161491394,
|
||
|
|
"eval_runtime": 1.1335,
|
||
|
|
"eval_samples_per_second": 82.931,
|
||
|
|
"eval_steps_per_second": 41.466,
|
||
|
|
"epoch": 2.0,
|
||
|
|
"step": 422
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.344713306427002,
|
||
|
|
"grad_norm": 14.642666816711426,
|
||
|
|
"learning_rate": 1.9136960600375236e-05,
|
||
|
|
"epoch": 2.037914691943128,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.2974468231201173,
|
||
|
|
"grad_norm": 13.815317153930664,
|
||
|
|
"learning_rate": 1.8198874296435272e-05,
|
||
|
|
"epoch": 2.085308056872038,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.3712547302246094,
|
||
|
|
"grad_norm": 14.043903350830078,
|
||
|
|
"learning_rate": 1.726078799249531e-05,
|
||
|
|
"epoch": 2.132701421800948,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.325570011138916,
|
||
|
|
"grad_norm": 13.121524810791016,
|
||
|
|
"learning_rate": 1.6322701688555348e-05,
|
||
|
|
"epoch": 2.1800947867298577,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.1255184173583985,
|
||
|
|
"grad_norm": 18.340551376342773,
|
||
|
|
"learning_rate": 1.5384615384615387e-05,
|
||
|
|
"epoch": 2.227488151658768,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.4051344871520997,
|
||
|
|
"grad_norm": 15.610395431518555,
|
||
|
|
"learning_rate": 1.4446529080675422e-05,
|
||
|
|
"epoch": 2.2748815165876777,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.2838367462158202,
|
||
|
|
"grad_norm": 12.021589279174805,
|
||
|
|
"learning_rate": 1.3508442776735461e-05,
|
||
|
|
"epoch": 2.322274881516588,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.6373512268066406,
|
||
|
|
"grad_norm": 11.820240020751953,
|
||
|
|
"learning_rate": 1.2570356472795497e-05,
|
||
|
|
"epoch": 2.3696682464454977,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.2228617668151855,
|
||
|
|
"grad_norm": 14.760135650634766,
|
||
|
|
"learning_rate": 1.1632270168855535e-05,
|
||
|
|
"epoch": 2.4170616113744074,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.3670686721801757,
|
||
|
|
"grad_norm": 12.443073272705078,
|
||
|
|
"learning_rate": 1.0694183864915573e-05,
|
||
|
|
"epoch": 2.4644549763033177,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.3356054306030274,
|
||
|
|
"grad_norm": 15.922508239746094,
|
||
|
|
"learning_rate": 9.756097560975611e-06,
|
||
|
|
"epoch": 2.5118483412322274,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 0.6968086242675782,
|
||
|
|
"grad_norm": 12.17047119140625,
|
||
|
|
"learning_rate": 8.818011257035647e-06,
|
||
|
|
"epoch": 2.5592417061611377,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.4029299736022949,
|
||
|
|
"grad_norm": 12.573970794677734,
|
||
|
|
"learning_rate": 7.879924953095685e-06,
|
||
|
|
"epoch": 2.6066350710900474,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.0916556358337401,
|
||
|
|
"grad_norm": 13.132047653198242,
|
||
|
|
"learning_rate": 6.941838649155723e-06,
|
||
|
|
"epoch": 2.654028436018957,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.1958709716796876,
|
||
|
|
"grad_norm": 12.399245262145996,
|
||
|
|
"learning_rate": 6.00375234521576e-06,
|
||
|
|
"epoch": 2.7014218009478674,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.1345650672912597,
|
||
|
|
"grad_norm": 12.746565818786621,
|
||
|
|
"learning_rate": 5.065666041275798e-06,
|
||
|
|
"epoch": 2.748815165876777,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.4366456031799317,
|
||
|
|
"grad_norm": 13.03442668914795,
|
||
|
|
"learning_rate": 4.127579737335835e-06,
|
||
|
|
"epoch": 2.7962085308056874,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.3605615615844726,
|
||
|
|
"grad_norm": 13.585875511169434,
|
||
|
|
"learning_rate": 3.189493433395872e-06,
|
||
|
|
"epoch": 2.843601895734597,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.2108879089355469,
|
||
|
|
"grad_norm": 13.078906059265137,
|
||
|
|
"learning_rate": 2.25140712945591e-06,
|
||
|
|
"epoch": 2.890995260663507,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 1.1100153923034668,
|
||
|
|
"grad_norm": 12.80677318572998,
|
||
|
|
"learning_rate": 1.3133208255159477e-06,
|
||
|
|
"epoch": 2.938388625592417,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"loss": 0.9917799949645996,
|
||
|
|
"grad_norm": 10.720328330993652,
|
||
|
|
"learning_rate": 3.75234521575985e-07,
|
||
|
|
"epoch": 2.985781990521327,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"eval_loss": 0.899703323841095,
|
||
|
|
"eval_runtime": 1.1268,
|
||
|
|
"eval_samples_per_second": 83.423,
|
||
|
|
"eval_steps_per_second": 41.711,
|
||
|
|
"epoch": 3.0,
|
||
|
|
"step": 633
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"train_runtime": 268.2648,
|
||
|
|
"train_samples_per_second": 9.427,
|
||
|
|
"train_steps_per_second": 2.36,
|
||
|
|
"total_flos": 330403774464000.0,
|
||
|
|
"train_loss": 1.9539168042970871,
|
||
|
|
"epoch": 3.0,
|
||
|
|
"step": 633
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|