rirv938-anthropic-grpo-_22923

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_22923_v2

model_name: rirv938-anthropic-grpo-_22923_v2

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-15T15:51:33+00:00

num_battles: 7114

num_wins: 3587

celo_rating: 1287.55

family_friendly_score: 0.5638000000000001

family_friendly_standard_error: 0.00701326685646568

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': 0.6428818624437936, 'latency_mean': 1.5554297113418578, 'latency_p50': 1.5621310472488403, 'latency_p90': 1.7232528448104858}, {'batch_size': 3, 'throughput': 1.2273941877657135, 'latency_mean': 2.4376298463344575, 'latency_p50': 2.4440670013427734, 'latency_p90': 2.695742440223694}, {'batch_size': 5, 'throughput': 1.5089867580557075, 'latency_mean': 3.301384823322296, 'latency_p50': 3.3005592823028564, 'latency_p90': 3.762298202514648}, {'batch_size': 6, 'throughput': 1.6016599478961342, 'latency_mean': 3.729607754945755, 'latency_p50': 3.719910502433777, 'latency_p90': 4.200700283050537}, {'batch_size': 8, 'throughput': 1.6699778924728685, 'latency_mean': 4.759310820102692, 'latency_p50': 4.785937190055847, 'latency_p90': 5.3572450399398805}, {'batch_size': 10, 'throughput': 1.7296316973991055, 'latency_mean': 5.744275373220444, 'latency_p50': 5.754645466804504, 'latency_p90': 6.394128370285034}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_22923_v2

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp444_95ff_20ww2_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.6

us_pacific_date: 2025-05-15

win_ratio: 0.5042170368287883

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', '</s>', '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-22923-v2-mkmlizer
Waiting for job on rirv938-anthropic-grpo-22923-v2-mkmlizer to finish
rirv938-anthropic-grpo-22923-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-22923-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-22923-v2-mkmlizer: Downloaded to shared memory in 81.445s
rirv938-anthropic-grpo-22923-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_w4exnt1, device:0
rirv938-anthropic-grpo-22923-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-22923-v2-mkmlizer: quantized model in 41.793s
rirv938-anthropic-grpo-22923-v2-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp444_95ff_20ww2_merged in 123.238s
rirv938-anthropic-grpo-22923-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-22923-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-22923-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-22923-v2
rirv938-anthropic-grpo-22923-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-22923-v2/config.json
rirv938-anthropic-grpo-22923-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-22923-v2/special_tokens_map.json
rirv938-anthropic-grpo-22923-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-22923-v2/tokenizer_config.json
rirv938-anthropic-grpo-22923-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-22923-v2/tokenizer.json
rirv938-anthropic-grpo-22923-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-22923-v2/flywheel_model.0.safetensors
rirv938-anthropic-grpo-22923-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.46it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.39it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.85it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 30.35it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 21.54it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 19.63it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.18it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 29.52it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.03it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.42it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:11, 26.74it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:11, 27.60it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 30.06it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.43it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 27.09it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 27.25it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 27.13it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 30.03it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 28.87it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.26it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 29.73it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 23.82it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:11, 21.60it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.50it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 27.75it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 30.31it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.21it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.27it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.40it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.66it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.58it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.35it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.25it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 28.47it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.50it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:06, 30.48it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 26.98it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 33.20it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.71it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 22.85it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 20.83it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:06, 25.55it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 23.57it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:05, 27.94it/s]
Loading 0:  56%|█████▌    | 203/363 [00:07<00:06, 25.20it/s]
Loading 0:  57%|█████▋    | 208/363 [00:07<00:05, 29.84it/s]
Loading 0:  58%|█████▊    | 212/363 [00:07<00:05, 25.73it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:04, 30.04it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 31.36it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 22.41it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 21.84it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 26.69it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 24.57it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 29.02it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 26.29it/s]
Loading 0:  70%|██████▉   | 253/363 [00:09<00:03, 31.13it/s]
Loading 0:  71%|███████   | 257/363 [00:09<00:03, 27.58it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 25.60it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 20.98it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 27.42it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 26.80it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 28.94it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.09it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.15it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 28.98it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 29.10it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 24.76it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.84it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.23it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 29.94it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 28.93it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 31.09it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 29.64it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.49it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.67it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  2.00it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.69it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.88it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  5.01it/s]
Loading 0: 100%|█████████▉| 362/363 [00:20<00:00,  7.11it/s]
                                                            
Job rirv938-anthropic-grpo-22923-v2-mkmlizer completed after 145.1s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-22923-v2-mkmlizer
Pipeline stage MKMLizer completed in 145.66s
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-v2
Waiting for inference service rirv938-anthropic-grpo-22923-v2 to be ready
Inference service rirv938-anthropic-grpo-22923-v2 ready after 130.69042706489563s
Pipeline stage MKMLDeployer completed in 131.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1347289085388184s
Received healthy response to inference request in 1.997385025024414s
Received healthy response to inference request in 1.848353624343872s
Received healthy response to inference request in 1.5942301750183105s
Received healthy response to inference request in 1.5895566940307617s
5 requests
0 failed requests
5th percentile: 1.5904913902282716
10th percentile: 1.5914260864257812
20th percentile: 1.5932954788208007
30th percentile: 1.645054864883423
40th percentile: 1.7467042446136474
50th percentile: 1.848353624343872
60th percentile: 1.907966184616089
70th percentile: 1.9675787448883055
80th percentile: 2.024853801727295
90th percentile: 2.0797913551330565
95th percentile: 2.1072601318359374
99th percentile: 2.129235153198242
mean time: 1.8328508853912353
Pipeline stage StressChecker completed in 10.54s
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 0.72s
Shutdown handler de-registered
rirv938-anthropic-grpo-_22923_v2 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-22923-v2-profiler
Waiting for inference service rirv938-anthropic-grpo-22923-v2-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 2745.81s
Shutdown handler de-registered
rirv938-anthropic-grpo-_22923_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_22923_v2 status is now torndown due to DeploymentManager action