chaiml-llama-8b-multihea_7878

developer_uid: rirv938
submission_id: chaiml-llama-8b-multihea_7878_v1
model_name: chaiml-llama-8b-multihea_7878_v1
model_group: ChaiML/llama_8b_multihea
status: inactive
timestamp: 2024-12-04T20:05:35+00:00
num_battles: 23706
num_wins: 11745
celo_rating: 1259.29
family_friendly_score: 0.5902000000000001
family_friendly_standard_error: 0.006955055139968338
submission_type: basic
model_repo: ChaiML/llama_8b_multihead_204m_512_v3_tokens_step_398208
model_architecture: MultiHeadLlamaClassifier
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 256
max_output_tokens: 1
display_name: chaiml-llama-8b-multihea_7878_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/llama_8b_multihead_204m_512_v3_tokens_step_398208
model_size: 8B
ranking_group: single
us_pacific_date: 2024-12-04
win_ratio: 0.49544419134396356
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 256, 'best_of': 1, 'max_output_tokens': 1}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', 'truncate_by_message': False}
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 chaiml-llama-8b-multihea-7878-v1-mkmlizer
Waiting for job on chaiml-llama-8b-multihea-7878-v1-mkmlizer to finish
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║       /___/                                                         ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║  Version: 0.11.37                                                   ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihea-7878-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-multihea-7878-v1-mkmlizer: Downloaded to shared memory in 24.534s
chaiml-llama-8b-multihea-7878-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp60l_ea_e, device:0
chaiml-llama-8b-multihea-7878-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-multihea-7878-v1-mkmlizer: quantized model in 16.830s
chaiml-llama-8b-multihea-7878-v1-mkmlizer: Processed model ChaiML/llama_8b_multihead_204m_512_v3_tokens_step_398208 in 41.365s
chaiml-llama-8b-multihea-7878-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-multihea-7878-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-multihea-7878-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7878-v1
chaiml-llama-8b-multihea-7878-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7878-v1/config.json
chaiml-llama-8b-multihea-7878-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7878-v1/special_tokens_map.json
chaiml-llama-8b-multihea-7878-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7878-v1/tokenizer_config.json
chaiml-llama-8b-multihea-7878-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7878-v1/tokenizer.json
chaiml-llama-8b-multihea-7878-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7878-v1/flywheel_model.0.safetensors
chaiml-llama-8b-multihea-7878-v1-mkmlizer: 
Loading 0:   0%|          | 0/294 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/294 [00:00<00:08, 33.95it/s]
Loading 0:   4%|▍         | 13/294 [00:00<00:05, 53.95it/s]
Loading 0:   6%|▋         | 19/294 [00:00<00:05, 50.13it/s]
Loading 0:   9%|▊         | 25/294 [00:00<00:05, 50.10it/s]
Loading 0:  11%|█         | 31/294 [00:00<00:05, 50.20it/s]
Loading 0:  13%|█▎        | 37/294 [00:00<00:05, 43.47it/s]
Loading 0:  14%|█▍        | 42/294 [00:00<00:06, 41.66it/s]
Loading 0:  17%|█▋        | 49/294 [00:01<00:05, 46.87it/s]
Loading 0:  19%|█▊        | 55/294 [00:01<00:05, 45.54it/s]
Loading 0:  20%|██        | 60/294 [00:01<00:05, 45.10it/s]
Loading 0:  23%|██▎       | 67/294 [00:01<00:04, 50.60it/s]
Loading 0:  25%|██▍       | 73/294 [00:01<00:04, 49.12it/s]
Loading 0:  27%|██▋       | 79/294 [00:01<00:04, 48.19it/s]
Loading 0:  29%|██▊       | 84/294 [00:01<00:06, 31.04it/s]
Loading 0:  30%|██▉       | 88/294 [00:02<00:06, 32.18it/s]
Loading 0:  32%|███▏      | 94/294 [00:02<00:05, 37.02it/s]
Loading 0:  34%|███▍      | 100/294 [00:02<00:05, 37.91it/s]
Loading 0:  36%|███▌      | 105/294 [00:02<00:04, 40.16it/s]
Loading 0:  38%|███▊      | 112/294 [00:02<00:03, 47.23it/s]
Loading 0:  40%|████      | 118/294 [00:02<00:03, 46.76it/s]
