Running pipeline stage MKMLizer
Starting job with name chaiml-elo-alignment-run-3-v25-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v25-mkmlizer to finish
chaiml-elo-alignment-run-3-v25-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ _____ __ __ ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ /___/ ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ Version: 0.9.9 ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ belonging to: ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v25-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-elo-alignment-run-3-v25-mkmlizer: Downloaded to shared memory in 44.116s
chaiml-elo-alignment-run-3-v25-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmph_iwf_xt, device:0
chaiml-elo-alignment-run-3-v25-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v25-mkmlizer: quantized model in 28.789s
chaiml-elo-alignment-run-3-v25-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 72.905s
chaiml-elo-alignment-run-3-v25-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v25-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v25/config.json
chaiml-elo-alignment-run-3-v25-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v25/special_tokens_map.json
chaiml-elo-alignment-run-3-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v25/tokenizer_config.json
chaiml-elo-alignment-run-3-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v25/tokenizer.json
chaiml-elo-alignment-run-3-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v25/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v25-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-elo-alignment-run-3-v25-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.98it/s]
Loading 0: 4%|▍ | 12/291 [00:00<00:07, 36.85it/s]
Loading 0: 5%|▌ | 16/291 [00:00<00:07, 34.48it/s]
Loading 0: 7%|▋ | 21/291 [00:00<00:07, 37.49it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:07, 35.29it/s]
Loading 0: 10%|█ | 30/291 [00:00<00:06, 39.06it/s]
Loading 0: 12%|█▏ | 34/291 [00:01<00:10, 25.50it/s]
Loading 0: 13%|█▎ | 38/291 [00:01<00:09, 26.85it/s]
Loading 0: 14%|█▍ | 42/291 [00:01<00:09, 26.18it/s]
Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 31.89it/s]
Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 31.61it/s]
Loading 0: 20%|█▉ | 57/291 [00:01<00:07, 33.31it/s]
Loading 0: 21%|██ | 61/291 [00:01<00:07, 32.57it/s]
Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 35.41it/s]
Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 33.66it/s]
Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 33.61it/s]
Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 32.94it/s]
Loading 0: 28%|██▊ | 82/291 [00:02<00:09, 22.93it/s]
Loading 0: 30%|██▉ | 86/291 [00:02<00:07, 25.92it/s]
Loading 0: 31%|███ | 90/291 [00:02<00:07, 28.62it/s]
Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 29.34it/s]
Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 33.16it/s]
Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 32.28it/s]
Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 35.40it/s]
Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 33.85it/s]
Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 33.66it/s]
Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 38.42it/s]
Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 36.27it/s]
Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 29.65it/s]
Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 29.55it/s]
Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 28.04it/s]
Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.30it/s]
Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 32.65it/s]
Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 34.67it/s]
Loading 0: 55%|█████▍ | 160/291 [00:05<00:03, 33.88it/s]
Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 36.74it/s]
Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 34.37it/s]
Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 36.55it/s]
Loading 0: 61%|██████ | 178/291 [00:05<00:03, 35.02it/s]
Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 41.03it/s]
Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 24.90it/s]
Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 26.20it/s]
Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.44it/s]
Loading 0: 70%|███████ | 205/291 [00:06<00:02, 31.80it/s]
Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 34.08it/s]
Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 32.20it/s]
Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 34.90it/s]
Loading 0: 77%|███████▋ | 223/291 [00:06<00:02, 33.75it/s]
Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 33.55it/s]
Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 33.94it/s]
Loading 0: 81%|████████ | 235/291 [00:07<00:02, 25.38it/s]
Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 25.34it/s]
Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 33.15it/s]
Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 32.80it/s]
Loading 0: 88%|████████▊ | 255/291 [00:07<00:01, 35.17it/s]
Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 33.70it/s]
Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 36.32it/s]
Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 34.95it/s]
Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 36.75it/s]
Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 35.17it/s]
Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 34.54it/s]
Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.58it/s]
Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.21it/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-elo-alignment-run-3-v25-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v25-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-elo-alignment-run-3-v25-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v25-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-elo-alignment-run-3-v25-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v25-mkmlizer:
Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]
Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.15s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.07s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.23s/it]
chaiml-elo-alignment-run-3-v25-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.42it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 4.00it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.64it/s]
chaiml-elo-alignment-run-3-v25-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-alignment-run-3-v25-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-alignment-run-3-v25-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-alignment-run-3-v25-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v25_reward
chaiml-elo-alignment-run-3-v25-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v25_reward/config.json
chaiml-elo-alignment-run-3-v25-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v25_reward/special_tokens_map.json
chaiml-elo-alignment-run-3-v25-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v25_reward/tokenizer_config.json
chaiml-elo-alignment-run-3-v25-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v25_reward/merges.txt
chaiml-elo-alignment-run-3-v25-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v25_reward/vocab.json
chaiml-elo-alignment-run-3-v25-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v25_reward/tokenizer.json
chaiml-elo-alignment-run-3-v25-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v25_reward/reward.tensors
Job chaiml-elo-alignment-run-3-v25-mkmlizer completed after 125.45s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v25-mkmlizer
Pipeline stage MKMLizer completed in 126.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-alignment-run-3-v25
Waiting for inference service chaiml-elo-alignment-run-3-v25 to be ready
Inference service chaiml-elo-alignment-run-3-v25 ready after 181.18598818778992s
Pipeline stage ISVCDeployer completed in 183.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1418604850769043s
Received healthy response to inference request in 1.348679542541504s
Received healthy response to inference request in 1.3581690788269043s
Received healthy response to inference request in 1.3907570838928223s
Received healthy response to inference request in 1.2910666465759277s
5 requests
0 failed requests
5th percentile: 1.302589225769043
10th percentile: 1.3141118049621583
20th percentile: 1.3371569633483886
30th percentile: 1.350577449798584
40th percentile: 1.3543732643127442
50th percentile: 1.3581690788269043
60th percentile: 1.3712042808532714
70th percentile: 1.3842394828796387
80th percentile: 1.5409777641296387
90th percentile: 1.8414191246032716
95th percentile: 1.9916398048400878
99th percentile: 2.111816349029541
mean time: 1.5061065673828125
Pipeline stage StressChecker completed in 8.20s
chaiml-elo-alignment-run-3_v25 status is now deployed due to DeploymentManager action
chaiml-elo-alignment-run-3_v25 status is now inactive due to auto deactivation removed underperforming models
chaiml-elo-alignment-run-3_v25 status is now deployed due to admin request
chaiml-elo-alignment-run-3_v25 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-elo-alignment-run-3_v25
Running pipeline stage ISVCDeleter
Checking if service chaiml-elo-alignment-run-3-v25 is running
Tearing down inference service chaiml-elo-alignment-run-3-v25
Service chaiml-elo-alignment-run-3-v25 has been torndown
Pipeline stage ISVCDeleter completed in 6.87s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v25/config.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v25/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v25/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v25/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v25/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v25_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v25_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v25_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v25_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v25_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v25_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v25_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.76s
chaiml-elo-alignment-run-3_v25 status is now torndown due to DeploymentManager action