submission_id: rica40325-mistral-3678_v4
developer_uid: rica40325
best_of: 8
celo_rating: 1251.89
display_name: rica40325-mistral-13b-2452_v1
family_friendly_score: 0.5580413920684473
family_friendly_standard_error: 0.009224875630298892
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
ineligible_reason: num_battles<5000
is_internal_developer: False
language_model: rica40325/mistral-3678
latencies: [{'batch_size': 1, 'throughput': 0.6093599779689766, 'latency_mean': 1.6410063922405242, 'latency_p50': 1.6484968662261963, 'latency_p90': 1.81440212726593}, {'batch_size': 3, 'throughput': 1.0666667385525221, 'latency_mean': 2.8024880158901215, 'latency_p50': 2.810359835624695, 'latency_p90': 3.104001498222351}, {'batch_size': 5, 'throughput': 1.2216083475180162, 'latency_mean': 4.077530711889267, 'latency_p50': 4.065055966377258, 'latency_p90': 4.629594087600708}, {'batch_size': 6, 'throughput': 1.244151102352851, 'latency_mean': 4.812072250843048, 'latency_p50': 4.823949217796326, 'latency_p90': 5.417690348625183}, {'batch_size': 8, 'throughput': 1.2289082411337817, 'latency_mean': 6.475214786529541, 'latency_p50': 6.502179861068726, 'latency_p90': 7.2816787481307985}, {'batch_size': 10, 'throughput': 1.180741725857425, 'latency_mean': 8.423697692155837, 'latency_p50': 8.507376670837402, 'latency_p90': 9.580698251724243}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: rica40325/mistral-3678
model_name: rica40325-mistral-13b-2452_v1
model_num_parameters: 12772070400.0
model_repo: rica40325/mistral-3678
model_size: 13B
num_battles: 2957
num_wins: 1470
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.19
timestamp: 2024-09-26T06:36:57+00:00
us_pacific_date: 2024-09-25
win_ratio: 0.4971254649983091
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rica40325-mistral-3678-v4-mkmlizer
Waiting for job on rica40325-mistral-3678-v4-mkmlizer to finish
rica40325-mistral-3678-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-mistral-3678-v4-mkmlizer: ║     _____            __           __                                ║
rica40325-mistral-3678-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-mistral-3678-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-mistral-3678-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-mistral-3678-v4-mkmlizer: ║       /___/                                                         ║
rica40325-mistral-3678-v4-mkmlizer: ║                                                                     ║
rica40325-mistral-3678-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
rica40325-mistral-3678-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-mistral-3678-v4-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-mistral-3678-v4-mkmlizer: ║                                                                     ║
rica40325-mistral-3678-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-mistral-3678-v4-mkmlizer: ║  belonging to:                                                      ║
rica40325-mistral-3678-v4-mkmlizer: ║                                                                     ║
rica40325-mistral-3678-v4-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-mistral-3678-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-mistral-3678-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-mistral-3678-v4-mkmlizer: ║                                                                     ║
rica40325-mistral-3678-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-mistral-3678-v4-mkmlizer: Downloaded to shared memory in 50.600s
rica40325-mistral-3678-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppbew5vqg, device:0
rica40325-mistral-3678-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-mistral-3678-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
rica40325-mistral-3678-v4-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rica40325-mistral-3678-v4-mkmlizer: quantized model in 36.345s
rica40325-mistral-3678-v4-mkmlizer: Processed model rica40325/mistral-3678 in 86.945s
rica40325-mistral-3678-v4-mkmlizer: creating bucket guanaco-mkml-models
rica40325-mistral-3678-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-mistral-3678-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-mistral-3678-v4
rica40325-mistral-3678-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-mistral-3678-v4/config.json
rica40325-mistral-3678-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-mistral-3678-v4/special_tokens_map.json
rica40325-mistral-3678-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-mistral-3678-v4/tokenizer_config.json
rica40325-mistral-3678-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-mistral-3678-v4/tokenizer.json
rica40325-mistral-3678-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-mistral-3678-v4/flywheel_model.0.safetensors
