Training in progress, step 696
Browse files- logs/amlt_code_runner.txt +13 -13
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- training_args.bin +1 -1
logs/amlt_code_runner.txt
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
-
2025-04-16 09:
|
2 |
-
2025-04-16 09:
|
3 |
-
2025-04-16 09:
|
4 |
-
2025-04-16 09:
|
5 |
-
2025-04-16 09:
|
6 |
-
2025-04-16 09:
|
7 |
-
2025-04-16 09:
|
8 |
-
2025-04-16 09:
|
9 |
-
2025-04-16 09:
|
10 |
-
2025-04-16 09:
|
11 |
-
2025-04-16 09:
|
12 |
-
2025-04-16 09:
|
13 |
-
2025-04-16 09:
|
|
|
1 |
+
2025-04-16 09:37:37,326:amlt-code-runner:INFO - SINGULARITY_LOCATION: centralus
|
2 |
+
2025-04-16 09:37:37,327:amlt-code-runner:INFO - AISC_INSTANCE_TYPE: Singularity.ND96_v4
|
3 |
+
2025-04-16 09:37:40,416:amlt-code-runner:INFO - Not removing AzureML's cd commands from /etc/profile due to an error: [Errno 13] Permission denied: '/etc/profile'
|
4 |
+
2025-04-16 09:37:40,416:amlt-code-runner:WARNING - Environment variable 'NCCL_SOCKET_IFNAME' already set to '=eth0', not changing to '^docker0,lo'
|
5 |
+
2025-04-16 09:37:40,416:amlt-code-runner:INFO - RANK = 0
|
6 |
+
2025-04-16 09:37:40,416:amlt-code-runner:INFO - LOCAL_RANK = None
|
7 |
+
2025-04-16 09:37:40,416:amlt-code-runner:INFO - WORLD_SIZE = 1
|
8 |
+
2025-04-16 09:37:40,416:amlt-code-runner:INFO - MASTER_ADDR = node-0
|
9 |
+
2025-04-16 09:37:40,416:amlt-code-runner:INFO - MASTER_PORT = 9500
|
10 |
+
2025-04-16 09:37:40,417:amlt-code-runner:WARNING - Installing amlt runtime dependencies: ['wrapt', 'azure-identity', 'python-dateutil', 'pytz'] into /tmp/amlt-user-base
|
11 |
+
2025-04-16 09:37:41,988:amlt-code-runner:INFO - Executing ./amlt_setup.sh, ./amlt_run.sh
|
12 |
+
2025-04-16 09:37:42,061:background_dirsync:INFO - Starting directory syncer from '/scratch/amlt_code/outputs' to '/mnt/output/projects/amlt_project/amlt-results/7255445584.54456-fd6f9646-57d9-4aae-9985-e79f5f6e9d15', every 30.000000s
|
13 |
+
2025-04-16 09:37:42,064:background_dirsync:INFO - Starting directory syncer from '/scratch/azureml/cr/j/9e4869b65a3d443b986070748b2b821d/exe/wd/logs' to '/scratch/amlt_code/outputs/logs', every 30.000000s
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1953ee06b177965fccca1a71b974e867224711366ae35e6248c8c5439ad633d8
|
3 |
size 4943162336
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cd66ee6396a7edd5a67238f4fa5bcd5a1b4887b7359211a222dc924d058ffe8
|
3 |
size 4999819336
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53c6b5a2d1e853edc08ce727925578fc83e60e4a397d6998b428ed2decb5ec16
|
3 |
size 4540516344
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7736
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b8a0c91643e25dc49e84a98435c6cc575963630214c01b46eeb33dff405d0c4
|
3 |
size 7736
|