rirv938-anthropic-grpo-_12256

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_12256_v1

model_name: rirv938-anthropic-grpo-_12256_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-16T03:22:58+00:00

num_battles: 9542

num_wins: 5046

celo_rating: 1292.05

family_friendly_score: 0.5609999999999999

family_friendly_standard_error: 0.007018247644533499

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp592_95ff_beta6_2_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': 0.6182958787089174, 'latency_mean': 1.6172770059108734, 'latency_p50': 1.6032284498214722, 'latency_p90': 1.799573302268982}, {'batch_size': 3, 'throughput': 1.1465909829314938, 'latency_mean': 2.613056672811508, 'latency_p50': 2.6152007579803467, 'latency_p90': 2.8973403215408324}, {'batch_size': 5, 'throughput': 1.392573593686654, 'latency_mean': 3.5767078578472136, 'latency_p50': 3.578849196434021, 'latency_p90': 4.009142589569092}, {'batch_size': 6, 'throughput': 1.4672494650752108, 'latency_mean': 4.0613366687297825, 'latency_p50': 4.094329118728638, 'latency_p90': 4.516502547264099}, {'batch_size': 8, 'throughput': 1.5387659505799314, 'latency_mean': 5.15777778506279, 'latency_p50': 5.16450560092926, 'latency_p90': 5.81218729019165}, {'batch_size': 10, 'throughput': 1.6001938223047096, 'latency_mean': 6.195387016534806, 'latency_p50': 6.175057053565979, 'latency_p90': 6.972961473464966}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_12256_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp592_95ff_beta6_2_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.42

us_pacific_date: 2025-05-15

win_ratio: 0.5288199538880738

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:', '\n', '###', '</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 rirv938-anthropic-grpo-12256-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-12256-v1-mkmlizer to finish
rirv938-anthropic-grpo-12256-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-12256-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-12256-v1-mkmlizer: Downloaded to shared memory in 83.060s
rirv938-anthropic-grpo-12256-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkzbyjk35, device:0
rirv938-anthropic-grpo-12256-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-12256-v1-mkmlizer: quantized model in 40.866s
rirv938-anthropic-grpo-12256-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp592_95ff_beta6_2_merged in 123.926s
rirv938-anthropic-grpo-12256-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-12256-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-12256-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-12256-v1
rirv938-anthropic-grpo-12256-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-12256-v1/tokenizer_config.json
rirv938-anthropic-grpo-12256-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-12256-v1/tokenizer.json
rirv938-anthropic-grpo-12256-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-12256-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-12256-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.37it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 29.06it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 26.14it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:09, 35.23it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.96it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:13, 24.10it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.37it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 30.04it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 29.10it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.84it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.60it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:10, 29.68it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 25.08it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.13it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 28.73it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 28.21it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:10, 26.37it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:09, 29.23it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.67it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 33.25it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 31.40it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 25.59it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.73it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 29.30it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 28.41it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.70it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.25it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.90it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.68it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.80it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 27.18it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 25.61it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:08, 24.48it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 31.14it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 30.12it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.44it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.83it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 33.07it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.07it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.82it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:07, 22.27it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 29.07it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:05, 28.41it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 31.09it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 30.12it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.19it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.56it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 30.76it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 26.30it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.94it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.95it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.83it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 29.62it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 31.70it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 30.63it/s]
Loading 0:  70%|███████   | 255/363 [00:08<00:03, 32.85it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.74it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.93it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 22.29it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 29.27it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:02, 28.71it/s]
Loading 0:  78%|███████▊  | 282/363 [00:09<00:02, 30.94it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.58it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.57it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.07it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 30.49it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 26.30it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 24.39it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.60it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.04it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 28.53it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.05it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 29.52it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 31.59it/s]
Loading 0:  94%|█████████▎| 340/363 [00:11<00:00, 30.04it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  1.98it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.67it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.87it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.03it/s]
                                                            
Job rirv938-anthropic-grpo-12256-v1-mkmlizer completed after 155.17s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-12256-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.82s
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 rirv938-anthropic-grpo-12256-v1
Waiting for inference service rirv938-anthropic-grpo-12256-v1 to be ready
Inference service rirv938-anthropic-grpo-12256-v1 ready after 140.79448318481445s
Pipeline stage MKMLDeployer completed in 141.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5393552780151367s
Received healthy response to inference request in 1.8117268085479736s
Received healthy response to inference request in 1.6832246780395508s
Received healthy response to inference request in 1.609330177307129s
Received healthy response to inference request in 1.6923365592956543s
5 requests
0 failed requests
5th percentile: 1.6241090774536133
10th percentile: 1.6388879776000977
20th percentile: 1.6684457778930664
30th percentile: 1.6850470542907714
40th percentile: 1.6886918067932128
50th percentile: 1.6923365592956543
60th percentile: 1.740092658996582
70th percentile: 1.7878487586975098
80th percentile: 1.9572525024414065
90th percentile: 2.2483038902282715
95th percentile: 2.393829584121704
99th percentile: 2.51025013923645
mean time: 1.867194700241089
Pipeline stage StressChecker completed in 10.86s
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 0.71s
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 0.66s
Shutdown handler de-registered
rirv938-anthropic-grpo-_12256_v1 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 rirv938-anthropic-grpo-12256-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-12256-v1-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2869.11s
Shutdown handler de-registered
rirv938-anthropic-grpo-_12256_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_12256_v1 status is now torndown due to DeploymentManager action