Training in progress, step 39800
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +41 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 58745928
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4eadd9bd319cc90c51da7d6b58281dcb8714d55b4c561d3672289c3e88052d48
|
| 3 |
size 58745928
|
trainer_log.jsonl
CHANGED
|
@@ -8117,3 +8117,44 @@
|
|
| 8117 |
{"current_steps": 39600, "total_steps": 40000, "loss": 0.0, "lr": 1.2397742806111168e-08, "epoch": 440.0, "percentage": 99.0, "elapsed_time": "4:29:53", "remaining_time": "0:02:43", "throughput": 685.11, "total_tokens": 11094352}
|
| 8118 |
{"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.3569253385066986, "epoch": 440.0, "percentage": 99.0, "elapsed_time": "4:29:54", "remaining_time": "0:02:43", "throughput": 685.05, "total_tokens": 11094352}
|
| 8119 |
{"current_steps": 39605, "total_steps": 40000, "loss": 0.0, "lr": 1.209052442764369e-08, "epoch": 440.05555555555554, "percentage": 99.01, "elapsed_time": "4:29:58", "remaining_time": "0:02:41", "throughput": 684.99, "total_tokens": 11095760}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8117 |
{"current_steps": 39600, "total_steps": 40000, "loss": 0.0, "lr": 1.2397742806111168e-08, "epoch": 440.0, "percentage": 99.0, "elapsed_time": "4:29:53", "remaining_time": "0:02:43", "throughput": 685.11, "total_tokens": 11094352}
|
| 8118 |
{"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.3569253385066986, "epoch": 440.0, "percentage": 99.0, "elapsed_time": "4:29:54", "remaining_time": "0:02:43", "throughput": 685.05, "total_tokens": 11094352}
|
| 8119 |
{"current_steps": 39605, "total_steps": 40000, "loss": 0.0, "lr": 1.209052442764369e-08, "epoch": 440.05555555555554, "percentage": 99.01, "elapsed_time": "4:29:58", "remaining_time": "0:02:41", "throughput": 684.99, "total_tokens": 11095760}
|
| 8120 |
+
{"current_steps": 39610, "total_steps": 40000, "loss": 0.0, "lr": 1.17871594988328e-08, "epoch": 440.1111111111111, "percentage": 99.02, "elapsed_time": "4:30:00", "remaining_time": "0:02:39", "throughput": 684.99, "total_tokens": 11097184}
|
| 8121 |
+
{"current_steps": 39615, "total_steps": 40000, "loss": 0.0, "lr": 1.1487648066466072e-08, "epoch": 440.1666666666667, "percentage": 99.04, "elapsed_time": "4:30:02", "remaining_time": "0:02:37", "throughput": 684.99, "total_tokens": 11098544}
|
| 8122 |
+
{"current_steps": 39620, "total_steps": 40000, "loss": 0.0, "lr": 1.1191990176728784e-08, "epoch": 440.22222222222223, "percentage": 99.05, "elapsed_time": "4:30:04", "remaining_time": "0:02:35", "throughput": 685.0, "total_tokens": 11099968}
|
| 8123 |
+
{"current_steps": 39625, "total_steps": 40000, "loss": 0.0, "lr": 1.0900185875215018e-08, "epoch": 440.27777777777777, "percentage": 99.06, "elapsed_time": "4:30:06", "remaining_time": "0:02:33", "throughput": 685.0, "total_tokens": 11101360}
|
| 8124 |
+
{"current_steps": 39630, "total_steps": 40000, "loss": 0.0, "lr": 1.0612235206924891e-08, "epoch": 440.3333333333333, "percentage": 99.08, "elapsed_time": "4:30:08", "remaining_time": "0:02:31", "throughput": 685.01, "total_tokens": 11102800}
|
| 8125 |
+
{"current_steps": 39635, "total_steps": 40000, "loss": 0.0, "lr": 1.0328138216264549e-08, "epoch": 440.3888888888889, "percentage": 99.09, "elapsed_time": "4:30:10", "remaining_time": "0:02:29", "throughput": 685.02, "total_tokens": 11104240}
|
| 8126 |
+
{"current_steps": 39640, "total_steps": 40000, "loss": 0.0, "lr": 1.004789494704339e-08, "epoch": 440.44444444444446, "percentage": 99.1, "elapsed_time": "4:30:12", "remaining_time": "0:02:27", "throughput": 685.02, "total_tokens": 11105648}
|
| 8127 |
+
{"current_steps": 39645, "total_steps": 40000, "loss": 0.0, "lr": 9.771505442482397e-09, "epoch": 440.5, "percentage": 99.11, "elapsed_time": "4:30:14", "remaining_time": "0:02:25", "throughput": 685.03, "total_tokens": 11107072}
|
| 8128 |
+
{"current_steps": 39650, "total_steps": 40000, "loss": 0.0, "lr": 9.498969745200259e-09, "epoch": 440.55555555555554, "percentage": 99.12, "elapsed_time": "4:30:15", "remaining_time": "0:02:23", "throughput": 685.03, "total_tokens": 11108448}
