chaiml-anthropic-grpo-4_66492

developer_uid: rirv938

submission_id: chaiml-anthropic-grpo-4_66492_v2

model_name: chaiml-anthropic-grpo-4_66492_v2

model_group: ChaiML/anthropic_grpo_40

status: torndown

timestamp: 2025-05-01T18:37:57+00:00

num_battles: 7943

num_wins: 4144

celo_rating: 1320.79

family_friendly_score: 0.5626

family_friendly_standard_error: 0.0070154292812343285

submission_type: basic

model_repo: ChaiML/anthropic_grpo_40k_cp1184_95ff

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6415673338423681, 'latency_mean': 1.5586127483844756, 'latency_p50': 1.566162347793579, 'latency_p90': 1.7203287363052369}, {'batch_size': 3, 'throughput': 1.2389326713473738, 'latency_mean': 2.4154837369918822, 'latency_p50': 2.427758812904358, 'latency_p90': 2.6457164764404295}, {'batch_size': 5, 'throughput': 1.5373631486762422, 'latency_mean': 3.2280371260643004, 'latency_p50': 3.211416721343994, 'latency_p90': 3.6513672590255735}, {'batch_size': 6, 'throughput': 1.6322514045986078, 'latency_mean': 3.6460717618465424, 'latency_p50': 3.664403796195984, 'latency_p90': 4.069917702674866}, {'batch_size': 8, 'throughput': 1.724764212747972, 'latency_mean': 4.602198275327683, 'latency_p50': 4.613961338996887, 'latency_p90': 5.235052061080933}, {'batch_size': 10, 'throughput': 1.7504920032645102, 'latency_mean': 5.66878231048584, 'latency_p50': 5.6450196504592896, 'latency_p90': 6.463067078590393}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-anthropic-grpo-4_66492_v2

is_internal_developer: True

language_model: ChaiML/anthropic_grpo_40k_cp1184_95ff

model_size: 13B

ranking_group: single

throughput_3p7s: 1.65

us_pacific_date: 2025-05-01

win_ratio: 0.5217172353015234

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'You:', '</s>', '###'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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 chaiml-anthropic-grpo-4-66492-v2-mkmlizer
Waiting for job on chaiml-anthropic-grpo-4-66492-v2-mkmlizer to finish
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║       /___/                                                         ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: Downloaded to shared memory in 61.258s
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9auavkge, device:0
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: quantized model in 41.654s
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: Processed model ChaiML/anthropic_grpo_40k_cp1184_95ff in 102.912s
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v2
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v2/config.json
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v2/special_tokens_map.json
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v2/tokenizer_config.json
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v2/tokenizer.json
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v2/flywheel_model.0.safetensors
chaiml-anthropic-grpo-4-66492-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.26it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 29.07it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.76it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 36.27it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.86it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 25.63it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 27.21it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.71it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.61it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.20it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 28.05it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:11, 27.71it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.79it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 18.76it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:11, 25.49it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:11, 25.62it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.90it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:10, 27.28it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:10, 26.52it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:09, 29.46it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 28.73it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.54it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.83it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 27.26it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:09, 25.04it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:08, 27.75it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:09, 24.79it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:07, 29.92it/s]
Loading 0:  36%|███▌      | 131/363 [00:04<00:08, 26.27it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 30.32it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.82it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 24.13it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.69it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 28.88it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 28.00it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.51it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.90it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.58it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.87it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.11it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 21.16it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 28.06it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 27.45it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.45it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.48it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.95it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.51it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 30.97it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 26.35it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.59it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.69it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.78it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 29.81it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 32.05it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 29.50it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.96it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.40it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.79it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.81it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 28.91it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 28.37it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 31.12it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.76it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.17it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.68it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 28.95it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 24.88it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.55it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.41it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 29.47it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 28.77it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.46it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 30.33it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.52it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.17it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.95it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.61it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.80it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  4.93it/s]
                                                            
Job chaiml-anthropic-grpo-4-66492-v2-mkmlizer completed after 125.4s with status: succeeded
Stopping job with name chaiml-anthropic-grpo-4-66492-v2-mkmlizer
Pipeline stage MKMLizer completed in 125.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-anthropic-grpo-4-66492-v2
Waiting for inference service chaiml-anthropic-grpo-4-66492-v2 to be ready
Inference service chaiml-anthropic-grpo-4-66492-v2 ready after 150.46862936019897s
Pipeline stage MKMLDeployer completed in 151.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3177435398101807s
Received healthy response to inference request in 1.8628313541412354s
Received healthy response to inference request in 1.7790310382843018s
Received healthy response to inference request in 1.6095116138458252s
Received healthy response to inference request in 1.5564334392547607s
5 requests
0 failed requests
5th percentile: 1.5670490741729737
10th percentile: 1.5776647090911866
20th percentile: 1.5988959789276123
30th percentile: 1.6434154987335206
40th percentile: 1.711223268508911
50th percentile: 1.7790310382843018
60th percentile: 1.812551164627075
70th percentile: 1.8460712909698487
80th percentile: 1.9538137912750244
90th percentile: 2.1357786655426025
95th percentile: 2.2267611026763916
99th percentile: 2.299547052383423
mean time: 1.8251101970672607
Pipeline stage StressChecker completed in 10.55s
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 0.72s
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 0.70s
Shutdown handler de-registered
chaiml-anthropic-grpo-4_66492_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-anthropic-grpo-4-66492-v2-profiler
Waiting for inference service chaiml-anthropic-grpo-4-66492-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 3144.03s
Shutdown handler de-registered
chaiml-anthropic-grpo-4_66492_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-anthropic-grpo-4_66492_v2 status is now torndown due to DeploymentManager action