developer_uid: rirv938
submission_id: rirv938-96p-4ff-rirv938_33201_v1
model_name: rirv938-96p-4ff-rirv938_33201_v1
model_group: rirv938/96p_4ff_rirv938_
status: torndown
timestamp: 2025-04-03T16:59:46+00:00
num_battles: 7643
num_wins: 4248
celo_rating: 1342.23
family_friendly_score: 0.5294
family_friendly_standard_error: 0.0070588333313657435
submission_type: basic
model_repo: rirv938/96p_4ff_rirv938_20k_100p_0ff_ri_19485_v1_cp1500_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': 0.3853577983474407, 'latency_mean': 2.594925972223282, 'latency_p50': 2.603460669517517, 'latency_p90': 2.8706281423568725}, {'batch_size': 3, 'throughput': 0.8013288401148843, 'latency_mean': 3.729756704568863, 'latency_p50': 3.7016942501068115, 'latency_p90': 4.154864120483398}, {'batch_size': 5, 'throughput': 1.0555598279197271, 'latency_mean': 4.708389703035355, 'latency_p50': 4.720183372497559, 'latency_p90': 5.271678233146668}, {'batch_size': 6, 'throughput': 1.136113701277502, 'latency_mean': 5.245771694183349, 'latency_p50': 5.238930702209473, 'latency_p90': 5.84315595626831}, {'batch_size': 10, 'throughput': 1.3062416667825845, 'latency_mean': 7.567482386827469, 'latency_p50': 7.6111977100372314, 'latency_p90': 8.498528981208802}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-96p-4ff-rirv938_33201_v1
is_internal_developer: True
language_model: rirv938/96p_4ff_rirv938_20k_100p_0ff_ri_19485_v1_cp1500_v3
model_size: 24B
ranking_group: single
throughput_3p7s: 0.8
us_pacific_date: 2025-04-03
win_ratio: 0.5558026952767238
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': ['###', 'You:', '\n', '</s>'], '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 rirv938-96p-4ff-rirv938-33201-v1-mkmlizer
Waiting for job on rirv938-96p-4ff-rirv938-33201-v1-mkmlizer to finish
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ _____ __ __ ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ /___/ ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ belonging to: ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ║ ║
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v5: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v5-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_v5: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Connection pool is full, discarding connection: %s. Connection pool size: %s
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: Downloaded to shared memory in 186.747s
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkaj7474y, device:0
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v5: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: quantized model in 64.856s
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: Processed model rirv938/96p_4ff_rirv938_20k_100p_0ff_ri_19485_v1_cp1500_v3 in 251.604s
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-96p-4ff-rirv938-33201-v1
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-96p-4ff-rirv938-33201-v1/config.json
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-96p-4ff-rirv938-33201-v1/special_tokens_map.json
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-96p-4ff-rirv938-33201-v1/tokenizer_config.json
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-96p-4ff-rirv938-33201-v1/tokenizer.json
