chaiml-mn12b-syn1-tune9

developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn12b-syn1-tune9_v1
model_name: chaiml-mn12b-syn1-tune9_v1
model_group: ChaiML/mn12b_syn1_tune9
status: torndown
timestamp: 2025-09-04T20:57:45+00:00
num_battles: 5714
num_wins: 2780
celo_rating: 1246.16
family_friendly_score: 0.5662
family_friendly_standard_error: 0.007008816733229655
submission_type: basic
model_repo: ChaiML/mn12b_syn1_tune9
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.9281584594479396, 'latency_mean': 1.0772916090488434, 'latency_p50': 1.0821754932403564, 'latency_p90': 1.2014571666717528}, {'batch_size': 5, 'throughput': 2.441319912731758, 'latency_mean': 2.0399845802783965, 'latency_p50': 2.048259139060974, 'latency_p90': 2.3039601325988768}, {'batch_size': 10, 'throughput': 3.0517494297174657, 'latency_mean': 3.2449963593482973, 'latency_p50': 3.24304461479187, 'latency_p90': 3.679018974304199}, {'batch_size': 15, 'throughput': 3.233395841507541, 'latency_mean': 4.574936780929566, 'latency_p50': 4.624311685562134, 'latency_p90': 5.2003641605377195}, {'batch_size': 20, 'throughput': 3.284689516278459, 'latency_mean': 5.9863213241100315, 'latency_p50': 6.009531021118164, 'latency_p90': 6.935902118682861}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn12b-syn1-tune9_v1
is_internal_developer: False
language_model: ChaiML/mn12b_syn1_tune9
model_size: 13B
ranking_group: single
throughput_3p7s: 3.17
us_pacific_date: 2025-09-04
win_ratio: 0.4865243262163108
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': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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 chaiml-mn12b-syn1-tune9-v1-mkmlizer
Waiting for job on chaiml-mn12b-syn1-tune9-v1-mkmlizer to finish
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║                                                                     ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║                                                                     ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║                                                                     ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║                                                                     ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ║                                                                     ║
chaiml-mn12b-syn1-tune9-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn12b-syn1-tune9-v1-mkmlizer: Downloaded to shared memory in 36.284s
chaiml-mn12b-syn1-tune9-v1-mkmlizer: Checking if ChaiML/mn12b_syn1_tune9 already exists in ChaiML
chaiml-mn12b-syn1-tune9-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpi84b28id, device:0
chaiml-mn12b-syn1-tune9-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-nis-sft-24b-osmo_64694_v1: HTTPConnectionPool(host='chaiml-nis-sft-24b-osmo-64694-v1-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
HTTP Request: %s %s "%s %d %s"
chaiml-mn12b-syn1-tune9-v1-mkmlizer: quantized model in 147.463s
chaiml-mn12b-syn1-tune9-v1-mkmlizer: Processed model ChaiML/mn12b_syn1_tune9 in 183.748s