Loading 0:  42%|████▏     | 123/294 [00:02<00:03, 46.31it/s]
Loading 0:  44%|████▍     | 130/294 [00:02<00:03, 52.31it/s]
Loading 0:  46%|████▋     | 136/294 [00:03<00:03, 50.27it/s]
Loading 0:  48%|████▊     | 142/294 [00:03<00:03, 50.37it/s]
Loading 0:  50%|█████     | 148/294 [00:03<00:02, 52.66it/s]
Loading 0:  52%|█████▏    | 154/294 [00:03<00:02, 47.31it/s]
Loading 0:  54%|█████▍    | 159/294 [00:03<00:03, 44.68it/s]
Loading 0:  56%|█████▋    | 166/294 [00:03<00:02, 48.96it/s]
Loading 0:  59%|█████▊    | 172/294 [00:03<00:02, 46.66it/s]
Loading 0:  61%|██████    | 179/294 [00:03<00:02, 52.17it/s]
Loading 0:  63%|██████▎   | 186/294 [00:04<00:02, 50.62it/s]
Loading 0:  65%|██████▌   | 192/294 [00:04<00:03, 33.96it/s]
Loading 0:  67%|██████▋   | 198/294 [00:04<00:02, 38.79it/s]
Loading 0:  69%|██████▉   | 203/294 [00:04<00:02, 36.91it/s]
Loading 0:  72%|███████▏  | 211/294 [00:04<00:01, 45.19it/s]
Loading 0:  74%|███████▍  | 217/294 [00:04<00:01, 45.69it/s]
Loading 0:  76%|███████▌  | 223/294 [00:04<00:01, 48.00it/s]
Loading 0:  78%|███████▊  | 230/294 [00:05<00:01, 44.87it/s]
Loading 0:  81%|████████  | 238/294 [00:05<00:01, 51.63it/s]
Loading 0:  83%|████████▎ | 244/294 [00:05<00:00, 50.13it/s]
Loading 0:  85%|████████▌ | 250/294 [00:05<00:00, 51.72it/s]
Loading 0:  87%|████████▋ | 257/294 [00:05<00:00, 48.00it/s]
Loading 0:  90%|█████████ | 265/294 [00:05<00:00, 54.47it/s]
Loading 0:  92%|█████████▏| 271/294 [00:05<00:00, 52.31it/s]
Loading 0:  94%|█████████▍| 277/294 [00:06<00:00, 53.84it/s]
Loading 0:  96%|█████████▋| 283/294 [00:06<00:00, 48.67it/s]
Loading 0:  98%|█████████▊| 289/294 [00:06<00:00, 36.17it/s]
                                                            
Job chaiml-llama-8b-multihea-7878-v1-mkmlizer completed after 63.36s with status: succeeded
Stopping job with name chaiml-llama-8b-multihea-7878-v1-mkmlizer
Pipeline stage MKMLizer completed in 63.95s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-multihea-7878-v1
Waiting for inference service chaiml-llama-8b-multihea-7878-v1 to be ready
Inference service chaiml-llama-8b-multihea-7878-v1 ready after 160.58508324623108s
Pipeline stage MKMLDeployer completed in 161.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.192441701889038s
Received healthy response to inference request in 2.959777593612671s
Received healthy response to inference request in 3.660569190979004s
Received healthy response to inference request in 2.8351497650146484s
Received healthy response to inference request in 3.0366580486297607s
5 requests
0 failed requests
5th percentile: 2.860075330734253
10th percentile: 2.8850008964538576
20th percentile: 2.9348520278930663
30th percentile: 2.975153684616089
40th percentile: 3.005905866622925
50th percentile: 3.0366580486297607
60th percentile: 3.286222505569458
70th percentile: 3.5357869625091554
80th percentile: 3.7669436931610107
90th percentile: 3.9796926975250244
95th percentile: 4.086067199707031
99th percentile: 4.171166801452637
mean time: 3.3369192600250246
Pipeline stage StressChecker completed in 18.09s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.46s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.39s
Shutdown handler de-registered
chaiml-llama-8b-multihea_7878_v1 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-multihea-7878-v1-profiler
Waiting for inference service chaiml-llama-8b-multihea-7878-v1-profiler to be ready
Inference service chaiml-llama-8b-multihea-7878-v1-profiler ready after 170.40792512893677s
Pipeline stage MKMLProfilerDeployer completed in 170.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult523a8d30f24b4076a36e0c460c70d54c-deplopwr4s:/code/chaiverse_profiler_1733343194 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult523a8d30f24b4076a36e0c460c70d54c-deplopwr4s --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1733343194 && python profiles.py profile --best_of_n 1 --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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1733343194/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult523a8d30f24b4076a36e0c460c70d54c-deplopwr4s:/code/chaiverse_profiler_1733346383 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult523a8d30f24b4076a36e0c460c70d54c-deplopwr4s:/code/chaiverse_profiler_1733346384 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult523a8d30f24b4076a36e0c460c70d54c-deplopwr4s --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1733346384 && python profiles.py profile --best_of_n 1 --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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1733346384/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7878-v1-profiler is running
