developer_uid: rirv938
submission_id: chaiml-llama-8b-multih_78780_v27
model_name: chaiml-llama-8b-multih_78780_v27
model_group: ChaiML/llama_8b_multihea
status: torndown
timestamp: 2025-02-13T22:36:21+00:00
num_battles: 5413
num_wins: 2849
celo_rating: 1293.1
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_v27
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: 2025-02-13
win_ratio: 0.5263255126547202
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-v27-mkmlizer
Waiting for job on chaiml-llama-8b-multih-78780-v27-mkmlizer to finish
chaiml-llama-8b-multih-78780-v27-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ _____ __ __ ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ /___/ ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ Version: 0.12.8 ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ║ ║
chaiml-llama-8b-multih-78780-v27-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-multih-78780-v27-mkmlizer: Downloaded to shared memory in 24.147s
chaiml-llama-8b-multih-78780-v27-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv_bsun5j, device:0
chaiml-llama-8b-multih-78780-v27-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-multih-78780-v27-mkmlizer: quantized model in 16.064s
chaiml-llama-8b-multih-78780-v27-mkmlizer: Processed model ChaiML/llama_8b_multihead_204m_512_v3_tokens_step_398208 in 40.212s
chaiml-llama-8b-multih-78780-v27-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-multih-78780-v27-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-multih-78780-v27-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v27
chaiml-llama-8b-multih-78780-v27-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v27/special_tokens_map.json
chaiml-llama-8b-multih-78780-v27-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v27/tokenizer_config.json
chaiml-llama-8b-multih-78780-v27-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v27/tokenizer.json
chaiml-llama-8b-multih-78780-v27-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v27/flywheel_model.0.safetensors
chaiml-llama-8b-multih-78780-v27-mkmlizer: Loading 0: 0%| | 0/294 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/294 [00:00<00:07, 38.37it/s] Loading 0: 4%|▍ | 13/294 [00:00<00:05, 55.57it/s] Loading 0: 6%|▋ | 19/294 [00:00<00:05, 48.37it/s] Loading 0: 8%|▊ | 24/294 [00:00<00:05, 47.06it/s] Loading 0: 11%|█ | 31/294 [00:00<00:04, 52.93it/s] Loading 0: 13%|█▎ | 37/294 [00:00<00:05, 48.61it/s] Loading 0: 14%|█▍ | 42/294 [00:00<00:05, 47.00it/s] Loading 0: 17%|█▋ | 49/294 [00:00<00:04, 52.06it/s] Loading 0: 19%|█▊ | 55/294 [00:01<00:04, 48.10it/s] Loading 0: 20%|██ | 60/294 [00:01<00:04, 47.28it/s] Loading 0: 23%|██▎ | 67/294 [00:01<00:04, 51.55it/s] Loading 0: 25%|██▍ | 73/294 [00:01<00:04, 47.84it/s] Loading 0: 27%|██▋ | 78/294 [00:01<00:04, 47.15it/s] Loading 0: 28%|██▊ | 83/294 [00:01<00:06, 32.66it/s] Loading 0: 30%|██▉ | 87/294 [00:01<00:06, 33.16it/s] Loading 0: 32%|███▏ | 94/294 [00:02<00:04, 40.38it/s] Loading 0: 34%|███▍ | 100/294 [00:02<00:04, 40.76it/s] Loading 0: 36%|███▌ | 105/294 [00:02<00:04, 41.65it/s] Loading 0: 38%|███▊ | 112/294 [00:02<00:03, 47.62it/s] Loading 0: 40%|████ | 118/294 [00:02<00:03, 45.70it/s] Loading 0: 42%|████▏ | 123/294 [00:02<00:03, 45.60it/s] Loading 0: 44%|████▍ | 130/294 [00:02<00:03, 50.79it/s] Loading 0: 46%|████▋ | 136/294 [00:02<00:03, 47.48it/s] Loading 0: 48%|████▊ | 141/294 [00:03<00:03, 46.84it/s] Loading 0: 50%|█████ | 148/294 [00:03<00:02, 52.01it/s] Loading 0: 52%|█████▏ | 154/294 [00:03<00:02, 