penfever commited on
Commit
82763c1
·
verified ·
1 Parent(s): 123792f

Training in progress, step 3200

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b45f096f5903e6bbd55e8d9a412ee1407c5104c3be80aa71513c5916f91f605d
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad26d8df3739f82fdb1372aef22a2b12267b546356b27176c841d96682dd300d
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b1aa2798bf9280a80ae1008699ee022e68f9501796ef2d04ba394445a6422c1
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4645b04ceb38a20dd912f77beed57ec03e2de5a72c3fb5de962f02446686c2b
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:530b5a664ef0ba0c6a653879cc943b37de3a83026766a8e0c4487956623e4a03
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231aa76326313e39c3cb1a51e63fe72fb29065fd78bababc873bc06598276d93
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4be3c58e13214068a94dbe4ccf4ef5dcacd2af9681ac666d4b81e3fc488a5e6
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05625740286433e5262989b75909a29e5ced4682a051a660e021b15858dc7933
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -1248,3 +1248,72 @@
1248
  {"current_steps": 3035, "total_steps": 3747, "loss": 0.3853, "lr": 4.2527951656511425e-06, "epoch": 0.8099948291104402, "percentage": 81.0, "elapsed_time": "23:08:45", "remaining_time": "5:25:47"}
1249
  {"current_steps": 3210, "total_steps": 7494, "loss": 0.3876, "lr": 2.8252018977914644e-05, "epoch": 0.42834981901886543, "percentage": 42.83, "elapsed_time": "23:12:35", "remaining_time": "1 day, 6:58:31"}
1250
  {"current_steps": 3040, "total_steps": 3747, "loss": 0.387, "lr": 4.1955293855613364e-06, "epoch": 0.8113292522226485, "percentage": 81.13, "elapsed_time": "23:10:59", "remaining_time": "5:23:29"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1248
  {"current_steps": 3035, "total_steps": 3747, "loss": 0.3853, "lr": 4.2527951656511425e-06, "epoch": 0.8099948291104402, "percentage": 81.0, "elapsed_time": "23:08:45", "remaining_time": "5:25:47"}
1249
  {"current_steps": 3210, "total_steps": 7494, "loss": 0.3876, "lr": 2.8252018977914644e-05, "epoch": 0.42834981901886543, "percentage": 42.83, "elapsed_time": "23:12:35", "remaining_time": "1 day, 6:58:31"}
1250
  {"current_steps": 3040, "total_steps": 3747, "loss": 0.387, "lr": 4.1955293855613364e-06, "epoch": 0.8113292522226485, "percentage": 81.13, "elapsed_time": "23:10:59", "remaining_time": "5:23:29"}
1251
+ {"current_steps": 3215, "total_steps": 7494, "loss": 0.3869, "lr": 2.8209563149685047e-05, "epoch": 0.42901703057496954, "percentage": 42.9, "elapsed_time": "23:14:42", "remaining_time": "1 day, 6:56:17"}
1252
+ {"current_steps": 3045, "total_steps": 3747, "loss": 0.3849, "lr": 4.138606565723926e-06, "epoch": 0.8126636753348568, "percentage": 81.27, "elapsed_time": "23:13:12", "remaining_time": "5:21:11"}
1253
+ {"current_steps": 3220, "total_steps": 7494, "loss": 0.3868, "lr": 2.81670627840942e-05, "epoch": 0.4296842421310737, "percentage": 42.97, "elapsed_time": "23:16:51", "remaining_time": "1 day, 6:54:05"}
1254
+ {"current_steps": 3050, "total_steps": 3747, "loss": 0.3841, "lr": 4.082027941375772e-06, "epoch": 0.813998098447065, "percentage": 81.4, "elapsed_time": "23:15:27", "remaining_time": "5:18:53"}
1255
+ {"current_steps": 3225, "total_steps": 7494, "loss": 0.3884, "lr": 2.8124518111709078e-05, "epoch": 0.43035145368717787, "percentage": 43.03, "elapsed_time": "23:19:00", "remaining_time": "1 day, 6:51:53"}
