chaiml-llama-8b-multih_78780

developer_uid: rirv938
submission_id: chaiml-llama-8b-multih_78780_v26
model_name: chaiml-llama-8b-multih_78780_v26
model_group: ChaiML/llama_8b_multihea
status: torndown
timestamp: 2025-02-13T00:31:38+00:00
num_battles: 7595
num_wins: 4009
celo_rating: 1292.15
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
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: 2048
max_output_tokens: 1
display_name: chaiml-llama-8b-multih_78780_v26
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: 2025-02-12
win_ratio: 0.5278472679394338
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': 2048, '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': '{bot_name}:{message}', '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-multih-78780-v26-mkmlizer
Waiting for job on chaiml-llama-8b-multih-78780-v26-mkmlizer to finish
Failed to get response for submission dtnewman-daniel-2025021_12303_v7: HTTPConnectionPool(host='dtnewman-daniel-2025021-12303-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission dtnewman-daniel-2025021_12303_v5: HTTPConnectionPool(host='dtnewman-daniel-2025021-12303-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission dtnewman-daniel-2025021_12303_v7: HTTPConnectionPool(host='dtnewman-daniel-2025021-12303-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-llama-8b-multih-78780-v26-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║     _____            __           __                                ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║       /___/                                                         ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v26-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-multih-78780-v26-mkmlizer: Downloaded to shared memory in 24.219s
chaiml-llama-8b-multih-78780-v26-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjf2s91ap, device:0
chaiml-llama-8b-multih-78780-v26-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-multih-78780-v26-mkmlizer: quantized model in 15.655s
chaiml-llama-8b-multih-78780-v26-mkmlizer: Processed model ChaiML/llama_8b_multihead_204m_512_v3_tokens_step_398208 in 39.880s
chaiml-llama-8b-multih-78780-v26-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-multih-78780-v26-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-multih-78780-v26-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v26
chaiml-llama-8b-multih-78780-v26-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v26/config.json
chaiml-llama-8b-multih-78780-v26-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v26/special_tokens_map.json
chaiml-llama-8b-multih-78780-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v26/tokenizer_config.json
chaiml-llama-8b-multih-78780-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v26/tokenizer.json
chaiml-llama-8b-multih-78780-v26-mkmlizer: 
Loading 0:   0%|          | 0/294 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/294 [00:00<00:07, 37.62it/s]
Loading 0:   4%|▍         | 13/294 [00:00<00:04, 58.24it/s]
Loading 0:   7%|▋         | 20/294 [00:00<00:04, 57.40it/s]
Loading 0:   9%|▉         | 26/294 [00:00<00:04, 57.01it/s]
Loading 0:  11%|█         | 32/294 [00:00<00:05, 50.19it/s]
Loading 0:  14%|█▎        | 40/294 [00:00<00:04, 58.48it/s]
Loading 0:  16%|█▌        | 47/294 [00:00<00:04, 57.16it/s]
Loading 0:  18%|█▊        | 53/294 [00:00<00:04, 56.85it/s]
Loading 0:  20%|██        | 59/294 [00:01<00:04, 50.85it/s]
Loading 0:  23%|██▎       | 68/294 [00:01<00:04, 52.65it/s]
Loading 0:  26%|██▌       | 76/294 [00:01<00:03, 58.87it/s]
Loading 0:  28%|██▊       | 83/294 [00:01<00:04, 43.16it/s]
Loading 0:  30%|███       | 89/294 [00:01<00:04, 43.66it/s]
Loading 0:  32%|███▏      | 94/294 [00:01<00:04, 44.89it/s]
Loading 0:  34%|███▍      | 100/294 [00:01<00:04, 45.65it/s]
Loading 0:  36%|███▌      | 106/294 [00:02<00:03, 48.82it/s]
Loading 0:  38%|███▊      | 113/294 [00:02<00:03, 47.87it/s]
Loading 0:  41%|████      | 121/294 [00:02<00:03, 55.40it/s]
Loading 0:  43%|████▎     | 127/294 [00:02<00:03, 53.06it/s]
Loading 0:  45%|████▌     | 133/294 [00:02<00:02, 54.80it/s]
Loading 0:  47%|████▋     | 139/294 [00:02<00:02, 55.43it/s]
Loading 0:  49%|████▉     | 145/294 [00:02<00:02, 53.30it/s]
Loading 0:  51%|█████▏    | 151/294 [00:02<00:02, 54.28it/s]
Loading 0:  53%|█████▎    | 157/294 [00:03<00:02, 55.71it/s]
Loading 0:  55%|█████▌    | 163/294 [00:03<00:02, 53.25it/s]
Loading 0:  57%|█████▋    | 169/294 [00:03<00:02, 54.67it/s]
Loading 0:  60%|██████    | 177/294 [00:03<00:02, 55.85it/s]
Loading 0:  62%|██████▏   | 183/294 [00:03<00:02, 55.05it/s]
Loading 0:  64%|██████▍   | 189/294 [00:03<00:02, 37.62it/s]
Loading 0:  66%|██████▌   | 194/294 [00:03<00:02, 39.94it/s]
Loading 0:  69%|██████▊   | 202/294 [00:03<00:01, 47.80it/s]
Loading 0:  71%|███████   | 208/294 [00:04<00:01, 47.83it/s]
Loading 0:  73%|███████▎  | 214/294 [00:04<00:01, 50.57it/s]
Loading 0:  75%|███████▌  | 221/294 [00:04<00:01, 47.22it/s]
Loading 0:  78%|███████▊  | 230/294 [00:04<00:01, 49.91it/s]
Loading 0:  81%|████████▏ | 239/294 [00:04<00:01, 51.86it/s]
Loading 0:  84%|████████▍ | 248/294 [00:04<00:00, 53.74it/s]
Loading 0:  87%|████████▋ | 257/294 [00:05<00:00, 54.72it/s]
