chaiml-anthropic-grpo-40_3002

developer_uid: rirv938

submission_id: chaiml-anthropic-grpo-40_3002_v1

model_name: chaiml-anthropic-grpo-40_3002_v1

model_group: ChaiML/anthropic_grpo_40

status: torndown

timestamp: 2025-05-15T23:00:49+00:00

num_battles: 7588

num_wins: 3789

celo_rating: 1289.2

family_friendly_score: 0.5658000000000001

family_friendly_standard_error: 0.007009570029609519

submission_type: basic

model_repo: ChaiML/anthropic_grpo_40k_cp234_95ff_beta4_merged

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': 0.6415225642774219, 'latency_mean': 1.5587199902534485, 'latency_p50': 1.5621932744979858, 'latency_p90': 1.7195661544799805}, {'batch_size': 3, 'throughput': 1.249498579704008, 'latency_mean': 2.393636031150818, 'latency_p50': 2.3923193216323853, 'latency_p90': 2.6517720460891723}, {'batch_size': 5, 'throughput': 1.533716969055349, 'latency_mean': 3.2496290373802186, 'latency_p50': 3.2499395608901978, 'latency_p90': 3.7075966119766237}, {'batch_size': 6, 'throughput': 1.6152729944894106, 'latency_mean': 3.6895847284793852, 'latency_p50': 3.7155829668045044, 'latency_p90': 4.063240623474121}, {'batch_size': 8, 'throughput': 1.7337160442851907, 'latency_mean': 4.587777438163758, 'latency_p50': 4.545045495033264, 'latency_p90': 5.317406082153321}, {'batch_size': 10, 'throughput': 1.7500921819484943, 'latency_mean': 5.649907555580139, 'latency_p50': 5.670520663261414, 'latency_p90': 6.383211851119995}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-anthropic-grpo-40_3002_v1

is_internal_developer: True

language_model: ChaiML/anthropic_grpo_40k_cp234_95ff_beta4_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.63

us_pacific_date: 2025-05-15

win_ratio: 0.4993410648392198

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': ['You:', '</s>', '\n', '###'], '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-40-3002-v1-mkmlizer
Waiting for job on chaiml-anthropic-grpo-40-3002-v1-mkmlizer to finish
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║       /___/                                                         ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: Downloaded to shared memory in 60.674s
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3c55koap, device:0
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: quantized model in 41.604s
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: Processed model ChaiML/anthropic_grpo_40k_cp234_95ff_beta4_merged in 102.279s
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-anthropic-grpo-40-3002-v1
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-40-3002-v1/config.json
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-40-3002-v1/special_tokens_map.json
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-40-3002-v1/tokenizer_config.json
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-40-3002-v1/tokenizer.json
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-anthropic-grpo-40-3002-v1/flywheel_model.0.safetensors
chaiml-anthropic-grpo-40-3002-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.01it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.96it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.47it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 31.02it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 21.61it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 19.36it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.98it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.42it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 27.87it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.24it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.39it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 28.26it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.51it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 23.99it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 21.14it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 27.47it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.84it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 23.56it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:09, 28.82it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.93it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.20it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.38it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.61it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 21.21it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 27.74it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 27.28it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.50it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.38it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.46it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 28.66it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 28.51it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:09, 24.03it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 22.96it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.36it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 28.86it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 28.03it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.40it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.85it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 31.03it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.75it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 23.87it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 21.08it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:06, 26.29it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:06, 24.36it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.98it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.34it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.12it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 29.44it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 29.45it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 24.90it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.54it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.32it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 28.78it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 27.74it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 28.06it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 25.09it/s]
Loading 0:  70%|██████▉   | 253/363 [00:09<00:03, 30.05it/s]
Loading 0:  71%|███████   | 257/363 [00:09<00:04, 26.18it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.37it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.76it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 28.31it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.86it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 29.99it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.64it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.29it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 28.48it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 28.75it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 24.22it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.25it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.62it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 29.24it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 28.47it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 30.63it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 29.10it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.24it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.18it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.98it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.65it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.84it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.98it/s]
                                                            
Job chaiml-anthropic-grpo-40-3002-v1-mkmlizer completed after 124.95s with status: succeeded
Stopping job with name chaiml-anthropic-grpo-40-3002-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.47s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-anthropic-grpo-40-3002-v1
Waiting for inference service chaiml-anthropic-grpo-40-3002-v1 to be ready
Inference service chaiml-anthropic-grpo-40-3002-v1 ready after 130.56030893325806s
Pipeline stage MKMLDeployer completed in 131.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.562915325164795s
Received healthy response to inference request in 1.8909523487091064s
Received healthy response to inference request in 1.6450116634368896s
Received healthy response to inference request in 2.0523509979248047s
Received healthy response to inference request in 1.578596830368042s
5 requests
0 failed requests
5th percentile: 1.5918797969818115
10th percentile: 1.605162763595581
20th percentile: 1.6317286968231202
30th percentile: 1.694199800491333
40th percentile: 1.7925760746002197
50th percentile: 1.8909523487091064
60th percentile: 1.9555118083953857
70th percentile: 2.020071268081665
80th percentile: 2.154463863372803
90th percentile: 2.3586895942687987
95th percentile: 2.460802459716797
99th percentile: 2.542492752075195
mean time: 1.9459654331207275
Pipeline stage StressChecker completed in 11.19s
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 0.91s
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 0.75s
Shutdown handler de-registered
chaiml-anthropic-grpo-40_3002_v1 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3000.61s
Shutdown handler de-registered
chaiml-anthropic-grpo-40_3002_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-anthropic-grpo-40_3002_v1 status is now torndown due to DeploymentManager action