rirv938-anthropic-grpo-4_3092

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-4_3092_v2

model_name: rirv938-anthropic-grpo-4_3092_v2

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-04-29T18:35:59+00:00

num_battles: 6230

num_wins: 3210

celo_rating: 1314.85

family_friendly_score: 0.5726

family_friendly_standard_error: 0.006996130930735931

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp888_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': 0.6425025826570941, 'latency_mean': 1.5563409638404846, 'latency_p50': 1.5536447763442993, 'latency_p90': 1.710384225845337}, {'batch_size': 3, 'throughput': 1.238271945395185, 'latency_mean': 2.4205042469501494, 'latency_p50': 2.428689479827881, 'latency_p90': 2.644639992713928}, {'batch_size': 5, 'throughput': 1.5212314084308634, 'latency_mean': 3.2681142032146453, 'latency_p50': 3.2300753593444824, 'latency_p90': 3.6538970947265623}, {'batch_size': 6, 'throughput': 1.6210172150236974, 'latency_mean': 3.680446535348892, 'latency_p50': 3.668575167655945, 'latency_p90': 4.0652930498123165}, {'batch_size': 8, 'throughput': 1.7071890730527968, 'latency_mean': 4.646947693824768, 'latency_p50': 4.689037799835205, 'latency_p90': 5.205236172676086}, {'batch_size': 10, 'throughput': 1.763069176546512, 'latency_mean': 5.61801740527153, 'latency_p50': 5.595381855964661, 'latency_p90': 6.412307262420654}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-4_3092_v2

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp888_95ff_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.63

us_pacific_date: 2025-04-29

win_ratio: 0.5152487961476726

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['You:', '<|eot_id|>', '<|end_of_text|>', '\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': '### Response:\n{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-4-3092-v2-mkmlizer
Waiting for job on rirv938-anthropic-grpo-4-3092-v2-mkmlizer to finish
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: Downloaded to shared memory in 81.477s
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3n04kkk4, device:0
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: quantized model in 43.352s
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp888_95ff_merged in 124.830s
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v2
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v2/config.json
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v2/special_tokens_map.json
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v2/tokenizer_config.json
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v2/tokenizer.json
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v2/flywheel_model.0.safetensors
rirv938-anthropic-grpo-4-3092-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.29it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.22it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 22.99it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 28.82it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:16, 21.06it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 18.91it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.85it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 26.37it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.78it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 28.23it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:12, 24.65it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 28.97it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.36it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.75it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 24.12it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 24.03it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 22.60it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.98it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.23it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 28.62it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 25.18it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:08, 29.43it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.54it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 24.06it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 22.47it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.85it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 23.77it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 27.82it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.56it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 28.50it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.36it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 20.76it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 20.24it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.56it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 22.68it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 26.95it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:08, 24.20it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 28.29it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 24.38it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 28.38it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 19.08it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.33it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 22.05it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 26.36it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 23.90it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 28.17it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 24.89it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:05, 29.05it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 29.81it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 20.80it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.15it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 24.63it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 22.85it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 27.13it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 24.38it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 28.66it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 25.24it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 29.39it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 19.44it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:03, 23.70it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:03, 22.14it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 26.58it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 24.25it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 28.79it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 25.51it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 28.52it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 28.71it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 20.83it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 20.61it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 25.21it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 23.55it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 28.17it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 25.10it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:00, 29.65it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:00, 26.05it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 30.49it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  1.99it/s]
Loading 0:  96%|█████████▋| 350/363 [00:20<00:05,  2.51it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.19it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.35it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.45it/s]
                                                            
Job rirv938-anthropic-grpo-4-3092-v2-mkmlizer completed after 167.07s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-4-3092-v2-mkmlizer
Pipeline stage MKMLizer completed in 167.58s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-4-3092-v2
Waiting for inference service rirv938-anthropic-grpo-4-3092-v2 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service rirv938-anthropic-grpo-4-3092-v2 ready after 140.83152532577515s
Pipeline stage MKMLDeployer completed in 141.30s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.1972815990448s
{"detail":"('http://alexdaoud-trainer-bajem-28556-v2-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{\"error\":\"ValueError : Out of range float values are not JSON compliant\"}')"}
Received unhealthy response to inference request!
Received healthy response to inference request in 1.651460886001587s
Received healthy response to inference request in 2.0585289001464844s
5 requests
2 failed requests
5th percentile: 1.7069694995880127
10th percentile: 1.7624781131744385
20th percentile: 1.87349534034729
30th percentile: 1.9549089431762696
40th percentile: 2.0067189216613768
50th percentile: 2.0585289001464844
60th percentile: 2.1140299797058106
70th percentile: 2.169531059265137
80th percentile: 5.832429933547977
90th percentile: 13.102726602554323
95th percentile: 16.73787493705749
99th percentile: 19.645993604660035
mean time: 5.641859722137451
%s, retrying in %s seconds...
Received healthy response to inference request in 1.5674397945404053s
Received healthy response to inference request in 1.594949722290039s
Received healthy response to inference request in 1.7210381031036377s
Received healthy response to inference request in 1.5163941383361816s
Received healthy response to inference request in 1.6308355331420898s
5 requests
0 failed requests
5th percentile: 1.5266032695770264
10th percentile: 1.5368124008178712
20th percentile: 1.5572306632995605
30th percentile: 1.572941780090332
40th percentile: 1.5839457511901855
50th percentile: 1.594949722290039
60th percentile: 1.6093040466308595
70th percentile: 1.6236583709716796
80th percentile: 1.6488760471343995
90th percentile: 1.6849570751190186
95th percentile: 1.702997589111328
99th percentile: 1.7174300003051757
mean time: 1.6061314582824706
Pipeline stage StressChecker completed in 38.95s
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 0.72s
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 0.71s
Shutdown handler de-registered
rirv938-anthropic-grpo-4_3092_v2 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 2792.85s
Shutdown handler de-registered
rirv938-anthropic-grpo-4_3092_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-4_3092_v2 status is now torndown due to DeploymentManager action