Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: Downloaded to shared memory in 22.796s
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:04<11:42, 2.43s/it]
Loading 0: 5%|▍ | 14/291 [00:04<01:12, 3.81it/s]
Loading 0: 9%|▉ | 27/291 [00:05<00:30, 8.73it/s]
Loading 0: 14%|█▍ | 41/291 [00:05<00:16, 15.54it/s]
Loading 0: 19%|█▊ | 54/291 [00:05<00:10, 23.49it/s]
Loading 0: 23%|██▎ | 66/291 [00:05<00:08, 25.43it/s]
Loading 0: 26%|██▋ | 77/291 [00:05<00:06, 32.96it/s]
Loading 0: 31%|███ | 90/291 [00:05<00:04, 44.05it/s]
Loading 0: 36%|███▌ | 104/291 [00:06<00:03, 56.45it/s]
Loading 0: 41%|████ | 118/291 [00:06<00:02, 70.06it/s]
Loading 0: 45%|████▌ | 131/291 [00:06<00:01, 80.06it/s]
Loading 0: 50%|████▉ | 145/291 [00:06<00:01, 91.86it/s]
Loading 0: 54%|█████▍ | 158/291 [00:06<00:01, 98.26it/s]
Loading 0: 59%|█████▉ | 171/291 [00:06<00:01, 65.04it/s]
Loading 0: 64%|██████▎ | 185/291 [00:06<00:01, 76.18it/s]
Loading 0: 68%|██████▊ | 199/291 [00:07<00:01, 88.46it/s]
Loading 0: 73%|███████▎ | 212/291 [00:07<00:00, 95.83it/s]
Loading 0: 78%|███████▊ | 227/291 [00:07<00:00, 108.37it/s]
Loading 0: 82%|████████▏ | 240/291 [00:07<00:00, 107.76it/s]
Loading 0: 88%|████████▊ | 256/291 [00:07<00:00, 120.06it/s]
Loading 0: 93%|█████████▎| 270/291 [00:07<00:00, 74.32it/s]
Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 84.28it/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-v26-mkmlizer: quantized model in 24.581s
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 47.377s
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v26
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v26/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v26/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v26/config.json
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v26/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v26/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
nitral-ai-hathor-l3-8b-v-01-v26-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-v26-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v26-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-v26-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v26-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-v26-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v26-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-v26-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: Saving duration: 0.154s
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 2.762s
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v26_reward
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v26_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v26_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v26_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v26_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v26_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v26_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v26_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer completed after 79.61s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v26-mkmlizer
Pipeline stage MKMLizer completed in 80.95s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.28s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v26
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v26 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v26 ready after 40.59836173057556s
Pipeline stage ISVCDeployer completed in 47.00s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.054417133331299s
Received healthy response to inference request in 1.3728883266448975s
Received healthy response to inference request in 1.3432271480560303s
Received healthy response to inference request in 1.3199236392974854s
Received healthy response to inference request in 1.420752763748169s
5 requests
0 failed requests
5th percentile: 1.3245843410491944
10th percentile: 1.3292450428009033
20th percentile: 1.3385664463043212
30th percentile: 1.3491593837738036
40th percentile: 1.3610238552093505
50th percentile: 1.3728883266448975
60th percentile: 1.392034101486206
70th percentile: 1.4111798763275147
80th percentile: 1.547485637664795
90th percentile: 1.800951385498047
95th percentile: 1.9276842594146728
99th percentile: 2.0290705585479736
mean time: 1.5022418022155761
Pipeline stage StressChecker completed in 10.53s
nitral-ai-hathor-l3-8b-v-01_v26 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v26 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-hathor-l3-8b-v-01_v26
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-hathor-l3-8b-v-01-v26 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.60s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v26/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v26/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v26/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v26/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v26/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v26_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v26_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v26_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v26_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v26_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v26_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v26_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.37s
nitral-ai-hathor-l3-8b-v-01_v26 status is now torndown due to DeploymentManager action