Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-colt-ta-3990-v3-mkmlizer
Waiting for job on nitral-ai-hathor-colt-ta-3990-v3-mkmlizer to finish
Stopping job with name nitral-ai-hathor-colt-ta-3990-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name nitral-ai-hathor-colt-ta-3990-v3-mkmlizer
Waiting for job on nitral-ai-hathor-colt-ta-3990-v3-mkmlizer to finish
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ /___/ ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ Version: 0.9.9 ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ║ ║
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: quantized model in 26.293s
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: Processed model Nitral-AI/Hathor_Colt_Tahsin-L3-8B-v0.945 in 48.457s
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-colt-ta-3990-v3
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-colt-ta-3990-v3/config.json
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-colt-ta-3990-v3/special_tokens_map.json
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-colt-ta-3990-v3/tokenizer_config.json
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-colt-ta-3990-v3/tokenizer.json
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-colt-ta-3990-v3/flywheel_model.0.safetensors
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:04<11:41, 2.43s/it]
Loading 0: 2%|▏ | 6/291 [00:04<03:06, 1.53it/s]
Loading 0: 4%|▍ | 13/291 [00:05<01:06, 4.18it/s]
Loading 0: 6%|▌ | 18/291 [00:05<00:41, 6.58it/s]
Loading 0: 8%|▊ | 23/291 [00:05<00:27, 9.61it/s]
Loading 0: 10%|▉ | 29/291 [00:05<00:19, 13.47it/s]
Loading 0: 12%|█▏ | 34/291 [00:05<00:14, 17.17it/s]
Loading 0: 14%|█▎ | 40/291 [00:05<00:11, 22.81it/s]
Loading 0: 15%|█▌ | 45/291 [00:05<00:09, 26.72it/s]
Loading 0: 17%|█▋ | 50/291 [00:05<00:07, 30.94it/s]
Loading 0: 19%|█▉ | 56/291 [00:06<00:07, 33.29it/s]
Loading 0: 21%|██ | 61/291 [00:06<00:09, 25.39it/s]
Loading 0: 23%|██▎ | 68/291 [00:06<00:06, 32.66it/s]
Loading 0: 25%|██▌ | 74/291 [00:06<00:06, 35.01it/s]
Loading 0: 27%|██▋ | 79/291 [00:06<00:05, 36.68it/s]
Loading 0: 30%|██▉ | 86/291 [00:06<00:04, 42.66it/s]
Loading 0: 32%|███▏ | 92/291 [00:06<00:04, 41.87it/s]
Loading 0: 33%|███▎ | 97/291 [00:07<00:04, 42.76it/s]
Loading 0: 36%|███▌ | 104/291 [00:07<00:03, 48.26it/s]
Loading 0: 38%|███▊ | 110/291 [00:07<00:03, 46.26it/s]
Loading 0: 40%|███▉ | 115/291 [00:07<00:03, 46.16it/s]
Loading 0: 42%|████▏ | 122/291 [00:07<00:03, 51.19it/s]
Loading 0: 44%|████▍ | 128/291 [00:07<00:03, 46.57it/s]
Loading 0: 46%|████▌ | 133/291 [00:07<00:03, 46.74it/s]
Loading 0: 48%|████▊ | 140/291 [00:07<00:02, 51.86it/s]
Loading 0: 50%|█████ | 146/291 [00:08<00:03, 47.63it/s]
Loading 0: 52%|█████▏ | 151/291 [00:08<00:03, 44.99it/s]
Loading 0: 54%|█████▍ | 158/291 [00:08<00:02, 49.90it/s]
Loading 0: 56%|█████▋ | 164/291 [00:08<00:02, 46.87it/s]
Loading 0: 58%|█████▊ | 169/291 [00:08<00:03, 31.84it/s]
Loading 0: 60%|██████ | 176/291 [00:08<00:02, 38.56it/s]
Loading 0: 63%|██████▎ | 182/291 [00:09<00:02, 39.19it/s]
Loading 0: 64%|██████▍ | 187/291 [00:09<00:02, 39.87it/s]
Loading 0: 67%|██████▋ | 194/291 [00:09<00:02, 45.61it/s]
Loading 0: 69%|██████▊ | 200/291 [00:09<00:02, 44.13it/s]
Loading 0: 70%|███████ | 205/291 [00:09<00:01, 43.96it/s]
Loading 0: 73%|███████▎ | 212/291 [00:09<00:01, 49.73it/s]
Loading 0: 75%|███████▍ | 218/291 [00:09<00:01, 47.40it/s]
Loading 0: 77%|███████▋ | 223/291 [00:09<00:01, 47.09it/s]
Loading 0: 79%|███████▉ | 230/291 [00:09<00:01, 51.75it/s]
Loading 0: 81%|████████ | 236/291 [00:10<00:01, 46.55it/s]
Loading 0: 83%|████████▎ | 241/291 [00:10<00:01, 46.09it/s]
