Training in progress, step 39800
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +42 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 18124968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03bdb5f66ac3b6a7596c7b83c26151e2aa647c956e19b5c70591cdf9d503b2e6
|
| 3 |
size 18124968
|
trainer_log.jsonl
CHANGED
|
@@ -8116,3 +8116,45 @@
|
|
| 8116 |
{"current_steps": 39595, "total_steps": 40000, "loss": 0.0, "lr": 1.2708814586862016e-08, "epoch": 694.6548672566372, "percentage": 98.99, "elapsed_time": "4:45:44", "remaining_time": "0:02:55", "throughput": 1311.69, "total_tokens": 22487672}
|
| 8117 |
{"current_steps": 39600, "total_steps": 40000, "loss": 0.0, "lr": 1.2397742806111168e-08, "epoch": 694.7433628318585, "percentage": 99.0, "elapsed_time": "4:45:46", "remaining_time": "0:02:53", "throughput": 1311.69, "total_tokens": 22490328}
|
| 8118 |
{"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.9180490970611572, "epoch": 694.7433628318585, "percentage": 99.0, "elapsed_time": "4:45:47", "remaining_time": "0:02:53", "throughput": 1311.61, "total_tokens": 22490328}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8116 |
{"current_steps": 39595, "total_steps": 40000, "loss": 0.0, "lr": 1.2708814586862016e-08, "epoch": 694.6548672566372, "percentage": 98.99, "elapsed_time": "4:45:44", "remaining_time": "0:02:55", "throughput": 1311.69, "total_tokens": 22487672}
|
| 8117 |
{"current_steps": 39600, "total_steps": 40000, "loss": 0.0, "lr": 1.2397742806111168e-08, "epoch": 694.7433628318585, "percentage": 99.0, "elapsed_time": "4:45:46", "remaining_time": "0:02:53", "throughput": 1311.69, "total_tokens": 22490328}
|
| 8118 |
{"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.9180490970611572, "epoch": 694.7433628318585, "percentage": 99.0, "elapsed_time": "4:45:47", "remaining_time": "0:02:53", "throughput": 1311.61, "total_tokens": 22490328}
|
| 8119 |
+
{"current_steps": 39605, "total_steps": 40000, "loss": 0.0, "lr": 1.209052442764369e-08, "epoch": 694.8318584070796, "percentage": 99.01, "elapsed_time": "4:45:51", "remaining_time": "0:02:51", "throughput": 1311.47, "total_tokens": 22493160}
|
| 8120 |
+
{"current_steps": 39610, "total_steps": 40000, "loss": 0.0, "lr": 1.17871594988328e-08, "epoch": 694.9203539823009, "percentage": 99.02, "elapsed_time": "4:45:53", "remaining_time": "0:02:48", "throughput": 1311.48, "total_tokens": 22496040}
|
| 8121 |
+
{"current_steps": 39615, "total_steps": 40000, "loss": 0.0, "lr": 1.1487648066466072e-08, "epoch": 695.0, "percentage": 99.04, "elapsed_time": "4:45:55", "remaining_time": "0:02:46", "throughput": 1311.49, "total_tokens": 22498816}
|
| 8122 |
+
{"current_steps": 39620, "total_steps": 40000, "loss": 0.0, "lr": 1.1191990176728784e-08, "epoch": 695.0884955752213, "percentage": 99.05, "elapsed_time": "4:45:57", "remaining_time": "0:02:44", "throughput": 1311.49, "total_tokens": 22501760}
|
| 8123 |
+
{"current_steps": 39625, "total_steps": 40000, "loss": 0.0, "lr": 1.0900185875215018e-08, "epoch": 695.1769911504425, "percentage": 99.06, "elapsed_time": "4:45:59", "remaining_time": "0:02:42", "throughput": 1311.51, "total_tokens": 22504800}
