rirv938-dotc-r2-grpo-20_14978

developer_uid: rirv938
submission_id: rirv938-dotc-r2-grpo-20_14978_v2
model_name: rirv938-dotc-r2-grpo-20_14978_v2
model_group: rirv938/dotc_r2_grpo_202
status: torndown
timestamp: 2025-10-06T16:58:25+00:00
num_battles: 5614
num_wins: 2864
celo_rating: 1293.78
family_friendly_score: 0.54
family_friendly_standard_error: 0.0070484040746824385
submission_type: basic
model_repo: rirv938/dotc_r2_grpo_20250929_cp312_sid_mn24b_v2preferwin1sy_merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.438822310264922, 'latency_mean': 2.278723212480545, 'latency_p50': 2.301952362060547, 'latency_p90': 2.5467185974121094}, {'batch_size': 3, 'throughput': 0.9303928412049978, 'latency_mean': 3.2155963838100434, 'latency_p50': 3.2059351205825806, 'latency_p90': 3.5682281494140624}, {'batch_size': 5, 'throughput': 1.2275858762093346, 'latency_mean': 4.052993091344834, 'latency_p50': 4.0609965324401855, 'latency_p90': 4.579316210746765}, {'batch_size': 6, 'throughput': 1.336133035297447, 'latency_mean': 4.455019609928131, 'latency_p50': 4.422531723976135, 'latency_p90': 5.010588884353638}, {'batch_size': 8, 'throughput': 1.4810083354581562, 'latency_mean': 5.34047455906868, 'latency_p50': 5.367164969444275, 'latency_p90': 6.050590968132019}, {'batch_size': 10, 'throughput': 1.598518959476093, 'latency_mean': 6.204715558290482, 'latency_p50': 6.220478177070618, 'latency_p90': 7.24149911403656}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: rirv938-dotc-r2-grpo-20_14978_v2
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: rirv938/dotc_r2_grpo_20250929_cp312_sid_mn24b_v2preferwin1sy_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.12
us_pacific_date: 2025-10-06
win_ratio: 0.5101531884574279
generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['###', '\n', '</s>', 'You:'], 'max_input_tokens': 1024, '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-dotc-r2-grpo-20-14978-v2-mkmlizer
Waiting for job on rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer to finish
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  Version: 0.30.2                                                    ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: Downloaded to shared memory in 98.993s
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: Checking if rirv938/dotc_r2_grpo_20250929_cp312_sid_mn24b_v2preferwin1sy_merged already exists in ChaiML
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6kua2nmf, device:0
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: quantized model in 50.235s
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: Processed model rirv938/dotc_r2_grpo_20250929_cp312_sid_mn24b_v2preferwin1sy_merged in 149.254s
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia/config.json
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia/tokenizer_config.json
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia/tokenizer.json
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: DEBUG retryable error: RequestError: send request failed
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: caused by: Put "https://object.ord1.coreweave.com/guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia/flywheel_model.1.safetensors?partNumber=140&uploadId=2~tJUGc9B0lP20BmePEjuGoZSqT5zb5-N": write tcp 10.0.10.201:36614->216.153.53.63:443: write: connection reset by peer
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:15, 23.32it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:18, 19.49it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:14, 24.89it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:22, 15.56it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:23, 15.06it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:17, 19.72it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:19, 17.27it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:13, 25.08it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:15, 20.85it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:17, 18.19it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:18, 17.75it/s]
