Running pipeline stage MKMLizer
Starting job with name chaiml-augment-alignment-v1-mkmlizer
Waiting for job on chaiml-augment-alignment-v1-mkmlizer to finish
chaiml-augment-alignment-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-augment-alignment-v1-mkmlizer: ║ _____ __ __ ║
chaiml-augment-alignment-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-augment-alignment-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-augment-alignment-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-augment-alignment-v1-mkmlizer: ║ /___/ ║
chaiml-augment-alignment-v1-mkmlizer: ║ ║
chaiml-augment-alignment-v1-mkmlizer: ║ Version: 0.8.14 ║
chaiml-augment-alignment-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-augment-alignment-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-augment-alignment-v1-mkmlizer: ║ ║
chaiml-augment-alignment-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-augment-alignment-v1-mkmlizer: ║ belonging to: ║
chaiml-augment-alignment-v1-mkmlizer: ║ ║
chaiml-augment-alignment-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-augment-alignment-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-augment-alignment-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-augment-alignment-v1-mkmlizer: ║ ║
chaiml-augment-alignment-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-augment-alignment-v1-mkmlizer: Downloaded to shared memory in 68.488s
chaiml-augment-alignment-v1-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-augment-alignment-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-augment-alignment-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:06, 45.04it/s]
Loading 0: 5%|▍ | 14/291 [00:00<00:04, 59.77it/s]
Loading 0: 8%|▊ | 23/291 [00:00<00:04, 63.69it/s]
Loading 0: 11%|█▏ | 33/291 [00:00<00:07, 36.76it/s]
Loading 0: 13%|█▎ | 38/291 [00:00<00:06, 38.88it/s]
Loading 0: 15%|█▍ | 43/291 [00:01<00:06, 40.54it/s]
Loading 0: 17%|█▋ | 50/291 [00:01<00:05, 44.45it/s]
Loading 0: 20%|██ | 59/291 [00:01<00:04, 51.28it/s]
Loading 0: 23%|██▎ | 68/291 [00:01<00:03, 56.23it/s]
Loading 0: 26%|██▋ | 77/291 [00:01<00:03, 62.84it/s]
Loading 0: 29%|██▉ | 84/291 [00:01<00:06, 34.35it/s]
Loading 0: 32%|███▏ | 92/291 [00:02<00:05, 39.68it/s]
Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 46.68it/s]
Loading 0: 37%|███▋ | 109/291 [00:02<00:03, 52.09it/s]
Loading 0: 40%|████ | 117/291 [00:02<00:03, 57.85it/s]
Loading 0: 43%|████▎ | 126/291 [00:02<00:02, 60.52it/s]
Loading 0: 46%|████▌ | 133/291 [00:02<00:04, 36.04it/s]
Loading 0: 48%|████▊ | 139/291 [00:03<00:04, 37.15it/s]
Loading 0: 51%|█████ | 148/291 [00:03<00:03, 44.06it/s]
Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 49.81it/s]
Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 54.26it/s]
Loading 0: 60%|██████ | 175/291 [00:03<00:02, 57.86it/s]
Loading 0: 64%|██████▍ | 186/291 [00:04<00:02, 40.03it/s]
Loading 0: 66%|██████▌ | 192/291 [00:04<00:02, 40.16it/s]
Loading 0: 69%|██████▉ | 201/291 [00:04<00:01, 46.14it/s]
Loading 0: 72%|███████▏ | 210/291 [00:04<00:01, 51.42it/s]
Loading 0: 75%|███████▌ | 219/291 [00:04<00:01, 55.76it/s]
Loading 0: 78%|███████▊ | 227/291 [00:04<00:01, 56.73it/s]
Loading 0: 80%|████████ | 234/291 [00:05<00:01, 34.28it/s]
Loading 0: 82%|████████▏ | 239/291 [00:05<00:01, 36.13it/s]
Loading 0: 85%|████████▌ | 248/291 [00:05<00:00, 43.40it/s]
Loading 0: 88%|████████▊ | 257/291 [00:05<00:00, 49.54it/s]
Loading 0: 91%|█████████▏| 266/291 [00:05<00:00, 54.61it/s]
Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 59.79it/s]
Loading 0: 97%|█████████▋| 282/291 [00:05<00:00, 64.38it/s]
Loading 0: 100%|█████████▉| 290/291 [00:12<00:00, 3.74it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaiml-augment-alignment-v1-mkmlizer: quantized model in 31.392s
chaiml-augment-alignment-v1-mkmlizer: Processed model ChaiML/augment-alignment in 99.881s
chaiml-augment-alignment-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-augment-alignment-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-augment-alignment-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-augment-alignment-v1
chaiml-augment-alignment-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-augment-alignment-v1/tokenizer_config.json
chaiml-augment-alignment-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-augment-alignment-v1/config.json
chaiml-augment-alignment-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-augment-alignment-v1/special_tokens_map.json
chaiml-augment-alignment-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-augment-alignment-v1/tokenizer.json
chaiml-augment-alignment-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-augment-alignment-v1/flywheel_model.0.safetensors
chaiml-augment-alignment-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-augment-alignment-v1-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.
