developer_uid: rirv938
submission_id: chaiml-llama-8b-multih_78780_v14
model_name: chaiml-llama-8b-multih_78780_v14
model_group: ChaiML/llama_8b_multihea
status: torndown
timestamp: 2025-01-31T00:14:42+00:00
num_battles: 5903
num_wins: 2951
celo_rating: 1271.19
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: 256
max_output_tokens: 1
display_name: chaiml-llama-8b-multih_78780_v14
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: 2025-01-30
win_ratio: 0.49991529730645434
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-multih-78780-v14-mkmlizer
Waiting for job on chaiml-llama-8b-multih-78780-v14-mkmlizer to finish
chaiml-llama-8b-multih-78780-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║     _____            __           __                                ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║       /___/                                                         ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║  Version: 0.11.37                                                   ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission rirv938-anthropic-40k-2_21217_v1: HTTPConnectionPool(host='rirv938-anthropic-40k-2-21217-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-llama-8b-multih-78780-v14-mkmlizer: Downloaded to shared memory in 24.172s
chaiml-llama-8b-multih-78780-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjy0mavc4, device:0
chaiml-llama-8b-multih-78780-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-multih-78780-v14-mkmlizer: quantized model in 15.421s
chaiml-llama-8b-multih-78780-v14-mkmlizer: Processed model ChaiML/llama_8b_multihead_204m_512_v3_tokens_step_398208 in 39.594s
chaiml-llama-8b-multih-78780-v14-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-multih-78780-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-multih-78780-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v14
chaiml-llama-8b-multih-78780-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v14/config.json
chaiml-llama-8b-multih-78780-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v14/special_tokens_map.json
chaiml-llama-8b-multih-78780-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v14/tokenizer_config.json
chaiml-llama-8b-multih-78780-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v14/flywheel_model.0.safetensors
chaiml-llama-8b-multih-78780-v14-mkmlizer: 
Loading 0:   0%|          | 0/294 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/294 [00:00<00:08, 32.72it/s]
Loading 0:   4%|▍         | 13/294 [00:00<00:05, 53.65it/s]
Loading 0:   6%|▋         | 19/294 [00:00<00:05, 48.90it/s]
Loading 0:   9%|▊         | 25/294 [00:00<00:05, 50.00it/s]
Loading 0:  11%|█         | 32/294 [00:00<00:05, 47.70it/s]
Loading 0:  14%|█▍        | 41/294 [00:00<00:04, 50.99it/s]
Loading 0:  17%|█▋        | 49/294 [00:00<00:04, 58.15it/s]
Loading 0:  19%|█▉        | 56/294 [00:01<00:04, 56.99it/s]
Loading 0:  21%|██        | 62/294 [00:01<00:04, 55.49it/s]
Loading 0:  23%|██▎       | 68/294 [00:01<00:04, 49.74it/s]
Loading 0:  26%|██▌       | 76/294 [00:01<00:03, 56.29it/s]
Loading 0:  28%|██▊       | 82/294 [00:01<00:04, 52.71it/s]
Loading 0:  30%|██▉       | 88/294 [00:01<00:06, 33.65it/s]
Loading 0:  32%|███▏      | 94/294 [00:02<00:05, 38.02it/s]
Loading 0:  34%|███▍      | 100/294 [00:02<00:05, 38.46it/s]
Loading 0:  36%|███▌      | 105/294 [00:02<00:04, 39.76it/s]
Loading 0:  38%|███▊      | 112/294 [00:02<00:03, 46.18it/s]
Loading 0:  40%|████      | 118/294 [00:02<00:03, 45.41it/s]
Loading 0:  42%|████▏     | 123/294 [00:02<00:03, 45.97it/s]
Loading 0:  45%|████▍     | 131/294 [00:02<00:03, 47.31it/s]
Loading 0:  47%|████▋     | 139/294 [00:02<00:02, 54.59it/s]
Loading 0:  49%|████▉     | 145/294 [00:03<00:02, 51.73it/s]
Loading 0:  51%|█████▏    | 151/294 [00:03<00:02, 52.97it/s]
Loading 0:  54%|█████▎    | 158/294 [00:03<00:02, 48.85it/s]
Loading 0:  56%|█████▋    | 166/294 [00:03<00:02, 55.07it/s]
Loading 0:  59%|█████▊    | 172/294 [00:03<00:02, 50.94it/s]
Loading 0:  61%|██████    | 179/294 [00:03<00:02, 54.81it/s]
Loading 0:  63%|██████▎   | 185/294 [00:03<00:01, 56.06it/s]
Loading 0:  65%|██████▍   | 191/294 [00:04<00:02, 35.76it/s]
Loading 0:  67%|██████▋   | 196/294 [00:04<00:02, 38.00it/s]
Loading 0:  69%|██████▉   | 203/294 [00:04<00:02, 39.77it/s]
Loading 0:  72%|███████▏  | 211/294 [00:04<00:01, 47.18it/s]
Loading 0:  74%|███████▍  | 217/294 [00:04<00:01, 46.24it/s]
Loading 0:  76%|███████▌  | 223/294 [00:04<00:01, 48.61it/s]