|
| 8124 |
+
{"current_steps": 39630, "total_steps": 40000, "loss": 0.0, "lr": 1.0612235206924891e-08, "epoch": 695.2654867256637, "percentage": 99.08, "elapsed_time": "4:46:01", "remaining_time": "0:02:40", "throughput": 1311.53, "total_tokens": 22507888}
|
| 8125 |
+
{"current_steps": 39635, "total_steps": 40000, "loss": 0.0, "lr": 1.0328138216264549e-08, "epoch": 695.3539823008849, "percentage": 99.09, "elapsed_time": "4:46:03", "remaining_time": "0:02:38", "throughput": 1311.5, "total_tokens": 22510160}
|
| 8126 |
+
{"current_steps": 39640, "total_steps": 40000, "loss": 0.0, "lr": 1.004789494704339e-08, "epoch": 695.4424778761062, "percentage": 99.1, "elapsed_time": "4:46:05", "remaining_time": "0:02:35", "throughput": 1311.5, "total_tokens": 22512816}
|
| 8127 |
+
{"current_steps": 39645, "total_steps": 40000, "loss": 0.0, "lr": 9.771505442482397e-09, "epoch": 695.5309734513274, "percentage": 99.11, "elapsed_time": "4:46:07", "remaining_time": "0:02:33", "throughput": 1311.52, "total_tokens": 22515760}
|
| 8128 |
+
{"current_steps": 39650, "total_steps": 40000, "loss": 0.0, "lr": 9.498969745200259e-09, "epoch": 695.6194690265487, "percentage": 99.12, "elapsed_time": "4:46:09", "remaining_time": "0:02:31", "throughput": 1311.53, "total_tokens": 22518624}
|
| 8129 |
+
{"current_steps": 39655, "total_steps": 40000, "loss": 0.0, "lr": 9.230287897230017e-09, "epoch": 695.70796460177, "percentage": 99.14, "elapsed_time": "4:46:11", "remaining_time": "0:02:29", "throughput": 1311.53, "total_tokens": 22521344}
|
| 8130 |
+
{"current_steps": 39660, "total_steps": 40000, "loss": 0.0, "lr": 8.965459940002419e-09, "epoch": 695.7964601769911, "percentage": 99.15, "elapsed_time": "4:46:13", "remaining_time": "0:02:27", "throughput": 1311.53, "total_tokens": 22524096}
|
| 8131 |
+
{"current_steps": 39665, "total_steps": 40000, "loss": 0.0, "lr": 8.704485914357019e-09, "epoch": 695.8849557522124, "percentage": 99.16, "elapsed_time": "4:46:15", "remaining_time": "0:02:25", "throughput": 1311.56, "total_tokens": 22527280}
|
| 8132 |
+
{"current_steps": 39670, "total_steps": 40000, "loss": 0.0, "lr": 8.447365860539402e-09, "epoch": 695.9734513274336, "percentage": 99.17, "elapsed_time": "4:46:17", "remaining_time": "0:02:22", "throughput": 1311.6, "total_tokens": 22530672}
|
| 8133 |
+
{"current_steps": 39675, "total_steps": 40000, "loss": 0.0, "lr": 8.194099818201184e-09, "epoch": 696.0530973451328, "percentage": 99.19, "elapsed_time": "4:46:20", "remaining_time": "0:02:20", "throughput": 1311.56, "total_tokens": 22532944}
|
| 8134 |
+
{"current_steps": 39680, "total_steps": 40000, "loss": 0.0, "lr": 7.944687826400011e-09, "epoch": 696.141592920354, "percentage": 99.2, "elapsed_time": "4:46:22", "remaining_time": "0:02:18", "throughput": 1311.61, "total_tokens": 22536400}
|
| 8135 |
+
{"current_steps": 39685, "total_steps": 40000, "loss": 0.0, "lr": 7.699129923599557e-09, "epoch": 696.2300884955753, "percentage": 99.21, "elapsed_time": "4:46:24", "remaining_time": "0:02:16", "throughput": 1311.58, "total_tokens": 22538688}
