Training in progress, epoch 3

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:409e10628f075e7a728f4f707a0b12bb1d8c8885e30a3292b12aa69a03789f5c
+oid sha256:1333ef5d571cc4ef2eb19f45335b146c46347a0544906cc14b1fac525e91d005
 size 4949453792

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fde077bef7eabaf0c170e66e265b77a4295440a5d5d0845997bd72a7d9fafa29
+oid sha256:3b03b55c5248cd5b2c689f5c9a975348bf172d1f7ee23acfb85b75d60cfe2178
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc977eaba717c2df9d7976feafc8c1d4ae7a2050f8901f1a993911cadddab99
+oid sha256:f73fcd6dcf1d83f9d455fe760d98cd92c8b54997dc0a29d349d8bdca07515cc6
 size 4546807800

trainer_log.jsonl

@@ -107,3 +107,55 @@
 {"current_steps": 1052, "total_steps": 1578, "eval_loss": 0.6316379308700562, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:47:34", "remaining_time": "0:53:47"}
 {"current_steps": 1060, "total_steps": 1578, "loss": 0.4716, "lr": 1.7006810417743453e-06, "epoch": 2.0152091254752853, "percentage": 67.17, "elapsed_time": "1:49:29", "remaining_time": "0:53:30"}
 {"current_steps": 1070, "total_steps": 1578, "loss": 0.4592, "lr": 1.6592012672852462e-06, "epoch": 2.0342205323193916, "percentage": 67.81, "elapsed_time": "1:50:30", "remaining_time": "0:52:27"}
+{"current_steps": 1080, "total_steps": 1578, "loss": 0.4568, "lr": 1.618200591733858e-06, "epoch": 2.053231939163498, "percentage": 68.44, "elapsed_time": "1:51:30", "remaining_time": "0:51:24"}
+{"current_steps": 1090, "total_steps": 1578, "loss": 0.4649, "lr": 1.5776970233736877e-06, "epoch": 2.0722433460076046, "percentage": 69.07, "elapsed_time": "1:52:30", "remaining_time": "0:50:22"}
+{"current_steps": 1100, "total_steps": 1578, "loss": 0.4584, "lr": 1.5377083521195849e-06, "epoch": 2.091254752851711, "percentage": 69.71, "elapsed_time": "1:53:30", "remaining_time": "0:49:19"}
+{"current_steps": 1110, "total_steps": 1578, "loss": 0.457, "lr": 1.4982521417340881e-06, "epoch": 2.1102661596958177, "percentage": 70.34, "elapsed_time": "1:54:30", "remaining_time": "0:48:16"}
+{"current_steps": 1120, "total_steps": 1578, "loss": 0.4613, "lr": 1.459345722113095e-06, "epoch": 2.129277566539924, "percentage": 70.98, "elapsed_time": "1:55:32", "remaining_time": "0:47:14"}
+{"current_steps": 1130, "total_steps": 1578, "loss": 0.4557, "lr": 1.4210061816742487e-06, "epoch": 2.1482889733840302, "percentage": 71.61, "elapsed_time": "1:56:33", "remaining_time": "0:46:12"}
+{"current_steps": 1140, "total_steps": 1578, "loss": 0.4638, "lr": 1.3832503598513939e-06, "epoch": 2.167300380228137, "percentage": 72.24, "elapsed_time": "1:57:33", "remaining_time": "0:45:10"}
+{"current_steps": 1150, "total_steps": 1578, "loss": 0.4539, "lr": 1.3460948396983833e-06, "epoch": 2.1863117870722433, "percentage": 72.88, "elapsed_time": "1:58:34", "remaining_time": "0:44:07"}
+{"current_steps": 1160, "total_steps": 1578, "loss": 0.4574, "lr": 1.3095559406054964e-06, "epoch": 2.20532319391635, "percentage": 73.51, "elapsed_time": "1:59:35", "remaining_time": "0:43:05"}
+{"current_steps": 1170, "total_steps": 1578, "loss": 0.4595, "lr": 1.2736497111316607e-06, "epoch": 2.2243346007604563, "percentage": 74.14, "elapsed_time": "2:00:36", "remaining_time": "0:42:03"}
+{"current_steps": 1180, "total_steps": 1578, "loss": 0.4565, "lr": 1.238391921955631e-06, "epoch": 2.2433460076045626, "percentage": 74.78, "elapsed_time": "2:01:37", "remaining_time": "0:41:01"}
+{"current_steps": 1190, "total_steps": 1578, "loss": 0.4623, "lr": 1.2037980589492116e-06, "epoch": 2.2623574144486693, "percentage": 75.41, "elapsed_time": "2:02:37", "remaining_time": "0:39:58"}
+{"current_steps": 1200, "total_steps": 1578, "loss": 0.4531, "lr": 1.1698833163755793e-06, "epoch": 2.2813688212927756, "percentage": 76.05, "elapsed_time": "2:03:39", "remaining_time": "0:38:57"}
