Training in progress, step 40000
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:aef1274a14d7a28396277a0c72cd56ebf6fd54a2bbdf51db7df354050f7306b4
|
| 3 |
size 58745928
|
trainer_log.jsonl
CHANGED
|
@@ -8158,3 +8158,44 @@
|
|
| 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}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 2.8128616110761898e-09, "epoch": 442.3333333333333, "percentage": 99.52, "elapsed_time": "4:31:21", "remaining_time": "0:01:17", "throughput": 685.01, "total_tokens": 11153232}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 2.6675215753724223e-09, "epoch": 442.3888888888889, "percentage": 99.54, "elapsed_time": "4:31:23", "remaining_time": "0:01:15", "throughput": 685.01, "total_tokens": 11154624}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 2.5260364424739557e-09, "epoch": 442.44444444444446, "percentage": 99.55, "elapsed_time": "4:31:25", "remaining_time": "0:01:13", "throughput": 685.01, "total_tokens": 11156016}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 2.3884062341994475e-09, "epoch": 442.5, "percentage": 99.56, "elapsed_time": "4:31:27", "remaining_time": "0:01:11", "throughput": 685.02, "total_tokens": 11157392}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 2.25463097177081e-09, "epoch": 442.55555555555554, "percentage": 99.58, "elapsed_time": "4:31:29", "remaining_time": "0:01:09", "throughput": 685.02, "total_tokens": 11158704}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 2.1247106758215397e-09, "epoch": 442.6111111111111, "percentage": 99.59, "elapsed_time": "4:31:31", "remaining_time": "0:01:07", "throughput": 685.02, "total_tokens": 11160112}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.998645366382834e-09, "epoch": 442.6666666666667, "percentage": 99.6, "elapsed_time": "4:31:33", "remaining_time": "0:01:05", "throughput": 685.03, "total_tokens": 11161520}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.876435062897475e-09, "epoch": 442.72222222222223, "percentage": 99.61, "elapsed_time": "4:31:35", "remaining_time": "0:01:03", "throughput": 685.03, "total_tokens": 11162912}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.758079784211497e-09, "epoch": 442.77777777777777, "percentage": 99.62, "elapsed_time": "4:31:37", "remaining_time": "0:01:01", "throughput": 685.04, "total_tokens": 11164320}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 1.6435795485797434e-09, "epoch": 442.8333333333333, "percentage": 99.64, "elapsed_time": "4:31:39", "remaining_time": "0:00:59", "throughput": 685.04, "total_tokens": 11165712}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 1.5329343736547596e-09, "epoch": 442.8888888888889, "percentage": 99.65, "elapsed_time": "4:31:41", "remaining_time": "0:00:57", "throughput": 685.05, "total_tokens": 11167168}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 1.4261442765006739e-09, "epoch": 442.94444444444446, "percentage": 99.66, "elapsed_time": "4:31:43", "remaining_time": "0:00:55", "throughput": 685.06, "total_tokens": 11168608}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 1.3232092735876445e-09, "epoch": 443.0, "percentage": 99.67, "elapsed_time": "4:31:45", "remaining_time": "0:00:53", "throughput": 685.05, "total_tokens": 11170064}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 1.2241293807918607e-09, "epoch": 443.05555555555554, "percentage": 99.69, "elapsed_time": "4:31:47", "remaining_time": "0:00:51", "throughput": 685.05, "total_tokens": 11171456}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 1.128904613387216e-09, "epoch": 443.1111111111111, "percentage": 99.7, "elapsed_time": "4:31:49", "remaining_time": "0:00:49", "throughput": 685.05, "total_tokens": 11172832}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 1.0375349860591853e-09, "epoch": 443.1666666666667, "percentage": 99.71, "elapsed_time": "4:31:51", "remaining_time": "0:00:47", "throughput": 685.06, "total_tokens": 11174288}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 9.5002051290205e-10, "epoch": 443.22222222222223, "percentage": 99.72, "elapsed_time": "4:31:53", "remaining_time": "0:00:44", "throughput": 685.06, "total_tokens": 11175664}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 8.663612074077954e-10, "epoch": 443.27777777777777, "percentage": 99.74, "elapsed_time": "4:31:55", "remaining_time": "0:00:42", "throughput": 685.07, "total_tokens": 11177056}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 7.865570824799884e-10, "epoch": 443.3333333333333, "percentage": 99.75, "elapsed_time": "4:31:57", "remaining_time": "0:00:40", "throughput": 685.07, "total_tokens": 11178480}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 7.106081504254514e-10, "epoch": 443.3888888888889, "percentage": 