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-96p-4ff-rirv938-33201-v1/flywheel_model.1.safetensors
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-96p-4ff-rirv938-33201-v1/flywheel_model.0.safetensors
rirv938-96p-4ff-rirv938-33201-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:00<00:12, 29.70it/s] Loading 0: 2%|▏ | 6/363 [00:00<00:26, 13.67it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:17, 20.68it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:24, 14.19it/s] Loading 0: 4%|▍ | 16/363 [00:01<00:27, 12.63it/s] Loading 0: 5%|▌ | 19/363 [00:01<00:22, 15.45it/s] Loading 0: 6%|▌ | 22/363 [00:01<00:22, 14.92it/s] Loading 0: 7%|▋ | 24/363 [00:01<00:24, 14.01it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:18, 18.35it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:14, 22.24it/s] Loading 0: 10%|▉ | 35/363 [00:02<00:21, 14.99it/s] Loading 0: 10%|█ | 38/363 [00:02<00:20, 15.52it/s] Loading 0: 11%|█ | 40/363 [00:02<00:23, 13.63it/s] Loading 0: 12%|█▏ | 42/363 [00:02<00:24, 13.06it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:18, 17.24it/s] Loading 0: 14%|█▍ | 50/363 [00:03<00:14, 20.97it/s] Loading 0: 15%|█▍ | 53/363 [00:03<00:21, 14.52it/s] Loading 0: 15%|█▌ | 55/363 [00:03<00:22, 13.39it/s] Loading 0: 16%|█▌ | 57/363 [00:03<00:21, 14.11it/s] Loading 0: 16%|█▋ | 59/363 [00:03<00:26, 11.65it/s] Loading 0: 18%|█▊ | 64/363 [00:04<00:17, 17.58it/s] Loading 0: 19%|█▊ | 68/363 [00:04<00:14, 20.99it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:19, 14.78it/s] Loading 0: 20%|██ | 74/363 [00:04<00:19, 15.14it/s] Loading 0: 21%|██ | 76/363 [00:04<00:21, 13.34it/s] Loading 0: 21%|██▏ | 78/363 [00:05<00:22, 12.77it/s] Loading 0: 23%|██▎ | 82/363 [00:05<00:16, 17.17it/s] Loading 0: 24%|██▎ | 86/363 [00:05<00:12, 21.33it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:18, 14.71it/s] Loading 0: 25%|██▌ | 92/363 [00:05<00:17, 15.06it/s] Loading 0: 26%|██▌ | 95/363 [00:06<00:15, 17.55it/s] Loading 0: 27%|██▋ | 99/363 [00:06<00:12, 21.01it/s] Loading 0: 28%|██▊ | 102/363 [00:06<00:13, 18.67it/s] Loading 0: 29%|██▉ | 105/363 [00:06<00:18, 14.03it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:19, 12.92it/s] Loading 0: 30%|███ | 109/363 [00:07<00:20, 12.15it/s] Loading 0: 31%|███ | 111/363 [00:07<00:19, 13.12it/s] Loading 0: 31%|███ | 113/363 [00:07<00:23, 10.69it/s] Loading 0: 33%|███▎ | 118/363 [00:07<00:14, 16.65it/s] Loading 0: 34%|███▎ | 122/363 [00:07<00:11, 20.55it/s] Loading 0: 34%|███▍ | 125/363 [00:08<00:16, 14.35it/s] Loading 0: 35%|███▌ | 128/363 [00:08<00:15, 15.10it/s] Loading 0: 36%|███▌ | 130/363 [00:08<00:17, 13.40it/s] Loading 0: 36%|███▋ | 132/363 [00:08<00:17, 12.84it/s] Loading 0: 37%|███▋ | 136/363 [00:08<00:13, 17.14it/s] Loading 0: 39%|███▊ | 140/363 [00:08<00:10, 21.01it/s] Loading 0: 39%|███▉ | 143/363 [00:09<00:14, 14.72it/s] Loading 0: 40%|███▉ | 145/363 [00:09<00:15, 13.90it/s] Loading 0: 40%|████ | 147/363 [00:09<00:14, 14.45it/s] Loading 0: 41%|████ | 149/363 [00:09<00:18, 11.77it/s] Loading 0: 42%|████▏ | 154/363 [00:09<00:11, 18.07it/s] Loading 0: 44%|████▎ | 158/363 [00:10<00:09, 22.00it/s] Loading 0: 44%|████▍ | 161/363 [00:10<00:13, 15.50it/s] Loading 0: 45%|████▌ | 164/363 [00:10<00:12, 16.10it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:15, 