alexcuadron-chai-ddpo

developer_uid: AlexCuadron

submission_id: alexcuadron-chai-ddpo_v3

model_name: alexcuadron-chai-ddpo_v3

model_group: AlexCuadron/chai-ddpo

status: torndown

timestamp: 2025-03-24T14:23:17+00:00

num_battles: 7355

num_wins: 3383

celo_rating: 1250.82

family_friendly_score: 0.6198

family_friendly_standard_error: 0.006865099562278758

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': 0.5993720568020625, 'latency_mean': 1.6683268320560456, 'latency_p50': 1.6595669984817505, 'latency_p90': 1.8397916078567504}, {'batch_size': 3, 'throughput': 1.077841264425655, 'latency_mean': 2.772247978448868, 'latency_p50': 2.786441445350647, 'latency_p90': 3.01751127243042}, {'batch_size': 5, 'throughput': 1.2984988715062415, 'latency_mean': 3.8363863706588743, 'latency_p50': 3.829584240913391, 'latency_p90': 4.265547513961792}, {'batch_size': 6, 'throughput': 1.358899915404406, 'latency_mean': 4.3915163516998295, 'latency_p50': 4.3915934562683105, 'latency_p90': 4.916913485527038}, {'batch_size': 8, 'throughput': 1.4225881414792965, 'latency_mean': 5.582223380804062, 'latency_p50': 5.596616864204407, 'latency_p90': 6.3161239385604855}, {'batch_size': 10, 'throughput': 1.458661494253698, 'latency_mean': 6.799818533658981, 'latency_p50': 6.786896705627441, 'latency_p90': 7.740097212791443}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexcuadron-chai-ddpo_v3

is_internal_developer: False

language_model: AlexCuadron/chai-ddpo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-03-24

win_ratio: 0.45995921142080215

generation_params: {'temperature': 0.4, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-v3-mkmlizer
Waiting for job on alexcuadron-chai-ddpo-v3-mkmlizer to finish
alexcuadron-chai-ddpo-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-chai-ddpo-v3-mkmlizer: ║     _____            __           __                                ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║       /___/                                                         ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║                                                                     ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║  https://mk1.ai                                                     ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║                                                                     ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║  belonging to:                                                      ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║                                                                     ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║  Chai Research Corp.                                                ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexcuadron-chai-ddpo-v3-mkmlizer: ║                                                                     ║
alexcuadron-chai-ddpo-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-chai-ddpo-v3-mkmlizer: Downloaded to shared memory in 30.686s
alexcuadron-chai-ddpo-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpym8p3xmr, device:0
alexcuadron-chai-ddpo-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-chai-ddpo-v3-mkmlizer: quantized model in 35.535s
alexcuadron-chai-ddpo-v3-mkmlizer: Processed model AlexCuadron/chai-ddpo in 66.222s
alexcuadron-chai-ddpo-v3-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-chai-ddpo-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-chai-ddpo-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-chai-ddpo-v3
alexcuadron-chai-ddpo-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-chai-ddpo-v3/special_tokens_map.json
alexcuadron-chai-ddpo-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-chai-ddpo-v3/config.json
alexcuadron-chai-ddpo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-chai-ddpo-v3/tokenizer_config.json
alexcuadron-chai-ddpo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-chai-ddpo-v3/tokenizer.json
alexcuadron-chai-ddpo-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-chai-ddpo-v3/flywheel_model.0.safetensors
alexcuadron-chai-ddpo-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 32.12it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 54.25it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:06, 51.13it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 52.36it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 47.93it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:05, 56.32it/s]
Loading 0:  13%|█▎        | 46/363 [00:00<00:05, 53.35it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:05, 53.27it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:05, 54.45it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 37.50it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 41.75it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.47it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:07, 39.86it/s]
Loading 0:  25%|██▍       | 89/363 [00:01<00:06, 43.09it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 41.82it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 39.68it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:06, 41.17it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 42.64it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 39.36it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 39.29it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 45.35it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:05, 44.21it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 40.54it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 31.69it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 30.15it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 29.94it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 37.06it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:05, 39.46it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 40.08it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 44.60it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 43.29it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 44.29it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 44.46it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:03, 43.95it/s]
Loading 0:  55%|█████▌    | 201/363 [00:04<00:03, 48.11it/s]
Loading 0:  57%|█████▋    | 206/363 [00:04<00:03, 48.33it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 48.51it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 47.23it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 35.51it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 35.45it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 34.81it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.07it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:02, 40.73it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 43.11it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 43.75it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 43.30it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 47.29it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:01, 47.80it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 47.04it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 44.99it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 42.78it/s]
Loading 0:  80%|████████  | 291/363 [00:06<00:01, 45.81it/s]
Loading 0:  82%|████████▏ | 296/363 [00:06<00:01, 43.92it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 45.63it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:20,  2.63it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:15,  3.36it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.46it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.43it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.53it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.56it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 17.19it/s]
Loading 0:  96%|█████████▋| 350/363 [00:14<00:00, 21.58it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 26.67it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 30.65it/s]
                                                            
Job alexcuadron-chai-ddpo-v3-mkmlizer completed after 93.99s with status: succeeded
Stopping job with name alexcuadron-chai-ddpo-v3-mkmlizer
Pipeline stage MKMLizer completed in 94.49s
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 alexcuadron-chai-ddpo-v3
Waiting for inference service alexcuadron-chai-ddpo-v3 to be ready
Inference service alexcuadron-chai-ddpo-v3 ready after 90.77093005180359s
Pipeline stage MKMLDeployer completed in 91.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.485691785812378s
Received healthy response to inference request in 1.6935627460479736s
Received healthy response to inference request in 1.7835109233856201s
Received healthy response to inference request in 1.4722185134887695s
Received healthy response to inference request in 1.4623987674713135s
5 requests
0 failed requests
5th percentile: 1.4643627166748048
10th percentile: 1.4663266658782959
20th percentile: 1.4702545642852782
30th percentile: 1.5164873600006104
40th percentile: 1.605025053024292
50th percentile: 1.6935627460479736
60th percentile: 1.7295420169830322
70th percentile: 1.7655212879180908
80th percentile: 1.9239470958709717
90th percentile: 2.204819440841675
95th percentile: 2.3452556133270264
99th percentile: 2.4576045513153075
mean time: 1.7794765472412108
Pipeline stage StressChecker completed in 10.16s
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 0.70s
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 0.69s
Shutdown handler de-registered
alexcuadron-chai-ddpo_v3 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexcuadron-chai-ddpo-v3-profiler
Waiting for inference service alexcuadron-chai-ddpo-v3-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 4365.17s
Shutdown handler de-registered
alexcuadron-chai-ddpo_v3 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-chai-ddpo_v3 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message