Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-exp-grpo-cp312-36146-v23-mkmlizer
Waiting for job on chaiml-exp-grpo-cp312-36146-v23-mkmlizer to finish
HTTP Request: %s %s "%s %d %s"
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Version: 0.30.2 ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ https://mk1.ai ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ belonging to: ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Chai Research Corp. ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_japas_2025-08-29: ('http://guanaco-model-mesh-load-balancer.model-mesh.k2.chaiverse.com/models/chaiml-nitral-dpos1-beta_5231_v4/predict', '{"detail":"1 validation error for RuntimeResponse\\npredictions\\n Field required [type=missing, input_value={\'detail\': \\"SamplingConfi...ment \'max_input_token\'\\"}, input_type=dict]\\n For further information visit https://errors.pydantic.dev/2.11/v/missing"}')
Failed to get response for submission blend_rurun_2025-08-28: ('http://guanaco-model-mesh-load-balancer.model-mesh.k2.chaiverse.com/models/chaiml-nitral-dpos1-beta_5231_v4/predict', '{"detail":"1 validation error for RuntimeResponse\\npredictions\\n Field required [type=missing, input_value={\'detail\': \\"SamplingConfi...ment \'max_input_token\'\\"}, input_type=dict]\\n For further information visit https://errors.pydantic.dev/2.11/v/missing"}')
Failed to get response for submission chaiml-nis-sft-24b-osmo_64694_v1: HTTPConnectionPool(host='chaiml-nis-sft-24b-osmo-64694-v1-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
Job chaiml-exp-grpo-cp312-36146-v23-mkmlizer completed after 1004.71s with status: failed
Stopping job with name chaiml-exp-grpo-cp312-36146-v23-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-exp-grpo-cp312-36146-v23-mkmlizer
Waiting for job on chaiml-exp-grpo-cp312-36146-v23-mkmlizer to finish
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Version: 0.30.2 ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ https://mk1.ai ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ belonging to: ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Chai Research Corp. ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: Downloaded to shared memory in 65.725s
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: Checking if ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged already exists in ChaiML
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpewe0st84, device:0
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: Saving flywheel model at /dev/shm/model_cache
HTTP Request: %s %s "%s %d %s"
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: quantized model in 294.450s
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: Processed model ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged in 360.176s
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/nvidia
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/nvidia/config.json
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/nvidia/special_tokens_map.json
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/nvidia/tokenizer_config.json
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/nvidia/tokenizer.json
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/nvidia/flywheel_model.1.safetensors
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/nvidia/flywheel_model.0.safetensors
chaiml-exp-grpo-cp312-36146-v23-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 3/363 [00:02<05:06, 1.18it/s]
Loading 0: 1%| | 4/363 [00:04<07:19, 1.22s/it]
Loading 0: 1%|▏ | 5/363 [00:06<08:56, 1.50s/it]
Loading 0: 2%|▏ | 8/363 [00:06<04:08, 1.43it/s]
Loading 0: 2%|▏ | 9/363 [00:07<03:36, 1.63it/s]
Loading 0: 3%|▎ | 10/363 [00:07<02:55, 2.01it/s]
Loading 0: 3%|▎ | 11/363 [00:07<02:34, 2.28it/s]
Loading 0: 3%|▎ | 12/363 [00:07<02:07, 2.75it/s]
Loading 0: 4%|▎ | 13/363 [00:09<04:46, 1.22it/s]
Loading 0: 4%|▍ | 14/363 [00:11<06:43, 1.15s/it]
Loading 0: 4%|▍ | 15/363 [00:13<08:15, 1.43s/it]
Loading 0: 5%|▍ | 18/363 [00:14<04:00, 1.43it/s]
Loading 0: 5%|▌ | 19/363 [00:14<03:19, 1.72it/s]
Loading 0: 6%|▌ | 21/363 [00:16<04:13, 1.35it/s]
Loading 0: 6%|▌ | 22/363 [00:18<05:44, 1.01s/it]
Loading 0: 6%|▋ | 23/363 [00:20<07:08, 1.26s/it]
Loading 0: 7%|▋ | 26/363 [00:20<03:50, 1.46it/s]
Loading 0: 7%|▋ | 27/363 [00:21<03:22, 1.66it/s]
Loading 0: 8%|▊ | 28/363 [00:21<02:46, 2.01it/s]
Loading 0: 8%|▊ | 30/363 [00:21<02:02, 2.72it/s]
Loading 0: 9%|▊ | 31/363 [00:21<01:54, 2.91it/s]
Loading 0: 9%|▉ | 32/363 [00:21<01:36, 3.43it/s]
Loading 0: 9%|▉ | 33/363 [00:22<01:22, 3.99it/s]
Loading 0: 9%|▉ | 34/363 [00:24<03:55, 1.40it/s]
Loading 0: 10%|▉ | 35/363 [00:26<05:51, 1.07s/it]
Loading 0: 10%|▉ | 36/363 [00:28<07:24, 1.36s/it]
Loading 0: 11%|█ | 39/363 [00:30<05:18, 1.02it/s]
Loading 0: 11%|█ | 40/363 [00:32<06:26, 1.20s/it]
Loading 0: 11%|█▏ | 41/363 [00:34<07:30, 1.40s/it]
Loading 0: 12%|█▏ | 44/363 [00:34<04:01, 1.32it/s]
Loading 0: 12%|█▏ | 45/363 [00:34<03:30, 1.51it/s]
Loading 0: 13%|█▎ | 46/363 [00:34<02:52, 1.83it/s]
Loading 0: 13%|█▎ | 48/363 [00:35<02:05, 2.51it/s]
Loading 0: 13%|█▎ | 49/363 [00:35<01:55, 2.72it/s]
Loading 0: 14%|█▍ | 50/363 [00:35<01:37, 3.22it/s]
Loading 0: 14%|█▍ | 51/363 [00:35<01:22, 3.77it/s]
Loading 0: 14%|█▍ | 52/363 [00:37<03:45, 1.38it/s]
Loading 0: 15%|█▍ | 53/363 [00:39<05:33, 1.08s/it]
Loading 0: 15%|█▍ | 54/363 [00:41<06:58, 1.36s/it]
Loading 0: 16%|█▌ | 57/363 [00:43<05:01, 1.02it/s]
Loading 0: 16%|█▌ | 58/363 [00:45<06:04, 1.20s/it]
Loading 0: 16%|█▋ | 59/363 [00:47<07:05, 1.40s/it]
Loading 0: 17%|█▋ | 62/363 [00:48<03:49, 1.31it/s]
Loading 0: 17%|█▋ | 63/363 [00:48<03:19, 1.50it/s]
Loading 0: 18%|█▊ | 64/363 [00:48<02:44, 1.82it/s]
Loading 0: 18%|█▊ | 66/363 [00:48<01:58, 2.50it/s]
Loading 0: 18%|█▊ | 67/363 [00:49<01:49, 2.71it/s]
Loading 0: 19%|█▊ | 68/363 [00:49<01:31, 3.21it/s]
Loading 0: 19%|█▉ | 69/363 [00:49<01:18, 3.77it/s]
Loading 0: 19%|█▉ | 70/363 [00:51<03:33, 1.37it/s]
Loading 0: 20%|█▉ | 71/363 [00:53<05:14, 1.08s/it]
Loading 0: 20%|█▉ | 72/363 [00:55<06:36, 1.36s/it]
Loading 0: 21%|██ | 75/363 [00:57<04:44, 1.01it/s]
Loading 0: 21%|██ | 76/363 [00:59<05:43, 1.20s/it]
Loading 0: 21%|██ | 77/363 [01:01<06:39, 1.40s/it]
Loading 0: 22%|██▏ | 80/363 [01:02<03:35, 1.31it/s]
Loading 0: 22%|██▏ | 81/363 [01:02<03:07, 1.51it/s]
Loading 0: 23%|██▎ | 82/363 [01:02<02:33, 1.82it/s]
Loading 0: 23%|██▎ | 84/363 [01:02<01:51, 2.50it/s]
Loading 0: 23%|██▎ | 85/363 [01:03<01:42, 2.71it/s]
Loading 0: 24%|██▎ | 86/363 [01:03<01:25, 3.22it/s]
