Running pipeline stage MKMLizer
Starting job with name cycy233-l3-e-v2-c1-v12-mkmlizer
Waiting for job on cycy233-l3-e-v2-c1-v12-mkmlizer to finish
Failed to get response for submission mistralai-mistral-nemo-i_9330_v9: ('http://mistralai-mistral-nemo-i-9330-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
cycy233-l3-e-v2-c1-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ _____ __ __ ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ /___/ ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ Version: 0.9.5.post3 ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ belonging to: ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c1-v12-mkmlizer: Downloaded to shared memory in 20.831s
cycy233-l3-e-v2-c1-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmbxgq3uc, device:0
cycy233-l3-e-v2-c1-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c1-v12-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:02, 119.05it/s]
Loading 0: 9%|▉ | 27/291 [00:00<00:02, 130.80it/s]
Loading 0: 14%|█▍ | 41/291 [00:00<00:02, 124.45it/s]
Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 135.79it/s]
Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 141.63it/s]
Loading 0: 31%|███ | 90/291 [00:00<00:02, 80.86it/s]
Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 90.04it/s]
Loading 0: 40%|████ | 117/291 [00:01<00:01, 100.09it/s]
Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 106.11it/s]
Loading 0: 51%|█████ | 147/291 [00:01<00:01, 118.56it/s]
Loading 0: 55%|█████▌ | 161/291 [00:01<00:01, 121.74it/s]
Loading 0: 60%|██████ | 176/291 [00:01<00:00, 129.17it/s]
Loading 0: 65%|██████▌ | 190/291 [00:01<00:01, 86.96it/s]
Loading 0: 70%|██████▉ | 203/291 [00:01<00:00, 92.65it/s]
Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 106.59it/s]
Loading 0: 81%|████████ | 236/291 [00:02<00:00, 119.11it/s]
Loading 0: 86%|████████▌ | 250/291 [00:02<00:00, 118.50it/s]
Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 123.66it/s]
Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 129.87it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-e-v2-c1-v12-mkmlizer: quantized model in 22.190s
cycy233-l3-e-v2-c1-v12-mkmlizer: Processed model cycy233/L3-e-v2-c1 in 43.022s
cycy233-l3-e-v2-c1-v12-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c1-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c1-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v12
cycy233-l3-e-v2-c1-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v12/config.json
cycy233-l3-e-v2-c1-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v12/special_tokens_map.json
cycy233-l3-e-v2-c1-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v12/tokenizer_config.json
cycy233-l3-e-v2-c1-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v12/tokenizer.json
cycy233-l3-e-v2-c1-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v12/flywheel_model.0.safetensors
cycy233-l3-e-v2-c1-v12-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v2-c1-v12-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.
cycy233-l3-e-v2-c1-v12-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c1-v12-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.
cycy233-l3-e-v2-c1-v12-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c1-v12-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.
cycy233-l3-e-v2-c1-v12-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c1-v12-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c1-v12-mkmlizer: Saving duration: 1.322s
cycy233-l3-e-v2-c1-v12-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.818s
cycy233-l3-e-v2-c1-v12-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c1-v12-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c1-v12-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v12_reward
cycy233-l3-e-v2-c1-v12-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v12_reward/config.json
cycy233-l3-e-v2-c1-v12-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v12_reward/special_tokens_map.json
cycy233-l3-e-v2-c1-v12-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v12_reward/tokenizer_config.json
cycy233-l3-e-v2-c1-v12-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v12_reward/merges.txt
cycy233-l3-e-v2-c1-v12-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v12_reward/vocab.json
cycy233-l3-e-v2-c1-v12-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v12_reward/tokenizer.json
cycy233-l3-e-v2-c1-v12-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v12_reward/reward.tensors
Job cycy233-l3-e-v2-c1-v12-mkmlizer completed after 85.15s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c1-v12-mkmlizer
Pipeline stage MKMLizer completed in 86.19s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c1-v12
Waiting for inference service cycy233-l3-e-v2-c1-v12 to be ready
Failed to get response for submission mistralai-mistral-nemo-i_9330_v9: ('http://mistralai-mistral-nemo-i-9330-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-i_9330_v9: ('http://mistralai-mistral-nemo-i-9330-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-i_9330_v9: ('http://mistralai-mistral-nemo-i-9330-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Retrying (%r) after connection broken by '%r': %s
Inference service cycy233-l3-e-v2-c1-v12 ready after 81.03700542449951s
Pipeline stage ISVCDeployer completed in 82.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3734898567199707s
Received healthy response to inference request in 1.4720609188079834s
Received healthy response to inference request in 1.457610845565796s
Received healthy response to inference request in 1.4426133632659912s
Received healthy response to inference request in 1.4988698959350586s
5 requests
0 failed requests
5th percentile: 1.445612859725952
10th percentile: 1.448612356185913
20th percentile: 1.454611349105835
30th percentile: 1.4605008602142333
40th percentile: 1.4662808895111084
50th percentile: 1.4720609188079834
60th percentile: 1.4827845096588135
70th percentile: 1.4935081005096436
80th percentile: 1.673793888092041
90th percentile: 2.023641872406006
95th percentile: 2.198565864562988
99th percentile: 2.338505058288574
mean time: 1.64892897605896
Pipeline stage StressChecker completed in 8.86s
cycy233-l3-e-v2-c1_v12 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c1_v12 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c1_v12
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c1-v12 is running
Tearing down inference service cycy233-l3-e-v2-c1-v12
Service cycy233-l3-e-v2-c1-v12 has been torndown
Pipeline stage ISVCDeleter completed in 4.48s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v12/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v12/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v12/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v12/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v12/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v12_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v12_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v12_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v12_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v12_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v12_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v12_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.17s
cycy233-l3-e-v2-c1_v12 status is now torndown due to DeploymentManager action