Upload folder using huggingface_hub
Browse files- action_decoder/chain/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/latest_checkpoint.txt +1 -1
- action_decoder/chain/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/model/iter_000002000.pt +3 -0
- action_decoder/chain/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/optim/iter_000002000.pt +3 -0
- action_decoder/chain/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/scheduler/iter_000002000.pt +3 -0
- action_decoder/chain/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/trainer/iter_000002000.pt +3 -0
- action_decoder/chain/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/stdout.log +21 -0
action_decoder/chain/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/latest_checkpoint.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
iter_000002000.pt
|
action_decoder/chain/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/model/iter_000002000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a8ed06f74357d67524d7c3a3b8e7e24aab7a3d964175ab8357a22e2b174f9ea
|
| 3 |
+
size 161817668
|
action_decoder/chain/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/optim/iter_000002000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68bf666d0fcbdb77340df2a380d6713bfdf7d78809d1cdb7b3f785dca4deb024
|
| 3 |
+
size 647025631
|
action_decoder/chain/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/scheduler/iter_000002000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca84df360cf96ab61e97368db93153f62818e5e02cde160fd6b3ee325627dbf2
|
| 3 |
+
size 1602
|
action_decoder/chain/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/trainer/iter_000002000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2b3774816544e78e539e7d51e64b43a30c795a2947d1fe5a7dbd70c48e434f7
|
| 3 |
+
size 892
|
action_decoder/chain/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/stdout.log
CHANGED
|
@@ -283,3 +283,24 @@ clock 1687.500000 1740.000000 1635.000000
|
|
| 283 |
[05-21 04:11:24|SUCCESS|cosmos_predict2/checkpointer.py:139:_save_worker_local] Saved checkpoint (local): checkpoints/vam/so101/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/trainer/iter_000001900.pt
|
| 284 |
[05-21 04:11:24|INFO|imaginaire/utils/misc.py:266:wrapper] Time spent on checkpoint saving (local): 0.0030 seconds
|
| 285 |
[05-21 04:11:25|INFO|imaginaire/trainer.py:388:validate] Validating at iteration 1900...
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 283 |
[05-21 04:11:24|SUCCESS|cosmos_predict2/checkpointer.py:139:_save_worker_local] Saved checkpoint (local): checkpoints/vam/so101/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/trainer/iter_000001900.pt
|
| 284 |
[05-21 04:11:24|INFO|imaginaire/utils/misc.py:266:wrapper] Time spent on checkpoint saving (local): 0.0030 seconds
|
| 285 |
[05-21 04:11:25|INFO|imaginaire/trainer.py:388:validate] Validating at iteration 1900...
|
| 286 |
+
[05-21 04:41:23|INFO|cosmos_predict2/callbacks/iter_speed.py:80:every_n_impl] 2000 : iter_speed 18.02 seconds per iteration | Loss: 1.5123
|
| 287 |
+
[05-21 04:41:23|INFO|cosmos_predict2/callbacks/device_monitor.py:145:every_n_impl] DeviceMonitor Stats:
|
| 288 |
+
Avg Max Min
|
| 289 |
+
cpu_mem_gb 67.468443 67.684208 67.252678
|
| 290 |
+
peak_gpu_mem_gb 18.604917 18.609647 18.600186
|
| 291 |
+
peak_gpu_mem_reserved_gb 28.161133 28.279297 28.042969
|
| 292 |
+
nvml_used_gpu_mem_gb 30.919250 31.037415 30.801086
|
| 293 |
+
nvml_free_gpu_mem_gb 62.664734 62.782898 62.546570
|
| 294 |
+
temp 72.500000 73.000000 72.000000
|
| 295 |
+
power 381152.500000 381569.000000 380736.000000
|
| 296 |
+
util 97.000000 100.000000 94.000000
|
| 297 |
+
clock 1710.000000 1755.000000 1665.000000
|
| 298 |
+
[05-21 04:41:24|SUCCESS|cosmos_predict2/checkpointer.py:139:_save_worker_local] Saved checkpoint (local): checkpoints/vam/so101/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/model/iter_000002000.pt
|
| 299 |
+
[05-21 04:41:24|INFO|imaginaire/utils/misc.py:266:wrapper] Time spent on checkpoint saving (local): 0.1482 seconds
|
| 300 |
+
[05-21 04:41:25|SUCCESS|cosmos_predict2/checkpointer.py:139:_save_worker_local] Saved checkpoint (local): checkpoints/vam/so101/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/optim/iter_000002000.pt
|
| 301 |
+
[05-21 04:41:25|INFO|imaginaire/utils/misc.py:266:wrapper] Time spent on checkpoint saving (local): 0.6196 seconds
|
| 302 |
+
[05-21 04:41:25|SUCCESS|cosmos_predict2/checkpointer.py:139:_save_worker_local] Saved checkpoint (local): checkpoints/vam/so101/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/scheduler/iter_000002000.pt
|
| 303 |
+
[05-21 04:41:25|INFO|imaginaire/utils/misc.py:266:wrapper] Time spent on checkpoint saving (local): 0.0026 seconds
|
| 304 |
+
[05-21 04:41:25|SUCCESS|cosmos_predict2/checkpointer.py:139:_save_worker_local] Saved checkpoint (local): checkpoints/vam/so101/w2a_so101_task3_1_103ep_lora32_iter2500_75m_2gpu/checkpoints/trainer/iter_000002000.pt
|
| 305 |
+
[05-21 04:41:25|INFO|imaginaire/utils/misc.py:266:wrapper] Time spent on checkpoint saving (local): 0.0026 seconds
|
| 306 |
+
[05-21 04:41:25|INFO|imaginaire/trainer.py:388:validate] Validating at iteration 2000...
|