chaiml-mn12b-syn1-tune9-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn12b-syn1-tune9-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn12b-syn1-tune9-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn12b-syn1-tune9-v1/nvidia
chaiml-mn12b-syn1-tune9-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn12b-syn1-tune9-v1/nvidia/config.json
chaiml-mn12b-syn1-tune9-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn12b-syn1-tune9-v1/nvidia/special_tokens_map.json
chaiml-mn12b-syn1-tune9-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn12b-syn1-tune9-v1/nvidia/tokenizer_config.json
chaiml-mn12b-syn1-tune9-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mn12b-syn1-tune9-v1/nvidia/tokenizer.json
chaiml-mn12b-syn1-tune9-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn12b-syn1-tune9-v1/nvidia/flywheel_model.0.safetensors
chaiml-mn12b-syn1-tune9-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<01:45,  3.40it/s]
Loading 0:   1%|          | 4/363 [00:01<02:54,  2.06it/s]
Loading 0:   1%|▏         | 5/363 [00:02<03:49,  1.56it/s]
Loading 0:   2%|▏         | 8/363 [00:03<01:58,  2.98it/s]
Loading 0:   2%|▏         | 9/363 [00:03<01:54,  3.09it/s]
Loading 0:   3%|▎         | 10/363 [00:03<01:38,  3.58it/s]
Loading 0:   3%|▎         | 12/363 [00:04<02:00,  2.91it/s]
Loading 0:   4%|▎         | 13/363 [00:05<02:41,  2.16it/s]
Loading 0:   4%|▍         | 14/363 [00:06<03:23,  1.72it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:57,  2.95it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:51,  3.08it/s]
Loading 0:   5%|▌         | 19/363 [00:06<01:38,  3.51it/s]
Loading 0:   6%|▌         | 21/363 [00:07<01:58,  2.88it/s]
Loading 0:   6%|▌         | 22/363 [00:08<02:36,  2.18it/s]
Loading 0:   6%|▋         | 23/363 [00:09<03:16,  1.73it/s]
Loading 0:   7%|▋         | 26/363 [00:09<01:54,  2.95it/s]
Loading 0:   7%|▋         | 27/363 [00:10<01:48,  3.10it/s]
Loading 0:   8%|▊         | 28/363 [00:10<01:33,  3.59it/s]
Loading 0:   8%|▊         | 30/363 [00:11<01:53,  2.94it/s]
Loading 0:   9%|▊         | 31/363 [00:12<02:31,  2.20it/s]
Loading 0:   9%|▉         | 32/363 [00:13<03:11,  1.73it/s]
Loading 0:  10%|▉         | 35/363 [00:13<01:51,  2.93it/s]
Loading 0:  10%|▉         | 36/363 [00:13<01:46,  3.06it/s]
Loading 0:  10%|█         | 37/363 [00:13<01:32,  3.53it/s]
Loading 0:  11%|█         | 39/363 [00:14<01:51,  2.91it/s]
Loading 0:  11%|█         | 40/363 [00:15<02:27,  2.19it/s]
Loading 0:  11%|█▏        | 41/363 [00:16<03:04,  1.75it/s]
Loading 0:  12%|█▏        | 44/363 [00:16<01:47,  2.97it/s]
Loading 0:  12%|█▏        | 45/363 [00:17<01:41,  3.12it/s]
Loading 0:  13%|█▎        | 46/363 [00:17<01:28,  3.58it/s]
Loading 0:  13%|█▎        | 48/363 [00:18<01:47,  2.93it/s]
Loading 0:  13%|█▎        | 49/363 [00:18<02:23,  2.19it/s]
Loading 0:  14%|█▍        | 50/363 [00:19<02:59,  1.75it/s]
Loading 0:  15%|█▍        | 53/363 [00:20<01:44,  2.95it/s]
Loading 0:  15%|█▍        | 54/363 [00:20<01:39,  3.11it/s]
Loading 0:  15%|█▌        | 55/363 [00:20<01:26,  3.55it/s]
Loading 0:  15%|█▌        | 56/363 [00:21<02:09,  2.37it/s]
Loading 0:  16%|█▌        | 58/363 [00:21<01:35,  3.19it/s]