Loading 0:  12%|█▏        | 43/363 [00:02<00:17, 18.08it/s]
Loading 0:  13%|█▎        | 48/363 [00:02<00:13, 24.05it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:14, 21.30it/s]
Loading 0:  15%|█▍        | 54/363 [00:02<00:19, 16.19it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:17, 17.84it/s]
Loading 0:  17%|█▋        | 61/363 [00:03<00:16, 18.18it/s]
Loading 0:  18%|█▊        | 66/363 [00:03<00:12, 24.05it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:13, 21.37it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:17, 16.28it/s]
Loading 0:  21%|██        | 76/363 [00:03<00:15, 17.98it/s]
Loading 0:  22%|██▏       | 79/363 [00:04<00:15, 18.50it/s]
Loading 0:  23%|██▎       | 84/363 [00:04<00:11, 24.05it/s]
Loading 0:  24%|██▍       | 87/363 [00:04<00:13, 20.84it/s]
Loading 0:  25%|██▍       | 90/363 [00:04<00:17, 15.90it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 24.38it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:10, 25.41it/s]
Loading 0:  29%|██▉       | 105/363 [00:05<00:13, 18.80it/s]
Loading 0:  30%|██▉       | 108/363 [00:05<00:16, 15.43it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:14, 17.15it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:14, 17.65it/s]
Loading 0:  33%|███▎      | 121/363 [00:06<00:09, 24.61it/s]
Loading 0:  34%|███▍      | 125/363 [00:06<00:12, 19.01it/s]
Loading 0:  35%|███▌      | 128/363 [00:06<00:11, 19.77it/s]
Loading 0:  36%|███▌      | 131/363 [00:06<00:14, 15.70it/s]
Loading 0:  38%|███▊      | 138/363 [00:06<00:09, 23.94it/s]
Loading 0:  39%|███▉      | 142/363 [00:07<00:10, 20.76it/s]
Loading 0:  40%|███▉      | 145/363 [00:07<00:11, 18.50it/s]
Loading 0:  41%|████      | 148/363 [00:07<00:11, 18.20it/s]
Loading 0:  42%|████▏     | 151/363 [00:07<00:11, 18.80it/s]
Loading 0:  43%|████▎     | 157/363 [00:07<00:07, 26.23it/s]
Loading 0:  44%|████▍     | 161/363 [00:08<00:10, 19.77it/s]
Loading 0:  45%|████▌     | 164/363 [00:08<00:09, 19.96it/s]
Loading 0:  46%|████▌     | 167/363 [00:08<00:12, 15.61it/s]
Loading 0:  48%|████▊     | 174/363 [00:08<00:07, 23.89it/s]
Loading 0:  49%|████▉     | 178/363 [00:09<00:08, 20.69it/s]
Loading 0:  50%|████▉     | 181/363 [00:09<00:09, 18.45it/s]
Loading 0:  51%|█████     | 184/363 [00:09<00:09, 18.04it/s]
Loading 0:  52%|█████▏    | 187/363 [00:09<00:09, 18.38it/s]
Loading 0:  53%|█████▎    | 193/363 [00:09<00:06, 25.57it/s]
Loading 0:  54%|█████▍    | 197/363 [00:10<00:08, 19.31it/s]
Loading 0:  55%|█████▌    | 200/363 [00:10<00:08, 19.73it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:08, 19.73it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:45,  1.39s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:58,  1.11s/it]
Loading 0:  57%|█████▋    | 207/363 [00:23<01:47,  1.45it/s]
Loading 0:  58%|█████▊    | 212/363 [00:24<01:03,  2.38it/s]
Loading 0:  59%|█████▉    | 215/363 [00:24<00:53,  2.78it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:41,  3.46it/s]
Loading 0:  61%|██████    | 220/363 [00:25<00:36,  3.94it/s]
Loading 0:  61%|██████    | 222/363 [00:25<00:30,  4.69it/s]
Loading 0:  63%|██████▎   | 228/363 [00:25<00:15,  8.52it/s]
Loading 0:  64%|██████▎   | 231/363 [00:25<00:13,  9.79it/s]
Loading 0:  64%|██████▍   | 234/363 [00:25<00:13,  9.82it/s]
Loading 0:  66%|██████▌   | 238/363 [00:26<00:10, 12.16it/s]
Loading 0:  66%|██████▋   | 241/363 [00:26<00:08, 13.67it/s]
Loading 0:  68%|██████▊   | 247/363 [00:26<00:05, 20.29it/s]
Loading 0:  69%|██████▉   | 251/363 [00:26<00:06, 16.97it/s]
Loading 0:  70%|██████▉   | 254/363 [00:26<00:06, 17.87it/s]
Loading 0:  71%|███████   | 257/363 [00:27<00:07, 14.70it/s]
Loading 0:  73%|███████▎  | 264/363 [00:27<00:04, 22.76it/s]
Loading 0:  74%|███████▍  | 268/363 [00:27<00:04, 20.09it/s]