Loading 0: 24%|██▍ | 87/363 [01:03<01:13, 3.78it/s]
Loading 0: 24%|██▍ | 88/363 [01:05<03:19, 1.38it/s]
Loading 0: 25%|██▍ | 89/363 [01:07<04:54, 1.08s/it]
Loading 0: 25%|██▍ | 90/363 [01:09<06:11, 1.36s/it]
Loading 0: 26%|██▌ | 93/363 [01:09<03:02, 1.48it/s]
Loading 0: 26%|██▌ | 94/363 [01:09<02:37, 1.70it/s]
Loading 0: 26%|██▌ | 95/363 [01:10<02:08, 2.08it/s]
Loading 0: 27%|██▋ | 97/363 [01:10<01:33, 2.84it/s]
Loading 0: 27%|██▋ | 98/363 [01:10<01:27, 3.02it/s]
Loading 0: 27%|██▋ | 99/363 [01:10<01:13, 3.58it/s]
Loading 0: 28%|██▊ | 101/363 [01:12<02:30, 1.74it/s]
Loading 0: 28%|██▊ | 102/363 [01:14<03:53, 1.12it/s]
Loading 0: 28%|██▊ | 103/363 [01:16<05:08, 1.19s/it]
Loading 0: 29%|██▉ | 105/363 [01:16<03:07, 1.38it/s]
Loading 0: 29%|██▉ | 106/363 [01:18<04:21, 1.02s/it]
Loading 0: 29%|██▉ | 107/363 [01:20<05:22, 1.26s/it]
Loading 0: 30%|██▉ | 108/363 [01:23<06:15, 1.47s/it]
Loading 0: 31%|███ | 111/363 [01:25<04:25, 1.05s/it]
Loading 0: 31%|███ | 112/363 [01:27<05:12, 1.25s/it]
Loading 0: 31%|███ | 113/363 [01:29<05:58, 1.44s/it]
Loading 0: 32%|███▏ | 116/363 [01:29<03:14, 1.27it/s]
Loading 0: 32%|███▏ | 117/363 [01:29<02:48, 1.46it/s]
Loading 0: 33%|███▎ | 118/363 [01:29<02:18, 1.77it/s]
Loading 0: 33%|███▎ | 120/363 [01:30<01:39, 2.43it/s]
Loading 0: 33%|███▎ | 121/363 [01:30<01:31, 2.65it/s]
Loading 0: 34%|███▎ | 122/363 [01:30<01:16, 3.16it/s]
Loading 0: 34%|███▍ | 123/363 [01:30<01:04, 3.70it/s]
Loading 0: 34%|███▍ | 124/363 [01:32<02:54, 1.37it/s]
Loading 0: 34%|███▍ | 125/363 [01:34<04:17, 1.08s/it]
Loading 0: 35%|███▍ | 126/363 [01:36<05:22, 1.36s/it]
Loading 0: 36%|███▌ | 129/363 [01:38<03:51, 1.01it/s]
Loading 0: 36%|███▌ | 130/363 [01:40<04:39, 1.20s/it]
Loading 0: 36%|███▌ | 131/363 [01:42<05:24, 1.40s/it]
Loading 0: 37%|███▋ | 134/363 [01:43<02:54, 1.31it/s]
Loading 0: 37%|███▋ | 135/363 [01:43<02:31, 1.50it/s]
Loading 0: 37%|███▋ | 136/363 [01:43<02:04, 1.82it/s]
Loading 0: 38%|███▊ | 138/363 [01:43<01:30, 2.50it/s]
Loading 0: 38%|███▊ | 139/363 [01:44<01:22, 2.71it/s]
Loading 0: 39%|███▊ | 140/363 [01:44<01:09, 3.20it/s]
Loading 0: 39%|███▉ | 141/363 [01:44<00:59, 3.75it/s]
Loading 0: 39%|███▉ | 142/363 [01:46<02:40, 1.37it/s]
Loading 0: 39%|███▉ | 143/363 [01:48<03:57, 1.08s/it]
Loading 0: 40%|███▉ | 144/363 [01:50<04:58, 1.36s/it]
Loading 0: 40%|████ | 147/363 [01:52<03:33, 1.01it/s]
Loading 0: 41%|████ | 148/363 [01:54<04:17, 1.20s/it]
Loading 0: 41%|████ | 149/363 [01:56<04:58, 1.40s/it]
Loading 0: 42%|████▏ | 152/363 [01:57<02:40, 1.32it/s]
Loading 0: 42%|████▏ | 153/363 [01:57<02:19, 1.51it/s]
Loading 0: 42%|████▏ | 154/363 [01:57<01:54, 1.83it/s]
Loading 0: 43%|████▎ | 156/363 [01:57<01:22, 2.50it/s]
Loading 0: 43%|████▎ | 157/363 [01:57<01:15, 2.72it/s]
Loading 0: 44%|████▎ | 158/363 [01:58<01:03, 3.23it/s]
Loading 0: 44%|████▍ | 159/363 [01:58<00:54, 3.78it/s]
Loading 0: 44%|████▍ | 160/363 [02:00<02:27, 1.38it/s]
Loading 0: 44%|████▍ | 161/363 [02:02<03:37, 1.08s/it]
Loading 0: 45%|████▍ | 162/363 [02:04<04:32, 1.36s/it]
Loading 0: 45%|████▌ | 165/363 [02:06<03:14, 1.02it/s]
Loading 0: 46%|████▌ | 166/363 [02:08<03:55, 1.20s/it]
Loading 0: 46%|████▌ | 167/363 [02:10<04:33, 1.39s/it]
Loading 0: 47%|████▋ | 170/363 [02:10<02:26, 1.32it/s]
Loading 0: 47%|████▋ | 171/363 [02:10<02:07, 1.51it/s]
Loading 0: 47%|████▋ | 172/363 [02:11<01:44, 1.83it/s]
Loading 0: 48%|████▊ | 174/363 [02:11<01:15, 2.51it/s]
Loading 0: 48%|████▊ | 175/363 [02:11<01:09, 2.72it/s]
Loading 0: 48%|████▊ | 176/363 [02:11<00:57, 3.23it/s]
Loading 0: 49%|████▉ | 177/363 [02:11<00:49, 3.76it/s]
Loading 0: 49%|████▉ | 178/363 [02:13<02:14, 1.38it/s]
Loading 0: 49%|████▉ | 179/363 [02:15<03:17, 1.08s/it]
Loading 0: 50%|████▉ | 180/363 [02:18<04:07, 1.35s/it]
Loading 0: 50%|█████ | 183/363 [02:20<02:56, 1.02it/s]
Loading 0: 51%|█████ | 184/363 [02:22<03:33, 1.19s/it]
Loading 0: 51%|█████ | 185/363 [02:24<04:08, 1.40s/it]
Loading 0: 52%|█████▏ | 188/363 [02:24<02:13, 1.31it/s]
Loading 0: 52%|█████▏ | 189/363 [02:24<01:55, 1.51it/s]
Loading 0: 52%|█████▏ | 190/363 [02:24<01:34, 1.83it/s]
Loading 0: 53%|█████▎ | 192/363 [02:25<01:08, 2.51it/s]
Loading 0: 53%|█████▎ | 193/363 [02:25<01:02, 2.72it/s]
Loading 0: 53%|█████▎ | 194/363 [02:25<00:52, 3.24it/s]
Loading 0: 54%|█████▎ | 195/363 [02:25<00:44, 3.79it/s]
Loading 0: 54%|█████▍ | 196/363 [02:27<02:00, 1.38it/s]
Loading 0: 54%|█████▍ | 197/363 [02:29<02:57, 1.07s/it]
Loading 0: 55%|█████▍ | 198/363 [02:31<03:42, 1.35s/it]
Loading 0: 55%|█████▌ | 201/363 [02:33<02:38, 1.02it/s]
Loading 0: 56%|█████▌ | 202/363 [02:35<03:11, 1.19s/it]
Loading 0: 56%|█████▌ | 203/363 [02:37<03:43, 1.40s/it]
Loading 0: 57%|█████▋ | 206/363 [02:38<01:59, 1.32it/s]
Loading 0: 57%|█████▋ | 207/363 [02:38<01:43, 1.50it/s]
Loading 0: 57%|█████▋ | 208/363 [02:38<01:25, 1.82it/s]
Loading 0: 58%|█████▊ | 210/363 [02:38<01:01, 2.49it/s]
Loading 0: 58%|█████▊ | 211/363 [02:39<00:56, 2.70it/s]
Loading 0: 58%|█████▊ | 212/363 [02:39<00:47, 3.21it/s]
Loading 0: 59%|█████▊ | 213/363 [02:39<00:39, 3.76it/s]
Loading 0: 59%|█████▉ | 214/363 [02:41<01:47, 1.38it/s]
Loading 0: 59%|█████▉ | 215/363 [02:43<02:38, 1.07s/it]
Loading 0: 60%|█████▉ | 216/363 [02:45<03:19, 1.36s/it]
Loading 0: 60%|██████ | 219/363 [02:47<02:21, 1.02it/s]
Loading 0: 61%|██████ | 220/363 [02:49<02:50, 1.19s/it]
Loading 0: 61%|██████ | 221/363 [02:51<03:17, 1.39s/it]
Loading 0: 62%|██████▏ | 224/363 [02:51<01:45, 1.32it/s]
Loading 0: 62%|██████▏ | 225/363 [02:52<01:31, 1.51it/s]
Loading 0: 62%|██████▏ | 226/363 [02:52<01:14, 1.83it/s]
Loading 0: 63%|██████▎ | 228/363 [02:52<00:54, 2.49it/s]
Loading 0: 63%|██████▎ | 229/363 [02:52<00:49, 2.70it/s]
Loading 0: 63%|██████▎ | 230/363 [02:52<00:41, 3.21it/s]
Loading 0: 64%|██████▎ | 231/363 [02:53<00:35, 3.76it/s]
Loading 0: 64%|██████▍ | 232/363 [02:55<01:34, 1.38it/s]
Loading 0: 64%|██████▍ | 233/363 [02:57<02:19, 1.07s/it]
Loading 0: 64%|██████▍ | 234/363 [02:59<02:54, 1.35s/it]
Loading 0: 65%|██████▌ | 237/363 [03:01<02:03, 1.02it/s]
Loading 0: 66%|██████▌ | 238/363 [03:03<02:28, 1.19s/it]
Loading 0: 66%|██████▌ | 239/363 [03:05<02:52, 1.39s/it]
Loading 0: 67%|██████▋ | 242/363 [03:05<01:31, 1.32it/s]
Loading 0: 67%|██████▋ | 243/363 [03:05<01:19, 1.51it/s]
Loading 0: 67%|██████▋ | 244/363 [03:05<01:04, 1.84it/s]
Loading 0: 68%|██████▊ | 246/363 [03:06<00:46, 2.52it/s]
Loading 0: 68%|██████▊ | 247/363 [03:06<00:42, 2.74it/s]
Loading 0: 68%|██████▊ | 248/363 [03:06<00:35, 3.24it/s]
Loading 0: 69%|██████▊ | 249/363 [03:06<00:30, 3.79it/s]
