developer_uid: rirv938
submission_id: chaiml-llama-8b-multih_78780_v25
model_name: chaiml-llama-8b-multih_78780_v25
model_group: ChaiML/llama_8b_multihea
status: torndown
timestamp: 2025-02-13T00:15:14+00:00
num_battles: 5999
num_wins: 3297
celo_rating: 1299.82
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_v25
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: 0.5495915985997666
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-v25-mkmlizer
Waiting for job on chaiml-llama-8b-multih-78780-v25-mkmlizer to finish
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)
chaiml-llama-8b-multih-78780-v25-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║     _____            __           __                                ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║       /___/                                                         ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║  https://mk1.ai                                                     ║
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)
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v25-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-v25-mkmlizer: Downloaded to shared memory in 36.191s
chaiml-llama-8b-multih-78780-v25-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwnbm14aa, device:0
chaiml-llama-8b-multih-78780-v25-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-multih-78780-v25-mkmlizer: quantized model in 16.269s
chaiml-llama-8b-multih-78780-v25-mkmlizer: Processed model ChaiML/llama_8b_multihead_204m_512_v3_tokens_step_398208 in 52.460s
chaiml-llama-8b-multih-78780-v25-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-multih-78780-v25-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-multih-78780-v25-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v25
chaiml-llama-8b-multih-78780-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v25/tokenizer.json
chaiml-llama-8b-multih-78780-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v25/flywheel_model.0.safetensors
chaiml-llama-8b-multih-78780-v25-mkmlizer: 
Loading 0:   0%|          | 0/294 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/294 [00:00<00:08, 33.61it/s]
Loading 0:   4%|▍         | 13/294 [00:00<00:05, 54.04it/s]
Loading 0:   6%|▋         | 19/294 [00:00<00:05, 51.31it/s]
Loading 0:   9%|▊         | 25/294 [00:00<00:05, 53.48it/s]
Loading 0:  11%|█         | 32/294 [00:00<00:05, 50.51it/s]
Loading 0:  14%|█▎        | 40/294 [00:00<00:04, 56.30it/s]
Loading 0:  16%|█▌        | 46/294 [00:00<00:04, 53.27it/s]
Loading 0:  18%|█▊        | 52/294 [00:00<00:04, 54.57it/s]
Loading 0:  20%|██        | 59/294 [00:01<00:04, 51.36it/s]
Loading 0:  22%|██▏       | 66/294 [00:01<00:04, 55.52it/s]
Loading 0:  24%|██▍       | 72/294 [00:01<00:04, 53.97it/s]
Loading 0:  27%|██▋       | 78/294 [00:01<00:04, 46.41it/s]
Loading 0:  28%|██▊       | 83/294 [00:01<00:05, 36.37it/s]
Loading 0:  30%|██▉       | 88/294 [00:01<00:05, 37.18it/s]
Loading 0:  32%|███▏      | 94/294 [00:01<00:04, 41.70it/s]
Loading 0:  34%|███▍      | 100/294 [00:02<00:04, 41.51it/s]
Loading 0:  36%|███▌      | 105/294 [00:02<00:04, 41.17it/s]
Loading 0:  38%|███▊      | 112/294 [00:02<00:03, 47.30it/s]
Loading 0:  40%|████      | 118/294 [00:02<00:03, 45.66it/s]
Loading 0:  42%|████▏     | 123/294 [00:02<00:03, 45.48it/s]
Loading 0:  44%|████▍     | 130/294 [00:02<00:03, 51.26it/s]
Loading 0:  46%|████▋     | 136/294 [00:02<00:03, 47.78it/s]
Loading 0:  48%|████▊     | 141/294 [00:02<00:03, 46.47it/s]
Loading 0:  50%|█████     | 148/294 [00:03<00:02, 51.96it/s]
Loading 0:  52%|█████▏    | 154/294 [00:03<00:02, 47.16it/s]
Loading 0:  54%|█████▍    | 159/294 [00:03<00:03, 43.84it/s]
Loading 0:  56%|█████▋    | 166/294 [00:03<00:02, 48.53it/s]
Loading 0:  59%|█████▊    | 172/294 [00:03<00:02, 46.34it/s]
Loading 0:  61%|██████    | 179/294 [00:03<00:02, 51.21it/s]
Loading 0:  63%|██████▎   | 185/294 [00:03<00:02, 52.03it/s]
Loading 0:  65%|██████▍   | 191/294 [00:04<00:02, 34.75it/s]
Loading 0:  67%|██████▋   | 196/294 [00:04<00:02, 35.87it/s]
Loading 0:  68%|██████▊   | 201/294 [00:04<00:02, 38.52it/s]
Loading 0:  70%|███████   | 206/294 [00:04<00:02, 40.93it/s]
Loading 0:  72%|███████▏  | 212/294 [00:04<00:02, 38.89it/s]
Loading 0:  75%|███████▍  | 220/294 [00:04<00:01, 47.68it/s]
Loading 0:  77%|███████▋  | 226/294 [00:04<00:01, 45.53it/s]
Loading 0:  79%|███████▊  | 231/294 [00:05<00:01, 45.09it/s]
Loading 0:  81%|████████  | 238/294 [00:05<00:01, 50.58it/s]
Loading 0:  83%|████████▎ | 244/294 [00:05<00:01, 47.64it/s]
Loading 0:  85%|████████▍ | 249/294 [00:05<00:00, 47.02it/s]
Loading 0:  87%|████████▋ | 256/294 [00:05<00:00, 52.08it/s]
Loading 0:  89%|████████▉ | 262/294 [00:05<00:00, 47.55it/s]
Loading 0:  91%|█████████ | 267/294 [00:05<00:00, 46.79it/s]
Loading 0:  93%|█████████▎| 274/294 [00:05<00:00, 51.67it/s]
Loading 0:  95%|█████████▌| 280/294 [00:06<00:00, 48.53it/s]
Loading 0:  97%|█████████▋| 285/294 [00:06<00:00, 48.23it/s]
Loading 0:  99%|█████████▊| 290/294 [00:06<00:00, 37.16it/s]
                                                            