Loading 0: 85%|████████▍ | 247/291 [00:10<00:00, 47.91it/s]
Loading 0: 87%|████████▋ | 252/291 [00:10<00:00, 47.66it/s]
Loading 0: 89%|████████▊ | 258/291 [00:10<00:00, 43.58it/s]
Loading 0: 91%|█████████▏| 266/291 [00:10<00:00, 35.70it/s]
Loading 0: 93%|█████████▎| 272/291 [00:11<00:00, 37.37it/s]
Loading 0: 95%|█████████▌| 277/291 [00:11<00:00, 39.29it/s]
Loading 0: 98%|█████████▊| 284/291 [00:11<00:00, 45.27it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 43.22it/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.
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: warnings.warn(
nitral-ai-hathor-colt-ta-3990-v3-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.
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: warnings.warn(
nitral-ai-hathor-colt-ta-3990-v3-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.
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: warnings.warn(
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: Saving duration: 1.396s
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.890s
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-colt-ta-3990-v3_reward/config.json
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-colt-ta-3990-v3_reward/special_tokens_map.json
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-colt-ta-3990-v3_reward/tokenizer_config.json
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-colt-ta-3990-v3_reward/merges.txt
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-colt-ta-3990-v3_reward/vocab.json
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-colt-ta-3990-v3_reward/tokenizer.json
nitral-ai-hathor-colt-ta-3990-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-colt-ta-3990-v3_reward/reward.tensors
Job nitral-ai-hathor-colt-ta-3990-v3-mkmlizer completed after 94.25s with status: succeeded
Stopping job with name nitral-ai-hathor-colt-ta-3990-v3-mkmlizer
Pipeline stage MKMLizer completed in 95.84s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-colt-ta-3990-v3
Waiting for inference service nitral-ai-hathor-colt-ta-3990-v3 to be ready
Failed to get response for submission chaiml-elo-alignment-run-3_v17: ('http://chaiml-elo-alignment-run-3-v17-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:49922->127.0.0.1:8080: read: connection reset by peer\n')
Inference service nitral-ai-hathor-colt-ta-3990-v3 ready after 201.30472207069397s
Pipeline stage ISVCDeployer completed in 203.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4172747135162354s
Received healthy response to inference request in 1.4889438152313232s
Received healthy response to inference request in 1.463721752166748s
Received healthy response to inference request in 1.4409971237182617s
Received healthy response to inference request in 1.4863059520721436s
5 requests
0 failed requests
5th percentile: 1.445542049407959
10th percentile: 1.4500869750976562
20th percentile: 1.4591768264770508
30th percentile: 1.4682385921478271
40th percentile: 1.4772722721099854
50th percentile: 1.4863059520721436
60th percentile: 1.4873610973358153
70th percentile: 1.4884162425994873
80th percentile: 1.6746099948883058
90th percentile: 2.0459423542022708
95th percentile: 2.231608533859253
99th percentile: 2.380141477584839
mean time: 1.6594486713409424
Pipeline stage StressChecker completed in 8.97s
nitral-ai-hathor-colt-ta_3990_v3 status is now deployed due to DeploymentManager action
nitral-ai-hathor-colt-ta_3990_v3 status is now inactive due to auto deactivation removed underperforming models
nitral-ai-hathor-colt-ta_3990_v3 status is now torndown due to DeploymentManager action