Loading 0: 69%|██████▉ | 250/363 [03:08<01:21, 1.38it/s]
Loading 0: 69%|██████▉ | 251/363 [03:10<02:00, 1.07s/it]
Loading 0: 69%|██████▉ | 252/363 [03:12<02:30, 1.35s/it]
Loading 0: 70%|███████ | 255/363 [03:14<01:45, 1.02it/s]
Loading 0: 71%|███████ | 256/363 [03:16<02:07, 1.19s/it]
Loading 0: 71%|███████ | 257/363 [03:18<02:27, 1.39s/it]
Loading 0: 72%|███████▏ | 260/363 [03:19<01:18, 1.32it/s]
Loading 0: 72%|███████▏ | 261/363 [03:19<01:07, 1.51it/s]
Loading 0: 72%|███████▏ | 262/363 [03:19<00:55, 1.83it/s]
Loading 0: 73%|███████▎ | 264/363 [03:19<00:39, 2.51it/s]
Loading 0: 73%|███████▎ | 265/363 [03:20<00:35, 2.73it/s]
Loading 0: 73%|███████▎ | 266/363 [03:20<00:30, 3.22it/s]
Loading 0: 74%|███████▎ | 267/363 [03:20<00:25, 3.77it/s]
Loading 0: 74%|███████▍ | 268/363 [03:22<01:08, 1.38it/s]
Loading 0: 74%|███████▍ | 269/363 [03:24<01:40, 1.07s/it]
Loading 0: 74%|███████▍ | 270/363 [03:26<02:05, 1.35s/it]
Loading 0: 75%|███████▌ | 273/363 [03:41<05:02, 3.37s/it]
Loading 0: 75%|███████▌ | 274/363 [03:43<04:34, 3.08s/it]
Loading 0: 76%|███████▌ | 275/363 [03:45<04:11, 2.86s/it]
Loading 0: 77%|███████▋ | 278/363 [03:46<02:07, 1.50s/it]
Loading 0: 77%|███████▋ | 279/363 [03:46<01:45, 1.26s/it]
Loading 0: 77%|███████▋ | 280/363 [03:46<01:24, 1.02s/it]
Loading 0: 78%|███████▊ | 282/363 [03:46<00:55, 1.46it/s]
Loading 0: 78%|███████▊ | 283/363 [03:46<00:47, 1.70it/s]
Loading 0: 78%|███████▊ | 284/363 [03:47<00:37, 2.09it/s]
Loading 0: 79%|███████▊ | 285/363 [03:47<00:30, 2.56it/s]
Loading 0: 79%|███████▉ | 286/363 [03:49<01:02, 1.23it/s]
Loading 0: 79%|███████▉ | 287/363 [03:51<01:26, 1.14s/it]
Loading 0: 79%|███████▉ | 288/363 [03:53<01:44, 1.40s/it]
Loading 0: 80%|████████ | 291/363 [03:55<01:12, 1.00s/it]
Loading 0: 80%|████████ | 292/363 [03:57<01:25, 1.21s/it]
Loading 0: 81%|████████ | 293/363 [03:59<01:37, 1.40s/it]
Loading 0: 82%|████████▏ | 296/363 [03:59<00:50, 1.33it/s]
Loading 0: 82%|████████▏ | 297/363 [03:59<00:43, 1.53it/s]
Loading 0: 82%|████████▏ | 298/363 [03:59<00:34, 1.86it/s]
Loading 0: 83%|████████▎ | 300/363 [04:00<00:24, 2.57it/s]
Loading 0: 83%|████████▎ | 301/363 [04:00<00:21, 2.83it/s]
Loading 0: 83%|████████▎ | 302/363 [04:00<00:18, 3.35it/s]
Loading 0: 83%|████████▎ | 303/363 [04:00<00:15, 3.91it/s]
Loading 0: 84%|████████▎ | 304/363 [04:02<00:42, 1.40it/s]
Loading 0: 84%|████████▍ | 305/363 [04:04<01:01, 1.06s/it]
Loading 0: 84%|████████▍ | 306/363 [04:06<01:16, 1.35s/it]
Loading 0: 85%|████████▌ | 309/363 [04:08<00:52, 1.02it/s]
Loading 0: 85%|████████▌ | 310/363 [04:10<01:02, 1.19s/it]
Loading 0: 86%|████████▌ | 311/363 [04:12<01:12, 1.39s/it]
Loading 0: 87%|████████▋ | 314/363 [04:13<00:36, 1.33it/s]
Loading 0: 87%|████████▋ | 315/363 [04:13<00:31, 1.54it/s]
Loading 0: 87%|████████▋ | 316/363 [04:13<00:25, 1.86it/s]
Loading 0: 88%|████████▊ | 318/363 [04:13<00:17, 2.59it/s]
Loading 0: 88%|████████▊ | 319/363 [04:13<00:15, 2.83it/s]
Loading 0: 88%|████████▊ | 320/363 [04:14<00:12, 3.35it/s]
Loading 0: 88%|████████▊ | 321/363 [04:14<00:10, 3.90it/s]
Loading 0: 89%|████████▊ | 322/363 [04:16<00:29, 1.40it/s]
Loading 0: 89%|████████▉ | 323/363 [04:18<00:42, 1.07s/it]
Loading 0: 89%|████████▉ | 324/363 [04:20<00:52, 1.34s/it]
Loading 0: 90%|█████████ | 327/363 [04:22<00:35, 1.02it/s]
Loading 0: 90%|█████████ | 328/363 [04:24<00:41, 1.19s/it]
Loading 0: 91%|█████████ | 329/363 [04:26<00:47, 1.38s/it]
Loading 0: 91%|█████████▏| 332/363 [04:26<00:23, 1.33it/s]
Loading 0: 92%|█████████▏| 333/363 [04:26<00:19, 1.54it/s]
Loading 0: 92%|█████████▏| 334/363 [04:26<00:15, 1.85it/s]
Loading 0: 93%|█████████▎| 336/363 [04:27<00:10, 2.56it/s]
Loading 0: 93%|█████████▎| 337/363 [04:27<00:09, 2.82it/s]
Loading 0: 93%|█████████▎| 338/363 [04:27<00:07, 3.34it/s]
Loading 0: 93%|█████████▎| 339/363 [04:27<00:06, 3.90it/s]
Loading 0: 94%|█████████▎| 340/363 [04:29<00:16, 1.39it/s]
Loading 0: 94%|█████████▍| 341/363 [04:31<00:23, 1.07s/it]
Loading 0: 94%|█████████▍| 342/363 [04:33<00:28, 1.35s/it]
Loading 0: 95%|█████████▌| 345/363 [04:35<00:17, 1.02it/s]
Loading 0: 95%|█████████▌| 346/363 [04:37<00:20, 1.19s/it]
Loading 0: 96%|█████████▌| 347/363 [04:39<00:22, 1.39s/it]
Loading 0: 96%|█████████▋| 350/363 [04:40<00:09, 1.33it/s]
Loading 0: 97%|█████████▋| 351/363 [04:40<00:07, 1.54it/s]
Loading 0: 97%|█████████▋| 352/363 [04:40<00:05, 1.86it/s]
Loading 0: 98%|█████████▊| 354/363 [04:40<00:03, 2.56it/s]
Loading 0: 98%|█████████▊| 355/363 [04:41<00:02, 2.79it/s]
Loading 0: 98%|█████████▊| 356/363 [04:41<00:02, 3.31it/s]
Loading 0: 98%|█████████▊| 357/363 [04:41<00:02, 2.94it/s]
Loading 0: 99%|█████████▉| 359/363 [04:43<00:02, 1.60it/s]
Loading 0: 99%|█████████▉| 360/363 [04:45<00:02, 1.06it/s]
Loading 0: 99%|█████████▉| 361/363 [04:47<00:02, 1.22s/it]
Job chaiml-exp-grpo-cp312-36146-v23-mkmlizer completed after 402.48s with status: succeeded
Stopping job with name chaiml-exp-grpo-cp312-36146-v23-mkmlizer
Pipeline stage MKMLizer completed in 1407.96s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v23
Waiting for inference service chaiml-exp-grpo-cp312-36146-v23 to be ready
HTTP Request: %s %s "%s %d %s"
Inference service chaiml-exp-grpo-cp312-36146-v23 ready after 50.058778285980225s
Pipeline stage MKMLDeployer completed in 50.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5293779373168945s
Received healthy response to inference request in 1.7360117435455322s
Received healthy response to inference request in 1.6878547668457031s
Received healthy response to inference request in 2.088054895401001s
Received healthy response to inference request in 1.620640754699707s
5 requests
0 failed requests
5th percentile: 1.6340835571289063
10th percentile: 1.6475263595581056
20th percentile: 1.6744119644165039
30th percentile: 1.697486162185669
40th percentile: 1.7167489528656006
50th percentile: 1.7360117435455322
60th percentile: 1.8768290042877198
70th percentile: 2.017646265029907
80th percentile: 2.1763195037841796
90th percentile: 2.3528487205505373
95th percentile: 2.441113328933716
99th percentile: 2.5117250156402586
mean time: 1.9323880195617675
Pipeline stage StressChecker completed in 11.18s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.64s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.64s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v23 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2695.36s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v23 status is now inactive due to auto deactivation removed underperforming models