chaiml-augment-alignment-v1-mkmlizer: warnings.warn(
chaiml-augment-alignment-v1-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`.
chaiml-augment-alignment-v1-mkmlizer: warnings.warn(
chaiml-augment-alignment-v1-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.
chaiml-augment-alignment-v1-mkmlizer: warnings.warn(
chaiml-augment-alignment-v1-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.
chaiml-augment-alignment-v1-mkmlizer: warnings.warn(
chaiml-augment-alignment-v1-mkmlizer:
Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]
Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.46s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.81s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.21s/it]
chaiml-augment-alignment-v1-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.63it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.63it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.41it/s]
chaiml-augment-alignment-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-augment-alignment-v1-mkmlizer: Saving duration: 2.234s
chaiml-augment-alignment-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.415s
chaiml-augment-alignment-v1-mkmlizer: creating bucket guanaco-reward-models
chaiml-augment-alignment-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-augment-alignment-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-augment-alignment-v1_reward
chaiml-augment-alignment-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-augment-alignment-v1_reward/config.json
chaiml-augment-alignment-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-augment-alignment-v1_reward/tokenizer_config.json
chaiml-augment-alignment-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-augment-alignment-v1_reward/special_tokens_map.json
chaiml-augment-alignment-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-augment-alignment-v1_reward/merges.txt
chaiml-augment-alignment-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-augment-alignment-v1_reward/vocab.json
chaiml-augment-alignment-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-augment-alignment-v1_reward/tokenizer.json
chaiml-augment-alignment-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-augment-alignment-v1_reward/reward.tensors
Job chaiml-augment-alignment-v1-mkmlizer completed after 149.97s with status: succeeded
Stopping job with name chaiml-augment-alignment-v1-mkmlizer
Pipeline stage MKMLizer completed in 150.92s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-augment-alignment-v1
Waiting for inference service chaiml-augment-alignment-v1 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service chaiml-augment-alignment-v1 ready after 452.3026006221771s
Pipeline stage ISVCDeployer completed in 459.36s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3103976249694824s
Received healthy response to inference request in 1.5976850986480713s
Received healthy response to inference request in 1.5288429260253906s
Connection pool is full, discarding connection: %s
Received healthy response to inference request in 1.5136032104492188s
Received healthy response to inference request in 1.5789031982421875s
5 requests
0 failed requests
5th percentile: 1.5166511535644531
10th percentile: 1.5196990966796875
20th percentile: 1.5257949829101562
30th percentile: 1.53885498046875
40th percentile: 1.5588790893554687
50th percentile: 1.5789031982421875
60th percentile: 1.586415958404541
70th percentile: 1.5939287185668944
80th percentile: 1.7402276039123536
90th percentile: 2.025312614440918
95th percentile: 2.1678551197052
99th percentile: 2.281889123916626
mean time: 1.7058864116668702
Pipeline stage StressChecker completed in 9.34s
chaiml-augment-alignment_v1 status is now deployed due to DeploymentManager action
chaiml-augment-alignment_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-augment-alignment_v1
Running pipeline stage ISVCDeleter
Checking if service chaiml-augment-alignment-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.45s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-augment-alignment-v1/config.json from bucket guanaco-mkml-models
Deleting key chaiml-augment-alignment-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-augment-alignment-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-augment-alignment-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-augment-alignment-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-augment-alignment-v1_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-augment-alignment-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-augment-alignment-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-augment-alignment-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-augment-alignment-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-augment-alignment-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-augment-alignment-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.63s
chaiml-augment-alignment_v1 status is now torndown due to DeploymentManager action