Loading 0:  75%|███████▍  | 271/363 [00:27<00:05, 18.11it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:04, 17.89it/s]
Loading 0:  76%|███████▋  | 277/363 [00:28<00:04, 18.33it/s]
Loading 0:  78%|███████▊  | 282/363 [00:28<00:03, 23.99it/s]
Loading 0:  79%|███████▊  | 285/363 [00:28<00:03, 21.77it/s]
Loading 0:  79%|███████▉  | 288/363 [00:28<00:04, 16.60it/s]
Loading 0:  80%|████████  | 292/363 [00:28<00:03, 18.22it/s]
Loading 0:  81%|████████▏ | 295/363 [00:28<00:03, 18.79it/s]
Loading 0:  83%|████████▎ | 301/363 [00:29<00:02, 26.27it/s]
Loading 0:  84%|████████▍ | 305/363 [00:29<00:02, 19.62it/s]
Loading 0:  85%|████████▍ | 308/363 [00:29<00:02, 19.92it/s]
Loading 0:  86%|████████▌ | 311/363 [00:29<00:03, 15.62it/s]
Loading 0:  88%|████████▊ | 318/363 [00:29<00:01, 23.90it/s]
Loading 0:  89%|████████▊ | 322/363 [00:30<00:01, 20.72it/s]
Loading 0:  90%|████████▉ | 325/363 [00:30<00:02, 18.43it/s]
Loading 0:  90%|█████████ | 328/363 [00:30<00:01, 18.13it/s]
Loading 0:  91%|█████████ | 331/363 [00:30<00:01, 18.52it/s]
Loading 0:  93%|█████████▎| 337/363 [00:30<00:01, 25.85it/s]
Loading 0:  94%|█████████▍| 341/363 [00:31<00:01, 19.56it/s]
Loading 0:  95%|█████████▍| 344/363 [00:31<00:00, 19.95it/s]
Loading 0:  96%|█████████▌| 347/363 [00:31<00:01, 15.73it/s]
Loading 0:  98%|█████████▊| 354/363 [00:31<00:00, 24.00it/s]
Loading 0:  99%|█████████▊| 358/363 [00:32<00:00, 15.42it/s]
Loading 0:  99%|█████████▉| 361/363 [00:32<00:00, 13.67it/s]
                                                            
ERROR "cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia/flywheel_model.1.safetensors": MultipartUpload: upload multipart failed upload id: 2~tJUGc9B0lP20BmePEjuGoZSqT5zb5-N caused by: SignatureDoesNotMatch:  status code: 403, request id: tx0000074d4ec84ba962d87-0068e3f629-121eb5841c-default, host id:
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia/flywheel_model.0.safetensors
Job rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer completed after 257.42s with status: failed
Stopping job with name rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer
Waiting for job on rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer to finish
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  Version: 0.30.2                                                    ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: Downloaded to shared memory in 93.572s
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: Checking if rirv938/dotc_r2_grpo_20250929_cp312_sid_mn24b_v2preferwin1sy_merged already exists in ChaiML
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnqa29d2g, device:0
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: quantized model in 50.657s
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: Processed model rirv938/dotc_r2_grpo_20250929_cp312_sid_mn24b_v2preferwin1sy_merged in 144.256s
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia/config.json
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia/special_tokens_map.json
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia/tokenizer_config.json
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia/tokenizer.json
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia/flywheel_model.1.safetensors
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-14978-v2/nvidia/flywheel_model.0.safetensors
rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:15, 23.84it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:17, 19.83it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:13, 25.29it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:22, 15.24it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:23, 14.67it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:18, 18.86it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:20, 16.21it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:14, 23.61it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:16, 20.01it/s]
