rirv938-anthropic-grpo-_18073

developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_18073_v1
model_name: rirv938-anthropic-grpo-_18073_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-21T16:34:25+00:00
num_battles: 8462
num_wins: 4559
celo_rating: 1320.74
family_friendly_score: 0.5768
family_friendly_standard_error: 0.006987156216945489
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp3744_96ff_new_rm_b3_merged
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
display_name: rirv938-anthropic-grpo-_18073_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp3744_96ff_new_rm_b3_merged
model_size: 13B
ranking_group: single
us_pacific_date: 2025-05-21
win_ratio: 0.5387615220987946
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': ['###', '</s>', '\n', 'You:'], '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-18073-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-18073-v1-mkmlizer to finish
rirv938-anthropic-grpo-18073-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-18073-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-18073-v1-mkmlizer: Downloaded to shared memory in 80.155s
rirv938-anthropic-grpo-18073-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf1svt1_8, device:0
rirv938-anthropic-grpo-18073-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-18073-v1-mkmlizer: quantized model in 41.396s
rirv938-anthropic-grpo-18073-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp3744_96ff_new_rm_b3_merged in 121.552s
rirv938-anthropic-grpo-18073-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-18073-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-18073-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-18073-v1
rirv938-anthropic-grpo-18073-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-18073-v1/config.json
rirv938-anthropic-grpo-18073-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-18073-v1/special_tokens_map.json
rirv938-anthropic-grpo-18073-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-18073-v1/tokenizer_config.json
rirv938-anthropic-grpo-18073-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-18073-v1/tokenizer.json
rirv938-anthropic-grpo-18073-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-18073-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-18073-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.24it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.41it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.60it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 36.98it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:15, 21.23it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 25.85it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.87it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.10it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.72it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.62it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.32it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.25it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.89it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 21.94it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 29.00it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 28.36it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 28.02it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:08, 31.11it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 30.01it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.68it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 31.14it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.88it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.00it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 29.32it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 27.82it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.65it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.99it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.00it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.95it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.20it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.09it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.90it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.14it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.46it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 29.97it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.60it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 31.49it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 33.44it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.48it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 23.31it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 20.83it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:06, 28.20it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 28.18it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.93it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.23it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.76it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 29.33it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:05, 28.66it/s]
Loading 0:  61%|██████    | 222/363 [00:07<00:04, 30.74it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 20.71it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 20.48it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 27.10it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 26.44it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:04, 29.13it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:04, 27.95it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 30.38it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 28.21it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 22.99it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 20.61it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 27.18it/s]
Loading 0:  76%|███████▌  | 276/363 [00:10<00:03, 25.70it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.15it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.98it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.87it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.62it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 30.90it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 26.58it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.89it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 24.02it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.95it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 29.31it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.76it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.29it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.93it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.83it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.97it/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 [00:19<00:01,  4.97it/s]
                                                            
Job rirv938-anthropic-grpo-18073-v1-mkmlizer completed after 145.42s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-18073-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.14s
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-18073-v1
Waiting for inference service rirv938-anthropic-grpo-18073-v1 to be ready
Inference service rirv938-anthropic-grpo-18073-v1 ready after 150.6309051513672s
Pipeline stage MKMLDeployer completed in 151.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.491734027862549s
Received healthy response to inference request in 1.877366065979004s
Received healthy response to inference request in 1.7909722328186035s
Received healthy response to inference request in 1.553640604019165s
Received healthy response to inference request in 1.673722743988037s
5 requests
0 failed requests
5th percentile: 1.5776570320129395
10th percentile: 1.601673460006714
20th percentile: 1.6497063159942627
30th percentile: 1.6971726417541504
40th percentile: 1.744072437286377
50th percentile: 1.7909722328186035
60th percentile: 1.8255297660827636
70th percentile: 1.8600872993469237
80th percentile: 2.000239658355713
90th percentile: 2.2459868431091308
95th percentile: 2.3688604354858396
99th percentile: 2.467159309387207
mean time: 1.8774871349334716
Pipeline stage StressChecker completed in 10.97s
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 0.68s
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 0.68s
Shutdown handler de-registered
rirv938-anthropic-grpo-_18073_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 3180.22s
Shutdown handler de-registered
rirv938-anthropic-grpo-_18073_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_18073_v1 status is now torndown due to DeploymentManager action