12.35it/s] Loading 0: 47%|████▋ | 172/363 [00:11<00:10, 17.50it/s] Loading 0: 48%|████▊ | 176/363 [00:11<00:08, 21.10it/s] Loading 0: 49%|████▉ | 179/363 [00:11<00:12, 15.31it/s] Loading 0: 50%|█████ | 182/363 [00:11<00:11, 15.83it/s] Loading 0: 51%|█████ | 185/363 [00:12<00:14, 12.35it/s] Loading 0: 52%|█████▏ | 190/363 [00:12<00:10, 17.29it/s] Loading 0: 53%|█████▎ | 194/363 [00:12<00:08, 20.69it/s] Loading 0: 54%|█████▍ | 197/363 [00:12<00:11, 15.02it/s] Loading 0: 55%|█████▌ | 200/363 [00:12<00:10, 15.59it/s] Loading 0: 56%|█████▌ | 203/363 [00:28<03:50, 1.44s/it] Loading 0: 57%|█████▋ | 207/363 [00:28<02:29, 1.04it/s] Loading 0: 58%|█████▊ | 210/363 [00:28<01:49, 1.40it/s] Loading 0: 59%|█████▊ | 213/363 [00:28<01:21, 1.85it/s] Loading 0: 60%|█████▉ | 216/363 [00:29<01:02, 2.36it/s] Loading 0: 60%|██████ | 219/363 [00:29<00:44, 3.21it/s] Loading 0: 61%|██████ | 222/363 [00:29<00:34, 4.05it/s] Loading 0: 62%|██████▏ | 226/363 [00:29<00:23, 5.94it/s] Loading 0: 63%|██████▎ | 230/363 [00:29<00:16, 8.29it/s] Loading 0: 64%|██████▍ | 233/363 [00:29<00:15, 8.34it/s] Loading 0: 65%|██████▌ | 236/363 [00:30<00:13, 9.71it/s] Loading 0: 66%|██████▌ | 239/363 [00:30<00:13, 9.10it/s] Loading 0: 67%|██████▋ | 244/363 [00:30<00:08, 13.35it/s] Loading 0: 68%|██████▊ | 248/363 [00:30<00:06, 16.61it/s] Loading 0: 69%|██████▉ | 251/363 [00:31<00:08, 13.37it/s] Loading 0: 70%|██████▉ | 254/363 [00:31<00:07, 14.19it/s] Loading 0: 71%|███████ | 257/363 [00:31<00:09, 11.49it/s] Loading 0: 72%|███████▏ | 262/363 [00:31<00:06, 16.20it/s] Loading 0: 73%|███████▎ | 266/363 [00:31<00:04, 19.69it/s] Loading 0: 74%|███████▍ | 269/363 [00:32<00:06, 14.41it/s] Loading 0: 75%|███████▍ | 272/363 [00:32<00:06, 15.12it/s] Loading 0: 76%|███████▌ | 275/363 [00:32<00:07, 12.12it/s] Loading 0: 77%|███████▋ | 280/363 [00:32<00:04, 16.88it/s] Loading 0: 78%|███████▊ | 284/363 [00:33<00:03, 19.95it/s] Loading 0: 79%|███████▉ | 287/363 [00:33<00:05, 14.88it/s] Loading 0: 80%|███████▉ | 290/363 [00:33<00:04, 15.26it/s] Loading 0: 81%|████████ | 293/363 [00:33<00:05, 12.15it/s] Loading 0: 82%|████████▏ | 298/363 [00:34<00:03, 16.87it/s] Loading 0: 83%|████████▎ | 302/363 [00:34<00:03, 20.03it/s] Loading 0: 84%|████████▍ | 305/363 [00:34<00:03, 14.89it/s] Loading 0: 85%|████████▍ | 308/363 [00:34<00:03, 15.52it/s] Loading 0: 86%|████████▌ | 311/363 [00:35<00:04, 12.19it/s] Loading 0: 87%|████████▋ | 316/363 [00:35<00:02, 16.59it/s] Loading 0: 88%|████████▊ | 320/363 [00:35<00:02, 19.12it/s] Loading 0: 89%|████████▉ | 323/363 [00:35<00:02, 14.47it/s] Loading 0: 90%|████████▉ | 325/363 [00:35<00:02, 13.88it/s] Loading 0: 90%|█████████ | 327/363 [00:36<00:02, 14.67it/s] Loading 0: 91%|█████████ | 329/363 [00:36<00:02, 12.20it/s] Loading 0: 92%|█████████▏| 334/363 [00:36<00:01, 18.53it/s] Loading 0: 93%|█████████▎| 338/363 [00:36<00:01, 22.52it/s] Loading 0: 94%|█████████▍| 341/363 [00:36<00:01, 15.85it/s] Loading 0: 95%|█████████▍| 344/363 [00:37<00:01, 16.27it/s] Loading 0: 96%|█████████▌| 347/363 [00:37<00:01, 12.57it/s] Loading 0: 97%|█████████▋| 352/363 [00:37<00:00, 17.97it/s] Loading 0: 98%|█████████▊| 356/363 [00:37<00:00, 21.53it/s] Loading 0: 99%|█████████▉| 360/363 [00:44<00:01, 1.70it/s] Loading 0: 100%|██████████| 363/363 [00:44<00:00, 2.18it/s]
