Running pipeline stage MKMLizer
Starting job with name mistralai-mistral-nemo-9330-v33-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v33-mkmlizer to finish
mistralai-mistral-nemo-9330-v33-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ _____ __ __ ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ /___/ ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ Version: 0.9.7 ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ https://mk1.ai ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ The license key for the current software has been verified as ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ belonging to: ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ Chai Research Corp. ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v33-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-nemo-9330-v33-mkmlizer: Downloaded to shared memory in 51.750s
mistralai-mistral-nemo-9330-v33-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2uemfqfc, device:0
mistralai-mistral-nemo-9330-v33-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v33-mkmlizer: quantized model in 36.019s
mistralai-mistral-nemo-9330-v33-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 87.769s
mistralai-mistral-nemo-9330-v33-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v33-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v33
mistralai-mistral-nemo-9330-v33-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v33/config.json
mistralai-mistral-nemo-9330-v33-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v33/special_tokens_map.json
mistralai-mistral-nemo-9330-v33-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v33/tokenizer_config.json
mistralai-mistral-nemo-9330-v33-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v33/tokenizer.json
mistralai-mistral-nemo-9330-v33-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v33/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v33-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
mistralai-mistral-nemo-9330-v33-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%|▏ | 5/363 [00:00<00:10, 33.03it/s]
Loading 0: 4%|▎ | 13/363 [00:00<00:06, 52.01it/s]
Loading 0: 5%|▌ | 19/363 [00:00<00:07, 43.23it/s]
Loading 0: 7%|▋ | 24/363 [00:00<00:07, 42.39it/s]
Loading 0: 9%|▊ | 31/363 [00:00<00:06, 47.84it/s]
Loading 0: 10%|█ | 37/363 [00:00<00:07, 44.89it/s]
Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 43.37it/s]
Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 48.33it/s]
Loading 0: 15%|█▌ | 55/363 [00:01<00:07, 43.48it/s]
Loading 0: 17%|█▋ | 61/363 [00:01<00:09, 32.96it/s]
Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 32.70it/s]
Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.18it/s]
Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 38.17it/s]
Loading 0: 23%|██▎ | 83/363 [00:02<00:07, 37.87it/s]
Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 43.02it/s]
Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 41.33it/s]
Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 40.86it/s]
Loading 0: 29%|██▉ | 107/363 [00:02<00:05, 45.18it/s]
Loading 0: 31%|███ | 112/363 [00:02<00:05, 45.86it/s]
Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 42.16it/s]
Loading 0: 34%|███▎ | 122/363 [00:02<00:05, 43.11it/s]
Loading 0: 35%|███▍ | 127/363 [00:03<00:06, 36.39it/s]
Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 43.26it/s]
Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 43.22it/s]
Loading 0: 40%|███▉ | 144/363 [00:03<00:07, 27.74it/s]
Loading 0: 41%|████ | 149/363 [00:03<00:07, 29.93it/s]
Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 36.65it/s]
Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 38.34it/s]
Loading 0: 46%|████▌ | 166/363 [00:04<00:04, 39.86it/s]
Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 38.80it/s]
Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 38.27it/s]
Loading 0: 50%|█████ | 183/363 [00:04<00:04, 43.21it/s]
Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 43.41it/s]
Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 43.16it/s]
Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 41.24it/s]
Loading 0: 56%|█████▌ | 204/363 [00:05<00:03, 40.84it/s]
Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 44.70it/s]
Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 45.11it/s]
Loading 0: 61%|██████ | 221/363 [00:05<00:02, 48.98it/s]
Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 32.21it/s]
Loading 0: 64%|██████▍ | 232/363 [00:05<00:03, 33.69it/s]
Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 37.05it/s]
Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 38.98it/s]
Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 41.00it/s]
Loading 0: 70%|██████▉ | 253/363 [00:06<00:02, 40.37it/s]
Loading 0: 71%|███████ | 258/363 [00:06<00:02, 39.66it/s]
Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 44.97it/s]
Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 43.23it/s]
Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 41.81it/s]
Loading 0: 78%|███████▊ | 282/363 [00:06<00:01, 46.03it/s]
Loading 0: 79%|███████▉ | 287/363 [00:07<00:01, 46.32it/s]
Loading 0: 80%|████████ | 292/363 [00:07<00:01, 46.52it/s]
Loading 0: 82%|████████▏ | 298/363 [00:07<00:01, 43.99it/s]
Loading 0: 84%|████████▎ | 304/363 [00:14<00:21, 2.68it/s]
Loading 0: 85%|████████▍ | 308/363 [00:14<00:16, 3.42it/s]
Loading 0: 86%|████████▌ | 312/363 [00:14<00:11, 4.40it/s]
Loading 0: 88%|████████▊ | 320/363 [00:14<00:05, 7.23it/s]
Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.72it/s]
Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.29it/s]
Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 17.15it/s]
Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 20.92it/s]
Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 24.28it/s]
Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 30.81it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 33.54it/s]
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
mistralai-mistral-nemo-9330-v33-mkmlizer: warnings.warn(
mistralai-mistral-nemo-9330-v33-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
mistralai-mistral-nemo-9330-v33-mkmlizer: warnings.warn(
mistralai-mistral-nemo-9330-v33-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
mistralai-mistral-nemo-9330-v33-mkmlizer: warnings.warn(
mistralai-mistral-nemo-9330-v33-mkmlizer:
Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]
Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.56s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.96s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.20s/it]
mistralai-mistral-nemo-9330-v33-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.16it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.58it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.25it/s]
mistralai-mistral-nemo-9330-v33-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
mistralai-mistral-nemo-9330-v33-mkmlizer: Saving duration: 1.334s
mistralai-mistral-nemo-9330-v33-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.363s
mistralai-mistral-nemo-9330-v33-mkmlizer: creating bucket guanaco-reward-models
mistralai-mistral-nemo-9330-v33-mkmlizer: Bucket 's3://guanaco-reward-models/' created
mistralai-mistral-nemo-9330-v33-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v33_reward
mistralai-mistral-nemo-9330-v33-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v33_reward/config.json
mistralai-mistral-nemo-9330-v33-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v33_reward/tokenizer_config.json
mistralai-mistral-nemo-9330-v33-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v33_reward/special_tokens_map.json
mistralai-mistral-nemo-9330-v33-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v33_reward/merges.txt
mistralai-mistral-nemo-9330-v33-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v33_reward/vocab.json
mistralai-mistral-nemo-9330-v33-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v33_reward/tokenizer.json
mistralai-mistral-nemo-9330-v33-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/mistralai-mistral-nemo-9330-v33_reward/reward.tensors
Job mistralai-mistral-nemo-9330-v33-mkmlizer completed after 136.54s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v33-mkmlizer
Pipeline stage MKMLizer completed in 137.71s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service mistralai-mistral-nemo-9330-v33
Waiting for inference service mistralai-mistral-nemo-9330-v33 to be ready
Inference service mistralai-mistral-nemo-9330-v33 ready after 140.95304608345032s
Pipeline stage ISVCDeployer completed in 142.73s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3278391361236572s
Received healthy response to inference request in 0.8684282302856445s
Received healthy response to inference request in 1.4963111877441406s
Received healthy response to inference request in 0.5821480751037598s
Received healthy response to inference request in 0.9425995349884033s
5 requests
0 failed requests
5th percentile: 0.6394041061401368
10th percentile: 0.6966601371765136
20th percentile: 0.8111721992492675
30th percentile: 0.8832624912261963
40th percentile: 0.9129310131072998
50th percentile: 0.9425995349884033
60th percentile: 1.0966953754425048
70th percentile: 1.2507912158966064
80th percentile: 1.361533546447754
90th percentile: 1.4289223670959472
95th percentile: 1.4626167774200438
99th percentile: 1.4895723056793213
mean time: 1.0434652328491212
Pipeline stage StressChecker completed in 5.95s
mistralai-mistral-nemo-_9330_v33 status is now deployed due to DeploymentManager action
mistralai-mistral-nemo-_9330_v33 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of mistralai-mistral-nemo-_9330_v33
Running pipeline stage ISVCDeleter
Checking if service mistralai-mistral-nemo-9330-v33 is running
Tearing down inference service mistralai-mistral-nemo-9330-v33
Service mistralai-mistral-nemo-9330-v33 has been torndown
Pipeline stage ISVCDeleter completed in 4.87s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key mistralai-mistral-nemo-9330-v33/config.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-nemo-9330-v33/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-mistral-nemo-9330-v33/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-nemo-9330-v33/tokenizer.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-nemo-9330-v33/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key mistralai-mistral-nemo-9330-v33_reward/config.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v33_reward/merges.txt from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v33_reward/reward.tensors from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v33_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v33_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v33_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-nemo-9330-v33_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.27s
mistralai-mistral-nemo-_9330_v33 status is now torndown due to DeploymentManager action