rirv938-100p-0ff-rirv93_49616

developer_uid: rirv938

submission_id: rirv938-100p-0ff-rirv93_49616_v1

model_name: rirv938-100p-0ff-rirv93_49616_v1

model_group: rirv938/100p_0ff_rirv938

status: torndown

timestamp: 2025-04-02T21:06:10+00:00

num_battles: 5830

num_wins: 2871

celo_rating: 1293.19

family_friendly_score: 0.5618000000000001

family_friendly_standard_error: 0.007016847725296595

submission_type: basic

model_repo: rirv938/100p_0ff_rirv938_mistral_24b_bon_82623_v1_cp156_v3

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3889072570012894, 'latency_mean': 2.5712449455261233, 'latency_p50': 2.5580583810806274, 'latency_p90': 2.8932274103164675}, {'batch_size': 3, 'throughput': 0.7827243117401101, 'latency_mean': 3.8184724712371825, 'latency_p50': 3.8320460319519043, 'latency_p90': 4.180351948738098}, {'batch_size': 5, 'throughput': 1.0373899961377337, 'latency_mean': 4.78428964138031, 'latency_p50': 4.788525581359863, 'latency_p90': 5.309921288490296}, {'batch_size': 6, 'throughput': 1.1228937501467517, 'latency_mean': 5.331363359689712, 'latency_p50': 5.32173478603363, 'latency_p90': 5.9989495277404785}, {'batch_size': 10, 'throughput': 1.2831933394842912, 'latency_mean': 7.732183672189713, 'latency_p50': 7.76558780670166, 'latency_p90': 8.757097434997558}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-100p-0ff-rirv93_49616_v1

is_internal_developer: True

language_model: rirv938/100p_0ff_rirv938_mistral_24b_bon_82623_v1_cp156_v3

model_size: 24B

ranking_group: single

throughput_3p7s: 0.76

us_pacific_date: 2025-04-02

win_ratio: 0.49245283018867925

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['</s>', '###', 'You:', '\n'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{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 rirv938-100p-0ff-rirv93-49616-v1-mkmlizer
Waiting for job on rirv938-100p-0ff-rirv93-49616-v1-mkmlizer to finish
Failed to get response for submission chaiml-gemma-exp3-dpo-s_66157_v1: HTTPConnectionPool(host='chaiml-gemma-exp3-dpo-s-66157-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v1: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v2: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v2: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: Downloaded to shared memory in 175.105s
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfbhwxt4x, device:0
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v1: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: quantized model in 64.981s
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: Processed model rirv938/100p_0ff_rirv938_mistral_24b_bon_82623_v1_cp156_v3 in 240.087s
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-49616-v1
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-49616-v1/config.json
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-49616-v1/special_tokens_map.json
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-49616-v1/tokenizer_config.json
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-49616-v1/tokenizer.json
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-49616-v1/flywheel_model.0.safetensors
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-49616-v1/flywheel_model.1.safetensors
rirv938-100p-0ff-rirv93-49616-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.82it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:25, 13.90it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:16, 20.93it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:25, 13.58it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:31, 11.13it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:21, 15.72it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:22, 15.23it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:23, 14.32it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.46it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.75it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.51it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:24, 13.54it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:22, 14.34it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:27, 11.60it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.35it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.76it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:22, 13.95it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:23, 13.14it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:22, 13.90it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:26, 11.48it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 17.00it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.06it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:20, 13.96it/s]
Loading 0:  20%|██        | 73/363 [00:04<00:22, 13.08it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:20, 13.93it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:24, 11.63it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.36it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.84it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 14.46it/s]
Loading 0:  25%|██▌       | 92/363 [00:06<00:18, 14.89it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.11it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 20.43it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 18.81it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:18, 14.23it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:19, 13.10it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:19, 12.76it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.63it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 11.27it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.25it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.84it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.74it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:16, 14.00it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:15, 14.88it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:19, 12.06it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.96it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.25it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 15.07it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:14, 15.35it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:15, 13.86it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:16, 13.31it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:11, 17.43it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 20.89it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 14.69it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 13.98it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:13, 14.92it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:16, 11.98it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:10, 17.90it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 21.14it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.98it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.68it/s]
Loading 0:  51%|█████     | 184/363 [00:12<00:13, 13.28it/s]
Loading 0:  51%|█████     | 186/363 [00:12<00:13, 12.92it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 16.92it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.39it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.69it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:11, 13.86it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<04:42,  1.74s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:35,  1.35s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:04,  1.25it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:26,  1.76it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:03,  2.35it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:51,  2.85it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:41,  3.48it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:32,  4.42it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:28,  4.95it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:15,  8.65it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:11, 11.64it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:12, 10.38it/s]
Loading 0:  65%|██████▍   | 235/363 [00:30<00:12, 10.46it/s]
Loading 0:  65%|██████▌   | 237/363 [00:30<00:10, 11.60it/s]
Loading 0:  66%|██████▌   | 239/363 [00:30<00:12,  9.99it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:07, 15.33it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 18.61it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:08, 13.69it/s]
Loading 0:  70%|██████▉   | 253/363 [00:31<00:08, 13.24it/s]
Loading 0:  70%|███████   | 255/363 [00:31<00:07, 14.06it/s]
Loading 0:  71%|███████   | 257/363 [00:31<00:09, 10.96it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:06, 16.70it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 20.32it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:06, 14.74it/s]
Loading 0:  75%|███████▍  | 272/363 [00:32<00:05, 15.18it/s]
Loading 0:  75%|███████▌  | 274/363 [00:32<00:06, 13.69it/s]
Loading 0:  76%|███████▌  | 276/363 [00:32<00:06, 13.14it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.43it/s]
Loading 0:  78%|███████▊  | 284/363 [00:33<00:03, 21.01it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 14.75it/s]
Loading 0:  80%|███████▉  | 289/363 [00:33<00:05, 13.97it/s]
Loading 0:  80%|████████  | 291/363 [00:33<00:04, 14.88it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 12.07it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:03, 18.07it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:02, 21.56it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:03, 14.61it/s]
Loading 0:  85%|████████▍ | 308/363 [00:34<00:03, 15.22it/s]
Loading 0:  85%|████████▌ | 310/363 [00:34<00:03, 13.73it/s]
Loading 0:  86%|████████▌ | 312/363 [00:35<00:03, 13.17it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 17.17it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:02, 20.59it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:02, 14.52it/s]
Loading 0:  90%|████████▉ | 325/363 [00:35<00:02, 13.76it/s]
Loading 0:  90%|█████████ | 327/363 [00:35<00:02, 14.79it/s]
Loading 0:  91%|█████████ | 329/363 [00:36<00:02, 11.37it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 16.95it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 20.19it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:01, 14.51it/s]
Loading 0:  94%|█████████▍| 343/363 [00:37<00:01, 13.80it/s]
Loading 0:  95%|█████████▌| 345/363 [00:37<00:01, 14.79it/s]
Loading 0:  96%|█████████▌| 347/363 [00:37<00:01, 11.77it/s]
Loading 0:  97%|█████████▋| 352/363 [00:37<00:00, 17.58it/s]
Loading 0:  98%|█████████▊| 356/363 [00:37<00:00, 20.81it/s]
Loading 0:  99%|█████████▉| 359/363 [00:44<00:02,  1.46it/s]
Loading 0:  99%|█████████▉| 361/363 [00:45<00:01,  1.75it/s]
                                                            