+{"current_steps": 1210, "total_steps": 1578, "loss": 0.4555, "lr": 1.1366625902156814e-06, "epoch": 2.3003802281368824, "percentage": 76.68, "elapsed_time": "2:04:40", "remaining_time": "0:37:54"}
+{"current_steps": 1220, "total_steps": 1578, "loss": 0.4601, "lr": 1.1041504716256456e-06, "epoch": 2.3193916349809887, "percentage": 77.31, "elapsed_time": "2:05:40", "remaining_time": "0:36:52"}
+{"current_steps": 1230, "total_steps": 1578, "loss": 0.4669, "lr": 1.0723612405280762e-06, "epoch": 2.338403041825095, "percentage": 77.95, "elapsed_time": "2:06:40", "remaining_time": "0:35:50"}
+{"current_steps": 1240, "total_steps": 1578, "loss": 0.4632, "lr": 1.0413088593400464e-06, "epoch": 2.3574144486692017, "percentage": 78.58, "elapsed_time": "2:07:42", "remaining_time": "0:34:48"}
+{"current_steps": 1250, "total_steps": 1578, "loss": 0.4564, "lr": 1.0110069668405487e-06, "epoch": 2.376425855513308, "percentage": 79.21, "elapsed_time": "2:08:43", "remaining_time": "0:33:46"}
+{"current_steps": 1260, "total_steps": 1578, "loss": 0.4639, "lr": 9.8146887218009e-07, "epoch": 2.3954372623574143, "percentage": 79.85, "elapsed_time": "2:09:43", "remaining_time": "0:32:44"}
+{"current_steps": 1270, "total_steps": 1578, "loss": 0.4615, "lr": 9.527075490350695e-07, "epoch": 2.414448669201521, "percentage": 80.48, "elapsed_time": "2:10:44", "remaining_time": "0:31:42"}
+{"current_steps": 1280, "total_steps": 1578, "loss": 0.4528, "lr": 9.247356299094966e-07, "epoch": 2.4334600760456273, "percentage": 81.12, "elapsed_time": "2:11:46", "remaining_time": "0:30:40"}
+{"current_steps": 1290, "total_steps": 1578, "loss": 0.4535, "lr": 8.975654005865671e-07, "epoch": 2.4524714828897336, "percentage": 81.75, "elapsed_time": "2:12:47", "remaining_time": "0:29:38"}
+{"current_steps": 1300, "total_steps": 1578, "loss": 0.4514, "lr": 8.712087947325155e-07, "epoch": 2.4714828897338403, "percentage": 82.38, "elapsed_time": "2:13:47", "remaining_time": "0:28:36"}
+{"current_steps": 1310, "total_steps": 1578, "loss": 0.456, "lr": 8.456773886551317e-07, "epoch": 2.4904942965779466, "percentage": 83.02, "elapsed_time": "2:14:50", "remaining_time": "0:27:35"}
+{"current_steps": 1320, "total_steps": 1578, "loss": 0.4584, "lr": 8.20982396219231e-07, "epoch": 2.5095057034220534, "percentage": 83.65, "elapsed_time": "2:15:50", "remaining_time": "0:26:33"}
+{"current_steps": 1330, "total_steps": 1578, "loss": 0.4576, "lr": 7.971346639213192e-07, "epoch": 2.5285171102661597, "percentage": 84.28, "elapsed_time": "2:16:51", "remaining_time": "0:25:31"}
+{"current_steps": 1340, "total_steps": 1578, "loss": 0.4585, "lr": 7.74144666125611e-07, "epoch": 2.5475285171102664, "percentage": 84.92, "elapsed_time": "2:17:53", "remaining_time": "0:24:29"}
+{"current_steps": 1350, "total_steps": 1578, "loss": 0.4617, "lr": 7.520225004634946e-07, "epoch": 2.5665399239543727, "percentage": 85.55, "elapsed_time": "2:18:54", "remaining_time": "0:23:27"}
+{"current_steps": 1360, "total_steps": 1578, "loss": 0.4525, "lr": 7.307778833984666e-07, "epoch": 2.585551330798479, "percentage": 86.19, "elapsed_time": "2:19:54", "remaining_time": "0:22:25"}
+{"current_steps": 1370, "total_steps": 1578, "loss": 0.4554, "lr": 7.104201459584814e-07, "epoch": 2.6045627376425857, "percentage": 86.82, "elapsed_time": "2:20:55", "remaining_time": "0:21:23"}
+{"current_steps": 1380, "total_steps": 1578, "loss": 0.4571, "lr": 6.909582296375923e-07, "epoch": 2.623574144486692, "percentage": 87.45, "elapsed_time": "2:21:57", "remaining_time": "0:20:22"}
+{"current_steps": 1390, "total_steps": 1578, "loss": 0.458, "lr": 6.724006824686814e-07, "epoch": 2.6425855513307983, "percentage": 88.09, "elapsed_time": "2:22:57", "remaining_time": "0:19:20"}