rica40325-mistral-3678-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:06, 52.10it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:04, 71.08it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:03, 89.33it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:03, 87.90it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:03, 87.78it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:14, 20.97it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:10, 28.21it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 35.15it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:06, 39.62it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:05, 47.72it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:04, 61.68it/s]
Loading 0:  34%|███▍      | 123/363 [00:02<00:03, 70.81it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 68.67it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:09, 22.11it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:06, 31.93it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.49it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 42.78it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:03, 51.40it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 57.31it/s]
Loading 0:  57%|█████▋    | 206/363 [00:04<00:02, 64.98it/s]
Loading 0:  59%|█████▉    | 215/363 [00:04<00:02, 67.60it/s]
Loading 0:  62%|██████▏   | 224/363 [00:05<00:06, 21.69it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:04, 31.04it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 37.12it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 43.45it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:01, 50.44it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 58.54it/s]
Loading 0:  79%|███████▉  | 287/363 [00:06<00:01, 65.75it/s]
Loading 0:  82%|████████▏ | 296/363 [00:06<00:00, 69.94it/s]
Loading 0:  84%|████████▍ | 305/363 [00:07<00:02, 21.27it/s]
Loading 0:  88%|████████▊ | 319/363 [00:07<00:01, 30.50it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 38.23it/s]
Loading 0:  94%|█████████▎| 340/363 [00:08<00:00, 44.04it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 50.75it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 57.65it/s]
                                                            

Job rica40325-mistral-3678-v4-mkmlizer completed after 112.38s with status: succeeded
Stopping job with name rica40325-mistral-3678-v4-mkmlizer
Pipeline stage MKMLizer completed in 113.13s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-mistral-3678-v4
Waiting for inference service rica40325-mistral-3678-v4 to be ready
Inference service rica40325-mistral-3678-v4 ready after 220.49341011047363s
Pipeline stage MKMLDeployer completed in 220.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.181234836578369s
Received healthy response to inference request in 1.7786619663238525s
Received healthy response to inference request in 1.8722882270812988s
Received healthy response to inference request in 2.1193835735321045s
Received healthy response to inference request in 1.7752270698547363s
5 requests
0 failed requests
5th percentile: 1.7759140491485597
10th percentile: 1.7766010284423828
20th percentile: 1.7779749870300292
30th percentile: 1.7973872184753419
40th percentile: 1.8348377227783204
50th percentile: 1.8722882270812988
60th percentile: 1.9711263656616211
70th percentile: 2.0699645042419434
80th percentile: 2.1317538261413573
90th percentile: 2.1564943313598635
95th percentile: 2.1688645839691163
99th percentile: 2.1787607860565186
mean time: 1.9453591346740722
Pipeline stage StressChecker completed in 10.33s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.76s
Shutdown handler de-registered
rica40325-mistral-3678_v4 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-mistral-3678-v4-profiler
Waiting for inference service rica40325-mistral-3678-v4-profiler to be ready
Inference service rica40325-mistral-3678-v4-profiler ready after 200.45610094070435s
Pipeline stage MKMLProfilerDeployer completed in 200.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-mistral-3678-v4-profiler-predictor-00001-deploymxhbwh:/code/chaiverse_profiler_1727333216 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-mistral-3678-v4-profiler-predictor-00001-deploymxhbwh --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727333216 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1727333216/summary.json'
kubectl exec -it rica40325-mistral-3678-v4-profiler-predictor-00001-deploymxhbwh --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727333216/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1177.39s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-mistral-3678-v4-profiler is running
Tearing down inference service rica40325-mistral-3678-v4-profiler
Service rica40325-mistral-3678-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.15s
Shutdown handler de-registered
rica40325-mistral-3678_v4 status is now inactive due to auto deactivation removed underperforming models
Deleting key chaiml-nemo-dare-linear-4360-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Waiting for inference service blend-rofur-2024-10-03 to be ready
Running pipeline stage MKMLModelDeleter
Cleaning model data from model cache