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage AMDMKMLizer
Starting job with name chaiml-exp-grpo-cp312-36146-v23-mkmlizer
Waiting for job on chaiml-exp-grpo-cp312-36146-v23-mkmlizer to finish
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: bash: no job control in this shell
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Version: 0.29.16+gfx942 ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Features: FLYWHEEL, CUDA, ROCM ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ https://mk1.ai ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ belonging to: ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Chai Research Corp. ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ Expiration: 2028-03-31 00:00:00 ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: Downloaded to shared memory in 186.569s
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: Checking if ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged already exists in ChaiML
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpg94i1h5g, device:0
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp-grpo-cp312-36146-v23-mkmlizer:
Loading 0: 0%| | 0.00/363 [00:00<?, ?it/s]
Loading 0: 3%|▎ | 10.0/363 [00:01<00:41, 8.43it/s]
Loading 0: 3%|▎ | 10.0/363 [00:01<00:41, 8.43it/s]
Loading 0: 4%|▍ | 14.0/363 [00:02<00:59, 5.90it/s]
Loading 0: 4%|▍ | 14.0/363 [00:02<00:59, 5.90it/s]
Loading 0: 6%|▌ | 22.0/363 [00:03<00:51, 6.62it/s]
Loading 0: 6%|▌ | 22.0/363 [00:03<00:51, 6.62it/s]
Loading 0: 9%|▉ | 33.0/363 [00:04<00:45, 7.21it/s]
Loading 0: 9%|▉ | 33.0/363 [00:04<00:45, 7.21it/s]
Loading 0: 11%|█ | 39.0/363 [00:05<00:47, 6.78it/s]
Loading 0: 11%|█ | 39.0/363 [00:05<00:47, 6.78it/s]
Loading 0: 14%|█▍ | 51.0/363 [00:06<00:40, 7.71it/s]
Loading 0: 14%|█▍ | 51.0/363 [00:06<00:40, 7.71it/s]
Loading 0: 16%|█▌ | 58.0/363 [00:08<00:43, 7.09it/s]
Loading 0: 16%|█▌ | 58.0/363 [00:08<00:43, 7.09it/s]
Loading 0: 19%|█▉ | 69.0/363 [00:09<00:37, 7.90it/s]
Loading 0: 19%|█▉ | 69.0/363 [00:09<00:37, 7.90it/s]
Loading 0: 21%|██ | 75.0/363 [00:10<00:39, 7.30it/s]
Loading 0: 21%|██ | 75.0/363 [00:10<00:39, 7.30it/s]
Loading 0: 24%|██▍ | 87.0/363 [00:11<00:34, 7.89it/s]
Loading 0: 24%|██▍ | 87.0/363 [00:11<00:34, 7.89it/s]
Loading 0: 27%|██▋ | 97.0/363 [00:12<00:31, 8.41it/s]
Loading 0: 27%|██▋ | 97.0/363 [00:12<00:31, 8.41it/s]
Loading 0: 29%|██▉ | 105/363 [00:13<00:33, 7.68it/s]
Loading 0: 29%|██▉ | 105/363 [00:13<00:33, 7.68it/s]
Loading 0: 31%|███ | 111/363 [00:15<00:34, 7.20it/s]
Loading 0: 31%|███ | 111/363 [00:15<00:34, 7.20it/s]
Loading 0: 34%|███▍ | 123/363 [00:16<00:30, 7.84it/s]
Loading 0: 34%|███▍ | 123/363 [00:16<00:30, 7.84it/s]
Loading 0: 36%|███▌ | 129/363 [00:17<00:32, 7.31it/s]
Loading 0: 36%|███▌ | 129/363 [00:17<00:32, 7.31it/s]
Loading 0: 39%|███▉ | 141/363 [00:18<00:27, 7.94it/s]
Loading 0: 39%|███▉ | 141/363 [00:18<00:27, 7.94it/s]
Loading 0: 41%|████ | 148/363 [00:19<00:29, 7.32it/s]
Loading 0: 41%|████ | 148/363 [00:19<00:29, 7.32it/s]
Loading 0: 44%|████▍ | 159/363 [00:20<00:25, 8.14it/s]
Loading 0: 44%|████▍ | 159/363 [00:20<00:25, 8.14it/s]
Loading 0: 45%|████▌ | 165/363 [00:21<00:26, 7.51it/s]
Loading 0: 45%|████▌ | 165/363 [00:21<00:26, 7.51it/s]
Loading 0: 49%|████▉ | 177/363 [00:23<00:22, 8.10it/s]
Loading 0: 49%|████▉ | 177/363 [00:23<00:22, 8.10it/s]
Loading 0: 50%|█████ | 183/363 [00:24<00:24, 7.50it/s]
Loading 0: 50%|█████ | 183/363 [00:24<00:24, 7.50it/s]
Loading 0: 54%|█████▎ | 195/363 [00:25<00:20, 8.07it/s]
Loading 0: 54%|█████▎ | 195/363 [00:25<00:20, 8.07it/s]
Loading 0: 55%|█████▌ | 201/363 [00:26<00:21, 7.49it/s]
Loading 0: 55%|█████▌ | 201/363 [00:26<00:21, 7.49it/s]
Loading 0: 59%|█████▊ | 213/363 [00:27<00:18, 8.09it/s]
Loading 0: 59%|█████▊ | 213/363 [00:27<00:18, 8.09it/s]
Loading 0: 60%|██████ | 219/363 [00:28<00:19, 7.50it/s]
Loading 0: 60%|██████ | 219/363 [00:28<00:19, 7.50it/s]
Loading 0: 64%|██████▎ | 231/363 [00:30<00:16, 8.12it/s]
Loading 0: 64%|██████▎ | 231/363 [00:30<00:16, 8.12it/s]
Loading 0: 65%|██████▌ | 237/363 [00:31<00:16, 7.46it/s]
Loading 0: 65%|██████▌ | 237/363 [00:31<00:16, 7.46it/s]
Loading 0: 69%|██████▊ | 249/363 [00:32<00:14, 7.98it/s]
Loading 0: 69%|██████▊ | 249/363 [00:32<00:14, 7.98it/s]
Loading 0: 70%|███████ | 255/363 [00:33<00:14, 7.45it/s]
Loading 0: 70%|███████ | 255/363 [00:33<00:14, 7.45it/s]
Loading 0: 74%|███████▎ | 267/363 [00:34<00:11, 8.06it/s]
Loading 0: 74%|███████▎ | 267/363 [00:34<00:11, 8.06it/s]
Loading 0: 75%|███████▌ | 274/363 [00:36<00:12, 7.40it/s]
Loading 0: 75%|███████▌ | 274/363 [00:36<00:12, 7.40it/s]
Loading 0: 79%|███████▊ | 285/363 [00:37<00:09, 8.23it/s]
Loading 0: 79%|███████▊ | 285/363 [00:37<00:09, 8.23it/s]
Loading 0: 80%|████████ | 291/363 [00:49<00:39, 1.81it/s]
Loading 0: 80%|████████ | 291/363 [00:49<00:39, 1.81it/s]
Loading 0: 83%|████████▎ | 303/363 [00:51<00:23, 2.61it/s]
Loading 0: 83%|████████▎ | 303/363 [00:51<00:23, 2.61it/s]
Loading 0: 85%|████████▌ | 309/363 [00:52<00:18, 2.96it/s]
Loading 0: 85%|████████▌ | 309/363 [00:52<00:18, 2.96it/s]
Loading 0: 88%|████████▊ | 321/363 [00:53<00:10, 3.99it/s]
Loading 0: 88%|████████▊ | 321/363 [00:53<00:10, 3.99it/s]
Loading 0: 90%|█████████ | 327/363 [00:54<00:08, 4.29it/s]
Loading 0: 90%|█████████ | 327/363 [00:54<00:08, 4.29it/s]
Loading 0: 93%|█████████▎| 339/363 [00:55<00:04, 5.39it/s]
Loading 0: 93%|█████████▎| 339/363 [00:55<00:04, 5.39it/s]
Loading 0: 95%|█████████▌| 345/363 [00:56<00:03, 5.51it/s]
Loading 0: 95%|█████████▌| 345/363 [00:56<00:03, 5.51it/s]
Loading 0: 98%|█████████▊| 357/363 [00:58<00:01, 5.51it/s]
Loading 0: 98%|█████████▊| 357/363 [00:58<00:01, 5.51it/s]
Loading 0: 100%|██████████| 363/363 [00:59<00:00, 5.75it/s]
Loading 0: 100%|██████████| 363/363 [00:59<00:00, 5.75it/s]
Loading 0: 100%|██████████| 363/363 [00:59<00:00, 6.07it/s]
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: quantized model in 72.052s
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: Processed model ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged in 258.621s
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/amd
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/amd/config.json
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/amd/special_tokens_map.json
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/amd/tokenizer_config.json
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/amd/tokenizer.json
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/amd/flywheel_model.1.safetensors