99.76, "elapsed_time": "4:31:59", "remaining_time": "0:00:38", "throughput": 685.07, "total_tokens": 11179856}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 6.385144229570372e-10, "epoch": 443.44444444444446, "percentage": 99.78, "elapsed_time": "4:32:01", "remaining_time": "0:00:36", "throughput": 685.08, "total_tokens": 11181264}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 5.70275911190854e-10, "epoch": 443.5, "percentage": 99.79, "elapsed_time": "4:32:03", "remaining_time": "0:00:34", "throughput": 685.08, "total_tokens": 11182624}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 5.058926256490403e-10, "epoch": 443.55555555555554, "percentage": 99.8, "elapsed_time": "4:32:05", "remaining_time": "0:00:32", "throughput": 685.09, "total_tokens": 11184032}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 4.4536457626254134e-10, "epoch": 443.6111111111111, "percentage": 99.81, "elapsed_time": "4:32:06", "remaining_time": "0:00:30", "throughput": 685.09, "total_tokens": 11185440}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 3.88691772365557e-10, "epoch": 443.6666666666667, "percentage": 99.83, "elapsed_time": "4:32:08", "remaining_time": "0:00:28", "throughput": 685.09, "total_tokens": 11186816}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 3.358742226955425e-10, "epoch": 443.72222222222223, "percentage": 99.84, "elapsed_time": "4:32:10", "remaining_time": "0:00:26", "throughput": 685.1, "total_tokens": 11188224}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 2.8691193539875925e-10, "epoch": 443.77777777777777, "percentage": 99.85, "elapsed_time": "4:32:12", "remaining_time": "0:00:24", "throughput": 685.11, "total_tokens": 11189664}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 2.418049180274995e-10, "epoch": 443.8333333333333, "percentage": 99.86, "elapsed_time": "4:32:14", "remaining_time": "0:00:22", "throughput": 685.11, "total_tokens": 11191072}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 2.005531775373104e-10, "epoch": 443.8888888888889, "percentage": 99.88, "elapsed_time": "4:32:16", "remaining_time": "0:00:20", "throughput": 685.12, "total_tokens": 11192480}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 1.6315672028699435e-10, "epoch": 443.94444444444446, "percentage": 99.89, "elapsed_time": "4:32:18", "remaining_time": "0:00:18", "throughput": 685.12, "total_tokens": 11193888}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.0, "lr": 1.2961555204693555e-10, "epoch": 444.0, "percentage": 99.9, "elapsed_time": "4:32:20", "remaining_time": "0:00:16", "throughput": 685.12, "total_tokens": 11195264}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 9.992967798799768e-11, "epoch": 444.05555555555554, "percentage": 99.91, "elapsed_time": "4:32:22", "remaining_time": "0:00:14", "throughput": 685.11, "total_tokens": 11196624}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 7.409910268707521e-11, "epoch": 444.1111111111111, "percentage": 99.92, "elapsed_time": "4:32:24", "remaining_time": "0:00:12", "throughput": 685.11, "total_tokens": 11198016}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 5.212383012986877e-11, "epoch": 444.1666666666667, "percentage": 99.94, "elapsed_time": "4:32:26", "remaining_time": "0:00:10", "throughput": 685.12, "total_tokens": 11199440}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 3.400386370533415e-11, "epoch": 444.22222222222223, "percentage": 99.95, "elapsed_time": "4:32:28", "remaining_time": "0:00:08", "throughput": 685.12, "total_tokens": 11200880}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.9739206205682258e-11, "epoch": 444.27777777777777, "percentage": 99.96, "elapsed_time": "4:32:30", "remaining_time": "0:00:06", "throughput": 685.13, "total_tokens": 11202304}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 9.329859829154685e-12, "epoch": 444.3333333333333, "percentage": 99.98, "elapsed_time": "4:32:32", "remaining_time": "0:00:04", "throughput": 685.13, "total_tokens": 11203696}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 2.7758261855748148e-12, "epoch": 444.3888888888889, "percentage": 99.99, "elapsed_time": "4:32:34", "remaining_time": "0:00:02", "throughput": 685.14, "total_tokens": 11205088}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 7.710628524559838e-14, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "4:32:36", "remaining_time": "0:00:00", "throughput": 685.14, "total_tokens": 11206480}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.33738812804222107, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "4:32:37", "remaining_time": "0:00:00", "throughput": 685.09, "total_tokens": 11206480}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "4:32:39", "remaining_time": "0:00:00", "throughput": 685.03, "total_tokens": 11206480}
|