Job rirv938-100p-0ff-rirv93-49616-v1-mkmlizer completed after 277.26s with status: succeeded
Stopping job with name rirv938-100p-0ff-rirv93-49616-v1-mkmlizer
Pipeline stage MKMLizer completed in 277.81s
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 rirv938-100p-0ff-rirv93-49616-v1
Waiting for inference service rirv938-100p-0ff-rirv93-49616-v1 to be ready
Inference service rirv938-100p-0ff-rirv93-49616-v1 ready after 110.75253558158875s
Pipeline stage MKMLDeployer completed in 111.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.33703875541687s
Received healthy response to inference request in 2.5129880905151367s
Received healthy response to inference request in 2.502784013748169s
Received healthy response to inference request in 2.698215961456299s
Received healthy response to inference request in 2.307706356048584s
5 requests
0 failed requests
5th percentile: 2.346721887588501
10th percentile: 2.385737419128418
20th percentile: 2.463768482208252
30th percentile: 2.5048248291015627
40th percentile: 2.5089064598083497
50th percentile: 2.5129880905151367
60th percentile: 2.5870792388916017
70th percentile: 2.6611703872680663
80th percentile: 2.825980520248413
90th percentile: 3.0815096378326414
95th percentile: 3.2092741966247558
99th percentile: 3.3114858436584473
mean time: 2.6717466354370116
Pipeline stage StressChecker completed in 14.80s
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 0.96s
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 0.66s
Shutdown handler de-registered
rirv938-100p-0ff-rirv93_49616_v1 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-100p-0ff-rirv93-49616-v1-profiler
Waiting for inference service rirv938-100p-0ff-rirv93-49616-v1-profiler to be ready
Inference service rirv938-100p-0ff-rirv93-49616-v1-profiler ready after 110.4205732345581s
Pipeline stage MKMLProfilerDeployer completed in 110.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-100p-0ff-rirdc25841ab6239d06f08b164c4a2ad703-deplozn6mk:/code/chaiverse_profiler_1743628531 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-100p-0ff-rirdc25841ab6239d06f08b164c4a2ad703-deplozn6mk --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1743628531 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 768 --output_tokens 64 --summary /code/chaiverse_profiler_1743628531/summary.json'
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 2909.35s
Shutdown handler de-registered
rirv938-100p-0ff-rirv93_49616_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-100p-0ff-rirv93_49616_v1 status is now torndown due to DeploymentManager action