rirv938-anthropic-grpo-_22923

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_22923_v1

model_name: rirv938-anthropic-grpo-_22923_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-15T02:56:03+00:00

num_battles: 7398

num_wins: 3738

celo_rating: 1292.4

family_friendly_score: 0.5378000000000001

family_friendly_standard_error: 0.007050832007642786

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp444_95ff_20ww2_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': 0.6414488217277471, 'latency_mean': 1.5589005076885223, 'latency_p50': 1.5579274892807007, 'latency_p90': 1.744136643409729}, {'batch_size': 3, 'throughput': 1.2365781295692069, 'latency_mean': 2.420078942775726, 'latency_p50': 2.412768602371216, 'latency_p90': 2.6885030984878537}, {'batch_size': 5, 'throughput': 1.5230523003670806, 'latency_mean': 3.2624259173870085, 'latency_p50': 3.2592194080352783, 'latency_p90': 3.63480486869812}, {'batch_size': 6, 'throughput': 1.6270155465991492, 'latency_mean': 3.670179911851883, 'latency_p50': 3.6828538179397583, 'latency_p90': 4.15220160484314}, {'batch_size': 8, 'throughput': 1.7057027010282615, 'latency_mean': 4.660660469532013, 'latency_p50': 4.6852216720581055, 'latency_p90': 5.20709261894226}, {'batch_size': 10, 'throughput': 1.755592712489405, 'latency_mean': 5.640918302536011, 'latency_p50': 5.645177245140076, 'latency_p90': 6.3681432723999025}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_22923_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp444_95ff_20ww2_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.64

us_pacific_date: 2025-05-14

win_ratio: 0.505271695052717

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 rirv938-anthropic-grpo-22923-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-22923-v1-mkmlizer to finish
rirv938-anthropic-grpo-22923-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-22923-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-22923-v1-mkmlizer: Downloaded to shared memory in 80.868s
rirv938-anthropic-grpo-22923-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9tr1723j, device:0
rirv938-anthropic-grpo-22923-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-22923-v1-mkmlizer: quantized model in 41.283s
rirv938-anthropic-grpo-22923-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp444_95ff_20ww2_merged in 122.152s
rirv938-anthropic-grpo-22923-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-22923-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-22923-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-22923-v1
rirv938-anthropic-grpo-22923-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-22923-v1/config.json
rirv938-anthropic-grpo-22923-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-22923-v1/special_tokens_map.json
rirv938-anthropic-grpo-22923-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-22923-v1/tokenizer_config.json
rirv938-anthropic-grpo-22923-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-22923-v1/tokenizer.json
rirv938-anthropic-grpo-22923-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-22923-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-22923-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.80it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.41it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 26.25it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:08, 38.07it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:14, 22.80it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 27.64it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 28.30it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 29.68it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 29.18it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.12it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.50it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:10, 30.28it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.16it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.27it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.51it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 29.31it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.70it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:09, 29.89it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.08it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.10it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.92it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 25.44it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.22it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:08, 29.25it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 27.32it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:08, 27.79it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:09, 24.21it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:08, 28.69it/s]
Loading 0:  36%|███▌      | 131/363 [00:04<00:09, 25.09it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 29.21it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.27it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.53it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.17it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 28.46it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 27.55it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 29.92it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.87it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 31.30it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.38it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 23.77it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.17it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:06, 28.07it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 27.80it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.85it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.06it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.78it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.73it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 29.89it/s]
Loading 0:  61%|██████    | 222/363 [00:07<00:04, 32.10it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 22.55it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 21.96it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 28.42it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 27.68it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 30.63it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 29.82it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 32.24it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.74it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.48it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.49it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 28.91it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 28.59it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 31.32it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.31it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.08it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.00it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 29.94it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 26.49it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.58it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.72it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.45it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 28.18it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 30.97it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.15it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 32.85it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 30.32it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.96it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.65it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.85it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  4.97it/s]
                                                            
Job rirv938-anthropic-grpo-22923-v1-mkmlizer completed after 145.64s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-22923-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.14s
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 rirv938-anthropic-grpo-22923-v1
Waiting for inference service rirv938-anthropic-grpo-22923-v1 to be ready
Inference service rirv938-anthropic-grpo-22923-v1 ready after 120.51264452934265s
Pipeline stage MKMLDeployer completed in 121.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6924643516540527s
Received healthy response to inference request in 1.6441349983215332s
Received healthy response to inference request in 1.9498426914215088s
Received healthy response to inference request in 1.789191484451294s
Received healthy response to inference request in 1.7964451313018799s
5 requests
0 failed requests
5th percentile: 1.6731462955474854
10th percentile: 1.7021575927734376
20th percentile: 1.7601801872253418
30th percentile: 1.790642213821411
40th percentile: 1.7935436725616456
50th percentile: 1.7964451313018799
60th percentile: 1.8578041553497315
70th percentile: 1.919163179397583
80th percentile: 2.098367023468018
90th percentile: 2.395415687561035
95th percentile: 2.5439400196075437
99th percentile: 2.662759485244751
mean time: 1.9744157314300537
Pipeline stage StressChecker completed in 11.36s
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 0.90s
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 0.79s
Shutdown handler de-registered
rirv938-anthropic-grpo-_22923_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 2757.79s
Shutdown handler de-registered
rirv938-anthropic-grpo-_22923_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_22923_v1 status is now torndown due to DeploymentManager action