Loading 0:  16%|█▋        | 59/363 [00:22<01:31,  3.33it/s]
Loading 0:  17%|█▋        | 60/363 [00:22<01:17,  3.90it/s]
Loading 0:  17%|█▋        | 61/363 [00:22<01:07,  4.46it/s]
Loading 0:  17%|█▋        | 62/363 [00:23<02:01,  2.49it/s]
Loading 0:  17%|█▋        | 63/363 [00:24<02:40,  1.87it/s]
Loading 0:  18%|█▊        | 64/363 [00:25<03:16,  1.52it/s]
Loading 0:  18%|█▊        | 67/363 [00:25<01:45,  2.82it/s]
Loading 0:  19%|█▊        | 68/363 [00:25<01:39,  2.97it/s]
Loading 0:  19%|█▉        | 69/363 [00:25<01:25,  3.44it/s]
Loading 0:  20%|█▉        | 71/363 [00:26<01:42,  2.85it/s]
Loading 0:  20%|█▉        | 72/363 [00:27<02:15,  2.14it/s]
Loading 0:  20%|██        | 73/363 [00:28<02:48,  1.72it/s]
Loading 0:  21%|██        | 76/363 [00:28<01:37,  2.95it/s]
Loading 0:  21%|██        | 77/363 [00:28<01:32,  3.11it/s]
Loading 0:  21%|██▏       | 78/363 [00:29<01:19,  3.59it/s]
Loading 0:  22%|██▏       | 80/363 [00:30<01:36,  2.93it/s]
Loading 0:  22%|██▏       | 81/363 [00:30<02:08,  2.19it/s]
Loading 0:  23%|██▎       | 82/363 [00:31<02:41,  1.74it/s]
Loading 0:  23%|██▎       | 85/363 [00:32<01:34,  2.95it/s]
Loading 0:  24%|██▎       | 86/363 [00:32<01:29,  3.11it/s]
Loading 0:  24%|██▍       | 87/363 [00:32<01:16,  3.59it/s]
Loading 0:  25%|██▍       | 89/363 [00:33<01:33,  2.94it/s]
Loading 0:  25%|██▍       | 90/363 [00:34<02:04,  2.20it/s]
Loading 0:  25%|██▌       | 91/363 [00:35<02:35,  1.75it/s]
Loading 0:  26%|██▌       | 94/363 [00:35<01:30,  2.97it/s]
Loading 0:  26%|██▌       | 95/363 [00:35<01:25,  3.12it/s]
Loading 0:  26%|██▋       | 96/363 [00:35<01:14,  3.59it/s]
Loading 0:  27%|██▋       | 98/363 [00:36<01:30,  2.94it/s]
Loading 0:  27%|██▋       | 99/363 [00:37<02:00,  2.20it/s]
Loading 0:  28%|██▊       | 100/363 [00:38<02:29,  1.76it/s]
Loading 0:  28%|██▊       | 103/363 [00:38<01:27,  2.98it/s]
Loading 0:  29%|██▊       | 104/363 [00:39<01:22,  3.13it/s]
Loading 0:  29%|██▉       | 105/363 [00:39<01:11,  3.60it/s]
Loading 0:  29%|██▉       | 106/363 [00:40<01:48,  2.38it/s]
Loading 0:  30%|██▉       | 108/363 [00:40<01:20,  3.19it/s]
Loading 0:  30%|███       | 109/363 [00:40<01:16,  3.34it/s]
Loading 0:  30%|███       | 110/363 [00:40<01:05,  3.84it/s]
Loading 0:  31%|███       | 112/363 [00:41<01:23,  2.99it/s]
Loading 0:  31%|███       | 113/363 [00:42<01:57,  2.13it/s]
Loading 0:  32%|███▏      | 116/363 [00:43<01:34,  2.61it/s]
Loading 0:  32%|███▏      | 117/363 [00:44<01:56,  2.10it/s]
Loading 0:  33%|███▎      | 118/363 [00:45<02:20,  1.74it/s]
Loading 0:  33%|███▎      | 121/363 [00:45<01:24,  2.86it/s]
Loading 0:  34%|███▎      | 122/363 [00:45<01:19,  3.03it/s]
Loading 0:  34%|███▍      | 123/363 [00:46<01:08,  3.48it/s]
Loading 0:  34%|███▍      | 125/363 [00:46<01:21,  2.90it/s]
Loading 0:  35%|███▍      | 126/363 [00:47<01:47,  2.20it/s]
Loading 0:  35%|███▍      | 127/363 [00:48<02:13,  1.76it/s]
Loading 0:  36%|███▌      | 130/363 [00:49<01:18,  2.97it/s]
Loading 0:  36%|███▌      | 131/363 [00:49<01:14,  3.12it/s]
Loading 0:  36%|███▋      | 132/363 [00:49<01:04,  3.61it/s]
Loading 0:  37%|███▋      | 134/363 [00:50<01:18,  2.94it/s]