+{"current_steps": 1400, "total_steps": 1578, "loss": 0.4576, "lr": 6.547556552690069e-07, "epoch": 2.661596958174905, "percentage": 88.72, "elapsed_time": "2:23:57", "remaining_time": "0:18:18"}
+{"current_steps": 1410, "total_steps": 1578, "loss": 0.4559, "lr": 6.380308980602119e-07, "epoch": 2.6806083650190113, "percentage": 89.35, "elapsed_time": "2:24:58", "remaining_time": "0:17:16"}
+{"current_steps": 1420, "total_steps": 1578, "loss": 0.458, "lr": 6.222337566643733e-07, "epoch": 2.6996197718631176, "percentage": 89.99, "elapsed_time": "2:26:01", "remaining_time": "0:16:14"}
+{"current_steps": 1430, "total_steps": 1578, "loss": 0.4523, "lr": 6.073711694775805e-07, "epoch": 2.7186311787072244, "percentage": 90.62, "elapsed_time": "2:27:02", "remaining_time": "0:15:13"}
+{"current_steps": 1440, "total_steps": 1578, "loss": 0.4592, "lr": 5.934496644224642e-07, "epoch": 2.7376425855513307, "percentage": 91.25, "elapsed_time": "2:28:04", "remaining_time": "0:14:11"}
+{"current_steps": 1450, "total_steps": 1578, "loss": 0.4587, "lr": 5.804753560810128e-07, "epoch": 2.7566539923954374, "percentage": 91.89, "elapsed_time": "2:29:05", "remaining_time": "0:13:09"}
+{"current_steps": 1460, "total_steps": 1578, "loss": 0.4558, "lr": 5.684539430089329e-07, "epoch": 2.7756653992395437, "percentage": 92.52, "elapsed_time": "2:30:05", "remaining_time": "0:12:07"}
+{"current_steps": 1470, "total_steps": 1578, "loss": 0.4585, "lr": 5.573907052327413e-07, "epoch": 2.7946768060836504, "percentage": 93.16, "elapsed_time": "2:31:06", "remaining_time": "0:11:06"}
+{"current_steps": 1480, "total_steps": 1578, "loss": 0.4555, "lr": 5.472905019306775e-07, "epoch": 2.8136882129277567, "percentage": 93.79, "elapsed_time": "2:32:08", "remaining_time": "0:10:04"}
+{"current_steps": 1490, "total_steps": 1578, "loss": 0.4529, "lr": 5.38157769298465e-07, "epoch": 2.832699619771863, "percentage": 94.42, "elapsed_time": "2:33:08", "remaining_time": "0:09:02"}
+{"current_steps": 1500, "total_steps": 1578, "loss": 0.4628, "lr": 5.2999651860085e-07, "epoch": 2.8517110266159698, "percentage": 95.06, "elapsed_time": "2:34:09", "remaining_time": "0:08:00"}
+{"current_steps": 1510, "total_steps": 1578, "loss": 0.4642, "lr": 5.228103344097825e-07, "epoch": 2.870722433460076, "percentage": 95.69, "elapsed_time": "2:35:10", "remaining_time": "0:06:59"}
+{"current_steps": 1520, "total_steps": 1578, "loss": 0.4541, "lr": 5.166023730300036e-07, "epoch": 2.8897338403041823, "percentage": 96.32, "elapsed_time": "2:36:11", "remaining_time": "0:05:57"}
+{"current_steps": 1530, "total_steps": 1578, "loss": 0.4607, "lr": 5.113753611127401e-07, "epoch": 2.908745247148289, "percentage": 96.96, "elapsed_time": "2:37:11", "remaining_time": "0:04:55"}
+{"current_steps": 1540, "total_steps": 1578, "loss": 0.4638, "lr": 5.071315944581075e-07, "epoch": 2.9277566539923954, "percentage": 97.59, "elapsed_time": "2:38:12", "remaining_time": "0:03:54"}
+{"current_steps": 1550, "total_steps": 1578, "loss": 0.455, "lr": 5.038729370067536e-07, "epoch": 2.9467680608365017, "percentage": 98.23, "elapsed_time": "2:39:13", "remaining_time": "0:02:52"}
+{"current_steps": 1560, "total_steps": 1578, "loss": 0.4556, "lr": 5.016008200211805e-07, "epoch": 2.9657794676806084, "percentage": 98.86, "elapsed_time": "2:40:14", "remaining_time": "0:01:50"}
+{"current_steps": 1570, "total_steps": 1578, "loss": 0.455, "lr": 5.003162414571072e-07, "epoch": 2.9847908745247147, "percentage": 99.49, "elapsed_time": "2:41:15", "remaining_time": "0:00:49"}
+{"current_steps": 1578, "total_steps": 1578, "eval_loss": 0.6586939692497253, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:44:01", "remaining_time": "0:00:00"}
+{"current_steps": 1578, "total_steps": 1578, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:45:00", "remaining_time": "0:00:00"}