Skipping deletion as no model was successfully uploaded
Running pipeline stage MKMLModelDeleter
chaiml-nemo-dare-linear-_7768_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 56.88s
Deleting key chaiml-nemo-dare-linear-4360-v1/special_tokens_map.json from bucket guanaco-mkml-models
Skipping deletion as no model was successfully uploaded
Deleting key chaiml-nemo-dare-linear-4360-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-dare-linear-4360-v1/special_tokens_map.json from bucket guanaco-mkml-models
Skipping deletion as no model was successfully uploaded
Deleting key chaiml-nemo-dare-linear-4360-v1/special_tokens_map.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 63.81s
Cleaning model data from S3
Shutdown handler not registered because Python interpreter is not running in the main thread
Deleting key chaiml-nemo-dare-ties-es-7425-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Shutdown handler de-registered
Deleting key chaiml-nemo-dare-linear-4360-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-dare-linear-4360-v1/tokenizer.json from bucket guanaco-mkml-models
Shutdown handler de-registered
Cleaning model data from model cache
run pipeline %s
Deleting key chaiml-nemo-dare-ties-es-7425-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-dare-linear-4360-v1/tokenizer_config.json from bucket guanaco-mkml-models
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
Shutdown handler de-registered
Deleting key chaiml-nemo-dare-linear-4360-v1/tokenizer_config.json from bucket guanaco-mkml-models
chaiml-nemo-dare-linear-_7768_v1 status is now torndown due to DeploymentManager action
Deleting key chaiml-nemo-dare-ties-es-7425-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-dare-ties-es-7425-v1/tokenizer.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 252.03s
run pipeline %s
run pipeline stage %s
chaiml-nemo-slerp-esao-b_5695_v1 status is now torndown due to DeploymentManager action
Deleting key chaiml-nemo-dare-ties-es-7425-v1/tokenizer.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 194.05s
Running pipeline stage ProductionBlendMKMLTemplater
Deleting key chaiml-nemo-dare-ties-es-7425-v1/tokenizer_config.json from bucket guanaco-mkml-models
Shutdown handler de-registered
Deleting key chaiml-nemo-dare-ties-es-7425-v1/tokenizer_config.json from bucket guanaco-mkml-models
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
chaiml-nemo-dare-linear-_4360_v1 status is now torndown due to DeploymentManager action
Running pipeline stage ProductionBlendMKMLTemplater
Checking if service rica40325-mistral-3678-v4 is running
Pipeline stage MKMLModelDeleter completed in 198.65s
chaiml-nemo-dare-linear-_4360_v1 status is now torndown due to DeploymentManager action
Pipeline stage ProductionBlendMKMLTemplater completed in 54.25s
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
Shutdown handler de-registered
Tearing down inference service rica40325-mistral-3678-v4
run pipeline stage %s
chaiml-nemo-dare-ties-es_7425_v1 status is now torndown due to DeploymentManager action
Pipeline stage ProductionBlendMKMLTemplater completed in 48.75s
chaiml-nemo-dare-ties-es_7425_v1 status is now torndown due to DeploymentManager action
Service rica40325-mistral-3678-v4 has been torndown
Running pipeline stage MKMLDeployer
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 96.91s
Creating inference service blend-rofur-2024-10-03
Running pipeline stage MKMLDeployer
run pipeline stage %s
Ignoring service blend-rofur-2024-10-03 already deployed
Running pipeline stage MKMLModelDeleter
Creating inference service blend-rofur-2024-10-03
Waiting for inference service blend-rofur-2024-10-03 to be ready
admin requested tearing down of rica40325-mistral-3678_v4
Cleaning model data from S3
admin requested tearing down of blend_rofur_2024-10-03
Ignoring service blend-rofur-2024-10-03 already deployed
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of sao10k-lyra-4-2-chai_v3
Cleaning model data from model cache
Shutdown handler not registered because Python interpreter is not running in the main thread
Waiting for inference service blend-rofur-2024-10-03 to be ready
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Deleting key rica40325-mistral-3678-v4/config.json from bucket guanaco-mkml-models
admin requested tearing down of sao10k-lyra-4-2-chai_v4
run pipeline %s
run pipeline stage %s
run pipeline %s
Deleting key rica40325-mistral-3678-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Running pipeline stage MKMLDeleter
admin requested tearing down of blend_rofur_2024-10-03
run pipeline stage %s
rica40325-mistral-3678_v4 status is now torndown due to DeploymentManager action
run pipeline stage %s
Shutdown handler de-registered
rica40325-mistral-3678_v4 status is now torndown due to DeploymentManager action
Tearing down inference service blend-rofur-2024-10-03
Pipeline stage MKMLModelDeleter completed in 13.61s
Shutdown handler not registered because Python interpreter is not running in the main thread