|
| 8129 |
+
{"current_steps": 39655, "total_steps": 40000, "loss": 0.0, "lr": 9.230287897230017e-09, "epoch": 440.6111111111111, "percentage": 99.14, "elapsed_time": "4:30:17", "remaining_time": "0:02:21", "throughput": 685.04, "total_tokens": 11109840}
|
| 8130 |
+
{"current_steps": 39660, "total_steps": 40000, "loss": 0.0, "lr": 8.965459940002419e-09, "epoch": 440.6666666666667, "percentage": 99.15, "elapsed_time": "4:30:19", "remaining_time": "0:02:19", "throughput": 685.04, "total_tokens": 11111264}
|
| 8131 |
+
{"current_steps": 39665, "total_steps": 40000, "loss": 0.0, "lr": 8.704485914357019e-09, "epoch": 440.72222222222223, "percentage": 99.16, "elapsed_time": "4:30:21", "remaining_time": "0:02:17", "throughput": 685.05, "total_tokens": 11112704}
|
| 8132 |
+
{"current_steps": 39670, "total_steps": 40000, "loss": 0.0, "lr": 8.447365860539402e-09, "epoch": 440.77777777777777, "percentage": 99.17, "elapsed_time": "4:30:23", "remaining_time": "0:02:14", "throughput": 685.05, "total_tokens": 11114112}
|
| 8133 |
+
{"current_steps": 39675, "total_steps": 40000, "loss": 0.0, "lr": 8.194099818201184e-09, "epoch": 440.8333333333333, "percentage": 99.19, "elapsed_time": "4:30:25", "remaining_time": "0:02:12", "throughput": 685.06, "total_tokens": 11115488}
|
| 8134 |
+
{"current_steps": 39680, "total_steps": 40000, "loss": 0.0, "lr": 7.944687826400011e-09, "epoch": 440.8888888888889, "percentage": 99.2, "elapsed_time": "4:30:27", "remaining_time": "0:02:10", "throughput": 685.06, "total_tokens": 11116880}
|
| 8135 |
+
{"current_steps": 39685, "total_steps": 40000, "loss": 0.0, "lr": 7.699129923599557e-09, "epoch": 440.94444444444446, "percentage": 99.21, "elapsed_time": "4:30:29", "remaining_time": "0:02:08", "throughput": 685.06, "total_tokens": 11118256}
|
| 8136 |
+
{"current_steps": 39690, "total_steps": 40000, "loss": 0.0, "lr": 7.457426147663982e-09, "epoch": 441.0, "percentage": 99.22, "elapsed_time": "4:30:31", "remaining_time": "0:02:06", "throughput": 685.06, "total_tokens": 11119632}
|
| 8137 |
+
{"current_steps": 39695, "total_steps": 40000, "loss": 0.0, "lr": 7.219576535871797e-09, "epoch": 441.05555555555554, "percentage": 99.24, "elapsed_time": "4:30:33", "remaining_time": "0:02:04", "throughput": 685.05, "total_tokens": 11121008}
|
| 8138 |
+
{"current_steps": 39700, "total_steps": 40000, "loss": 0.0, "lr": 6.985581124896445e-09, "epoch": 441.1111111111111, "percentage": 99.25, "elapsed_time": "4:30:35", "remaining_time": "0:02:02", "throughput": 685.06, "total_tokens": 11122448}
|
| 8139 |
+
{"current_steps": 39705, "total_steps": 40000, "loss": 0.0, "lr": 6.755439950828501e-09, "epoch": 441.1666666666667, "percentage": 99.26, "elapsed_time": "4:30:37", "remaining_time": "0:02:00", "throughput": 685.06, "total_tokens": 11123856}
|
| 8140 |
+
{"current_steps": 39710, "total_steps": 40000, "loss": 0.0, "lr": 6.5291530491562444e-09, "epoch": 441.22222222222223, "percentage": 99.28, "elapsed_time": "4:30:39", "remaining_time": "0:01:58", "throughput": 685.07, "total_tokens": 11125264}
|
| 8141 |
+
{"current_steps": 39715, "total_steps": 40000, "loss": 0.0, "lr": 6.3067204547739845e-09, "epoch": 441.27777777777777, "percentage": 99.29, "elapsed_time": "4:30:41", "remaining_time": "0:01:56", "throughput": 685.07, "total_tokens": 11126640}
|
| 8142 |
+
{"current_steps": 39720, "total_steps": 40000, "loss": 0.0, "lr": 6.088142201987612e-09, "epoch": 441.3333333333333, "percentage": 99.3, "elapsed_time": "4:30:43", "remaining_time": "0:01:54", "throughput": 685.07, "total_tokens": 11128048}
|
| 8143 |
+
{"current_steps": 39725, "total_steps": 40000, "loss": 0.0, "lr": 5.873418324503499e-09, "epoch": 441.3888888888889, "percentage": 99.31, "elapsed_time": "4:30:45", "remaining_time": "0:01:52", "throughput": 685.08, "total_tokens": 11129456}
|
| 8144 |
+
