Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ Version: 0.9.7 ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: Downloaded to shared memory in 23.091s
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmsuun79w, device:0
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: quantized model in 25.621s
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 48.713s
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v76
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v76/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v76/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v76/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:04<11:22, 2.36s/it]
Loading 0: 2%|▏ | 6/291 [00:04<03:01, 1.57it/s]
Loading 0: 4%|▍ | 13/291 [00:04<01:04, 4.30it/s]
Loading 0: 7%|▋ | 20/291 [00:05<00:35, 7.63it/s]
Loading 0: 9%|▊ | 25/291 [00:05<00:25, 10.56it/s]
Loading 0: 11%|█▏ | 33/291 [00:05<00:16, 15.93it/s]
Loading 0: 14%|█▍ | 42/291 [00:05<00:11, 22.37it/s]
Loading 0: 17%|█▋ | 50/291 [00:05<00:08, 29.59it/s]
Loading 0: 19%|█▉ | 56/291 [00:05<00:07, 32.42it/s]
Loading 0: 21%|██▏ | 62/291 [00:06<00:08, 27.76it/s]
Loading 0: 23%|██▎ | 68/291 [00:06<00:06, 32.66it/s]
Loading 0: 25%|██▌ | 74/291 [00:06<00:06, 35.21it/s]
Loading 0: 27%|██▋ | 79/291 [00:06<00:05, 37.44it/s]
Loading 0: 30%|██▉ | 86/291 [00:06<00:04, 43.92it/s]
Loading 0: 32%|███▏ | 92/291 [00:06<00:04, 42.52it/s]
Loading 0: 33%|███▎ | 97/291 [00:06<00:04, 43.66it/s]
Loading 0: 35%|███▌ | 103/291 [00:06<00:04, 46.31it/s]
Loading 0: 37%|███▋ | 108/291 [00:07<00:03, 46.51it/s]
Loading 0: 39%|███▉ | 113/291 [00:07<00:03, 47.09it/s]
Loading 0: 41%|████ | 119/291 [00:07<00:03, 45.44it/s]
Loading 0: 43%|████▎ | 124/291 [00:07<00:03, 45.61it/s]
Loading 0: 45%|████▌ | 131/291 [00:07<00:03, 52.08it/s]
Loading 0: 47%|████▋ | 137/291 [00:07<00:03, 49.34it/s]
Loading 0: 49%|████▉ | 143/291 [00:07<00:02, 51.17it/s]
Loading 0: 51%|█████ | 149/291 [00:07<00:02, 52.64it/s]
Loading 0: 53%|█████▎ | 155/291 [00:07<00:02, 47.57it/s]
Loading 0: 55%|█████▍ | 160/291 [00:08<00:02, 46.51it/s]
Loading 0: 57%|█████▋ | 166/291 [00:08<00:03, 35.54it/s]
Loading 0: 59%|█████▉ | 172/291 [00:08<00:02, 40.40it/s]
Loading 0: 61%|██████ | 177/291 [00:08<00:03, 37.78it/s]
Loading 0: 64%|██████▎ | 185/291 [00:08<00:02, 46.65it/s]
Loading 0: 66%|██████▌ | 191/291 [00:08<00:02, 45.81it/s]
Loading 0: 67%|██████▋ | 196/291 [00:08<00:02, 46.42it/s]
Loading 0: 70%|██████▉ | 203/291 [00:09<00:01, 52.15it/s]
Loading 0: 72%|███████▏ | 209/291 [00:09<00:01, 48.22it/s]
Loading 0: 74%|███████▍ | 215/291 [00:09<00:01, 50.31it/s]
Loading 0: 76%|███████▋ | 222/291 [00:09<00:01, 45.87it/s]
Loading 0: 79%|███████▉ | 230/291 [00:09<00:01, 52.65it/s]
Loading 0: 81%|████████ | 236/291 [00:09<00:01, 49.94it/s]
Loading 0: 83%|████████▎ | 242/291 [00:09<00:00, 51.47it/s]
Loading 0: 86%|████████▌ | 249/291 [00:09<00:00, 48.13it/s]
Loading 0: 88%|████████▊ | 257/291 [00:10<00:00, 55.21it/s]
Loading 0: 90%|█████████ | 263/291 [00:10<00:00, 51.53it/s]
Loading 0: 92%|█████████▏| 269/291 [00:10<00:00, 36.30it/s]
Loading 0: 95%|█████████▍| 276/291 [00:10<00:00, 37.64it/s]
Loading 0: 98%|█████████▊| 284/291 [00:10<00:00, 45.50it/s]
Loading 0: 100%|█████████▉| 290/291 [00:10<00:00, 44.06it/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.
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v76-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.
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v76-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.
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer:
Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]
Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.67s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.90s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.16s/it]
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.39it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.96it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.60it/s]
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: Saving duration: 1.352s
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.091s
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v76_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v76_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v76_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v76_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v76_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v76_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v76_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer completed after 95.51s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v76-mkmlizer
Pipeline stage MKMLizer completed in 95.96s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v76
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v76 to be ready
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-sao10k-l3-rp-v3-3-v76 ready after 141.30098152160645s
Pipeline stage ISVCDeployer completed in 141.73s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0476388931274414s
Received healthy response to inference request in 1.2383551597595215s
Received healthy response to inference request in 1.246826410293579s
Received healthy response to inference request in 1.2641594409942627s
Received healthy response to inference request in 1.2212369441986084s
5 requests
0 failed requests
5th percentile: 1.224660587310791
10th percentile: 1.2280842304229735
20th percentile: 1.234931516647339
30th percentile: 1.240049409866333
40th percentile: 1.243437910079956
50th percentile: 1.246826410293579
60th percentile: 1.2537596225738525
70th percentile: 1.260692834854126
80th percentile: 1.4208553314208985
90th percentile: 1.73424711227417
95th percentile: 1.8909430027008056
99th percentile: 2.016299715042114
mean time: 1.4036433696746826
Pipeline stage StressChecker completed in 7.66s
chaiml-sao10k-l3-rp-v3-3_v76 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v76 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v76
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v76 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v76
Service chaiml-sao10k-l3-rp-v3-3-v76 has been torndown
Pipeline stage ISVCDeleter completed in 4.85s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v76/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v76/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v76/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v76/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v76/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v76_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v76_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v76_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v76_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v76_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v76_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v76_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.64s
chaiml-sao10k-l3-rp-v3-3_v76 status is now torndown due to DeploymentManager action