Loading 0:  37%|███▋      | 135/363 [00:51<01:43,  2.20it/s]
Loading 0:  37%|███▋      | 136/363 [00:52<02:09,  1.76it/s]
Loading 0:  38%|███▊      | 139/363 [00:52<01:15,  2.97it/s]
Loading 0:  39%|███▊      | 140/363 [00:52<01:11,  3.12it/s]
Loading 0:  39%|███▉      | 141/363 [00:52<01:02,  3.57it/s]
Loading 0:  39%|███▉      | 142/363 [00:52<00:53,  4.11it/s]
Loading 0:  39%|███▉      | 143/363 [00:53<01:29,  2.47it/s]
Loading 0:  40%|███▉      | 144/363 [00:54<01:59,  1.83it/s]
Loading 0:  40%|████      | 147/363 [00:55<01:29,  2.43it/s]
Loading 0:  41%|████      | 148/363 [00:56<01:48,  1.98it/s]
Loading 0:  41%|████      | 149/363 [00:57<02:09,  1.65it/s]
Loading 0:  42%|████▏     | 152/363 [00:57<01:15,  2.79it/s]
Loading 0:  42%|████▏     | 153/363 [00:58<01:11,  2.96it/s]
Loading 0:  42%|████▏     | 154/363 [00:58<01:01,  3.43it/s]
Loading 0:  43%|████▎     | 156/363 [00:59<01:12,  2.87it/s]
Loading 0:  43%|████▎     | 157/363 [00:59<01:35,  2.16it/s]
Loading 0:  44%|████▎     | 158/363 [01:00<01:57,  1.74it/s]
Loading 0:  44%|████▍     | 161/363 [01:01<01:08,  2.95it/s]
Loading 0:  45%|████▍     | 162/363 [01:01<01:04,  3.11it/s]
Loading 0:  45%|████▍     | 163/363 [01:01<00:55,  3.59it/s]
Loading 0:  45%|████▌     | 165/363 [01:02<01:07,  2.94it/s]
Loading 0:  46%|████▌     | 166/363 [01:03<01:29,  2.20it/s]
Loading 0:  46%|████▌     | 167/363 [01:04<01:51,  1.76it/s]
Loading 0:  47%|████▋     | 170/363 [01:04<01:04,  2.97it/s]
Loading 0:  47%|████▋     | 171/363 [01:04<01:01,  3.13it/s]
Loading 0:  47%|████▋     | 172/363 [01:04<00:53,  3.60it/s]
Loading 0:  48%|████▊     | 174/363 [01:05<01:04,  2.95it/s]
Loading 0:  48%|████▊     | 175/363 [01:06<01:25,  2.21it/s]
Loading 0:  48%|████▊     | 176/363 [01:07<01:46,  1.76it/s]
Loading 0:  49%|████▉     | 179/363 [01:07<01:01,  2.98it/s]
Loading 0:  50%|████▉     | 180/363 [01:08<00:58,  3.13it/s]
Loading 0:  50%|████▉     | 181/363 [01:08<00:50,  3.61it/s]
Loading 0:  50%|█████     | 183/363 [01:09<01:01,  2.95it/s]
Loading 0:  51%|█████     | 184/363 [01:10<01:21,  2.21it/s]
Loading 0:  51%|█████     | 185/363 [01:11<01:40,  1.77it/s]
Loading 0:  52%|█████▏    | 188/363 [01:11<00:58,  2.99it/s]
Loading 0:  52%|█████▏    | 189/363 [01:11<00:55,  3.15it/s]
Loading 0:  52%|█████▏    | 190/363 [01:11<00:47,  3.63it/s]
Loading 0:  53%|█████▎    | 192/363 [01:12<00:57,  2.96it/s]
Loading 0:  53%|█████▎    | 193/363 [01:13<01:16,  2.22it/s]
Loading 0:  53%|█████▎    | 194/363 [01:14<01:35,  1.77it/s]
Loading 0:  54%|█████▍    | 197/363 [01:14<00:55,  2.99it/s]
Loading 0:  55%|█████▍    | 198/363 [01:14<00:52,  3.14it/s]
Loading 0:  55%|█████▍    | 199/363 [01:15<00:45,  3.62it/s]
Loading 0:  55%|█████▌    | 201/363 [01:15<00:54,  2.96it/s]
Loading 0:  56%|█████▌    | 202/363 [01:16<01:12,  2.22it/s]
Loading 0:  56%|█████▌    | 203/363 [01:17<01:30,  1.77it/s]
Loading 0:  57%|█████▋    | 206/363 [01:18<00:52,  3.00it/s]
Loading 0:  57%|█████▋    | 207/363 [01:18<00:49,  3.16it/s]
Loading 0:  57%|█████▋    | 208/363 [01:18<00:42,  3.63it/s]
Loading 0:  58%|█████▊    | 210/363 [01:19<00:51,  2.97it/s]
Loading 0:  58%|█████▊    | 211/363 [01:20<01:08,  2.21it/s]
