Training in progress, step 40000
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:cba09212a4e6704ce3ad0b89da2e3e963336f4e586904c35eef6a1ad43711f7a
|
| 3 |
size 18124968
|
trainer_log.jsonl
CHANGED
|
@@ -8157,3 +8157,45 @@
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 6.4918835141528675, "percentage": 99.49, "elapsed_time": "9:07:42", "remaining_time": "0:02:49", "throughput": 2330.02, "total_tokens": 76570480}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0001, "lr": 3.1151063006468193e-09, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "9:07:44", "remaining_time": "0:02:45", "throughput": 2330.2, "total_tokens": 76581104}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.4304603636264801, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "9:09:05", "remaining_time": "0:02:45", "throughput": 2324.47, "total_tokens": 76581104}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 6.4918835141528675, "percentage": 99.49, "elapsed_time": "9:07:42", "remaining_time": "0:02:49", "throughput": 2330.02, "total_tokens": 76570480}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0001, "lr": 3.1151063006468193e-09, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "9:07:44", "remaining_time": "0:02:45", "throughput": 2330.2, "total_tokens": 76581104}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.4304603636264801, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "9:09:05", "remaining_time": "0:02:45", "throughput": 2324.47, "total_tokens": 76581104}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 6.493514968594502, "percentage": 99.51, "elapsed_time": "9:09:09", "remaining_time": "0:02:41", "throughput": 2324.5, "total_tokens": 76590896}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.0109, "lr": 2.8128616110761898e-09, "epoch": 6.49433069581532, "percentage": 99.52, "elapsed_time": "9:09:11", "remaining_time": "0:02:37", "throughput": 2324.65, "total_tokens": 76600464}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.0002, "lr": 2.6675215753724223e-09, "epoch": 6.495146423036137, "percentage": 99.54, "elapsed_time": "9:09:13", "remaining_time": "0:02:33", "throughput": 2324.82, "total_tokens": 76610864}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 2.5260364424739557e-09, "epoch": 6.495962150256954, "percentage": 99.55, "elapsed_time": "9:09:15", "remaining_time": "0:02:28", "throughput": 2324.97, "total_tokens": 76620688}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 2.3884062341994475e-09, "epoch": 6.496777877477771, "percentage": 99.56, "elapsed_time": "9:09:17", "remaining_time": "0:02:24", "throughput": 2325.11, "total_tokens": 76630128}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.0006, "lr": 2.25463097177081e-09, "epoch": 6.497593604698589, "percentage": 99.58, "elapsed_time": "9:09:19", "remaining_time": "0:02:20", "throughput": 2325.21, "total_tokens": 76638128}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.0001, "lr": 2.1247106758215397e-09, "epoch": 6.498409331919406, "percentage": 99.59, "elapsed_time": "9:09:21", "remaining_time": "0:02:16", "throughput": 2325.3, "total_tokens": 76646032}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.0005, "lr": 1.998645366382834e-09, "epoch": 6.499225059140223, "percentage": 99.6, "elapsed_time": "9:09:23", "remaining_time": "0:02:12", "throughput": 2325.48, "total_tokens": 76656768}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.0002, "lr": 1.876435062897475e-09, "epoch": 6.5000407863610405, "percentage": 99.61, "elapsed_time": "9:09:25", "remaining_time": "0:02:08", "throughput": 2325.67, "total_tokens": 76667984}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.0002, "lr": 1.758079784211497e-09, "epoch": 6.500856513581859, "percentage": 99.62, "elapsed_time": "9:09:28", "remaining_time": "0:02:04", "throughput": 2325.81, "total_tokens": 76677392}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.043, "lr": 1.6435795485797434e-09, "epoch": 6.501672240802676, "percentage": 99.64, "elapsed_time": "9:09:30", "remaining_time": "0:01:59", "throughput": 2325.96, "total_tokens": 76687072}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.0001, "lr": 1.5329343736547596e-09, "epoch": 6.502487968023493, "percentage": 99.65, "elapsed_time": "9:09:32", "remaining_time": "0:01:55", "throughput": 2326.11, "total_tokens": 76696976}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.0001, "lr": 1.4261442765006739e-09, "epoch": 6.50330369524431, "percentage": 99.66, "elapsed_time": "9:09:34", "remaining_time": "0:01:51", "throughput": 2326.25, "total_tokens": 76706512}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 1.3232092735876445e-09, "epoch": 6.504119422465128, "percentage": 99.67, "elapsed_time": "9:09:36", "remaining_time": "0:01:47", "throughput": 2326.41, "total_tokens": 76716496}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.0001, "lr": 1.2241293807918607e-09, "epoch": 6.504935149685945, "percentage": 99.69, "elapsed_time": "9:09:38", "remaining_time": "0:01:43", "throughput": 2326.55, "total_tokens": 76725744}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.0001, "lr": 1.128904613387216e-09, "epoch": 6.505750876906762, "percentage": 99.7, "elapsed_time": "9:09:40", "remaining_time": "0:01:39", "throughput": 2326.72, "total_tokens": 76736368}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.0002, "lr": 1.0375349860591853e-09, "epoch": 6.506566604127579, "percentage": 99.71, "elapsed_time": "9:09:42", "remaining_time": "0:01:35", "throughput": 2326.9, "total_tokens": 76747024}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 9.5002051290205e-10, "epoch": 6.507382331348397, "percentage": 99.72, "elapsed_time": "9:09:44", "remaining_time": "0:01:30", "throughput": 