chaiml-exp-grpo-cp312-36146-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/amd/flywheel_model.0.safetensors
Job chaiml-exp-grpo-cp312-36146-v23-mkmlizer completed after 303.12s with status: succeeded
Stopping job with name chaiml-exp-grpo-cp312-36146-v23-mkmlizer
Pipeline stage AMDMKMLizer completed in 304.22s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-exp-grpo-cp312-36146-v23-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 0.37s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v23-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v23-profiler to be ready
Tearing down inference service chaiml-exp-grpo-cp312-36146-v23-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-exp-grpo-cp312-36146-v23-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v23-profiler to be ready
Tearing down inference service chaiml-exp-grpo-cp312-36146-v23-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-exp-grpo-cp312-36146-v23-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v23-profiler to be ready
Tearing down inference service chaiml-exp-grpo-cp312-36146-v23-profiler
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService chaiml-exp-grpo-cp312-36146-v23-profiler. The InferenceService is as following: {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'kind\': \'InferenceService\', \'metadata\': {\'annotations\': {\'autoscaling.knative.dev/class\': \'hpa.autoscaling.knative.dev\', \'autoscaling.knative.dev/container-concurrency-target-percentage\': \'70\', \'autoscaling.knative.dev/initial-scale\': \'1\', \'autoscaling.knative.dev/max-scale-down-rate\': \'1.1\', \'autoscaling.knative.dev/max-scale-up-rate\': \'2\', \'autoscaling.knative.dev/metric\': \'mean_pod_latency_ms_v2\', \'autoscaling.knative.dev/panic-threshold-percentage\': \'650\', \'autoscaling.knative.dev/panic-window-percentage\': \'35\', \'autoscaling.knative.dev/scale-down-delay\': \'30s\', \'autoscaling.knative.dev/scale-to-zero-grace-period\': \'10m\', \'autoscaling.knative.dev/stable-window\': \'180s\', \'autoscaling.knative.dev/target\': \'4000\', \'autoscaling.knative.dev/target-burst-capacity\': \'-1\', \'autoscaling.knative.dev/tick-interval\': \'15s\', \'features.knative.dev/http-full-duplex\': \'Enabled\', \'networking.knative.dev/ingress-class\': \'istio.ingress.networking.knative.dev\'}, \'creationTimestamp\': \'2025-09-22T18:58:31Z\', \'finalizers\': [\'inferenceservice.finalizers\'], \'generation\': 1, \'labels\': {\'knative.coreweave.cloud/ingress\': \'istio.ingress.networking.knative.dev\', \'prometheus.k.chaiverse.com\': \'true\', \'qos.coreweave.cloud/latency\': \'low\'}, \'managedFields\': [{\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:annotations\': {\'.\': {}, \'f:autoscaling.knative.dev/class\': {}, \'f:autoscaling.knative.dev/container-concurrency-target-percentage\': {}, \'f:autoscaling.knative.dev/initial-scale\': {}, \'f:autoscaling.knative.dev/max-scale-down-rate\': {}, \'f:autoscaling.knative.dev/max-scale-up-rate\': {}, \'f:autoscaling.knative.dev/metric\': {}, \'f:autoscaling.knative.dev/panic-threshold-percentage\': {}, \'f:autoscaling.knative.dev/panic-window-percentage\': {}, \'f:autoscaling.knative.dev/scale-down-delay\': {}, \'f:autoscaling.knative.dev/scale-to-zero-grace-period\': {}, \'f:autoscaling.knative.dev/stable-window\': {}, \'f:autoscaling.knative.dev/target\': {}, \'f:autoscaling.knative.dev/target-burst-capacity\': {}, \'f:autoscaling.knative.dev/tick-interval\': {}, \'f:features.knative.dev/http-full-duplex\': {}, \'f:networking.knative.dev/ingress-class\': {}}, \'f:labels\': {\'.\': {}, \'f:knative.coreweave.cloud/ingress\': {}, \'f:prometheus.k.chaiverse.com\': {}, \'f:qos.coreweave.cloud/latency\': {}}}, \'f:spec\': {\'.\': {}, \'f:predictor\': {\'.\': {}, \'f:affinity\': {\'.\': {}, \'f:nodeAffinity\': {\'.\': {}, \'f:tion\': {}, \'f:requiredDuringSchedulingIgnoredDuringExecution\': {}}}, \'f:containerConcurrency\': {}, \'f:containers\': {}, \'f:imagePullSecrets\': {}, \'f:maxReplicas\': {}, \'f:minReplicas\': {}, \'f:timeout\': {}, \'f:volumes\': {}}}}, \'manager\': \'OpenAPI-Generator\', \'operation\': \'Update\', \'time\': \'2025-09-22T18:58:31Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2025-09-22T18:58:31Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:status\': {\'.\': {}, \'f:components\': {\'.\': {}, \'f:predictor\': {\'.\': {}, \'f:latestCreatedRevision\': {}}}, \'f:conditions\': {}, \'f:modelStatus\': {\'.\': {}, \'f:states\': {\'.\': {}, \'f:activeModelState\': {}, \'f:targetModelState\': {}}, \'f:transitionStatus\': {}}, \'f:observedGeneration\': {}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'subresource\': \'status\', \'time\': \'2025-09-22T18:58:33Z\'}], \'name\': \'chaiml-exp-grpo-cp312-36146-v23-profiler\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'134351216\', \'uid\': \'8d8ebf35-edb9-4233-ab09-14fdba9bdeef\'}, \'spec\': {\'predictor\': {\'affinity\': {\'nodeAffinity\': {\'tion\': [{\'preference\': {\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\']}]}, \'weight\': 5}], \'requiredDuringSchedulingIgnoredDuringExecution\': {\'nodeSelectorTerms\': [{\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\', \'RTX_A6000\', \'L40S\']}]}]}}}, \'containerConcurrency\': 0, \'containers\': [{\'env\': [{\'name\': \'MAX_TOKEN_INPUT\', \'value\': \'1280\'}, {\'name\': \'BEST_OF\', \'value\': \'7\'}, {\'name\': \'TEMPERATURE\', \'value\': \'0.9\'}, {\'name\': \'PRESENCE_PENALTY\', \'value\': \'0.45\'}, {\'name\': \'FREQUENCY_PENALTY\', \'value\': \'0.45\'}, {\'name\': \'TOP_P\', \'value\': \'0.95\'}, {\'name\': \'MIN_P\', \'value\': \'0.05\'}, {\'name\': \'TOP_K\', \'value\': \'80\'}, {\'name\': \'STOPPING_WORDS\', \'value\': \'["\\\\\\\\n"]\'}, {\'name\': \'MAX_TOKENS\', \'value\': \'64\'}, {\'name\': \'MAX_BATCH_SIZE\', \'value\': \'128\'}, {\'name\': \'MAX_CACHED_RESPONSES\', \'value\': \'-1\'}, {\'name\': \'URL_ROUTE\', \'value\': \'GPT-J-6B-lit-v2\'}, {\'name\': \'OBJ_ACCESS_KEY_ID\', \'value\': \'LETMTTRMLFFAMTBK\'}, {\'name\': \'OBJ_SECRET_ACCESS_KEY\', \'value\': \'VwwZaqefOOoaouNxUk03oUmK9pVEfruJhjBHPGdgycK\'}, {\'name\': \'OBJ_ENDPOINT\', \'value\': \'https://accel-object.ord1.coreweave.com\'}, {\'name\': \'TENSORIZER_URI\', \'value\': \'s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/nvidia\'}, {\'name\': \'RESERVE_MEMORY\', \'value\': \'2048\'}, {\'name\': \'DOWNLOAD_TO_LOCAL\', \'value\': \'/dev/shm/model_cache\'}, {\'name\': \'NUM_GPUS\', \'value\': \'1\'}, {\'name\': \'MK1_QUANTIZATION_PROFILE\', \'value\': \'q4\'}, {\'name\': \'MK1_MKML_LICENSE_KEY\', \'valueFrom\': {\'secretKeyRef\': {\'key\': \'key\', \'name\': \'mkml-license-key\'}}}], \'image\': \'gcr.io/chai-959f8/chai-guanaco/mkml:mkml_v0.30.2\', \'imagePullPolicy\': \'IfNotPresent\', \'name\': \'kserve-container\', \'readinessProbe\': {\'exec\': {\'command\': [\'cat\', \'/tmp/ready\']}, \'failureThreshold\': 