Loading 0:  58%|█████▊    | 212/363 [01:21<01:25,  1.76it/s]
Loading 0:  59%|█████▉    | 215/363 [01:21<00:49,  2.98it/s]
Loading 0:  60%|█████▉    | 216/363 [01:21<00:46,  3.13it/s]
Loading 0:  60%|█████▉    | 217/363 [01:21<00:40,  3.60it/s]
Loading 0:  60%|██████    | 218/363 [01:22<01:00,  2.39it/s]
Loading 0:  61%|██████    | 220/363 [01:23<00:44,  3.21it/s]
Loading 0:  61%|██████    | 221/363 [01:23<00:42,  3.35it/s]
Loading 0:  61%|██████    | 222/363 [01:23<00:36,  3.91it/s]
Loading 0:  61%|██████▏   | 223/363 [01:23<00:31,  4.46it/s]
Loading 0:  62%|██████▏   | 224/363 [01:24<00:55,  2.51it/s]
Loading 0:  62%|██████▏   | 225/363 [01:25<01:15,  1.83it/s]
Loading 0:  63%|██████▎   | 228/363 [01:26<00:55,  2.45it/s]
Loading 0:  63%|██████▎   | 229/363 [01:27<01:07,  1.99it/s]
Loading 0:  63%|██████▎   | 230/363 [01:28<01:20,  1.66it/s]
Loading 0:  64%|██████▍   | 233/363 [01:28<00:46,  2.81it/s]
Loading 0:  64%|██████▍   | 234/363 [01:28<00:43,  2.98it/s]
Loading 0:  65%|██████▍   | 235/363 [01:28<00:37,  3.45it/s]
Loading 0:  65%|██████▌   | 237/363 [01:29<00:43,  2.89it/s]
Loading 0:  66%|██████▌   | 238/363 [01:30<00:57,  2.19it/s]
Loading 0:  66%|██████▌   | 239/363 [01:31<01:10,  1.76it/s]
Loading 0:  67%|██████▋   | 242/363 [01:31<00:40,  2.97it/s]
Loading 0:  67%|██████▋   | 243/363 [01:31<00:38,  3.13it/s]
Loading 0:  67%|██████▋   | 244/363 [01:32<00:33,  3.56it/s]
Loading 0:  68%|██████▊   | 246/363 [01:32<00:39,  2.94it/s]
Loading 0:  68%|██████▊   | 247/363 [01:33<00:52,  2.21it/s]
Loading 0:  68%|██████▊   | 248/363 [01:34<01:05,  1.77it/s]
Loading 0:  69%|██████▉   | 251/363 [01:35<00:37,  3.00it/s]
Loading 0:  69%|██████▉   | 252/363 [01:35<00:35,  3.15it/s]
Loading 0:  70%|██████▉   | 253/363 [01:35<00:30,  3.63it/s]
Loading 0:  70%|███████   | 255/363 [01:36<00:36,  2.97it/s]
Loading 0:  71%|███████   | 256/363 [01:37<00:48,  2.22it/s]
Loading 0:  71%|███████   | 257/363 [01:38<01:00,  1.77it/s]
Loading 0:  72%|███████▏  | 260/363 [01:38<00:34,  2.99it/s]
Loading 0:  72%|███████▏  | 261/363 [01:38<00:32,  3.14it/s]
Loading 0:  72%|███████▏  | 262/363 [01:38<00:27,  3.61it/s]
Loading 0:  73%|███████▎  | 264/363 [01:39<00:33,  2.96it/s]
Loading 0:  73%|███████▎  | 265/363 [01:40<00:44,  2.22it/s]
Loading 0:  73%|███████▎  | 266/363 [01:41<00:54,  1.78it/s]
Loading 0:  74%|███████▍  | 269/363 [01:41<00:31,  3.00it/s]
Loading 0:  74%|███████▍  | 270/363 [01:42<00:29,  3.15it/s]
Loading 0:  75%|███████▍  | 271/363 [01:42<00:25,  3.64it/s]
Loading 0:  75%|███████▌  | 273/363 [01:43<00:30,  2.98it/s]
Loading 0:  75%|███████▌  | 274/363 [01:43<00:39,  2.23it/s]
Loading 0:  76%|███████▌  | 275/363 [01:44<00:49,  1.77it/s]
Loading 0:  77%|███████▋  | 278/363 [01:45<00:28,  3.00it/s]
Loading 0:  77%|███████▋  | 279/363 [01:45<00:26,  3.15it/s]
Loading 0:  77%|███████▋  | 280/363 [01:45<00:22,  3.63it/s]
Loading 0:  78%|███████▊  | 282/363 [01:46<00:27,  2.98it/s]
Loading 0:  78%|███████▊  | 283/363 [01:47<00:35,  2.23it/s]
Loading 0:  78%|███████▊  | 284/363 [01:48<00:44,  1.77it/s]
Loading 0:  79%|███████▉  | 287/363 [01:48<00:25,  3.00it/s]
Loading 0:  79%|███████▉  | 288/363 [01:48<00:23,  3.16it/s]
