developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_90974_v1
model_name: rirv938-anthropic-grpo-_90974_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-14T01:20:12+00:00
num_battles: 6160
num_wins: 3246
celo_rating: 1295.95
family_friendly_score: 0.5389999999999999
family_friendly_standard_error: 0.0070495248066802345
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp888_95ff_20ww_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': 0.6388974116003074, 'latency_mean': 1.5651281714439391, 'latency_p50': 1.5740292072296143, 'latency_p90': 1.7177249670028687}, {'batch_size': 3, 'throughput': 1.2189207207648651, 'latency_mean': 2.454488524198532, 'latency_p50': 2.4584819078445435, 'latency_p90': 2.7592641353607177}, {'batch_size': 5, 'throughput': 1.5029942364760815, 'latency_mean': 3.315425386428833, 'latency_p50': 3.3028587102890015, 'latency_p90': 3.727329325675964}, {'batch_size': 6, 'throughput': 1.5919966525856974, 'latency_mean': 3.756431374549866, 'latency_p50': 3.7682626247406006, 'latency_p90': 4.206544494628906}, {'batch_size': 8, 'throughput': 1.674306032436889, 'latency_mean': 4.74170056939125, 'latency_p50': 4.752267956733704, 'latency_p90': 5.29334225654602}, {'batch_size': 10, 'throughput': 1.7064219587032448, 'latency_mean': 5.806637134552002, 'latency_p50': 5.808131694793701, 'latency_p90': 6.554643678665161}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_90974_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp888_95ff_20ww_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.59
us_pacific_date: 2025-05-13
win_ratio: 0.5269480519480519
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 rirv938-anthropic-grpo-90974-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-90974-v1-mkmlizer to finish
rirv938-anthropic-grpo-90974-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-90974-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Retrying (%r) after connection broken by '%r': %s
rirv938-anthropic-grpo-90974-v1-mkmlizer: Downloaded to shared memory in 85.480s
rirv938-anthropic-grpo-90974-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyyydnj47, device:0
rirv938-anthropic-grpo-90974-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-90974-v1-mkmlizer: quantized model in 41.800s
rirv938-anthropic-grpo-90974-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp888_95ff_20ww_merged in 127.280s
rirv938-anthropic-grpo-90974-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-90974-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-90974-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-90974-v1
rirv938-anthropic-grpo-90974-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-90974-v1/special_tokens_map.json
rirv938-anthropic-grpo-90974-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-90974-v1/config.json
rirv938-anthropic-grpo-90974-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-90974-v1/tokenizer_config.json
rirv938-anthropic-grpo-90974-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-90974-v1/tokenizer.json
rirv938-anthropic-grpo-90974-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-90974-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-90974-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.22it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.07it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.53it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 33.34it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:15, 21.93it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 21.13it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.56it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 25.27it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.16it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.38it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.62it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.96it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.12it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.18it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 21.45it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 28.50it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 28.45it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 27.35it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 30.31it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.55it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.31it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.67it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 23.95it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 21.31it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.53it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 27.63it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.50it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:09, 26.13it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 28.76it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 27.70it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:08, 28.22it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:09, 24.01it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.03it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.60it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 29.57it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 28.90it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 31.59it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.76it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 32.22it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.70it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.40it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.54it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:05, 28.76it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 27.42it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:05, 27.79it/s]
Loading 0:  56%|█████▌    | 203/363 [00:07<00:06, 24.21it/s]
Loading 0:  57%|█████▋    | 208/363 [00:07<00:05, 28.68it/s]
Loading 0:  58%|█████▊    | 212/363 [00:07<00:06, 24.93it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 29.65it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.26it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.78it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.57it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 28.90it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 27.41it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 29.61it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 28.27it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 30.82it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 28.82it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 23.51it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 20.91it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 28.27it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 28.07it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.65it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.18it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.16it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.32it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 29.96it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 25.62it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.11it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.31it/s]
Loading 0:  87%|████████▋ | 316/363 [00:11<00:01, 27.44it/s]
Loading 0:  88%|████████▊ | 320/363 [00:11<00:01, 24.92it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 29.86it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:01, 26.49it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 32.85it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 30.08it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  2.04it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.69it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.86it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.95it/s]
                                                            

Job rirv938-anthropic-grpo-90974-v1-mkmlizer completed after 155.34s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-90974-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.87s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-90974-v1
Waiting for inference service rirv938-anthropic-grpo-90974-v1 to be ready
Inference service rirv938-anthropic-grpo-90974-v1 ready after 130.51582717895508s
Pipeline stage MKMLDeployer completed in 131.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4728236198425293s
Received healthy response to inference request in 1.640981912612915s
Received healthy response to inference request in 1.9580340385437012s
Received healthy response to inference request in 1.585526943206787s
Received healthy response to inference request in 1.9655537605285645s
5 requests
0 failed requests
5th percentile: 1.5966179370880127
10th percentile: 1.6077089309692383
20th percentile: 1.6298909187316895
30th percentile: 1.7043923377990722
40th percentile: 1.8312131881713867
50th percentile: 1.9580340385437012
60th percentile: 1.9610419273376465
70th percentile: 1.9640498161315918
80th percentile: 2.0670077323913576
90th percentile: 2.2699156761169434
95th percentile: 2.371369647979736
99th percentile: 2.4525328254699708
mean time: 1.9245840549468993
Pipeline stage StressChecker completed in 11.20s
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 0.74s
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 0.88s
Shutdown handler de-registered
rirv938-anthropic-grpo-_90974_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 2874.50s
Shutdown handler de-registered
rirv938-anthropic-grpo-_90974_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_90974_v1 status is now torndown due to DeploymentManager action