2326.99, "total_tokens": 76754944}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 8.663612074077954e-10, "epoch": 6.5081980585692145, "percentage": 99.74, "elapsed_time": "9:09:46", "remaining_time": "0:01:26", "throughput": 2327.13, "total_tokens": 76764368}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.0001, "lr": 7.865570824799884e-10, "epoch": 6.509013785790032, "percentage": 99.75, "elapsed_time": "9:09:48", "remaining_time": "0:01:22", "throughput": 2327.29, "total_tokens": 76774384}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 7.106081504254514e-10, "epoch": 6.50982951301085, "percentage": 99.76, "elapsed_time": "9:09:50", "remaining_time": "0:01:18", "throughput": 2327.44, "total_tokens": 76784208}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 6.385144229570372e-10, "epoch": 6.510645240231667, "percentage": 99.78, "elapsed_time": "9:09:52", "remaining_time": "0:01:14", "throughput": 2327.58, "total_tokens": 76793600}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.0138, "lr": 5.70275911190854e-10, "epoch": 6.511460967452484, "percentage": 99.79, "elapsed_time": "9:09:55", "remaining_time": "0:01:10", "throughput": 2327.69, "total_tokens": 76802192}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.0001, "lr": 5.058926256490403e-10, "epoch": 6.512276694673301, "percentage": 99.8, "elapsed_time": "9:09:57", "remaining_time": "0:01:06", "throughput": 2327.82, "total_tokens": 76811264}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 4.4536457626254134e-10, "epoch": 6.513092421894118, "percentage": 99.81, "elapsed_time": "9:09:59", "remaining_time": "0:01:01", "throughput": 2327.94, "total_tokens": 76820224}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 3.88691772365557e-10, "epoch": 6.513908149114936, "percentage": 99.83, "elapsed_time": "9:10:01", "remaining_time": "0:00:57", "throughput": 2328.09, "total_tokens": 76829824}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 3.358742226955425e-10, "epoch": 6.514723876335753, "percentage": 99.84, "elapsed_time": "9:10:03", "remaining_time": "0:00:53", "throughput": 2328.22, "total_tokens": 76838992}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.0163, "lr": 2.8691193539875925e-10, "epoch": 6.5155396035565705, "percentage": 99.85, "elapsed_time": "9:10:05", "remaining_time": "0:00:49", "throughput": 2328.36, "total_tokens": 76848464}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.0004, "lr": 2.418049180274995e-10, "epoch": 6.5163553307773885, "percentage": 99.86, "elapsed_time": "9:10:07", "remaining_time": "0:00:45", "throughput": 2328.51, "total_tokens": 76858288}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.1063, "lr": 2.005531775373104e-10, "epoch": 6.517171057998206, "percentage": 99.88, "elapsed_time": "9:10:09", "remaining_time": "0:00:41", "throughput": 2328.64, "total_tokens": 76867280}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.0177, "lr": 1.6315672028699435e-10, "epoch": 6.517986785219023, "percentage": 99.89, "elapsed_time": "9:10:11", "remaining_time": "0:00:37", "throughput": 2328.79, "total_tokens": 76876992}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.0001, "lr": 1.2961555204693555e-10, "epoch": 6.51880251243984, "percentage": 99.9, "elapsed_time": "9:10:13", "remaining_time": "0:00:33", "throughput": 2328.94, "total_tokens": 76887008}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.0002, "lr": 9.992967798799768e-11, "epoch": 6.519618239660657, "percentage": 99.91, "elapsed_time": "9:10:15", "remaining_time": "0:00:28", "throughput": 2329.08, "total_tokens": 76896288}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 7.409910268707521e-11, "epoch": 6.520433966881475, "percentage": 99.92, "elapsed_time": "9:10:17", "remaining_time": "0:00:24", "throughput": 2329.23, "total_tokens": 76906288}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.0003, "lr": 5.212383012986877e-11, "epoch": 6.521249694102292, "percentage": 99.94, "elapsed_time": "9:10:19", "remaining_time": "0:00:20", "throughput": 2329.32, "total_tokens": 76914000}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 3.400386370533415e-11, "epoch": 6.522065421323109, "percentage": 99.95, "elapsed_time": "9:10:21", "remaining_time": "0:00:16", "throughput": 2329.45, "total_tokens": 76923104}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.0252, "lr": 1.9739206205682258e-11, "epoch": 6.522881148543927, "percentage": 99.96, "elapsed_time": "9:10:24", "remaining_time": "0:00:12", "throughput": 2329.62, "total_tokens": 76933424}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.001, "lr": 9.329859829154685e-12, "epoch": 6.523696875764744, "percentage": 99.98, "elapsed_time": "9:10:26", "remaining_time": "0:00:08", "throughput": 2329.78, "total_tokens": 76943616}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.0005, "lr": 2.7758261855748148e-12, "epoch": 6.524512602985562, "percentage": 99.99, "elapsed_time": "9:10:28", "remaining_time": "0:00:04", "throughput": 2329.93, "total_tokens": 76953296}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.0001, "lr": 7.710628524559838e-14, "epoch": 6.525328330206379, "percentage": 100.0, "elapsed_time": "9:10:30", "remaining_time": "0:00:00", "throughput": 2330.07, "total_tokens": 76963024}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.42914924025535583, "epoch": 6.525328330206379, "percentage": 100.0, "elapsed_time": "9:11:51", "remaining_time": "0:00:00", "throughput": 2324.39, "total_tokens": 76963024}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 6.525328330206379, "percentage": 100.0, "elapsed_time": "9:11:52", "remaining_time": "0:00:00", "throughput": 2324.27, "total_tokens": 76963024}
|