1, \'initialDelaySeconds\': 10, \'periodSeconds\': 10, \'successThreshold\': 1, \'timeoutSeconds\': 5}, \'resources\': {\'limits\': {\'cpu\': \'2\', \'memory\': \'26Gi\', \'nvidia.com/gpu\': \'1\'}, \'requests\': {\'cpu\': \'2\', \'memory\': \'26Gi\', \'nvidia.com/gpu\': \'1\'}}, \'volumeMounts\': [{\'mountPath\': \'/dev/shm\', \'name\': \'shared-memory-cache\'}]}], \'imagePullSecrets\': [{\'name\': \'docker-creds\'}], \'maxReplicas\': 1, \'minReplicas\': 1, \'timeout\': 60, \'volumes\': [{\'emptyDir\': {\'medium\': \'Memory\'}, \'name\': \'shared-memory-cache\'}]}}, \'status\': {\'components\': {\'predictor\': {\'latestCreatedRevision\': \'chaiml-exp-grpo-cp312-36146-v23-profiler-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2025-09-22T18:58:33Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2025-09-22T18:58:33Z\', \'message\': \'Revision "chaiml-exp-grpo-cp312-36146-v23-profiler-predictor-00001" failed with message: 0/35 nodes are available: 2 node(s) had untolerated taint {node.kubernetes.io/unreachable: }, 33 node(s) didn\\\'t match Pod\\\'s node affinity/selector. preemption: 0/35 nodes are available: 35 Preemption is not helpful for scheduling..\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2025-09-22T18:58:33Z\', \'message\': \'Configuration "chaiml-exp-grpo-cp312-36146-v23-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2025-09-22T18:58:33Z\', \'message\': \'Configuration "chaiml-exp-grpo-cp312-36146-v23-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2025-09-22T18:58:33Z\', \'message\': \'Configuration "chaiml-exp-grpo-cp312-36146-v23-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2025-09-22T18:58:33Z\', \'reason\': \'PredictorRouteReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'RoutesReady\'}], \'modelStatus\': {\'states\': {\'activeModelState\': \'\', \'targetModelState\': \'Pending\'}, \'transitionStatus\': \'InProgress\'}, \'observedGeneration\': 1}}')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.15s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v23-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v23-profiler to be ready
Tearing down inference service chaiml-exp-grpo-cp312-36146-v23-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-exp-grpo-cp312-36146-v23-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v23-profiler to be ready
Tearing down inference service chaiml-exp-grpo-cp312-36146-v23-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-exp-grpo-cp312-36146-v23-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v23-profiler to be ready
Tearing down inference service chaiml-exp-grpo-cp312-36146-v23-profiler
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService chaiml-exp-grpo-cp312-36146-v23-profiler. The InferenceService is as following: {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'kind\': \'InferenceService\', \'metadata\': {\'annotations\': {\'autoscaling.knative.dev/class\': \'hpa.autoscaling.knative.dev\', \'autoscaling.knative.dev/container-concurrency-target-percentage\': \'70\', \'autoscaling.knative.dev/initial-scale\': \'1\', \'autoscaling.knative.dev/max-scale-down-rate\': \'1.1\', \'autoscaling.knative.dev/max-scale-up-rate\': \'2\', \'autoscaling.knative.dev/metric\': \'mean_pod_latency_ms_v2\', \'autoscaling.knative.dev/panic-threshold-percentage\': \'650\', \'autoscaling.knative.dev/panic-window-percentage\': \'35\', \'autoscaling.knative.dev/scale-down-delay\': \'30s\', \'autoscaling.knative.dev/scale-to-zero-grace-period\': \'10m\', \'autoscaling.knative.dev/stable-window\': \'180s\', \'autoscaling.knative.dev/target\': \'4000\', \'autoscaling.knative.dev/target-burst-capacity\': \'-1\', \'autoscaling.knative.dev/tick-interval\': \'15s\', \'features.knative.dev/http-full-duplex\': \'Enabled\', \'networking.knative.dev/ingress-class\': \'istio.ingress.networking.knative.dev\'}, \'creationTimestamp\': \'2025-09-22T19:30:05Z\', \'finalizers\': [\'inferenceservice.finalizers\'], \'generation\': 1, \'labels\': {\'knative.coreweave.cloud/ingress\': \'istio.ingress.networking.knative.dev\', \'prometheus.k.chaiverse.com\': \'true\', \'qos.coreweave.cloud/latency\': \'low\'}, \'managedFields\': [{\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:annotations\': {\'.\': {}, \'f:autoscaling.knative.dev/class\': {}, \'f:autoscaling.knative.dev/container-concurrency-target-percentage\': {}, \'f:autoscaling.knative.dev/initial-scale\': {}, \'f:autoscaling.knative.dev/max-scale-down-rate\': {}, \'f:autoscaling.knative.dev/max-scale-up-rate\': {}, \'f:autoscaling.knative.dev/metric\': {}, \'f:autoscaling.knative.dev/panic-threshold-percentage\': {}, \'f:autoscaling.knative.dev/panic-window-percentage\': {}, \'f:autoscaling.knative.dev/scale-down-delay\': {}, \'f:autoscaling.knative.dev/scale-to-zero-grace-period\': {}, \'f:autoscaling.knative.dev/stable-window\': {}, \'f:autoscaling.knative.dev/target\': {}, \'f:autoscaling.knative.dev/target-burst-capacity\': {}, \'f:autoscaling.knative.dev/tick-interval\': {}, \'f:features.knative.dev/http-full-duplex\': {}, \'f:networking.knative.dev/ingress-class\': {}}, \'f:labels\': {\'.\': {}, \'f:knative.coreweave.cloud/ingress\': {}, \'f:prometheus.k.chaiverse.com\': {}, \'f:qos.coreweave.cloud/latency\': {}}}, \'f:spec\': {\'.\': {}, \'f:predictor\': {\'.\': {}, \'f:affinity\': {\'.\': {}, \'f:nodeAffinity\': {\'.\': {}, \'f:tion\': {}, \'f:requiredDuringSchedulingIgnoredDuringExecution\': {}}}, \'f:containerConcurrency\': {}, \'f:containers\': {}, \'f:imagePullSecrets\': {}, \'f:maxReplicas\': {}, \'f:minReplicas\': {}, \'f:timeout\': {}, \'f:volumes\': {}}}}, \'manager\': \'OpenAPI-Generator\', \'operation\': \'Update\', \'time\': \'2025-09-22T19:30:05Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2025-09-22T19:30:05Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:status\': {\'.\': {}, \'f:components\': {\'.\': {}, \'f:predictor\': {\'.\': {}, \'f:latestCreatedRevision\': {}}}, \'f:conditions\': {}, \'f:modelStatus\': {\'.\': {}, \'f:states\': {\'.