1256
+ {"current_steps": 3055, "total_steps": 3747, "loss": 0.3874, "lr": 4.025794740284616e-06, "epoch": 0.8153325215592734, "percentage": 81.53, "elapsed_time": "23:17:42", "remaining_time": "5:16:36"}
1257
+ {"current_steps": 3230, "total_steps": 7494, "loss": 0.3876, "lr": 2.8081929363337025e-05, "epoch": 0.43101866524328203, "percentage": 43.1, "elapsed_time": "23:21:07", "remaining_time": "1 day, 6:49:39"}
1258
+ {"current_steps": 3060, "total_steps": 3747, "loss": 0.386, "lr": 3.969908182722464e-06, "epoch": 0.8166669446714817, "percentage": 81.67, "elapsed_time": "23:19:57", "remaining_time": "5:14:18"}
1259
+ {"current_steps": 3235, "total_steps": 7494, "loss": 0.3867, "lr": 2.8039296770024486e-05, "epoch": 0.4316858767993862, "percentage": 43.17, "elapsed_time": "23:23:14", "remaining_time": "1 day, 6:47:25"}
1260
+ {"current_steps": 3065, "total_steps": 3747, "loss": 0.3877, "lr": 3.914369481439062e-06, "epoch": 0.81800136778369, "percentage": 81.8, "elapsed_time": "23:22:12", "remaining_time": "5:12:00"}
1261
+ {"current_steps": 3240, "total_steps": 7494, "loss": 0.3893, "lr": 2.7996620563055787e-05, "epoch": 0.4323530883554903, "percentage": 43.23, "elapsed_time": "23:25:21", "remaining_time": "1 day, 6:45:11"}
1262
+ {"current_steps": 3070, "total_steps": 3747, "loss": 0.3852, "lr": 3.859179841635612e-06, "epoch": 0.8193357908958984, "percentage": 81.93, "elapsed_time": "23:24:26", "remaining_time": "5:09:42"}
1263
+ {"current_steps": 3245, "total_steps": 7494, "loss": 0.3887, "lr": 2.795390097395185e-05, "epoch": 0.43302029991159446, "percentage": 43.3, "elapsed_time": "23:27:30", "remaining_time": "1 day, 6:42:59"}
1264
+ {"current_steps": 3250, "total_steps": 7494, "loss": 0.3883, "lr": 2.7911138234468954e-05, "epoch": 0.4336875114676986, "percentage": 43.37, "elapsed_time": "23:29:37", "remaining_time": "1 day, 6:40:45"}
1265
+ {"current_steps": 3075, "total_steps": 3747, "loss": 0.3873, "lr": 3.8043404609386205e-06, "epoch": 0.8206702140081066, "percentage": 82.07, "elapsed_time": "23:26:41", "remaining_time": "5:07:24"}
1266
+ {"current_steps": 3255, "total_steps": 7494, "loss": 0.384, "lr": 2.7868332576597458e-05, "epoch": 0.4343547230238028, "percentage": 43.43, "elapsed_time": "23:31:44", "remaining_time": "1 day, 6:38:30"}
1267
+ {"current_steps": 3080, "total_steps": 3747, "loss": 0.3855, "lr": 3.7498525293738875e-06, "epoch": 0.8220046371203149, "percentage": 82.2, "elapsed_time": "23:28:57", "remaining_time": "5:05:07"}
1268
+ {"current_steps": 3260, "total_steps": 7494, "loss": 0.3888, "lr": 2.7825484232560573e-05, "epoch": 0.4350219345799069, "percentage": 43.5, "elapsed_time": "23:33:52", "remaining_time": "1 day, 6:36:18"}
1269
+ {"current_steps": 3085, "total_steps": 3747, "loss": 0.3852, "lr": 3.695717229340694e-06, "epoch": 0.8233390602325232, "percentage": 82.33, "elapsed_time": "23:31:11", "remaining_time": "5:02:49"}
1270
+ {"current_steps": 3265, "total_steps": 7494, "loss": 0.389, "lr": 2.7782593434813076e-05, "epoch": 0.43568914613601106, "percentage": 43.57, "elapsed_time": "23:36:01", "remaining_time": "1 day, 6:34:06"}
1271
+ {"current_steps": 3090, "total_steps": 3747, "loss": 0.3875, "lr": 3.6419357355861573e-06, "epoch": 0.8246734833447316, "percentage": 82.47, "elapsed_time": "23:33:25", "remaining_time": "5:00:31"}
1272