rica40325-mistral-3678_v4 status is now torndown due to DeploymentManager action
admin requested tearing down of rica40325-mistral-3678_v4
admin requested tearing down of blend_rofur_2024-10-03
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of sao10k-lyra-4-2-chai_v3
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-nemo-slerp-esao-b_7186_v1
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-nemo-slerp-lexica_2910_v2
run pipeline stage %s
run pipeline %s
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLDeleter
run pipeline stage %s
Running pipeline stage ProductionBlendMKMLTemplater
run pipeline stage %s
run pipeline %s
admin requested tearing down of blend_rofur_2024-10-03
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLDeleter completed in 38.87s
admin requested tearing down of chaiml-nemo-slerp-esao-b_7186_v1
Pipeline stage %s skipped, reason=%s
Pipeline stage ProductionBlendMKMLTemplater completed in 42.34s
Skipping teardown as no inference service was successfully deployed
Running pipeline stage MKMLDeleter
run pipeline %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-nemo-slerp-lexica_2910_v2
Pipeline stage MKMLDeleter completed in 46.80s
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 42.24s
Skipping teardown as no inference service was successfully deployed
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-nemo-ties-esao-albert_v2
run pipeline stage %s
Running pipeline stage MKMLDeployer
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 49.87s
Running pipeline stage ProductionBlendMKMLTemplater
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-nemo-ties-lexical_2876_v1
Running pipeline stage MKMLModelDeleter
Running pipeline stage MKMLModelDeleter
Creating inference service blend-rofur-2024-10-03
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLModelDeleter completed in 62.75s
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
Cleaning model data from S3
Ignoring service blend-rofur-2024-10-03 already deployed
Running pipeline stage MKMLModelDeleter
Pipeline stage ProductionBlendMKMLTemplater completed in 69.19s
Shutdown handler de-registered
Skipping teardown as no inference service was successfully deployed
Running pipeline stage MKMLDeleter
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 65.40s
Skipping teardown as no inference service was successfully deployed
Running pipeline stage MKMLDeleter
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 65.40s
run pipeline %s
Cleaning model data from model cache
Waiting for inference service blend-rofur-2024-10-03 to be ready
Skipping deletion as no model was successfully uploaded
run pipeline stage %s
rica40325-mistral-3678_v4 status is now torndown due to DeploymentManager action
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 58.76s
Skipping teardown as no inference service was successfully deployed
sao10k-lyra-4-2-chai_v3 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
Deleting key chaiml-nemo-slerp-esao-b-7186-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Shutdown handler de-registered
admin requested tearing down of rica40325-mistral-3678_v4
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
admin requested tearing down of rica40325-mistral-3678_v4
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of sao10k-lyra-4-2-chai_v3
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of sao10k-lyra-4-2-chai_v4
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of blend_rofur_2024-10-03
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
Tearing down inference service blend-rofur-2024-10-03
Running pipeline stage MKMLDeleter
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 16.52s
run pipeline %s
%s, retrying in %s seconds...
Pipeline stage %s skipped, reason=%s
Tearing down inference service blend-rofur-2024-10-03
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline stage %s
Creating inference service blend-rofur-2024-10-03
Pipeline stage MKMLDeleter completed in 22.64s
%s, retrying in %s seconds...
Checking if service sao10k-lyra-4-2-chai-v4 is running
Running pipeline stage MKMLModelDeleter
Running pipeline stage ProductionBlendMKMLTemplater
Waiting for inference service blend-rofur-2024-10-03 to be ready
run pipeline stage %s
Creating inference service blend-rofur-2024-10-03
Pipeline stage %s skipped, reason=%s
Tearing down inference service sao10k-lyra-4-2-chai-v4
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
Ignoring service blend-rofur-2024-10-03 already deployed
Pipeline stage MKMLModelDeleter completed in 24.45s
Service sao10k-lyra-4-2-chai-v4 has been torndown
Pipeline stage ProductionBlendMKMLTemplater completed in 27.64s
Pipeline stage %s skipped, reason=%s
Waiting for inference service blend-rofur-2024-10-03 to be ready
Shutdown handler de-registered
Pipeline stage MKMLDeleter completed in 53.80s
Pipeline stage MKMLDeleter completed in 53.80s
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 22.46s
rica40325-mistral-3678_v4 status is now torndown due to DeploymentManager action