\': {}, \'f:activeModelState\': {}, \'f:targetModelState\': {}}, \'f:transitionStatus\': {}}, \'f:observedGeneration\': {}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'subresource\': \'status\', \'time\': \'2025-09-22T19:30:06Z\'}], \'name\': \'chaiml-exp-grpo-cp312-36146-v23-profiler\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'134381920\', \'uid\': \'4ccb9740-2ed9-4aba-8065-c02a70433875\'}, \'spec\': {\'predictor\': {\'affinity\': {\'nodeAffinity\': {\'tion\': [{\'preference\': {\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\']}]}, \'weight\': 5}], \'requiredDuringSchedulingIgnoredDuringExecution\': {\'nodeSelectorTerms\': [{\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\', \'RTX_A6000\', \'L40S\']}]}]}}}, \'containerConcurrency\': 0, \'containers\': [{\'env\': [{\'name\': \'MAX_TOKEN_INPUT\', \'value\': \'1280\'}, {\'name\': \'BEST_OF\', \'value\': \'7\'}, {\'name\': \'TEMPERATURE\', \'value\': \'0.9\'}, {\'name\': \'PRESENCE_PENALTY\', \'value\': \'0.45\'}, {\'name\': \'FREQUENCY_PENALTY\', \'value\': \'0.45\'}, {\'name\': \'TOP_P\', \'value\': \'0.95\'}, {\'name\': \'MIN_P\', \'value\': \'0.05\'}, {\'name\': \'TOP_K\', \'value\': \'80\'}, {\'name\': \'STOPPING_WORDS\', \'value\': \'["\\\\\\\\n"]\'}, {\'name\': \'MAX_TOKENS\', \'value\': \'64\'}, {\'name\': \'MAX_BATCH_SIZE\', \'value\': \'128\'}, {\'name\': \'MAX_CACHED_RESPONSES\', \'value\': \'-1\'}, {\'name\': \'URL_ROUTE\', \'value\': \'GPT-J-6B-lit-v2\'}, {\'name\': \'OBJ_ACCESS_KEY_ID\', \'value\': \'LETMTTRMLFFAMTBK\'}, {\'name\': \'OBJ_SECRET_ACCESS_KEY\', \'value\': \'VwwZaqefOOoaouNxUk03oUmK9pVEfruJhjBHPGdgycK\'}, {\'name\': \'OBJ_ENDPOINT\', \'value\': \'https://accel-object.ord1.coreweave.com\'}, {\'name\': \'TENSORIZER_URI\', \'value\': \'s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/nvidia\'}, {\'name\': \'RESERVE_MEMORY\', \'value\': \'2048\'}, {\'name\': \'DOWNLOAD_TO_LOCAL\', \'value\': \'/dev/shm/model_cache\'}, {\'name\': \'NUM_GPUS\', \'value\': \'1\'}, {\'name\': \'MK1_QUANTIZATION_PROFILE\', \'value\': \'q4\'}, {\'name\': \'MK1_MKML_LICENSE_KEY\', \'valueFrom\': {\'secretKeyRef\': {\'key\': \'key\', \'name\': \'mkml-license-key\'}}}], \'image\': \'gcr.io/chai-959f8/chai-guanaco/mkml:mkml_v0.30.2\', \'imagePullPolicy\': \'IfNotPresent\', \'name\': \'kserve-container\', \'readinessProbe\': {\'exec\': {\'command\': [\'cat\', \'/tmp/ready\']}, \'failureThreshold\': 1, \'initialDelaySeconds\': 10, \'periodSeconds\': 10, \'successThreshold\': 1, \'timeoutSeconds\': 5}, \'resources\': {\'limits\': {\'cpu\': \'2\', \'memory\': \'26Gi\', \'nvidia.com/gpu\': \'1\'}, \'requests\': {\'cpu\': \'2\', \'memory\': \'26Gi\', \'nvidia.com/gpu\': \'1\'}}, \'volumeMounts\': [{\'mountPath\': \'/dev/shm\', \'name\': \'shared-memory-cache\'}]}], \'imagePullSecrets\': [{\'name\': \'docker-creds\'}], \'maxReplicas\': 1, \'minReplicas\': 1, \'timeout\': 60, \'volumes\': [{\'emptyDir\': {\'medium\': \'Memory\'}, \'name\': \'shared-memory-cache\'}]}}, \'status\': {\'components\': {\'predictor\': {\'latestCreatedRevision\': \'chaiml-exp-grpo-cp312-36146-v23-profiler-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2025-09-22T19:30:06Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2025-09-22T19:30:06Z\', \'message\': \'Revision "chaiml-exp-grpo-cp312-36146-v23-profiler-predictor-00001" failed with message: 0/35 nodes are available: 2 node(s) had untolerated taint {node.kubernetes.io/unreachable: }, 33 node(s) didn\\\'t match Pod\\\'s node affinity/selector. preemption: 0/35 nodes are available: 35 Preemption is not helpful for scheduling..\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2025-09-22T19:30:06Z\', \'message\': \'Configuration "chaiml-exp-grpo-cp312-36146-v23-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2025-09-22T19:30:06Z\', \'message\': \'Configuration "chaiml-exp-grpo-cp312-36146-v23-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2025-09-22T19:30:06Z\', \'message\': \'Configuration "chaiml-exp-grpo-cp312-36146-v23-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2025-09-22T19:30:06Z\', \'reason\': \'PredictorRouteReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'RoutesReady\'}], \'modelStatus\': {\'states\': {\'activeModelState\': \'\', \'targetModelState\': \'Pending\'}, \'transitionStatus\': \'InProgress\'}, \'observedGeneration\': 1}}')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.15s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v23-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v23-profiler to be ready
Tearing down inference service chaiml-exp-grpo-cp312-36146-v23-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-exp-grpo-cp312-36146-v23-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v23-profiler to be ready
Tearing down inference service chaiml-exp-grpo-cp312-36146-v23-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-exp-grpo-cp312-36146-v23-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v23-profiler to be ready
Tearing down inference service chaiml-exp-grpo-cp312-36146-v23-profiler
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService chaiml-exp-grpo-cp312-36146-v23-profiler. The InferenceService is as following: {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'kind\': \'InferenceService\', \'metadata\': {\'annotations\': {\'autoscaling.knative.dev/class\': \'hpa.autoscaling.knative.dev\', \'autoscaling.knative.dev/container-concurrency-target-percentage\': \'70\', \'autoscaling.knative.dev/initial-scale\': \'1\', \'autoscaling.knative.dev/max-scale-down-rate\': \'1.1\', \'autoscaling.knative.dev/max-scale-up-rate\': \'2\', \'autoscaling.knative.dev/metric\': \'mean_pod_latency_ms_v2\', \'autoscaling.knative.dev/panic-threshold-percentage\': \'650\', \'autoscaling.knative.dev/panic-window-percentage\': \'35\', \'autoscaling.knative.dev/scale-down-delay\': \'30s\', \'autoscaling.knative.dev/scale-to-zero-grace-period\': \'10m\', \'autoscaling.knative.dev/stable-window\': \'180s\', \'autoscaling.knative.dev/target\': \'4000\', \'autoscaling.knative.dev/target-burst-capacity\': \'-1\', \'autoscaling.knative.dev/tick-interval\': \'15s\', \'features.knative.dev/http-full-duplex\': \'Enabled\', \'networking.knative.dev/ingress-class\': \'istio.ingress.networking.knative.dev\'}, \'creationTimestamp\': \'2025-09-22T20:01:26Z\', \'finalizers\': [\'inferenceservice.finalizers\'], \'generation\': 1, \'labels\': {\'knative.coreweave.cloud/ingress\': \'istio.ingress.networking.knative.dev\', \'prometheus.k.chaiverse.com\': \'true\', \'qos.coreweave.cloud/latency\': \'low\'}, \'managedFields\': [{\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:annotations\': {\'.