48.32it/s] Loading 0: 54%|█████▍ | 159/294 [00:03<00:02, 46.56it/s] Loading 0: 56%|█████▋ | 166/294 [00:03<00:02, 51.55it/s] Loading 0: 59%|█████▊ | 172/294 [00:03<00:02, 47.31it/s] Loading 0: 61%|██████ | 179/294 [00:03<00:02, 52.07it/s] Loading 0: 63%|██████▎ | 185/294 [00:03<00:02, 53.13it/s] Loading 0: 65%|██████▍ | 191/294 [00:04<00:03, 32.59it/s] Loading 0: 67%|██████▋ | 196/294 [00:04<00:02, 34.61it/s] Loading 0: 69%|██████▊ | 202/294 [00:04<00:02, 39.05it/s] Loading 0: 71%|███████ | 208/294 [00:04<00:02, 39.79it/s] Loading 0: 72%|███████▏ | 213/294 [00:04<00:01, 41.26it/s] Loading 0: 75%|███████▍ | 220/294 [00:04<00:01, 47.46it/s] Loading 0: 77%|███████▋ | 226/294 [00:05<00:01, 44.91it/s] Loading 0: 79%|███████▊ | 231/294 [00:05<00:01, 44.75it/s] Loading 0: 81%|████████ | 238/294 [00:05<00:01, 49.46it/s] Loading 0: 83%|████████▎ | 244/294 [00:05<00:01, 46.26it/s] Loading 0: 85%|████████▍ | 249/294 [00:05<00:01, 44.64it/s] Loading 0: 87%|████████▋ | 256/294 [00:05<00:00, 49.83it/s] Loading 0: 89%|████████▉ | 262/294 [00:05<00:00, 46.20it/s] Loading 0: 91%|█████████ | 267/294 [00:05<00:00, 44.93it/s] Loading 0: 93%|█████████▎| 274/294 [00:06<00:00, 49.38it/s] Loading 0: 95%|█████████▌| 280/294 [00:06<00:00, 45.62it/s] Loading 0: 97%|█████████▋| 285/294 [00:06<00:00, 45.10it/s] Loading 0: 99%|█████████▊| 290/294 [00:06<00:00, 30.32it/s]
Job chaiml-llama-8b-multih-78780-v27-mkmlizer completed after 165.23s with status: succeeded
Stopping job with name chaiml-llama-8b-multih-78780-v27-mkmlizer
Pipeline stage MKMLizer completed in 165.67s
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-v27
Waiting for inference service chaiml-llama-8b-multih-78780-v27 to be ready
Inference service chaiml-llama-8b-multih-78780-v27 ready after 180.62168884277344s
Pipeline stage MKMLDeployer completed in 181.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.045507192611694s
Received healthy response to inference request in 2.0427215099334717s
Received healthy response to inference request in 3.727919816970825s
Received healthy response to inference request in 2.988464117050171s
Received healthy response to inference request in 2.577091932296753s
5 requests
0 failed requests
5th percentile: 2.149595594406128
10th percentile: 2.2564696788787844
20th percentile: 2.4702178478240966
30th percentile: 2.6593663692474365
40th percentile: 2.8239152431488037
50th percentile: 2.988464117050171
60th percentile: 3.284246397018433
70th percentile: 3.5800286769866942
80th percentile: 3.991437292098999
90th percentile: 4.5184722423553465
95th percentile: 4.78198971748352
99th percentile: 4.9928036975860595
mean time: 3.276340913772583
Pipeline stage StressChecker completed in 17.71s
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 0.62s
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 0.60s
Shutdown handler de-registered
chaiml-llama-8b-multih_78780_v27 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-multih-78780-v27-profiler
Waiting for inference service chaiml-llama-8b-multih-78780-v27-profiler to be ready
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
clean up pipeline due to error=DeploymentChecksError("'message'")
Shutdown handler de-registered
chaiml-llama-8b-multih_78780_v27 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-multih_78780_v27 status is now torndown due to DeploymentManager action
chaiml-llama-8b-multih_78780_v27 status is now torndown due to DeploymentManager action
chaiml-llama-8b-multih_78780_v27 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1