Upload folder using huggingface_hub
Browse files- action_decoder/chain/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/latest_checkpoint.txt +1 -1
- action_decoder/chain/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/model/iter_000001000.pt +3 -0
- action_decoder/chain/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/optim/iter_000001000.pt +3 -0
- action_decoder/chain/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/scheduler/iter_000001000.pt +3 -0
- action_decoder/chain/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/trainer/iter_000001000.pt +3 -0
- action_decoder/chain/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/stdout.log +20 -0
action_decoder/chain/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/latest_checkpoint.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
iter_000001000.pt
|
action_decoder/chain/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/model/iter_000001000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b4e4b07d9a3c757289357e3b41e0ae71e62360ce04974eefead29a53e1498f8
|
| 3 |
+
size 161817668
|
action_decoder/chain/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/optim/iter_000001000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:822d754b45942f93a39ee002b70f5b4590b70c72a0fdc8790a0b2e4cc2914345
|
| 3 |
+
size 647025631
|
action_decoder/chain/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/scheduler/iter_000001000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47a6bae9e822d2753aee6b0b62d6f98bb46ade9ec4e41da26490e0201d09c172
|
| 3 |
+
size 1602
|
action_decoder/chain/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/trainer/iter_000001000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42a8eb54f575f232d4f03d7c9594005cb06ae9ffb4bc249977d1154493cfbf75
|
| 3 |
+
size 892
|
action_decoder/chain/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/stdout.log
CHANGED
|
@@ -182,3 +182,23 @@
|
|
| 182 |
[05-20 08:05:31|SUCCESS|cosmos_predict2/checkpointer.py:139:_save_worker_local] Saved checkpoint (local): checkpoints/vam/so101/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/trainer/iter_000000900.pt
|
| 183 |
[05-20 08:05:31|INFO|imaginaire/utils/misc.py:266:wrapper] Time spent on checkpoint saving (local): 0.0009 seconds
|
| 184 |
[05-20 08:05:31|INFO|imaginaire/trainer.py:388:validate] Validating at iteration 900...
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 182 |
[05-20 08:05:31|SUCCESS|cosmos_predict2/checkpointer.py:139:_save_worker_local] Saved checkpoint (local): checkpoints/vam/so101/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/trainer/iter_000000900.pt
|
| 183 |
[05-20 08:05:31|INFO|imaginaire/utils/misc.py:266:wrapper] Time spent on checkpoint saving (local): 0.0009 seconds
|
| 184 |
[05-20 08:05:31|INFO|imaginaire/trainer.py:388:validate] Validating at iteration 900...
|
| 185 |
+
[05-20 08:39:11|INFO|cosmos_predict2/callbacks/device_monitor.py:145:every_n_impl] DeviceMonitor Stats:
|
| 186 |
+
Avg Max Min
|
| 187 |
+
cpu_mem_gb 80.738853 84.667767 76.809940
|
| 188 |
+
peak_gpu_mem_gb 18.603743 18.610725 18.596760
|
| 189 |
+
peak_gpu_mem_reserved_gb 27.959961 27.978516 27.941406
|
| 190 |
+
nvml_used_gpu_mem_gb 29.467285 29.485840 29.448730
|
| 191 |
+
nvml_free_gpu_mem_gb 50.180176 50.198730 50.161621
|
| 192 |
+
temp 69.000000 72.000000 66.000000
|
| 193 |
+
power 337843.000000 338515.000000 337171.000000
|
| 194 |
+
util 97.500000 100.000000 95.000000
|
| 195 |
+
clock 1567.500000 1575.000000 1560.000000
|
| 196 |
+
[05-20 08:39:12|SUCCESS|cosmos_predict2/checkpointer.py:139:_save_worker_local] Saved checkpoint (local): checkpoints/vam/so101/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/model/iter_000001000.pt
|
| 197 |
+
[05-20 08:39:12|INFO|imaginaire/utils/misc.py:266:wrapper] Time spent on checkpoint saving (local): 0.1491 seconds
|
| 198 |
+
[05-20 08:39:13|SUCCESS|cosmos_predict2/checkpointer.py:139:_save_worker_local] Saved checkpoint (local): checkpoints/vam/so101/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/optim/iter_000001000.pt
|
| 199 |
+
[05-20 08:39:13|INFO|imaginaire/utils/misc.py:266:wrapper] Time spent on checkpoint saving (local): 0.5753 seconds
|
| 200 |
+
[05-20 08:39:13|SUCCESS|cosmos_predict2/checkpointer.py:139:_save_worker_local] Saved checkpoint (local): checkpoints/vam/so101/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/scheduler/iter_000001000.pt
|
| 201 |
+
[05-20 08:39:13|INFO|imaginaire/utils/misc.py:266:wrapper] Time spent on checkpoint saving (local): 0.0014 seconds
|
| 202 |
+
[05-20 08:39:13|SUCCESS|cosmos_predict2/checkpointer.py:139:_save_worker_local] Saved checkpoint (local): checkpoints/vam/so101/w2a_so101_task2_slow_136ep_lora32_iter2500_75m_2gpu/checkpoints/trainer/iter_000001000.pt
|
| 203 |
+
[05-20 08:39:13|INFO|imaginaire/utils/misc.py:266:wrapper] Time spent on checkpoint saving (local): 0.0015 seconds
|
| 204 |
+
[05-20 08:39:13|INFO|imaginaire/trainer.py:388:validate] Validating at iteration 1000...
|