rirv938-anthropic-grpo-_55195

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_55195_v1

model_name: rirv938-anthropic-grpo-_55195_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-18T15:18:10+00:00

num_battles: 7980

num_wins: 3989

celo_rating: 1284.9

family_friendly_score: 0.5536

family_friendly_standard_error: 0.00703032061857779

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp30_98ff_g2b15_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': 0.6361503073333498, 'latency_mean': 1.5718731033802031, 'latency_p50': 1.582861065864563, 'latency_p90': 1.7316836357116698}, {'batch_size': 3, 'throughput': 1.2131068493764323, 'latency_mean': 2.4680385065078734, 'latency_p50': 2.4845441579818726, 'latency_p90': 2.7272067308425902}, {'batch_size': 5, 'throughput': 1.516208680268884, 'latency_mean': 3.2827507281303405, 'latency_p50': 3.2558226585388184, 'latency_p90': 3.7088555335998534}, {'batch_size': 6, 'throughput': 1.588494594201978, 'latency_mean': 3.7513915407657623, 'latency_p50': 3.7630467414855957, 'latency_p90': 4.146803522109986}, {'batch_size': 8, 'throughput': 1.6689791998865717, 'latency_mean': 4.748505018949508, 'latency_p50': 4.782891750335693, 'latency_p90': 5.355007457733154}, {'batch_size': 10, 'throughput': 1.7072203080148043, 'latency_mean': 5.79930363535881, 'latency_p50': 5.832258701324463, 'latency_p90': 6.566723442077636}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_55195_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp30_98ff_g2b15_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.59

us_pacific_date: 2025-05-18

win_ratio: 0.49987468671679197

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>', 'You:', '\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-55195-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-55195-v1-mkmlizer to finish
rirv938-anthropic-grpo-55195-v1-mkmlizer: Downloaded to shared memory in 77.995s
rirv938-anthropic-grpo-55195-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdcfoewg7, device:0
rirv938-anthropic-grpo-55195-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-55195-v1-mkmlizer: quantized model in 41.806s
rirv938-anthropic-grpo-55195-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp30_98ff_g2b15_merged in 119.801s
rirv938-anthropic-grpo-55195-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-55195-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-55195-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-55195-v1
rirv938-anthropic-grpo-55195-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55195-v1/special_tokens_map.json
rirv938-anthropic-grpo-55195-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55195-v1/config.json
rirv938-anthropic-grpo-55195-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-55195-v1/tokenizer_config.json
rirv938-anthropic-grpo-55195-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-55195-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-55195-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.43it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.74it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.56it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:09, 34.43it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.77it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:14, 22.67it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.47it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 29.95it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.74it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.75it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.98it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.15it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.82it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 21.75it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 28.42it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 27.67it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:11, 25.82it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 30.38it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.02it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.21it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 29.43it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.71it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:12, 21.34it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.13it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 27.73it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.68it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.68it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.04it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.87it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 29.87it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.84it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.27it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.98it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 29.49it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 28.72it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 30.88it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.46it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 31.31it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.98it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 23.37it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.14it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:06, 26.22it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:06, 24.34it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.81it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.20it/s]
Loading 0:  58%|█████▊    | 209/363 [00:07<00:04, 31.40it/s]
Loading 0:  59%|█████▊    | 213/363 [00:07<00:05, 26.67it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:05, 28.89it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.08it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.84it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.66it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 28.83it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 27.92it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 30.08it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 28.71it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 30.68it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.16it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 23.86it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.34it/s]
Loading 0:  75%|███████▍  | 271/363 [00:09<00:03, 26.72it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:03, 24.60it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.97it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.26it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.36it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.67it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 29.28it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:01, 31.46it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 22.18it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.11it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 28.90it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 27.64it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 29.90it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 28.93it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.18it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.66it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.98it/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,  4.95it/s]
                                                            
Job rirv938-anthropic-grpo-55195-v1-mkmlizer completed after 144.72s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-55195-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.25s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-55195-v1
Waiting for inference service rirv938-anthropic-grpo-55195-v1 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service rirv938-anthropic-grpo-55195-v1 ready after 150.612065076828s
Pipeline stage MKMLDeployer completed in 151.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.081721782684326s
Received healthy response to inference request in 1.9028851985931396s
Received healthy response to inference request in 1.8442113399505615s
Received healthy response to inference request in 1.8358314037322998s
Received healthy response to inference request in 1.8295865058898926s
5 requests
0 failed requests
5th percentile: 1.830835485458374
10th percentile: 1.8320844650268555
20th percentile: 1.8345824241638184
30th percentile: 1.837507390975952
40th percentile: 1.8408593654632568
50th percentile: 1.8442113399505615
60th percentile: 1.8676808834075929
70th percentile: 1.891150426864624
80th percentile: 1.938652515411377
90th percentile: 2.0101871490478516
95th percentile: 2.045954465866089
99th percentile: 2.0745683193206785
mean time: 1.8988472461700439
Pipeline stage StressChecker completed in 10.92s
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 0.69s
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 1.02s
Shutdown handler de-registered
rirv938-anthropic-grpo-_55195_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 3076.76s
Shutdown handler de-registered
rirv938-anthropic-grpo-_55195_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_55195_v1 status is now torndown due to DeploymentManager action