Job chaiml-llama-8b-multih-78780-v25-mkmlizer completed after 205.42s with status: succeeded
Stopping job with name chaiml-llama-8b-multih-78780-v25-mkmlizer
Pipeline stage MKMLizer completed in 205.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-multih-78780-v25
Waiting for inference service chaiml-llama-8b-multih-78780-v25 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_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_v6: HTTPConnectionPool(host='dtnewman-daniel-2025021-12303-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-llama-8b-multih-78780-v25 ready after 221.11056089401245s
Pipeline stage MKMLDeployer completed in 221.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.410952568054199s
Received healthy response to inference request in 3.207380771636963s
Received healthy response to inference request in 2.6141579151153564s
Received healthy response to inference request in 2.240788698196411s
Received healthy response to inference request in 3.1118226051330566s
5 requests
0 failed requests
5th percentile: 2.3154625415802004
10th percentile: 2.390136384963989
20th percentile: 2.539484071731567
30th percentile: 2.7136908531188966
40th percentile: 2.9127567291259764
50th percentile: 3.1118226051330566
60th percentile: 3.150045871734619
70th percentile: 3.1882691383361816
80th percentile: 3.4480951309204104
90th percentile: 3.929523849487305
95th percentile: 4.170238208770752
99th percentile: 4.36280969619751
mean time: 3.117020511627197
Pipeline stage StressChecker completed in 16.80s
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 0.66s
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 0.68s
Shutdown handler de-registered
chaiml-llama-8b-multih_78780_v25 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-multih-78780-v25-profiler
Waiting for inference service chaiml-llama-8b-multih-78780-v25-profiler to be ready
Inference service chaiml-llama-8b-multih-78780-v25-profiler ready after 220.84523224830627s
Pipeline stage MKMLProfilerDeployer completed in 221.24s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult2d4c11037199fa66fa3858bb0d9b4093-deplo8spcx:/code/chaiverse_profiler_1739406422 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult2d4c11037199fa66fa3858bb0d9b4093-deplo8spcx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739406422 && 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_1739406422/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multih-78780-v25-profiler is running
Tearing down inference service chaiml-llama-8b-multih-78780-v25-profiler
Service chaiml-llama-8b-multih-78780-v25-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.34s
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-v25-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.20s
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-v25-profiler
Waiting for inference service chaiml-llama-8b-multih-78780-v25-profiler to be ready
Inference service chaiml-llama-8b-multih-78780-v25-profiler ready after 281.0273084640503s
Pipeline stage MKMLProfilerDeployer completed in 281.34s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult2d4c11037199fa66fa3858bb0d9b4093-deplo5tjvx:/code/chaiverse_profiler_1739410110 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult2d4c11037199fa66fa3858bb0d9b4093-deplo5tjvx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739410110 && 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_1739410110/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multih-78780-v25-profiler is running
Tearing down inference service chaiml-llama-8b-multih-78780-v25-profiler
Service chaiml-llama-8b-multih-78780-v25-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.08s
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-v25-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.04s
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-v25-profiler
Waiting for inference service chaiml-llama-8b-multih-78780-v25-profiler to be ready
Inference service chaiml-llama-8b-multih-78780-v25-profiler ready after 50.232513666152954s
Pipeline stage MKMLProfilerDeployer completed in 50.55s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult2d4c11037199fa66fa3858bb0d9b4093-deplom954l:/code/chaiverse_profiler_1739413502 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult2d4c11037199fa66fa3858bb0d9b4093-deplom954l --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739413502 && 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_1739413502/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multih-78780-v25-profiler is running
Tearing down inference service chaiml-llama-8b-multih-78780-v25-profiler
Service chaiml-llama-8b-multih-78780-v25-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.71s
Shutdown handler de-registered
chaiml-llama-8b-multih_78780_v25 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-multih_78780_v25 status is now torndown due to DeploymentManager action
chaiml-llama-8b-multih_78780_v25 status is now torndown due to DeploymentManager action
chaiml-llama-8b-multih_78780_v25 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1