Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: Downloaded to shared memory in 25.375s
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:05<13:32, 2.81s/it]
Loading 0: 4%|▍ | 13/291 [00:05<01:30, 3.07it/s]
Loading 0: 8%|▊ | 24/291 [00:05<00:39, 6.69it/s]
Loading 0: 14%|█▎ | 40/291 [00:05<00:18, 13.74it/s]
Loading 0: 18%|█▊ | 51/291 [00:06<00:12, 19.57it/s]
Loading 0: 21%|██▏ | 62/291 [00:06<00:11, 20.71it/s]
Loading 0: 26%|██▌ | 76/291 [00:06<00:07, 30.32it/s]
Loading 0: 30%|██▉ | 87/291 [00:06<00:05, 38.07it/s]
Loading 0: 35%|███▌ | 103/291 [00:06<00:03, 53.18it/s]
Loading 0: 40%|███▉ | 115/291 [00:06<00:02, 62.48it/s]
Loading 0: 45%|████▍ | 130/291 [00:07<00:02, 77.13it/s]
Loading 0: 49%|████▉ | 143/291 [00:07<00:01, 84.56it/s]
Loading 0: 54%|█████▍ | 157/291 [00:07<00:01, 95.75it/s]
Loading 0: 58%|█████▊ | 170/291 [00:07<00:02, 55.47it/s]
Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 67.73it/s]
Loading 0: 67%|██████▋ | 195/291 [00:07<00:01, 73.01it/s]
Loading 0: 73%|███████▎ | 211/291 [00:08<00:00, 89.14it/s]
Loading 0: 77%|███████▋ | 223/291 [00:08<00:00, 93.57it/s]
Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 105.43it/s]
Loading 0: 86%|████████▋ | 251/291 [00:08<00:00, 106.95it/s]
Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 114.04it/s]
Loading 0: 96%|█████████▌| 278/291 [00:08<00:00, 60.55it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: quantized model in 29.212s
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 54.588s
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v61
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v61/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v61/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v61/config.json
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v61/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v61/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: Saving duration: 0.187s
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 2.248s
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v61_reward
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v61_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v61_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v61_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v61_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v61_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v61_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v61_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer completed after 73.65s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v61-mkmlizer
Pipeline stage MKMLizer completed in 74.66s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v61
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v61 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v61 ready after 40.20113492012024s
Pipeline stage ISVCDeployer completed in 47.53s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8922622203826904s
Received healthy response to inference request in 1.016965389251709s
Received healthy response to inference request in 1.1072049140930176s
Received healthy response to inference request in 1.0675642490386963s
Received healthy response to inference request in 1.1158778667449951s
5 requests
0 failed requests
5th percentile: 1.0270851612091065
10th percentile: 1.0372049331665039
20th percentile: 1.0574444770812987
30th percentile: 1.0754923820495605
40th percentile: 1.091348648071289
50th percentile: 1.1072049140930176
60th percentile: 1.1106740951538085
70th percentile: 1.1141432762145995
80th percentile: 1.2711547374725343
90th percentile: 1.5817084789276123
95th percentile: 1.7369853496551513
99th percentile: 1.8612068462371827
mean time: 1.2399749279022216
Pipeline stage StressChecker completed in 7.02s
nitral-ai-hathor-l3-8b-v-01_v61 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v61 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-hathor-l3-8b-v-01_v61
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-hathor-l3-8b-v-01-v61 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.59s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v61/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v61/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v61/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v61/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v61/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v61_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v61_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v61_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v61_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v61_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v61_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v61_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.50s
nitral-ai-hathor-l3-8b-v-01_v61 status is now torndown due to DeploymentManager action