Training in progress, step 15
Browse files- logs/amlt_code_runner.txt +20 -20
- 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
|
@@ -1,21 +1,21 @@
|
|
| 1 |
-
2025-04-
|
| 2 |
-
2025-04-
|
| 3 |
-
2025-04-
|
| 4 |
-
2025-04-
|
| 5 |
-
2025-04-
|
| 6 |
-
2025-04-
|
| 7 |
-
2025-04-
|
| 8 |
-
2025-04-
|
| 9 |
-
2025-04-
|
| 10 |
-
2025-04-
|
| 11 |
-
2025-04-
|
| 12 |
-
2025-04-
|
| 13 |
-
2025-04-
|
| 14 |
-
2025-04-
|
| 15 |
-
2025-04-
|
| 16 |
|
| 17 |
-
2025-04-
|
| 18 |
-
2025-04-
|
| 19 |
-
2025-04-
|
| 20 |
-
2025-04-
|
| 21 |
-
2025-04-
|
|
|
|
| 1 |
+
2025-04-10 18:35:34,106:amlt-code-runner:INFO - SINGULARITY_LOCATION: centralus
|
| 2 |
+
2025-04-10 18:35:34,106:amlt-code-runner:INFO - AISC_INSTANCE_TYPE: Singularity.ND96_v4
|
| 3 |
+
2025-04-10 18:35:37,221:amlt-code-runner:INFO - Not removing AzureML's cd commands from /etc/profile due to an error: [Errno 13] Permission denied: '/etc/profile'
|
| 4 |
+
2025-04-10 18:35:37,221:amlt-code-runner:WARNING - Environment variable 'NCCL_SOCKET_IFNAME' already set to '=eth0', not changing to '^docker0,lo'
|
| 5 |
+
2025-04-10 18:35:37,221:amlt-code-runner:INFO - RANK = 0
|
| 6 |
+
2025-04-10 18:35:37,221:amlt-code-runner:INFO - LOCAL_RANK = None
|
| 7 |
+
2025-04-10 18:35:37,221:amlt-code-runner:INFO - WORLD_SIZE = 1
|
| 8 |
+
2025-04-10 18:35:37,221:amlt-code-runner:INFO - MASTER_ADDR = node-0
|
| 9 |
+
2025-04-10 18:35:37,221:amlt-code-runner:INFO - MASTER_PORT = 9500
|
| 10 |
+
2025-04-10 18:35:37,223:amlt-code-runner:WARNING - Installing amlt runtime dependencies: ['wrapt', 'azure-identity', 'python-dateutil', 'pytz'] into /tmp/amlt-user-base
|
| 11 |
+
2025-04-10 18:35:38,792:amlt-code-runner:INFO - Setting WANDB_RUN_ID to 'sincere_feast_96p6v4qzfp_42'
|
| 12 |
+
2025-04-10 18:35:38,792:amlt-code-runner:INFO - Expanding HyperDrive arguments into /tmp/amlt_run_hd.sh
|
| 13 |
+
2025-04-10 18:35:39,132:amlt-code-runner:INFO - Parsing tracking uri /mlflow/v1.0/subscriptions/bbd59374-b76d-4cb5-88b6-2be35debc7cf/resourceGroups/jordan/providers/Microsoft.MachineLearningServices/workspaces/jordanws
|
| 14 |
+
2025-04-10 18:35:39,132:amlt-code-runner:INFO - Tracking uri /mlflow/v1.0/subscriptions/bbd59374-b76d-4cb5-88b6-2be35debc7cf/resourceGroups/jordan/providers/Microsoft.MachineLearningServices/workspaces/jordanws has sub id bbd59374-b76d-4cb5-88b6-2be35debc7cf, resource group jordan, and workspace jordanws
|
| 15 |
+
2025-04-10 18:35:39,132:aml_token_auth:WARNING - The AzureMLTokenAuthentication created will not be updated due to missing params. The token expires on 2025-04-30 23:33:23.
|
| 16 |
|
| 17 |
+
2025-04-10 18:35:39,134:urllib3.connectionpool:DEBUG - Starting new HTTPS connection (1): eastus.api.azureml.ms:443
|
| 18 |
+
2025-04-10 18:35:39,637:urllib3.connectionpool:DEBUG - https://eastus.api.azureml.ms:443 "POST /mlflow/v1.0/subscriptions/bbd59374-b76d-4cb5-88b6-2be35debc7cf/resourceGroups/jordan/providers/Microsoft.MachineLearningServices/workspaces/jordanws/api/2.0/mlflow/runs/set-tag HTTP/11" 200 3
|
| 19 |
+
2025-04-10 18:35:39,661:amlt-code-runner:INFO - Executing ./amlt_setup.sh, /tmp/amlt_run_hd.sh
|
| 20 |
+
2025-04-10 18:35:39,729:background_dirsync:INFO - Starting directory syncer from '/scratch/amlt_code/outputs' to '/mnt/output/projects/amlt_project/amlt-results/sincere_feast_96p6v4qzfp_42', every 30.000000s
|
| 21 |
+
2025-04-10 18:35:39,732:background_dirsync:INFO - Starting directory syncer from '/scratch/azureml/cr/j/230a37106d5d4302b2cbbe1ec95a1d61/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 sha256:94fe3f869065adb553bc26063f5557a8299f2aaaa838804d7ae91cecc48e5350
|
| 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 sha256:85b0ee74fa9995387bf4e4f160f8453281a09059775bf5fc906dccd23717c058
|
| 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 sha256:7e6a8bcf798f939695e045e6822cbf5f82ce8027b269bc8619283bd31f558967
|
| 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 sha256:877493711e5c89898b644c5efa347531ba04a127c15b73f761565f75873c002c
|
| 3 |
size 7736
|