Loading 0:  10%|▉         | 36/363 [00:02<00:21, 15.01it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:19, 16.54it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:20, 15.74it/s]
Loading 0:  13%|█▎        | 47/363 [00:02<00:14, 21.75it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:15, 20.20it/s]
Loading 0:  15%|█▍        | 54/363 [00:03<00:20, 15.38it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:18, 16.90it/s]
Loading 0:  17%|█▋        | 61/363 [00:03<00:17, 17.35it/s]
Loading 0:  18%|█▊        | 66/363 [00:03<00:12, 23.02it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:14, 20.01it/s]
Loading 0:  20%|█▉        | 72/363 [00:04<00:18, 15.32it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:17, 16.84it/s]
Loading 0:  22%|██▏       | 79/363 [00:04<00:16, 17.37it/s]
Loading 0:  23%|██▎       | 84/363 [00:04<00:12, 23.05it/s]
Loading 0:  24%|██▍       | 87/363 [00:04<00:13, 19.82it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:17, 15.40it/s]
Loading 0:  27%|██▋       | 97/363 [00:05<00:11, 23.87it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:10, 24.84it/s]
Loading 0:  29%|██▉       | 105/363 [00:05<00:14, 18.16it/s]
Loading 0:  30%|██▉       | 108/363 [00:05<00:16, 15.00it/s]
Loading 0:  31%|███       | 112/363 [00:06<00:15, 16.59it/s]
Loading 0:  32%|███▏      | 115/363 [00:06<00:14, 17.19it/s]
Loading 0:  33%|███▎      | 121/363 [00:06<00:10, 24.02it/s]
Loading 0:  34%|███▍      | 125/363 [00:06<00:12, 18.32it/s]
Loading 0:  35%|███▌      | 128/363 [00:06<00:12, 18.91it/s]
Loading 0:  36%|███▌      | 131/363 [00:07<00:15, 15.09it/s]
Loading 0:  38%|███▊      | 138/363 [00:07<00:09, 23.11it/s]
Loading 0:  39%|███▉      | 142/363 [00:07<00:11, 19.92it/s]
Loading 0:  40%|███▉      | 145/363 [00:07<00:12, 17.93it/s]
Loading 0:  41%|████      | 148/363 [00:08<00:12, 17.55it/s]
Loading 0:  42%|████▏     | 151/363 [00:08<00:11, 17.89it/s]
Loading 0:  43%|████▎     | 156/363 [00:08<00:08, 23.62it/s]
Loading 0:  44%|████▍     | 159/363 [00:08<00:09, 20.93it/s]
Loading 0:  45%|████▍     | 162/363 [00:08<00:12, 16.07it/s]
Loading 0:  46%|████▌     | 166/363 [00:08<00:11, 17.69it/s]
Loading 0:  47%|████▋     | 169/363 [00:09<00:10, 18.15it/s]
Loading 0:  48%|████▊     | 175/363 [00:09<00:07, 25.44it/s]
Loading 0:  49%|████▉     | 179/363 [00:09<00:09, 18.87it/s]
Loading 0:  50%|█████     | 182/363 [00:09<00:09, 19.30it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:11, 15.19it/s]
Loading 0:  53%|█████▎    | 192/363 [00:10<00:07, 23.29it/s]
Loading 0:  54%|█████▍    | 196/363 [00:10<00:08, 20.25it/s]
Loading 0:  55%|█████▍    | 199/363 [00:10<00:09, 18.10it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:09, 18.10it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:18,  1.22s/it]
Loading 0:  56%|█████▌    | 203/363 [00:24<02:42,  1.02s/it]
Loading 0:  57%|█████▋    | 207/363 [00:24<01:42,  1.53it/s]
Loading 0:  58%|█████▊    | 211/363 [00:24<01:06,  2.28it/s]
Loading 0:  59%|█████▉    | 214/363 [00:24<00:51,  2.90it/s]
Loading 0:  60%|█████▉    | 217/363 [00:25<00:39,  3.70it/s]
Loading 0:  61%|██████    | 220/363 [00:25<00:30,  4.76it/s]
Loading 0:  61%|██████    | 222/363 [00:25<00:25,  5.55it/s]
Loading 0:  63%|██████▎   | 228/363 [00:25<00:13,  9.72it/s]
Loading 0:  64%|██████▎   | 231/363 [00:25<00:12, 10.83it/s]
Loading 0:  64%|██████▍   | 234/363 [00:25<00:12, 10.54it/s]
Loading 0:  66%|██████▌   | 238/363 [00:26<00:09, 12.83it/s]
Loading 0:  66%|██████▋   | 241/363 [00:26<00:08, 13.76it/s]
Loading 0:  68%|██████▊   | 247/363 [00:26<00:05, 20.31it/s]
Loading 0:  69%|██████▉   | 251/363 [00:26<00:06, 16.74it/s]
Loading 0:  70%|██████▉   | 254/363 [00:26<00:06, 17.62it/s]
Loading 0:  71%|███████   | 257/363 [00:27<00:07, 14.50it/s]
Loading 0:  73%|███████▎  | 264/363 [00:27<00:04, 22.44it/s]
Loading 0:  74%|███████▍  | 268/363 [00:27<00:04, 19.89it/s]