Loading 0:  90%|█████████ | 265/294 [00:05<00:00, 60.12it/s]
Loading 0:  93%|█████████▎| 272/294 [00:05<00:00, 54.57it/s]
Loading 0:  95%|█████████▍| 278/294 [00:05<00:00, 54.81it/s]
Loading 0:  97%|█████████▋| 284/294 [00:05<00:00, 49.70it/s]
Loading 0:  99%|█████████▊| 290/294 [00:05<00:00, 42.47it/s]
                                                            
Job chaiml-llama-8b-multih-78780-v26-mkmlizer completed after 195.41s with status: succeeded
Stopping job with name chaiml-llama-8b-multih-78780-v26-mkmlizer
Pipeline stage MKMLizer completed in 195.86s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-multih-78780-v26
Waiting for inference service chaiml-llama-8b-multih-78780-v26 to be ready
Failed to get response for submission dtnewman-daniel-2025021_12303_v8: HTTPConnectionPool(host='dtnewman-daniel-2025021-12303-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission dtnewman-daniel-2025021_12303_v8: HTTPConnectionPool(host='dtnewman-daniel-2025021-12303-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission dtnewman-daniel-2025021_12303_v7: HTTPConnectionPool(host='dtnewman-daniel-2025021-12303-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-llama-8b-multih-78780-v26 ready after 220.93763899803162s
Pipeline stage MKMLDeployer completed in 221.40s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.987224817276001s
Received healthy response to inference request in 2.7573282718658447s
Received healthy response to inference request in 3.818723201751709s
Received healthy response to inference request in 2.067108392715454s
Received healthy response to inference request in 2.9160749912261963s
5 requests
0 failed requests
5th percentile: 2.2051523685455323
10th percentile: 2.3431963443756105
20th percentile: 2.6192842960357665
30th percentile: 2.789077615737915
40th percentile: 2.8525763034820555
50th percentile: 2.9160749912261963
60th percentile: 2.944534921646118
70th percentile: 2.97299485206604
80th percentile: 3.1535244941711427
90th percentile: 3.486123847961426
95th percentile: 3.6524235248565673
99th percentile: 3.785463266372681
mean time: 2.909291934967041
Pipeline stage StressChecker completed in 15.65s
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 0.59s
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 0.61s
Shutdown handler de-registered
chaiml-llama-8b-multih_78780_v26 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError("'message'")
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError("'message'")
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multih-78780-v26-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.32s
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-multih-78780-v26-profiler
Waiting for inference service chaiml-llama-8b-multih-78780-v26-profiler to be ready
Inference service chaiml-llama-8b-multih-78780-v26-profiler ready after 180.68147945404053s
Pipeline stage MKMLProfilerDeployer completed in 181.02s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult476f31a65508c7291085bc40bfa8a9fd-deplo9kzgh:/code/chaiverse_profiler_1739411007 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult476f31a65508c7291085bc40bfa8a9fd-deplo9kzgh --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739411007 && 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 2048 --output_tokens 1 --summary /code/chaiverse_profiler_1739411007/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multih-78780-v26-profiler is running
Tearing down inference service chaiml-llama-8b-multih-78780-v26-profiler
Service chaiml-llama-8b-multih-78780-v26-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.06s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multih-78780-v26-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.14s
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-multih-78780-v26-profiler
Waiting for inference service chaiml-llama-8b-multih-78780-v26-profiler to be ready
Inference service chaiml-llama-8b-multih-78780-v26-profiler ready after 40.255438566207886s
Pipeline stage MKMLProfilerDeployer completed in 40.59s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult476f31a65508c7291085bc40bfa8a9fd-deplohld7m:/code/chaiverse_profiler_1739414521 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult476f31a65508c7291085bc40bfa8a9fd-deplohld7m --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739414521 && 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 2048 --output_tokens 1 --summary /code/chaiverse_profiler_1739414521/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multih-78780-v26-profiler is running
Tearing down inference service chaiml-llama-8b-multih-78780-v26-profiler
Service chaiml-llama-8b-multih-78780-v26-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.96s
Shutdown handler de-registered
chaiml-llama-8b-multih_78780_v26 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-multih_78780_v26 status is now torndown due to DeploymentManager action
chaiml-llama-8b-multih_78780_v26 status is now torndown due to DeploymentManager action
chaiml-llama-8b-multih_78780_v26 status is now torndown due to DeploymentManager action
ChatRequest
Bot Name
Generation Params
Prompt Formatter
ChatMessage 1
Sender
Message
User Message