|
| 8136 |
+
{"current_steps": 39690, "total_steps": 40000, "loss": 0.0, "lr": 7.457426147663982e-09, "epoch": 696.3185840707964, "percentage": 99.22, "elapsed_time": "4:46:26", "remaining_time": "0:02:14", "throughput": 1311.63, "total_tokens": 22542336}
|
| 8137 |
+
{"current_steps": 39695, "total_steps": 40000, "loss": 0.0, "lr": 7.219576535871797e-09, "epoch": 696.4070796460177, "percentage": 99.24, "elapsed_time": "4:46:28", "remaining_time": "0:02:12", "throughput": 1311.64, "total_tokens": 22545184}
|
| 8138 |
+
{"current_steps": 39700, "total_steps": 40000, "loss": 0.0, "lr": 6.985581124896445e-09, "epoch": 696.4955752212389, "percentage": 99.25, "elapsed_time": "4:46:30", "remaining_time": "0:02:09", "throughput": 1311.64, "total_tokens": 22547920}
|
| 8139 |
+
{"current_steps": 39705, "total_steps": 40000, "loss": 0.0, "lr": 6.755439950828501e-09, "epoch": 696.5840707964602, "percentage": 99.26, "elapsed_time": "4:46:32", "remaining_time": "0:02:07", "throughput": 1311.64, "total_tokens": 22550592}
|
| 8140 |
+
{"current_steps": 39710, "total_steps": 40000, "loss": 0.0, "lr": 6.5291530491562444e-09, "epoch": 696.6725663716815, "percentage": 99.28, "elapsed_time": "4:46:34", "remaining_time": "0:02:05", "throughput": 1311.64, "total_tokens": 22553216}
|
| 8141 |
+
{"current_steps": 39715, "total_steps": 40000, "loss": 0.0, "lr": 6.3067204547739845e-09, "epoch": 696.7610619469026, "percentage": 99.29, "elapsed_time": "4:46:36", "remaining_time": "0:02:03", "throughput": 1311.65, "total_tokens": 22556144}
|
| 8142 |
+
{"current_steps": 39720, "total_steps": 40000, "loss": 0.0, "lr": 6.088142201987612e-09, "epoch": 696.8495575221239, "percentage": 99.3, "elapsed_time": "4:46:38", "remaining_time": "0:02:01", "throughput": 1311.68, "total_tokens": 22559264}
|
| 8143 |
+
{"current_steps": 39725, "total_steps": 40000, "loss": 0.0, "lr": 5.873418324503499e-09, "epoch": 696.9380530973451, "percentage": 99.31, "elapsed_time": "4:46:40", "remaining_time": "0:01:59", "throughput": 1311.68, "total_tokens": 22562016}
|
| 8144 |
+
{"current_steps": 39730, "total_steps": 40000, "loss": 0.0, "lr": 5.6625488554340465e-09, "epoch": 697.0176991150443, "percentage": 99.33, "elapsed_time": "4:46:43", "remaining_time": "0:01:56", "throughput": 1311.64, "total_tokens": 22564280}
|
| 8145 |
+
{"current_steps": 39735, "total_steps": 40000, "loss": 0.0, "lr": 5.455533827297688e-09, "epoch": 697.1061946902655, "percentage": 99.34, "elapsed_time": "4:46:45", "remaining_time": "0:01:54", "throughput": 1311.66, "total_tokens": 22567400}
|
| 8146 |
+
{"current_steps": 39740, "total_steps": 40000, "loss": 0.0, "lr": 5.252373272018885e-09, "epoch": 697.1946902654868, "percentage": 99.35, "elapsed_time": "4:46:47", "remaining_time": "0:01:52", "throughput": 1311.69, "total_tokens": 22570520}
|
| 8147 |
+
{"current_steps": 39745, "total_steps": 40000, "loss": 0.0, "lr": 5.053067220925356e-09, "epoch": 697.2831858407079, "percentage": 99.36, "elapsed_time": "4:46:49", "remaining_time": "0:01:50", "throughput": 1311.7, "total_tokens": 22573336}
