Running pipeline stage MKMLizer
Starting job with name chaiml-elo-alignment-run-3-v31-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v31-mkmlizer to finish
Stopping job with name chaiml-elo-alignment-run-3-v31-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-elo-alignment-run-3-v31-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v31-mkmlizer to finish
chaiml-elo-alignment-run-3-v31-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ _____ __ __ ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ /___/ ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ Version: 0.9.9 ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ belonging to: ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v31-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v31-mkmlizer: Downloaded to shared memory in 59.845s
chaiml-elo-alignment-run-3-v31-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9r_museh, device:0
chaiml-elo-alignment-run-3-v31-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v31-mkmlizer: quantized model in 28.307s
chaiml-elo-alignment-run-3-v31-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 88.152s
chaiml-elo-alignment-run-3-v31-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v31-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v31-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v31
chaiml-elo-alignment-run-3-v31-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v31/config.json
chaiml-elo-alignment-run-3-v31-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v31/special_tokens_map.json
chaiml-elo-alignment-run-3-v31-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v31/tokenizer_config.json
chaiml-elo-alignment-run-3-v31-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v31/tokenizer.json
chaiml-elo-alignment-run-3-v31-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v31/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v31-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-elo-alignment-run-3-v31-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:10, 27.56it/s]
Loading 0: 4%|▍ | 12/291 [00:00<00:07, 37.48it/s]
Loading 0: 5%|▌ | 16/291 [00:00<00:07, 35.00it/s]
Loading 0: 7%|▋ | 21/291 [00:00<00:07, 37.38it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:07, 35.42it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:06, 41.50it/s]
Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 24.83it/s]
Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 26.65it/s]
Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 33.75it/s]
Loading 0: 18%|█▊ | 53/291 [00:01<00:06, 34.72it/s]
Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 35.29it/s]
Loading 0: 21%|██ | 61/291 [00:01<00:06, 33.93it/s]
Loading 0: 23%|██▎ | 66/291 [00:01<00:06, 37.05it/s]
Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 35.45it/s]
Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 34.89it/s]
Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 34.84it/s]
Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 25.26it/s]
Loading 0: 30%|██▉ | 86/291 [00:02<00:07, 27.91it/s]
Loading 0: 31%|███ | 90/291 [00:02<00:06, 30.08it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 30.43it/s]
Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 33.74it/s]
Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 32.36it/s]
Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 35.67it/s]
Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 34.55it/s]
Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 34.96it/s]
Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 39.42it/s]
Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 36.89it/s]
Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 31.01it/s]
Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 30.76it/s]
Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 28.75it/s]
Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.76it/s]
Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 33.12it/s]
Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 35.77it/s]
Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 34.79it/s]
Loading 0: 57%|█████▋ | 165/291 [00:04<00:03, 37.18it/s]
Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 35.40it/s]
Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 38.15it/s]
Loading 0: 61%|██████ | 178/291 [00:05<00:03, 36.47it/s]
Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 41.96it/s]
Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 25.32it/s]
Loading 0: 67%|██████▋ | 194/291 [00:05<00:03, 26.97it/s]
Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 33.81it/s]
Loading 0: 71%|███████ | 206/291 [00:06<00:02, 34.57it/s]
Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 34.86it/s]
Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 33.96it/s]
Loading 0: 75%|███████▌ | 219/291 [00:06<00:01, 36.73it/s]
Loading 0: 77%|███████▋ | 223/291 [00:06<00:01, 35.10it/s]
Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 34.33it/s]
Loading 0: 79%|███████▉ | 231/291 [00:06<00:01, 34.32it/s]
Loading 0: 81%|████████ | 235/291 [00:07<00:02, 25.97it/s]
Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 25.80it/s]
Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 33.82it/s]
Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 33.04it/s]
Loading 0: 88%|████████▊ | 255/291 [00:07<00:01, 34.44it/s]
Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 33.44it/s]
Loading 0: 91%|█████████ | 264/291 [00:07<00:00, 35.37it/s]
Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 34.04it/s]
Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 36.26it/s]
Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 35.04it/s]
Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 35.38it/s]
Loading 0: 98%|█████████▊| 286/291 [00:13<00:01, 2.59it/s]
Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.22it/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-v31-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v31-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-v31-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v31-mkmlizer:
Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]
Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.70s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.22s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.44s/it]
chaiml-elo-alignment-run-3-v31-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.40it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.95it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.60it/s]
chaiml-elo-alignment-run-3-v31-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-alignment-run-3-v31-mkmlizer: Saving duration: 1.352s
chaiml-elo-alignment-run-3-v31-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.162s
chaiml-elo-alignment-run-3-v31-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-alignment-run-3-v31-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-alignment-run-3-v31-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v31_reward
chaiml-elo-alignment-run-3-v31-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v31_reward/config.json
chaiml-elo-alignment-run-3-v31-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v31_reward/special_tokens_map.json
chaiml-elo-alignment-run-3-v31-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v31_reward/tokenizer_config.json
chaiml-elo-alignment-run-3-v31-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v31_reward/merges.txt
chaiml-elo-alignment-run-3-v31-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v31_reward/vocab.json
chaiml-elo-alignment-run-3-v31-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v31_reward/tokenizer.json
chaiml-elo-alignment-run-3-v31-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v31_reward/reward.tensors
Job chaiml-elo-alignment-run-3-v31-mkmlizer completed after 136.07s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v31-mkmlizer
Pipeline stage MKMLizer completed in 138.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-alignment-run-3-v31
Waiting for inference service chaiml-elo-alignment-run-3-v31 to be ready
Inference service chaiml-elo-alignment-run-3-v31 ready after 201.40486478805542s
Pipeline stage ISVCDeployer completed in 203.81s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.217034101486206s
Received healthy response to inference request in 1.35117769241333s
Received healthy response to inference request in 1.3878395557403564s
Received healthy response to inference request in 1.3882668018341064s
Received healthy response to inference request in 1.2962000370025635s
5 requests
0 failed requests
5th percentile: 1.3071955680847167
10th percentile: 1.3181910991668702
20th percentile: 1.3401821613311768
30th percentile: 1.3585100650787354
40th percentile: 1.3731748104095458
50th percentile: 1.3878395557403564
60th percentile: 1.3880104541778564
70th percentile: 1.3881813526153564
80th percentile: 1.5540202617645265
90th percentile: 1.8855271816253663
95th percentile: 2.051280641555786
99th percentile: 2.183883409500122
mean time: 1.5281036376953125
Pipeline stage StressChecker completed in 8.33s
chaiml-elo-alignment-run-3_v31 status is now deployed due to DeploymentManager action
chaiml-elo-alignment-run-3_v31 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-elo-alignment-run-3_v31
Running pipeline stage ISVCDeleter
Checking if service chaiml-elo-alignment-run-3-v31 is running
Tearing down inference service chaiml-elo-alignment-run-3-v31
Service chaiml-elo-alignment-run-3-v31 has been torndown
Pipeline stage ISVCDeleter completed in 5.40s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v31/config.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v31/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v31/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v31/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v31/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v31_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v31_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v31_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v31_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v31_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v31_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v31_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.63s
chaiml-elo-alignment-run-3_v31 status is now torndown due to DeploymentManager action