{"current_steps": 39730, "total_steps": 40000, "loss": 0.0, "lr": 5.6625488554340465e-09, "epoch": 441.44444444444446, "percentage": 99.33, "elapsed_time": "4:30:47", "remaining_time": "0:01:50", "throughput": 685.09, "total_tokens": 11130880}
|
| 8145 |
+
{"current_steps": 39735, "total_steps": 40000, "loss": 0.0, "lr": 5.455533827297688e-09, "epoch": 441.5, "percentage": 99.34, "elapsed_time": "4:30:49", "remaining_time": "0:01:48", "throughput": 685.09, "total_tokens": 11132288}
|
| 8146 |
+
{"current_steps": 39740, "total_steps": 40000, "loss": 0.0, "lr": 5.252373272018885e-09, "epoch": 441.55555555555554, "percentage": 99.35, "elapsed_time": "4:30:51", "remaining_time": "0:01:46", "throughput": 685.09, "total_tokens": 11133696}
|
| 8147 |
+
{"current_steps": 39745, "total_steps": 40000, "loss": 0.0, "lr": 5.053067220925356e-09, "epoch": 441.6111111111111, "percentage": 99.36, "elapsed_time": "4:30:53", "remaining_time": "0:01:44", "throughput": 685.1, "total_tokens": 11135104}
|
| 8148 |
+
{"current_steps": 39750, "total_steps": 40000, "loss": 0.0, "lr": 4.857615704759177e-09, "epoch": 441.6666666666667, "percentage": 99.38, "elapsed_time": "4:30:55", "remaining_time": "0:01:42", "throughput": 685.1, "total_tokens": 11136480}
|
| 8149 |
+
{"current_steps": 39755, "total_steps": 40000, "loss": 0.0, "lr": 4.666018753654577e-09, "epoch": 441.72222222222223, "percentage": 99.39, "elapsed_time": "4:30:57", "remaining_time": "0:01:40", "throughput": 685.11, "total_tokens": 11137888}
|
| 8150 |
+
{"current_steps": 39760, "total_steps": 40000, "loss": 0.0, "lr": 4.478276397162917e-09, "epoch": 441.77777777777777, "percentage": 99.4, "elapsed_time": "4:30:59", "remaining_time": "0:01:38", "throughput": 685.11, "total_tokens": 11139232}
|
| 8151 |
+
{"current_steps": 39765, "total_steps": 40000, "loss": 0.0, "lr": 4.294388664233262e-09, "epoch": 441.8333333333333, "percentage": 99.41, "elapsed_time": "4:31:01", "remaining_time": "0:01:36", "throughput": 685.11, "total_tokens": 11140608}
|
| 8152 |
+
{"current_steps": 39770, "total_steps": 40000, "loss": 0.0, "lr": 4.114355583223484e-09, "epoch": 441.8888888888889, "percentage": 99.42, "elapsed_time": "4:31:02", "remaining_time": "0:01:34", "throughput": 685.12, "total_tokens": 11142032}
|
| 8153 |
+
{"current_steps": 39775, "total_steps": 40000, "loss": 0.0, "lr": 3.9381771818974845e-09, "epoch": 441.94444444444446, "percentage": 99.44, "elapsed_time": "4:31:04", "remaining_time": "0:01:32", "throughput": 685.12, "total_tokens": 11143440}
|
| 8154 |
+
{"current_steps": 39780, "total_steps": 40000, "loss": 0.0, "lr": 3.765853487427973e-09, "epoch": 442.0, "percentage": 99.45, "elapsed_time": "4:31:07", "remaining_time": "0:01:29", "throughput": 685.12, "total_tokens": 11144800}
|
| 8155 |
+
{"current_steps": 39785, "total_steps": 40000, "loss": 0.0, "lr": 3.5973845263825857e-09, "epoch": 442.05555555555554, "percentage": 99.46, "elapsed_time": "4:31:09", "remaining_time": "0:01:27", "throughput": 685.11, "total_tokens": 11146208}
|
| 8156 |
+
{"current_steps": 39790, "total_steps": 40000, "loss": 0.0, "lr": 3.4327703247488684e-09, "epoch": 442.1111111111111, "percentage": 99.48, "elapsed_time": "4:31:11", "remaining_time": "0:01:25", "throughput": 685.11, "total_tokens": 11147648}
|
| 8157 |
+
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 442.1666666666667, "percentage": 99.49, "elapsed_time": "4:31:13", "remaining_time": "0:01:23", "throughput": 685.11, "total_tokens": 11149008}
|
| 8158 |
+
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "4:31:15", "remaining_time": "0:01:21", "throughput": 685.11, "total_tokens": 11150400}
|
| 8159 |
+
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.3495562970638275, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "4:31:16", "remaining_time": "0:01:21", "throughput": 685.06, "total_tokens": 11150400}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 442.27777777777777, "percentage": 99.51, "elapsed_time": "4:31:19", "remaining_time": "0:01:19", "throughput": 685.0, "total_tokens": 11151792}
|