Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ Version: 0.9.5.post2 ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: Downloaded to shared memory in 37.298s
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: lm_head.weight torch.Size([139542528])
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v38/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: 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-v38-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: 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-v38-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v38-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-v38-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer:
Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]
Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.09s/it]
Downloading shards: 100%|██████████| 2/2 [00:10<00:00, 4.85s/it]
Downloading shards: 100%|██████████| 2/2 [00:10<00:00, 5.04s/it]
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.92it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.10it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.84it/s]
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: Saving duration: 1.741s
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.102s
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v38_reward
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v38_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v38_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v38_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v38_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v38_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v38_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v38_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer completed after 104.3s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v38-mkmlizer
Pipeline stage MKMLizer completed in 105.30s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v38
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v38 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v38 ready after 50.306214570999146s
Pipeline stage ISVCDeployer completed in 57.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.590754270553589s
Received healthy response to inference request in 1.7371826171875s
Received healthy response to inference request in 1.728837251663208s
Received healthy response to inference request in 1.6833136081695557s
Received healthy response to inference request in 1.6950972080230713s
5 requests
0 failed requests
5th percentile: 1.6856703281402587
10th percentile: 1.6880270481109618
20th percentile: 1.6927404880523682
30th percentile: 1.7018452167510987
40th percentile: 1.7153412342071532
50th percentile: 1.728837251663208
60th percentile: 1.7321753978729248
70th percentile: 1.7355135440826417
80th percentile: 1.907896947860718
90th percentile: 2.2493256092071534
95th percentile: 2.420039939880371
99th percentile: 2.556611404418945
mean time: 1.8870369911193847
Pipeline stage StressChecker completed in 10.35s
chaiml-sao10k-l3-rp-v3-3_v38 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v38 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v38
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v38 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.00s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v38/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v38/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v38/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v38/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v38/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v38_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v38_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v38_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v38_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v38_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v38_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v38_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.20s
chaiml-sao10k-l3-rp-v3-3_v38 status is now torndown due to DeploymentManager action