\': {}, \'f:autoscaling.knative.dev/class\': {}, \'f:autoscaling.knative.dev/container-concurrency-target-percentage\': {}, \'f:autoscaling.knative.dev/initial-scale\': {}, \'f:autoscaling.knative.dev/max-scale-down-rate\': {}, \'f:autoscaling.knative.dev/max-scale-up-rate\': {}, \'f:autoscaling.knative.dev/metric\': {}, \'f:autoscaling.knative.dev/panic-threshold-percentage\': {}, \'f:autoscaling.knative.dev/panic-window-percentage\': {}, \'f:autoscaling.knative.dev/scale-down-delay\': {}, \'f:autoscaling.knative.dev/scale-to-zero-grace-period\': {}, \'f:autoscaling.knative.dev/stable-window\': {}, \'f:autoscaling.knative.dev/target\': {}, \'f:autoscaling.knative.dev/target-burst-capacity\': {}, \'f:autoscaling.knative.dev/tick-interval\': {}, \'f:features.knative.dev/http-full-duplex\': {}, \'f:networking.knative.dev/ingress-class\': {}}, \'f:labels\': {\'.\': {}, \'f:knative.coreweave.cloud/ingress\': {}, \'f:prometheus.k.chaiverse.com\': {}, \'f:qos.coreweave.cloud/latency\': {}}}, \'f:spec\': {\'.\': {}, \'f:predictor\': {\'.\': {}, \'f:affinity\': {\'.\': {}, \'f:nodeAffinity\': {\'.\': {}, \'f:tion\': {}, \'f:requiredDuringSchedulingIgnoredDuringExecution\': {}}}, \'f:containerConcurrency\': {}, \'f:containers\': {}, \'f:imagePullSecrets\': {}, \'f:maxReplicas\': {}, \'f:minReplicas\': {}, \'f:timeout\': {}, \'f:volumes\': {}}}}, \'manager\': \'OpenAPI-Generator\', \'operation\': \'Update\', \'time\': \'2025-09-22T20:01:26Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2025-09-22T20:01:26Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:status\': {\'.\': {}, \'f:components\': {\'.\': {}, \'f:predictor\': {\'.\': {}, \'f:latestCreatedRevision\': {}}}, \'f:conditions\': {}, \'f:modelStatus\': {\'.\': {}, \'f:states\': {\'.\': {}, \'f:activeModelState\': {}, \'f:targetModelState\': {}}, \'f:transitionStatus\': {}}, \'f:observedGeneration\': {}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'subresource\': \'status\', \'time\': \'2025-09-22T20:01:27Z\'}], \'name\': \'chaiml-exp-grpo-cp312-36146-v23-profiler\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'134412619\', \'uid\': \'425bcea9-9f72-4a04-b328-aeaac91f178c\'}, \'spec\': {\'predictor\': {\'affinity\': {\'nodeAffinity\': {\'tion\': [{\'preference\': {\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\']}]}, \'weight\': 5}], \'requiredDuringSchedulingIgnoredDuringExecution\': {\'nodeSelectorTerms\': [{\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\', \'RTX_A6000\', \'L40S\']}]}]}}}, \'containerConcurrency\': 0, \'containers\': [{\'env\': [{\'name\': \'MAX_TOKEN_INPUT\', \'value\': \'1280\'}, {\'name\': \'BEST_OF\', \'value\': \'7\'}, {\'name\': \'TEMPERATURE\', \'value\': \'0.9\'}, {\'name\': \'PRESENCE_PENALTY\', \'value\': \'0.45\'}, {\'name\': \'FREQUENCY_PENALTY\', \'value\': \'0.45\'}, {\'name\': \'TOP_P\', \'value\': \'0.95\'}, {\'name\': \'MIN_P\', \'value\': \'0.05\'}, {\'name\': \'TOP_K\', \'value\': \'80\'}, {\'name\': \'STOPPING_WORDS\', \'value\': \'["\\\\\\\\n"]\'}, {\'name\': \'MAX_TOKENS\', \'value\': \'64\'}, {\'name\': \'MAX_BATCH_SIZE\', \'value\': \'128\'}, {\'name\': \'MAX_CACHED_RESPONSES\', \'value\': \'-1\'}, {\'name\': \'URL_ROUTE\', \'value\': \'GPT-J-6B-lit-v2\'}, {\'name\': \'OBJ_ACCESS_KEY_ID\', \'value\': \'LETMTTRMLFFAMTBK\'}, {\'name\': \'OBJ_SECRET_ACCESS_KEY\', \'value\': \'VwwZaqefOOoaouNxUk03oUmK9pVEfruJhjBHPGdgycK\'}, {\'name\': \'OBJ_ENDPOINT\', \'value\': \'https://accel-object.ord1.coreweave.com\'}, {\'name\': \'TENSORIZER_URI\', \'value\': \'s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v23/nvidia\'}, {\'name\': \'RESERVE_MEMORY\', \'value\': \'2048\'}, {\'name\': \'DOWNLOAD_TO_LOCAL\', \'value\': \'/dev/shm/model_cache\'}, {\'name\': \'NUM_GPUS\', \'value\': \'1\'}, {\'name\': \'MK1_QUANTIZATION_PROFILE\', \'value\': \'q4\'}, {\'name\': \'MK1_MKML_LICENSE_KEY\', \'valueFrom\': {\'secretKeyRef\': {\'key\': \'key\', \'name\': \'mkml-license-key\'}}}], \'image\': \'gcr.io/chai-959f8/chai-guanaco/mkml:mkml_v0.30.2\', \'imagePullPolicy\': \'IfNotPresent\', \'name\': \'kserve-container\', \'readinessProbe\': {\'exec\': {\'command\': [\'cat\', \'/tmp/ready\']}, \'failureThreshold\': 1, \'initialDelaySeconds\': 10, \'periodSeconds\': 10, \'successThreshold\': 1, \'timeoutSeconds\': 5}, \'resources\': {\'limits\': {\'cpu\': \'2\', \'memory\': \'26Gi\', \'nvidia.com/gpu\': \'1\'}, \'requests\': {\'cpu\': \'2\', \'memory\': \'26Gi\', \'nvidia.com/gpu\': \'1\'}}, \'volumeMounts\': [{\'mountPath\': \'/dev/shm\', \'name\': \'shared-memory-cache\'}]}], \'imagePullSecrets\': [{\'name\': \'docker-creds\'}], \'maxReplicas\': 1, \'minReplicas\': 1, \'timeout\': 60, \'volumes\': [{\'emptyDir\': {\'medium\': \'Memory\'}, \'name\': \'shared-memory-cache\'}]}}, \'status\': {\'components\': {\'predictor\': {\'latestCreatedRevision\': \'chaiml-exp-grpo-cp312-36146-v23-profiler-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2025-09-22T20:01:27Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2025-09-22T20:01:27Z\', \'message\': \'Revision "chaiml-exp-grpo-cp312-36146-v23-profiler-predictor-00001" failed with message: 0/35 nodes are available: 2 node(s) had untolerated taint {node.kubernetes.io/unreachable: }, 33 node(s) didn\\\'t match Pod\\\'s node affinity/selector. preemption: 0/35 nodes are available: 35 Preemption is not helpful for scheduling..\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2025-09-22T20:01:27Z\', \'message\': \'Configuration "chaiml-exp-grpo-cp312-36146-v23-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2025-09-22T20:01:27Z\', \'message\': \'Configuration "chaiml-exp-grpo-cp312-36146-v23-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2025-09-22T20:01:27Z\', \'message\': \'Configuration "chaiml-exp-grpo-cp312-36146-v23-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2025-09-22T20:01:27Z\', \'reason\': \'PredictorRouteReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'RoutesReady\'}], \'modelStatus\': {\'states\': {\'activeModelState\': \'\', \'targetModelState\': \'Pending\'}, \'transitionStatus\': \'InProgress\'}, \'observedGeneration\': 1}}')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.14s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v23 status is now protected due to ABTestQueueItem