Loading 0:  78%|███████▊  | 230/294 [00:04<00:01, 47.68it/s]
Loading 0:  81%|████████  | 237/294 [00:04<00:01, 51.51it/s]
Loading 0:  83%|████████▎ | 244/294 [00:05<00:00, 50.39it/s]
Loading 0:  85%|████████▌ | 250/294 [00:05<00:00, 51.83it/s]
Loading 0:  87%|████████▋ | 257/294 [00:05<00:00, 49.77it/s]
Loading 0:  90%|█████████ | 265/294 [00:05<00:00, 56.62it/s]
Loading 0:  92%|█████████▏| 271/294 [00:05<00:00, 53.77it/s]
Loading 0:  95%|█████████▍| 278/294 [00:05<00:00, 57.26it/s]
Loading 0:  97%|█████████▋| 284/294 [00:05<00:00, 51.63it/s]
Loading 0:  99%|█████████▊| 290/294 [00:06<00:00, 35.43it/s]
                                                            

Job chaiml-llama-8b-multih-78780-v14-mkmlizer completed after 63.45s with status: succeeded
Stopping job with name chaiml-llama-8b-multih-78780-v14-mkmlizer
Pipeline stage MKMLizer completed in 63.92s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-multih-78780-v14
Waiting for inference service chaiml-llama-8b-multih-78780-v14 to be ready
Inference service chaiml-llama-8b-multih-78780-v14 ready after 211.07752418518066s
Pipeline stage MKMLDeployer completed in 211.57s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.776150226593018s
Received healthy response to inference request in 2.636522054672241s
Received healthy response to inference request in 3.87119722366333s
Received healthy response to inference request in 3.0169146060943604s
Received healthy response to inference request in 2.3549017906188965s
5 requests
0 failed requests
5th percentile: 2.4112258434295653
10th percentile: 2.4675498962402345
20th percentile: 2.5801980018615724
30th percentile: 2.712600564956665
40th percentile: 2.8647575855255125
50th percentile: 3.0169146060943604
60th percentile: 3.3586276531219483
70th percentile: 3.700340700149536
80th percentile: 4.052187824249268
90th percentile: 4.414169025421143
95th percentile: 4.59515962600708
99th percentile: 4.73995210647583
mean time: 3.331137180328369
%s, retrying in %s seconds...
Received healthy response to inference request in 4.592703819274902s
Received healthy response to inference request in 3.8558549880981445s
Received healthy response to inference request in 4.692291259765625s
Received healthy response to inference request in 3.3066282272338867s
Received healthy response to inference request in 2.8669686317443848s
5 requests
0 failed requests
5th percentile: 2.954900550842285
10th percentile: 3.0428324699401856
20th percentile: 3.2186963081359865
30th percentile: 3.4164735794067385
40th percentile: 3.6361642837524415
50th percentile: 3.8558549880981445
60th percentile: 4.1505945205688475
70th percentile: 4.44533405303955
80th percentile: 4.612621307373047
90th percentile: 4.652456283569336
95th percentile: 4.6723737716674805
99th percentile: 4.688307762145996
mean time: 3.8628893852233888
%s, retrying in %s seconds...
Received healthy response to inference request in 4.451005697250366s
Received healthy response to inference request in 3.251856803894043s
Received healthy response to inference request in 2.438136577606201s
Received healthy response to inference request in 2.6539957523345947s
Received healthy response to inference request in 2.7180557250976562s
5 requests
0 failed requests
5th percentile: 2.48130841255188
10th percentile: 2.5244802474975585
20th percentile: 2.610823917388916
30th percentile: 2.666807746887207
40th percentile: 2.6924317359924315
50th percentile: 2.7180557250976562
60th percentile: 2.931576156616211
70th percentile: 3.1450965881347654
80th percentile: 3.4916865825653076
90th percentile: 3.971346139907837
95th percentile: 4.211175918579102
99th percentile: 4.403039741516113
mean time: 3.1026101112365723
Pipeline stage StressChecker completed in 55.38s
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 0.76s
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 0.64s
Shutdown handler de-registered
chaiml-llama-8b-multih_78780_v14 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("[Errno 2] No such file or directory: '/tmp/prometheus/histogram_59.db'")
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("[Errno 2] No such file or directory: '/tmp/prometheus/histogram_59.db'")
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("[Errno 2] No such file or directory: '/tmp/prometheus/histogram_59.db'")
Shutdown handler de-registered
chaiml-llama-8b-multih_78780_v14 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-multih_78780_v14 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1