rirv938-anthropic-grpo-_44019

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_44019_v4

model_name: rirv938-anthropic-grpo-_44019_v4

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-13T17:51:49+00:00

num_battles: 5852

num_wins: 3090

celo_rating: 1305.59

family_friendly_score: 0.5506

family_friendly_standard_error: 0.007034765667739047

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp148_95ff_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': 0.6497271408080305, 'latency_mean': 1.5390158426761626, 'latency_p50': 1.52471125125885, 'latency_p90': 1.7034898281097413}, {'batch_size': 3, 'throughput': 1.2425889654581883, 'latency_mean': 2.4068057417869566, 'latency_p50': 2.3913891315460205, 'latency_p90': 2.6717100858688356}, {'batch_size': 5, 'throughput': 1.5215731692624614, 'latency_mean': 3.2650531792640685, 'latency_p50': 3.260945439338684, 'latency_p90': 3.6543216943740844}, {'batch_size': 6, 'throughput': 1.6112970241983118, 'latency_mean': 3.693673177957535, 'latency_p50': 3.690214514732361, 'latency_p90': 4.175116634368896}, {'batch_size': 8, 'throughput': 1.7037619314352956, 'latency_mean': 4.66882527589798, 'latency_p50': 4.658705472946167, 'latency_p90': 5.239307713508606}, {'batch_size': 10, 'throughput': 1.7349536830310193, 'latency_mean': 5.7005655026435855, 'latency_p50': 5.716810822486877, 'latency_p90': 6.393330478668213}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_44019_v4

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp148_95ff_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.63

us_pacific_date: 2025-05-13

win_ratio: 0.5280246069719754

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-44019-v4-mkmlizer
Waiting for job on rirv938-anthropic-grpo-44019-v4-mkmlizer to finish
rirv938-anthropic-grpo-44019-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-44019-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-44019-v4-mkmlizer: Downloaded to shared memory in 79.272s
rirv938-anthropic-grpo-44019-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpngk6e3dx, device:0
rirv938-anthropic-grpo-44019-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-44019-v4-mkmlizer: quantized model in 41.741s
rirv938-anthropic-grpo-44019-v4-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp148_95ff_merged in 121.013s
rirv938-anthropic-grpo-44019-v4-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-44019-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-44019-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v4
rirv938-anthropic-grpo-44019-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v4/config.json
rirv938-anthropic-grpo-44019-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v4/special_tokens_map.json
rirv938-anthropic-grpo-44019-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v4/tokenizer_config.json
rirv938-anthropic-grpo-44019-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v4/tokenizer.json
rirv938-anthropic-grpo-44019-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-44019-v4/flywheel_model.0.safetensors
rirv938-anthropic-grpo-44019-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.81it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.65it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.10it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 33.82it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.44it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:14, 22.44it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 25.86it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 27.79it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 29.19it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.01it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.18it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.93it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.67it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.82it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.05it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 28.58it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 28.10it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:11, 25.62it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 29.96it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 28.62it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 30.89it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 29.51it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.53it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:12, 21.14it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.11it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 27.10it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.45it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.59it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.00it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.64it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 29.57it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.85it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.31it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.13it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 29.80it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 28.65it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.56it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.33it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.83it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.01it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 23.53it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.04it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 27.79it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 27.53it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 29.93it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 28.28it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 30.65it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 29.48it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 29.72it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.56it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.04it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.97it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 29.46it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 28.69it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 31.14it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 29.74it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.54it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.50it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 25.08it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.88it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 28.66it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.90it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.28it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.30it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.06it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.72it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 29.81it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 25.60it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.99it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.94it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 29.67it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 28.84it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 30.80it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 29.55it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.81it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 30.16it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.97it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.66it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.86it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  4.98it/s]
                                                            
Job rirv938-anthropic-grpo-44019-v4-mkmlizer completed after 146.74s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-44019-v4-mkmlizer
Pipeline stage MKMLizer completed in 147.28s
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-44019-v4
Waiting for inference service rirv938-anthropic-grpo-44019-v4 to be ready
Inference service rirv938-anthropic-grpo-44019-v4 ready after 120.5073356628418s
Pipeline stage MKMLDeployer completed in 121.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1424734592437744s
Received healthy response to inference request in 2.1428003311157227s
Received healthy response to inference request in 1.7411284446716309s
Received healthy response to inference request in 1.735884189605713s
Received healthy response to inference request in 1.6822943687438965s
5 requests
0 failed requests
5th percentile: 1.6930123329162599
10th percentile: 1.703730297088623
20th percentile: 1.7251662254333495
30th percentile: 1.7369330406188965
40th percentile: 1.7390307426452636
50th percentile: 1.7411284446716309
60th percentile: 1.9016664505004883
70th percentile: 2.062204456329346
80th percentile: 2.142538833618164
90th percentile: 2.1426695823669433
95th percentile: 2.142734956741333
99th percentile: 2.1427872562408448
mean time: 1.8889161586761474
Pipeline stage StressChecker completed in 10.68s
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 0.88s
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 0.74s
Shutdown handler de-registered
rirv938-anthropic-grpo-_44019_v4 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 2660.81s
Shutdown handler de-registered
rirv938-anthropic-grpo-_44019_v4 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_44019_v4 status is now torndown due to DeploymentManager action