|
| 8148 |
+
{"current_steps": 39750, "total_steps": 40000, "loss": 0.0, "lr": 4.857615704759177e-09, "epoch": 697.3716814159292, "percentage": 99.38, "elapsed_time": "4:46:51", "remaining_time": "0:01:48", "throughput": 1311.7, "total_tokens": 22576152}
|
| 8149 |
+
{"current_steps": 39755, "total_steps": 40000, "loss": 0.0, "lr": 4.666018753654577e-09, "epoch": 697.4601769911504, "percentage": 99.39, "elapsed_time": "4:46:53", "remaining_time": "0:01:46", "throughput": 1311.71, "total_tokens": 22578920}
|
| 8150 |
+
{"current_steps": 39760, "total_steps": 40000, "loss": 0.0, "lr": 4.478276397162917e-09, "epoch": 697.5486725663717, "percentage": 99.4, "elapsed_time": "4:46:55", "remaining_time": "0:01:43", "throughput": 1311.69, "total_tokens": 22581352}
|
| 8151 |
+
{"current_steps": 39765, "total_steps": 40000, "loss": 0.0, "lr": 4.294388664233262e-09, "epoch": 697.637168141593, "percentage": 99.41, "elapsed_time": "4:46:57", "remaining_time": "0:01:41", "throughput": 1311.69, "total_tokens": 22584152}
|
| 8152 |
+
{"current_steps": 39770, "total_steps": 40000, "loss": 0.0, "lr": 4.114355583223484e-09, "epoch": 697.7256637168142, "percentage": 99.42, "elapsed_time": "4:46:59", "remaining_time": "0:01:39", "throughput": 1311.72, "total_tokens": 22587384}
|
| 8153 |
+
{"current_steps": 39775, "total_steps": 40000, "loss": 0.0, "lr": 3.9381771818974845e-09, "epoch": 697.8141592920354, "percentage": 99.44, "elapsed_time": "4:47:01", "remaining_time": "0:01:37", "throughput": 1311.74, "total_tokens": 22590296}
|
| 8154 |
+
{"current_steps": 39780, "total_steps": 40000, "loss": 0.0, "lr": 3.765853487427973e-09, "epoch": 697.9026548672566, "percentage": 99.45, "elapsed_time": "4:47:03", "remaining_time": "0:01:35", "throughput": 1311.74, "total_tokens": 22593032}
|
| 8155 |
+
{"current_steps": 39785, "total_steps": 40000, "loss": 0.0, "lr": 3.5973845263825857e-09, "epoch": 697.9911504424779, "percentage": 99.46, "elapsed_time": "4:47:05", "remaining_time": "0:01:33", "throughput": 1311.76, "total_tokens": 22596136}
|
| 8156 |
+
{"current_steps": 39790, "total_steps": 40000, "loss": 0.0, "lr": 3.4327703247488684e-09, "epoch": 698.070796460177, "percentage": 99.48, "elapsed_time": "4:47:08", "remaining_time": "0:01:30", "throughput": 1311.72, "total_tokens": 22598352}
|
| 8157 |
+
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 698.1592920353983, "percentage": 99.49, "elapsed_time": "4:47:10", "remaining_time": "0:01:28", "throughput": 1311.72, "total_tokens": 22601024}
|
| 8158 |
+
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "4:47:12", "remaining_time": "0:01:26", "throughput": 1311.74, "total_tokens": 22604096}
|
| 8159 |
+
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.909034013748169, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "4:47:13", "remaining_time": "0:01:26", "throughput": 1311.66, "total_tokens": 22604096}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 698.3362831858407, "percentage": 99.51, "elapsed_time": "4:47:18", "remaining_time": "0:01:24", "throughput": 1311.44, "total_tokens": 22607040}
|