Job rirv938-96p-4ff-rirv938-33201-v1-mkmlizer completed after 289.0s with status: succeeded
Stopping job with name rirv938-96p-4ff-rirv938-33201-v1-mkmlizer
Pipeline stage MKMLizer completed in 289.61s
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 rirv938-96p-4ff-rirv938-33201-v1
Waiting for inference service rirv938-96p-4ff-rirv938-33201-v1 to be ready
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v5: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v5-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_v5: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Inference service rirv938-96p-4ff-rirv938-33201-v1 ready after 210.69054555892944s
Pipeline stage MKMLDeployer completed in 211.23s
run pipeline stage %s
Running pipeline stage StressChecker
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
{"detail":"HTTPConnectionPool(host='rirv938-96p-4ff-rirv938-33201-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7941d03e2d90>, 'Connection to rirv938-96p-4ff-rirv938-33201-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))"}
Received unhealthy response to inference request!
Received healthy response to inference request in 3.1155128479003906s
Received healthy response to inference request in 2.8003463745117188s
Received healthy response to inference request in 2.6304008960723877s
Received healthy response to inference request in 2.5214452743530273s
5 requests
1 failed requests
5th percentile: 2.5432363986968993
10th percentile: 2.5650275230407713
20th percentile: 2.6086097717285157
30th percentile: 2.664389991760254
40th percentile: 2.7323681831359865
50th percentile: 2.8003463745117188
60th percentile: 2.9264129638671874
70th percentile: 3.052479553222656
80th percentile: 4.949348926544191
90th percentile: 8.617021083831787
95th percentile: 10.450857162475584
99th percentile: 11.917926025390624
mean time: 4.670479726791382
%s, retrying in %s seconds...
Received healthy response to inference request in 2.6007015705108643s
Received healthy response to inference request in 2.62660813331604s
Retrying (%r) after connection broken by '%r': %s
Received healthy response to inference request in 2.5832767486572266s
Received healthy response to inference request in 2.715613603591919s
Received healthy response to inference request in 2.73362398147583s
5 requests
0 failed requests
5th percentile: 2.586761713027954
10th percentile: 2.5902466773986816
20th percentile: 2.5972166061401367
30th percentile: 2.6058828830718994
40th percentile: 2.6162455081939697
50th percentile: 2.62660813331604
60th percentile: 2.6622103214263917
70th percentile: 2.6978125095367433
80th percentile: 2.719215679168701
90th percentile: 2.7264198303222655
95th percentile: 2.730021905899048
99th percentile: 2.7329035663604735
mean time: 2.651964807510376
Pipeline stage StressChecker completed in 39.66s
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 0.65s
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 0.70s
Shutdown handler de-registered
rirv938-96p-4ff-rirv938_33201_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4894.13s
Shutdown handler de-registered
rirv938-96p-4ff-rirv938_33201_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-96p-4ff-rirv938_33201_v1 status is now torndown due to DeploymentManager action