Loading 0:  75%|███████▍  | 271/363 [00:27<00:05, 17.86it/s]
Loading 0:  75%|███████▌  | 274/363 [00:28<00:05, 17.68it/s]
Loading 0:  76%|███████▋  | 277/363 [00:28<00:04, 18.16it/s]
Loading 0:  78%|███████▊  | 283/363 [00:28<00:03, 25.33it/s]
Loading 0:  79%|███████▉  | 287/363 [00:28<00:03, 19.22it/s]
Loading 0:  80%|███████▉  | 290/363 [00:28<00:03, 19.32it/s]
Loading 0:  81%|████████  | 293/363 [00:29<00:04, 15.30it/s]
Loading 0:  83%|████████▎ | 300/363 [00:29<00:02, 23.42it/s]
Loading 0:  84%|████████▎ | 304/363 [00:29<00:02, 20.59it/s]
Loading 0:  85%|████████▍ | 307/363 [00:29<00:03, 18.32it/s]
Loading 0:  85%|████████▌ | 310/363 [00:29<00:02, 17.84it/s]
Loading 0:  86%|████████▌ | 313/363 [00:30<00:02, 18.34it/s]
Loading 0:  88%|████████▊ | 319/363 [00:30<00:01, 25.55it/s]
Loading 0:  89%|████████▉ | 323/363 [00:30<00:02, 19.20it/s]
Loading 0:  90%|████████▉ | 326/363 [00:30<00:01, 19.59it/s]
Loading 0:  91%|█████████ | 329/363 [00:30<00:02, 15.51it/s]
Loading 0:  93%|█████████▎| 336/363 [00:31<00:01, 23.70it/s]
Loading 0:  94%|█████████▎| 340/363 [00:31<00:01, 20.66it/s]
Loading 0:  94%|█████████▍| 343/363 [00:31<00:01, 18.36it/s]
Loading 0:  95%|█████████▌| 346/363 [00:31<00:00, 18.03it/s]
Loading 0:  96%|█████████▌| 349/363 [00:31<00:00, 18.39it/s]
Loading 0:  98%|█████████▊| 355/363 [00:31<00:00, 25.69it/s]
Loading 0:  99%|█████████▉| 359/363 [00:32<00:00, 14.46it/s]
Loading 0: 100%|█████████▉| 362/363 [00:32<00:00, 14.09it/s]
                                                            
Job rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer completed after 216.96s with status: succeeded
Stopping job with name rirv938-dotc-r2-grpo-20-14978-v2-mkmlizer
Pipeline stage MKMLizer completed in 475.98s
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-dotc-r2-grpo-20-14978-v2
Waiting for inference service rirv938-dotc-r2-grpo-20-14978-v2 to be ready
Failed to get response for submission chaiml-mn24b-v2preferwi_3050_v33: HTTPConnectionPool(host='chaiml-mn24b-v2preferwi-3050-v33-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.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 0x74ba28355a10>, 'Connection to chaiml-mn24b-v2preferwi-3050-v33-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com timed out. (connect timeout=12.0)'))
Inference service rirv938-dotc-r2-grpo-20-14978-v2 ready after 70.44617128372192s
Pipeline stage MKMLDeployer completed in 71.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4363629817962646s
Received healthy response to inference request in 2.239138603210449s
Received healthy response to inference request in 3.190816640853882s
Received healthy response to inference request in 2.1251766681671143s
Received healthy response to inference request in 2.3438405990600586s
5 requests
0 failed requests
5th percentile: 2.147969055175781
10th percentile: 2.1707614421844483
20th percentile: 2.2163462162017824
30th percentile: 2.260079002380371
40th percentile: 2.3019598007202147
50th percentile: 2.3438405990600586
60th percentile: 2.380849552154541
70th percentile: 2.4178585052490233
80th percentile: 2.5872537136077884
90th percentile: 2.889035177230835
95th percentile: 3.039925909042358
99th percentile: 3.160638494491577
mean time: 2.467067098617554
Pipeline stage StressChecker completed in 14.10s
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 0.76s
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 0.68s
Shutdown handler de-registered
rirv938-dotc-r2-grpo-20_14978_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-dotc-r2-grpo-20-14978-v2-profiler
Waiting for inference service rirv938-dotc-r2-grpo-20-14978-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 3008.64s
Shutdown handler de-registered
rirv938-dotc-r2-grpo-20_14978_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-dotc-r2-grpo-20_14978_v2 status is now torndown due to DeploymentManager action