Tearing down inference service chaiml-llama-8b-multihea-7878-v1-profiler
Service chaiml-llama-8b-multihea-7878-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.56s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7878-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.68s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-multihea-7878-v1-profiler
Waiting for inference service chaiml-llama-8b-multihea-7878-v1-profiler to be ready
Inference service chaiml-llama-8b-multihea-7878-v1-profiler ready after 120.29568529129028s
Pipeline stage MKMLProfilerDeployer completed in 120.59s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult523a8d30f24b4076a36e0c460c70d54c-deplojjmg6:/code/chaiverse_profiler_1733346778 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult523a8d30f24b4076a36e0c460c70d54c-deplojjmg6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1733346778 && python profiles.py profile --best_of_n 1 --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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1733346778/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult523a8d30f24b4076a36e0c460c70d54c-deplojjmg6:/code/chaiverse_profiler_1733349955 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult523a8d30f24b4076a36e0c460c70d54c-deplojjmg6:/code/chaiverse_profiler_1733349960 --namespace tenant-chaiml-guanaco
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nerror: unable to upgrade connection: container not found ("kserve-container")\n, output: ')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7878-v1-profiler is running
Tearing down inference service chaiml-llama-8b-multihea-7878-v1-profiler
Service chaiml-llama-8b-multihea-7878-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.91s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7878-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.64s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-multihea-7878-v1-profiler
Waiting for inference service chaiml-llama-8b-multihea-7878-v1-profiler to be ready
Inference service chaiml-llama-8b-multihea-7878-v1-profiler ready after 160.36852598190308s
Pipeline stage MKMLProfilerDeployer completed in 160.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult523a8d30f24b4076a36e0c460c70d54c-deplodxz82:/code/chaiverse_profiler_1733350162 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult523a8d30f24b4076a36e0c460c70d54c-deplodxz82 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1733350162 && python profiles.py profile --best_of_n 1 --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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1733350162/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult523a8d30f24b4076a36e0c460c70d54c-deplodxz82:/code/chaiverse_profiler_1733353321 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult523a8d30f24b4076a36e0c460c70d54c-deplodxz82 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1733353321 && python profiles.py profile --best_of_n 1 --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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1733353321/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7878-v1-profiler is running
Tearing down inference service chaiml-llama-8b-multihea-7878-v1-profiler
Service chaiml-llama-8b-multihea-7878-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.71s
Shutdown handler de-registered
chaiml-llama-8b-multihea_7878_v1 status is now inactive due to auto deactivation removed underperforming models