+ {"current_steps": 3270, "total_steps": 7494, "loss": 0.3869, "lr": 2.7739660416040055e-05, "epoch": 0.4363563576921152, "percentage": 43.63, "elapsed_time": "23:38:09", "remaining_time": "1 day, 6:31:53"}
1273
+ {"current_steps": 3095, "total_steps": 3747, "loss": 0.3861, "lr": 3.5885092151797142e-06, "epoch": 0.8260079064569399, "percentage": 82.6, "elapsed_time": "23:35:42", "remaining_time": "4:58:14"}
1274
+ {"current_steps": 3275, "total_steps": 7494, "loss": 0.3881, "lr": 2.7696685409155648e-05, "epoch": 0.4370235692482194, "percentage": 43.7, "elapsed_time": "23:40:16", "remaining_time": "1 day, 6:29:39"}
1275
+ {"current_steps": 3100, "total_steps": 3747, "loss": 0.3849, "lr": 3.535438827487807e-06, "epoch": 0.8273423295691481, "percentage": 82.73, "elapsed_time": "23:37:57", "remaining_time": "4:55:56"}
1276
+ {"current_steps": 3280, "total_steps": 7494, "loss": 0.3832, "lr": 2.7653668647301797e-05, "epoch": 0.43769078080432355, "percentage": 43.77, "elapsed_time": "23:42:23", "remaining_time": "1 day, 6:27:25"}
1277
+ {"current_steps": 3105, "total_steps": 3747, "loss": 0.3863, "lr": 3.482725724148728e-06, "epoch": 0.8286767526813564, "percentage": 82.87, "elapsed_time": "23:40:11", "remaining_time": "4:53:38"}
1278
+ {"current_steps": 3285, "total_steps": 7494, "loss": 0.3888, "lr": 2.7610610363846953e-05, "epoch": 0.43835799236042766, "percentage": 43.84, "elapsed_time": "23:44:32", "remaining_time": "1 day, 6:25:13"}
1279
+ {"current_steps": 3110, "total_steps": 3747, "loss": 0.382, "lr": 3.430371049047634e-06, "epoch": 0.8300111757935648, "percentage": 83.0, "elapsed_time": "23:42:26", "remaining_time": "4:51:20"}
1280
+ {"current_steps": 3290, "total_steps": 7494, "loss": 0.3856, "lr": 2.7567510792384825e-05, "epoch": 0.4390252039165318, "percentage": 43.9, "elapsed_time": "23:46:41", "remaining_time": "1 day, 6:23:02"}
1281
+ {"current_steps": 3115, "total_steps": 3747, "loss": 0.3861, "lr": 3.378375938291698e-06, "epoch": 0.8313455989057731, "percentage": 83.13, "elapsed_time": "23:44:41", "remaining_time": "4:49:03"}
1282
+ {"current_steps": 3295, "total_steps": 7494, "loss": 0.3892, "lr": 2.7524370166733114e-05, "epoch": 0.439692415472636, "percentage": 43.97, "elapsed_time": "23:48:48", "remaining_time": "1 day, 6:20:48"}
1283
+ {"current_steps": 3120, "total_steps": 3747, "loss": 0.3864, "lr": 3.3267415201854923e-06, "epoch": 0.8326800220179813, "percentage": 83.27, "elapsed_time": "23:46:55", "remaining_time": "4:46:45"}
1284
+ {"current_steps": 3300, "total_steps": 7494, "loss": 0.3883, "lr": 2.7481188720932253e-05, "epoch": 0.44035962702874015, "percentage": 44.04, "elapsed_time": "23:50:56", "remaining_time": "1 day, 6:18:35"}
1285
+ {"current_steps": 3125, "total_steps": 3747, "loss": 0.3866, "lr": 3.275468915206468e-06, "epoch": 0.8340144451301896, "percentage": 83.4, "elapsed_time": "23:49:10", "remaining_time": "4:44:27"}
1286
+ {"current_steps": 3305, "total_steps": 7494, "loss": 0.3884, "lr": 2.74379666892441e-05, "epoch": 0.4410268385848443, "percentage": 44.1, "elapsed_time": "23:53:03", "remaining_time": "1 day, 6:16:21"}
1287
+ {"current_steps": 3130, "total_steps": 3747, "loss": 0.3837, "lr": 3.224559235980671e-06, "epoch": 0.835348868242398, "percentage": 83.53, "elapsed_time": "23:51:26", "remaining_time": "4:42:10"}
1288
+ {"current_steps": 3310, "total_steps": 7494, "loss": 0.3854, "lr": 2.7394704306150716e-05, "epoch": 0.4416940501409484, "percentage": 44.17, "elapsed_time": "23:55:10", "remaining_time": "1 day, 6:14:08"}
