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 58745928
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:685b681fb47ebca4ffd23cf2554a5dcad1496ae3129af86894c3c17e4e49fbce
|
| 3 |
size 58745928
|
trainer_log.jsonl
CHANGED
|
@@ -8157,3 +8157,45 @@
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 193.17917675544794, "percentage": 99.49, "elapsed_time": "8:59:43", "remaining_time": "0:02:46", "throughput": 2021.01, "total_tokens": 65447648}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 193.20338983050848, "percentage": 99.5, "elapsed_time": "8:59:47", "remaining_time": "0:02:42", "throughput": 2021.02, "total_tokens": 65455776}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.7654255628585815, "epoch": 193.20338983050848, "percentage": 99.5, "elapsed_time": "8:59:52", "remaining_time": "0:02:42", "throughput": 2020.68, "total_tokens": 65455776}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 193.17917675544794, "percentage": 99.49, "elapsed_time": "8:59:43", "remaining_time": "0:02:46", "throughput": 2021.01, "total_tokens": 65447648}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 193.20338983050848, "percentage": 99.5, "elapsed_time": "8:59:47", "remaining_time": "0:02:42", "throughput": 2021.02, "total_tokens": 65455776}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.7654255628585815, "epoch": 193.20338983050848, "percentage": 99.5, "elapsed_time": "8:59:52", "remaining_time": "0:02:42", "throughput": 2020.68, "total_tokens": 65455776}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 193.227602905569, "percentage": 99.51, "elapsed_time": "8:59:58", "remaining_time": "0:02:38", "throughput": 2020.59, "total_tokens": 65464128}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 2.8128616110761898e-09, "epoch": 193.25181598062954, "percentage": 99.52, "elapsed_time": "9:00:02", "remaining_time": "0:02:34", "throughput": 2020.6, "total_tokens": 65472320}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 2.6675215753724223e-09, "epoch": 193.27602905569006, "percentage": 99.54, "elapsed_time": "9:00:06", "remaining_time": "0:02:30", "throughput": 2020.61, "total_tokens": 65480448}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 2.5260364424739557e-09, "epoch": 193.3002421307506, "percentage": 99.55, "elapsed_time": "9:00:10", "remaining_time": "0:02:26", "throughput": 2020.61, "total_tokens": 65488480}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 2.3884062341994475e-09, "epoch": 193.32445520581115, "percentage": 99.56, "elapsed_time": "9:00:14", "remaining_time": "0:02:22", "throughput": 2020.63, "total_tokens": 65496608}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 2.25463097177081e-09, "epoch": 193.34866828087166, "percentage": 99.58, "elapsed_time": "9:00:17", "remaining_time": "0:02:18", "throughput": 2020.63, "total_tokens": 65504672}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 2.1247106758215397e-09, "epoch": 193.3728813559322, "percentage": 99.59, "elapsed_time": "9:00:21", "remaining_time": "0:02:14", "throughput": 2020.65, "total_tokens": 65513184}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.998645366382834e-09, "epoch": 193.39709443099272, "percentage": 99.6, "elapsed_time": "9:00:25", "remaining_time": "0:02:10", "throughput": 2020.67, "total_tokens": 65521408}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.876435062897475e-09, "epoch": 193.42130750605327, "percentage": 99.61, "elapsed_time": "9:00:29", "remaining_time": "0:02:06", "throughput": 2020.68, "total_tokens": 65529536}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.758079784211497e-09, "epoch": 193.4455205811138, "percentage": 99.62, "elapsed_time": "9:00:33", "remaining_time": "0:02:02", "throughput": 2020.69, "total_tokens": 65537728}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 1.6435795485797434e-09, "epoch": 193.46973365617433, "percentage": 99.64, "elapsed_time": "9:00:37", "remaining_time": "0:01:58", "throughput": 2020.7, "total_tokens": 65545792}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 1.5329343736547596e-09, "epoch": 193.49394673123487, "percentage": 99.65, "elapsed_time": "9:00:41", "remaining_time": "0:01:53", "throughput": 2020.72, "total_tokens": 65554272}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 1.4261442765006739e-09, "epoch": 193.5181598062954, "percentage": 99.66, "elapsed_time": "9:00:44", "remaining_time": "0:01:49", "throughput": 2020.73, "total_tokens": 65562496}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 1.3232092735876445e-09, "epoch": 193.54237288135593, "percentage": 99.67, "elapsed_time": "9:00:48", "remaining_time": "0:01:45", "throughput": 2020.74, "total_tokens": 65570688}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 1.2241293807918607e-09, "epoch": 193.56658595641647, "percentage": 99.69, "elapsed_time": "9:00:52", "remaining_time": "0:01:41", "throughput": 2020.76, "total_tokens": 65579008}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 1.128904613387216e-09, "epoch": 193.590799031477, "percentage": 99.7, "elapsed_time": "9:00:56", "remaining_time": "0:01:37", "throughput": 2020.77, "total_tokens": 65587040}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 1.0375349860591853e-09, "epoch": 193.61501210653753, "percentage": 99.71, "elapsed_time": "9:01:00", "remaining_time": "0:01:33", "throughput": 2020.78, "total_tokens": 65595232}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 9.5002051290205e-10, "epoch": 193.63922518159805, "percentage": 99.72, "elapsed_time": "9:01:04", "remaining_time": "0:01:29", "throughput": 