developer_uid: AlexCuadron
submission_id: alexcuadron-chai-ddpo_v2
model_name: alexcuadron-chai-ddpo_v2
model_group: AlexCuadron/chai-ddpo
status: torndown
timestamp: 2025-03-24T02:19:22+00:00
num_battles: 11887
num_wins: 5569
celo_rating: 1258.94
family_friendly_score: 0.6024
family_friendly_standard_error: 0.006921188337272726
submission_type: basic
model_repo: AlexCuadron/chai-ddpo
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6112409269198157, 'latency_mean': 1.6359348964691163, 'latency_p50': 1.632412075996399, 'latency_p90': 1.8135633230209351}, {'batch_size': 3, 'throughput': 1.105282477438492, 'latency_mean': 2.702063239812851, 'latency_p50': 2.6915903091430664, 'latency_p90': 2.9808666944503783}, {'batch_size': 5, 'throughput': 1.3300673382296877, 'latency_mean': 3.7403469395637514, 'latency_p50': 3.7390458583831787, 'latency_p90': 4.163921117782593}, {'batch_size': 6, 'throughput': 1.398398940595871, 'latency_mean': 4.261363281011581, 'latency_p50': 4.268154740333557, 'latency_p90': 4.769031023979187}, {'batch_size': 8, 'throughput': 1.462058540802306, 'latency_mean': 5.437093330621719, 'latency_p50': 5.4634246826171875, 'latency_p90': 6.08996467590332}, {'batch_size': 10, 'throughput': 1.5073474312392885, 'latency_mean': 6.587327874898911, 'latency_p50': 6.604068040847778, 'latency_p90': 7.452836179733276}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-chai-ddpo_v2
is_internal_developer: False
language_model: AlexCuadron/chai-ddpo
model_size: 13B
ranking_group: single
throughput_3p7s: 1.33
us_pacific_date: 2025-03-23
win_ratio: 0.4684949945318415
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '####', 'Me:', 'You:', 'Bot:', 'User:', '</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', '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 alexcuadron-chai-ddpo-v2-mkmlizer
Waiting for job on alexcuadron-chai-ddpo-v2-mkmlizer to finish
alexcuadron-chai-ddpo-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-chai-ddpo-v2-mkmlizer: ║     _____            __           __                                ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║       /___/                                                         ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║  https://mk1.ai                                                     ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║  belonging to:                                                      ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║  Chai Research Corp.                                                ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexcuadron-chai-ddpo-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-ddpo-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-chai-ddpo-v2-mkmlizer: Downloaded to shared memory in 39.091s
alexcuadron-chai-ddpo-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpat_dyifz, device:0
alexcuadron-chai-ddpo-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-chai-ddpo-v2-mkmlizer: quantized model in 35.285s
alexcuadron-chai-ddpo-v2-mkmlizer: Processed model AlexCuadron/chai-ddpo in 74.377s
alexcuadron-chai-ddpo-v2-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-chai-ddpo-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-chai-ddpo-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-chai-ddpo-v2
alexcuadron-chai-ddpo-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-chai-ddpo-v2/config.json
alexcuadron-chai-ddpo-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-chai-ddpo-v2/special_tokens_map.json
alexcuadron-chai-ddpo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-chai-ddpo-v2/tokenizer_config.json
alexcuadron-chai-ddpo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-chai-ddpo-v2/tokenizer.json
alexcuadron-chai-ddpo-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-chai-ddpo-v2/flywheel_model.0.safetensors
alexcuadron-chai-ddpo-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 29.99it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.38it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 48.80it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 49.77it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.33it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 50.29it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 51.05it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 53.11it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 50.95it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 37.29it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 37.73it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 41.74it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 42.15it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 42.88it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 48.29it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 46.49it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 44.59it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 53.17it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 49.20it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:05, 47.62it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 46.91it/s]
Loading 0:  36%|███▌      | 131/363 [00:02<00:04, 46.77it/s]
Loading 0:  37%|███▋      | 136/363 [00:02<00:05, 39.81it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 34.05it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.61it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 33.74it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 39.76it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:04, 41.18it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 43.05it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:04, 43.58it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 43.40it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 47.72it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 46.23it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:03, 45.27it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 49.84it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:03, 47.23it/s]
Loading 0:  59%|█████▊    | 213/363 [00:04<00:03, 45.56it/s]
Loading 0:  61%|██████    | 220/363 [00:04<00:02, 51.46it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 33.63it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 35.19it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 40.82it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:02, 42.83it/s]
Loading 0:  68%|██████▊   | 248/363 [00:05<00:03, 36.35it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 44.12it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 44.42it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 44.12it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 47.90it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 49.50it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 44.87it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 48.76it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 46.12it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:20,  2.88it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:15,  3.61it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:11,  4.59it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:05,  7.41it/s]
Loading 0:  90%|████████▉ | 326/363 [00:13<00:03,  9.94it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.42it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 17.31it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 21.30it/s]
Loading 0:  96%|█████████▋| 350/363 [00:14<00:00, 25.96it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 31.11it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 34.52it/s]
                                                            

Job alexcuadron-chai-ddpo-v2-mkmlizer completed after 104.45s with status: succeeded
Stopping job with name alexcuadron-chai-ddpo-v2-mkmlizer
Pipeline stage MKMLizer completed in 104.98s
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 alexcuadron-chai-ddpo-v2
Waiting for inference service alexcuadron-chai-ddpo-v2 to be ready
Inference service alexcuadron-chai-ddpo-v2 ready after 80.37977886199951s
Pipeline stage MKMLDeployer completed in 80.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.224231004714966s
Received healthy response to inference request in 1.5828523635864258s
Received healthy response to inference request in 1.5651726722717285s
Received healthy response to inference request in 1.6420238018035889s
Received healthy response to inference request in 1.6190578937530518s
5 requests
0 failed requests
5th percentile: 1.568708610534668
10th percentile: 1.5722445487976073
20th percentile: 1.5793164253234864
30th percentile: 1.590093469619751
40th percentile: 1.6045756816864014
50th percentile: 1.6190578937530518
60th percentile: 1.6282442569732667
70th percentile: 1.6374306201934814
80th percentile: 1.7584652423858644
90th percentile: 1.9913481235504151
95th percentile: 2.1077895641326903
99th percentile: 2.2009427165985107
mean time: 1.726667547225952
Pipeline stage StressChecker completed in 9.96s
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 0.67s
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
alexcuadron-chai-ddpo_v2 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexcuadron-chai-ddpo-v2-profiler
Waiting for inference service alexcuadron-chai-ddpo-v2-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4324.93s
Shutdown handler de-registered
alexcuadron-chai-ddpo_v2 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-chai-ddpo_v2 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1