1289
+ {"current_steps": 3135, "total_steps": 3747, "loss": 0.3908, "lr": 3.1740135872585753e-06, "epoch": 0.8366832913546063, "percentage": 83.67, "elapsed_time": "23:53:43", "remaining_time": "4:39:53"}
1290
+ {"current_steps": 3315, "total_steps": 7494, "loss": 0.3846, "lr": 2.7351401806353068e-05, "epoch": 0.4423612616970526, "percentage": 44.24, "elapsed_time": "23:57:19", "remaining_time": "1 day, 6:11:56"}
1291
+ {"current_steps": 3140, "total_steps": 3747, "loss": 0.3838, "lr": 3.1238330658911155e-06, "epoch": 0.8380177144668146, "percentage": 83.8, "elapsed_time": "23:55:57", "remaining_time": "4:37:35"}
1292
+ {"current_steps": 3320, "total_steps": 7494, "loss": 0.3891, "lr": 2.7308059424769755e-05, "epoch": 0.44302847325315675, "percentage": 44.3, "elapsed_time": "23:59:27", "remaining_time": "1 day, 6:09:44"}
1293
+ {"current_steps": 3145, "total_steps": 3747, "loss": 0.3858, "lr": 3.074018760805899e-06, "epoch": 0.8393521375790228, "percentage": 83.93, "elapsed_time": "23:58:12", "remaining_time": "4:35:17"}
1294
+ {"current_steps": 3325, "total_steps": 7494, "loss": 0.383, "lr": 2.7264677396535737e-05, "epoch": 0.4436956848092609, "percentage": 44.37, "elapsed_time": "1 day, 0:01:34", "remaining_time": "1 day, 6:07:30"}
1295
+ {"current_steps": 3150, "total_steps": 3747, "loss": 0.3886, "lr": 3.0245717529835584e-06, "epoch": 0.8406865606912312, "percentage": 84.07, "elapsed_time": "1 day, 0:00:30", "remaining_time": "4:33:00"}
1296
+ {"current_steps": 3330, "total_steps": 7494, "loss": 0.392, "lr": 2.7221255957001056e-05, "epoch": 0.444362896365365, "percentage": 44.44, "elapsed_time": "1 day, 0:03:44", "remaining_time": "1 day, 6:05:19"}
1297
+ {"current_steps": 3155, "total_steps": 3747, "loss": 0.3868, "lr": 2.9754931154342914e-06, "epoch": 0.8420209838034395, "percentage": 84.2, "elapsed_time": "1 day, 0:02:43", "remaining_time": "4:30:42"}
1298
+ {"current_steps": 3335, "total_steps": 7494, "loss": 0.3876, "lr": 2.7177795341729573e-05, "epoch": 0.4450301079214692, "percentage": 44.5, "elapsed_time": "1 day, 0:05:51", "remaining_time": "1 day, 6:03:05"}
1299
+ {"current_steps": 3340, "total_steps": 7494, "loss": 0.3852, "lr": 2.7134295786497666e-05, "epoch": 0.44569731947757335, "percentage": 44.57, "elapsed_time": "1 day, 0:07:58", "remaining_time": "1 day, 6:00:51"}
1300
+ {"current_steps": 3160, "total_steps": 3747, "loss": 0.3874, "lr": 2.9267839131746066e-06, "epoch": 0.8433554069156478, "percentage": 84.33, "elapsed_time": "1 day, 0:05:00", "remaining_time": "4:28:25"}
1301
+ {"current_steps": 3345, "total_steps": 7494, "loss": 0.3873, "lr": 2.7090757527292976e-05, "epoch": 0.4463645310336775, "percentage": 44.64, "elapsed_time": "1 day, 0:10:05", "remaining_time": "1 day, 5:58:37"}
1302
+ {"current_steps": 3165, "total_steps": 3747, "loss": 0.3886, "lr": 2.8784452032041743e-06, "epoch": 0.8446898300278561, "percentage": 84.47, "elapsed_time": "1 day, 0:07:15", "remaining_time": "4:26:07"}
1303
+ {"current_steps": 3350, "total_steps": 7494, "loss": 0.3894, "lr": 2.7047180800313113e-05, "epoch": 0.4470317425897817, "percentage": 44.7, "elapsed_time": "1 day, 0:12:12", "remaining_time": "1 day, 5:56:24"}
1304
+ {"current_steps": 3170, "total_steps": 3747, "loss": 0.3853, "lr": 2.830478034482904e-06, "epoch": 0.8460242531400644, "percentage": 84.6, "elapsed_time": "1 day, 0:09:29", "remaining_time": "4:23:50"}
1305