2020.79, "total_tokens": 65603328}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 8.663612074077954e-10, "epoch": 193.6634382566586, "percentage": 99.74, "elapsed_time": "9:01:08", "remaining_time": "0:01:25", "throughput": 2020.8, "total_tokens": 65611488}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 7.865570824799884e-10, "epoch": 193.68765133171914, "percentage": 99.75, "elapsed_time": "9:01:11", "remaining_time": "0:01:21", "throughput": 2020.82, "total_tokens": 65619840}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 7.106081504254514e-10, "epoch": 193.71186440677965, "percentage": 99.76, "elapsed_time": "9:01:15", "remaining_time": "0:01:17", "throughput": 2020.83, "total_tokens": 65628128}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 6.385144229570372e-10, "epoch": 193.7360774818402, "percentage": 99.78, "elapsed_time": "9:01:19", "remaining_time": "0:01:13", "throughput": 2020.84, "total_tokens": 65636256}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 5.70275911190854e-10, "epoch": 193.7602905569007, "percentage": 99.79, "elapsed_time": "9:01:23", "remaining_time": "0:01:09", "throughput": 2020.85, "total_tokens": 65644224}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 5.058926256490403e-10, "epoch": 193.78450363196126, "percentage": 99.8, "elapsed_time": "9:01:27", "remaining_time": "0:01:05", "throughput": 2020.86, "total_tokens": 65652224}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 4.4536457626254134e-10, "epoch": 193.8087167070218, "percentage": 99.81, "elapsed_time": "9:01:31", "remaining_time": "0:01:01", "throughput": 2020.87, "total_tokens": 65660416}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 3.88691772365557e-10, "epoch": 193.83292978208232, "percentage": 99.83, "elapsed_time": "9:01:35", "remaining_time": "0:00:56", "throughput": 2020.89, "total_tokens": 65668832}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 3.358742226955425e-10, "epoch": 193.85714285714286, "percentage": 99.84, "elapsed_time": "9:01:38", "remaining_time": "0:00:52", "throughput": 2020.9, "total_tokens": 65677120}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 2.8691193539875925e-10, "epoch": 193.88135593220338, "percentage": 99.85, "elapsed_time": "9:01:42", "remaining_time": "0:00:48", "throughput": 2020.91, "total_tokens": 65685184}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 2.418049180274995e-10, "epoch": 193.90556900726392, "percentage": 99.86, "elapsed_time": "9:01:46", "remaining_time": "0:00:44", "throughput": 2020.93, "total_tokens": 65693664}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 2.005531775373104e-10, "epoch": 193.92978208232446, "percentage": 99.88, "elapsed_time": "9:01:50", "remaining_time": "0:00:40", "throughput": 2020.94, "total_tokens": 65701888}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 1.6315672028699435e-10, "epoch": 193.95399515738498, "percentage": 99.89, "elapsed_time": "9:01:54", "remaining_time": "0:00:36", "throughput": 2020.95, "total_tokens": 65710048}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.0, "lr": 1.2961555204693555e-10, "epoch": 193.97820823244552, "percentage": 99.9, "elapsed_time": "9:01:58", "remaining_time": "0:00:32", "throughput": 2020.97, "total_tokens": 65718400}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 9.992967798799768e-11, "epoch": 194.0048426150121, "percentage": 99.91, "elapsed_time": "9:02:02", "remaining_time": "0:00:28", "throughput": 2020.95, "total_tokens": 65726784}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 7.409910268707521e-11, "epoch": 194.02905569007265, "percentage": 99.92, "elapsed_time": "9:02:06", "remaining_time": "0:00:24", "throughput": 2020.96, "total_tokens": 65734848}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 5.212383012986877e-11, "epoch": 194.05326876513317, "percentage": 99.94, "elapsed_time": "9:02:10", "remaining_time": "0:00:20", "throughput": 2020.97, "total_tokens": 65743104}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 3.400386370533415e-11, "epoch": 194.0774818401937, "percentage": 99.95, "elapsed_time": "9:02:14", "remaining_time": "0:00:16", "throughput": 2020.99, "total_tokens": 65751328}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.9739206205682258e-11, "epoch": 194.10169491525423, "percentage": 99.96, "elapsed_time": "9:02:18", "remaining_time": "0:00:12", "throughput": 2021.0, "total_tokens": 65759488}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 9.329859829154685e-12, "epoch": 194.12590799031477, "percentage": 99.98, "elapsed_time": "9:02:21", "remaining_time": "0:00:08", "throughput": 2021.01, "total_tokens": 65767552}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 2.7758261855748148e-12, "epoch": 194.15012106537532, "percentage": 99.99, "elapsed_time": "9:02:25", "remaining_time": "0:00:04", "throughput": 2021.02, "total_tokens": 65775744}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 7.710628524559838e-14, "epoch": 194.17433414043583, "percentage": 100.0, "elapsed_time": "9:02:29", "remaining_time": "0:00:00", "throughput": 2021.04, "total_tokens": 65784064}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.7646282315254211, "epoch": 194.17433414043583, "percentage": 100.0, "elapsed_time": "9:02:35", "remaining_time": "0:00:00", "throughput": 2020.7, "total_tokens": 65784064}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 194.17433414043583, "percentage": 100.0, "elapsed_time": "9:02:36", "remaining_time": "0:00:00", "throughput": 2020.59, "total_tokens": 65784064}
|