+ {"current_steps": 3355, "total_steps": 7494, "loss": 0.3895, "lr": 2.700356584196437e-05, "epoch": 0.4476989541458858, "percentage": 44.77, "elapsed_time": "1 day, 0:14:21", "remaining_time": "1 day, 5:54:12"}
1306
+ {"current_steps": 3175, "total_steps": 3747, "loss": 0.3896, "lr": 2.782883447908202e-06, "epoch": 0.8473586762522727, "percentage": 84.73, "elapsed_time": "1 day, 0:11:45", "remaining_time": "4:21:32"}
1307
+ {"current_steps": 3360, "total_steps": 7494, "loss": 0.3861, "lr": 2.6959912888860453e-05, "epoch": 0.44836616570198995, "percentage": 44.84, "elapsed_time": "1 day, 0:16:27", "remaining_time": "1 day, 5:51:58"}
1308
+ {"current_steps": 3180, "total_steps": 3747, "loss": 0.3845, "lr": 2.735662476292351e-06, "epoch": 0.848693099364481, "percentage": 84.87, "elapsed_time": "1 day, 0:14:02", "remaining_time": "4:19:15"}
1309
+ {"current_steps": 3365, "total_steps": 7494, "loss": 0.3838, "lr": 2.6916222177821193e-05, "epoch": 0.4490333772580941, "percentage": 44.9, "elapsed_time": "1 day, 0:18:35", "remaining_time": "1 day, 5:49:45"}
1310
+ {"current_steps": 3185, "total_steps": 3747, "loss": 0.3866, "lr": 2.6888161443401118e-06, "epoch": 0.8500275224766893, "percentage": 85.0, "elapsed_time": "1 day, 0:16:16", "remaining_time": "4:16:57"}
1311
+ {"current_steps": 3370, "total_steps": 7494, "loss": 0.3896, "lr": 2.687249394587126e-05, "epoch": 0.4497005888141983, "percentage": 44.97, "elapsed_time": "1 day, 0:20:43", "remaining_time": "1 day, 5:47:32"}
1312
+ {"current_steps": 3190, "total_steps": 3747, "loss": 0.3923, "lr": 2.6423454686264883e-06, "epoch": 0.8513619455888976, "percentage": 85.13, "elapsed_time": "1 day, 0:18:31", "remaining_time": "4:14:40"}
1313
+ {"current_steps": 3375, "total_steps": 7494, "loss": 0.3903, "lr": 2.6828728430238872e-05, "epoch": 0.45036780037030244, "percentage": 45.04, "elapsed_time": "1 day, 0:22:51", "remaining_time": "1 day, 5:45:20"}
1314
+ {"current_steps": 3195, "total_steps": 3747, "loss": 0.3887, "lr": 2.596251457574681e-06, "epoch": 0.8526963687011059, "percentage": 85.27, "elapsed_time": "1 day, 0:20:45", "remaining_time": "4:12:22"}
1315
+ {"current_steps": 3380, "total_steps": 7494, "loss": 0.3876, "lr": 2.6784925868354518e-05, "epoch": 0.45103501192640655, "percentage": 45.1, "elapsed_time": "1 day, 0:24:59", "remaining_time": "1 day, 5:43:07"}
1316
+ {"current_steps": 3200, "total_steps": 3747, "loss": 0.3889, "lr": 2.550535111434176e-06, "epoch": 0.8540307918133142, "percentage": 85.4, "elapsed_time": "1 day, 0:22:58", "remaining_time": "4:10:04"}
1317
+ {"current_steps": 3385, "total_steps": 7494, "loss": 0.3896, "lr": 2.6741086497849665e-05, "epoch": 0.4517022234825107, "percentage": 45.17, "elapsed_time": "1 day, 0:27:07", "remaining_time": "1 day, 5:40:54"}
1318
+ {"current_steps": 3205, "total_steps": 3747, "loss": 0.3864, "lr": 2.5051974222590467e-06, "epoch": 0.8553652149255225, "percentage": 85.54, "elapsed_time": "1 day, 0:26:03", "remaining_time": "4:07:55"}
1319
+ {"current_steps": 3390, "total_steps": 7494, "loss": 0.3886, "lr": 2.6697210556555463e-05, "epoch": 0.4523694350386149, "percentage": 45.24, "elapsed_time": "1 day, 0:29:15", "remaining_time": "1 day, 5:38:43"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:faef8f640aeb0967ee23f89e5aaf95d5b6a87e72c99cdb18533d8bea2f0800d0
3
  size 8721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e0005fa4bdbdd9e6df3dffe1366935d69894cd3319e42465b97ab7a8ab7762b
3
  size 8721