Loading 0:  80%|███████▉  | 289/363 [01:48<00:20,  3.63it/s]
Loading 0:  80%|████████  | 291/363 [01:49<00:24,  2.98it/s]
Loading 0:  80%|████████  | 292/363 [01:50<00:31,  2.23it/s]
Loading 0:  81%|████████  | 293/363 [01:51<00:39,  1.78it/s]
Loading 0:  82%|████████▏ | 296/363 [01:51<00:22,  3.01it/s]
Loading 0:  82%|████████▏ | 297/363 [01:52<00:20,  3.16it/s]
Loading 0:  82%|████████▏ | 298/363 [01:52<00:17,  3.65it/s]
Loading 0:  82%|████████▏ | 299/363 [01:53<00:26,  2.41it/s]
Loading 0:  83%|████████▎ | 301/363 [01:53<00:19,  3.22it/s]
Loading 0:  83%|████████▎ | 302/363 [01:53<00:18,  3.37it/s]
Loading 0:  83%|████████▎ | 303/363 [01:53<00:15,  3.90it/s]
Loading 0:  84%|████████▎ | 304/363 [01:54<00:15,  3.76it/s]
Loading 0:  84%|████████▍ | 306/363 [01:54<00:19,  2.97it/s]
Loading 0:  85%|████████▍ | 307/363 [01:55<00:26,  2.11it/s]
Loading 0:  85%|████████▌ | 310/363 [01:56<00:20,  2.62it/s]
Loading 0:  86%|████████▌ | 311/363 [01:57<00:24,  2.10it/s]
Loading 0:  86%|████████▌ | 312/363 [01:58<00:29,  1.74it/s]
Loading 0:  87%|████████▋ | 315/363 [01:58<00:16,  2.87it/s]
Loading 0:  87%|████████▋ | 316/363 [01:59<00:15,  3.02it/s]
Loading 0:  87%|████████▋ | 317/363 [01:59<00:13,  3.47it/s]
Loading 0:  88%|████████▊ | 319/363 [02:00<00:15,  2.91it/s]
Loading 0:  88%|████████▊ | 320/363 [02:00<00:19,  2.20it/s]
Loading 0:  88%|████████▊ | 321/363 [02:01<00:23,  1.76it/s]
Loading 0:  89%|████████▉ | 324/363 [02:02<00:13,  2.97it/s]
Loading 0:  90%|████████▉ | 325/363 [02:02<00:12,  3.13it/s]
Loading 0:  90%|████████▉ | 326/363 [02:02<00:10,  3.61it/s]
Loading 0:  90%|█████████ | 328/363 [02:03<00:11,  2.97it/s]
Loading 0:  91%|█████████ | 329/363 [02:04<00:15,  2.22it/s]
Loading 0:  91%|█████████ | 330/363 [02:05<00:18,  1.77it/s]
Loading 0:  92%|█████████▏| 333/363 [02:05<00:10,  3.00it/s]
Loading 0:  92%|█████████▏| 334/363 [02:05<00:09,  3.15it/s]
Loading 0:  92%|█████████▏| 335/363 [02:05<00:07,  3.64it/s]
Loading 0:  93%|█████████▎| 337/363 [02:06<00:08,  2.97it/s]
Loading 0:  93%|█████████▎| 338/363 [02:07<00:11,  2.22it/s]
Loading 0:  93%|█████████▎| 339/363 [02:08<00:13,  1.78it/s]
Loading 0:  94%|█████████▍| 342/363 [02:08<00:06,  3.00it/s]
Loading 0:  94%|█████████▍| 343/363 [02:09<00:06,  3.15it/s]
Loading 0:  95%|█████████▍| 344/363 [02:09<00:05,  3.63it/s]
Loading 0:  95%|█████████▌| 346/363 [02:10<00:05,  2.95it/s]
Loading 0:  96%|█████████▌| 347/363 [02:11<00:07,  2.21it/s]
Loading 0:  96%|█████████▌| 348/363 [02:11<00:08,  1.77it/s]
Loading 0:  97%|█████████▋| 351/363 [02:12<00:04,  2.99it/s]
Loading 0:  97%|█████████▋| 352/363 [02:12<00:03,  3.14it/s]
Loading 0:  97%|█████████▋| 353/363 [02:12<00:02,  3.62it/s]
Loading 0:  98%|█████████▊| 355/363 [02:13<00:02,  2.93it/s]
Loading 0:  98%|█████████▊| 356/363 [02:14<00:03,  2.20it/s]
Loading 0:  98%|█████████▊| 357/363 [02:15<00:03,  1.76it/s]
Loading 0:  99%|█████████▉| 360/363 [02:15<00:01,  2.98it/s]
Loading 0:  99%|█████████▉| 361/363 [02:15<00:00,  3.13it/s]
Loading 0: 100%|█████████▉| 362/363 [02:16<00:00,  3.61it/s]
                                                            
Job chaiml-mn12b-syn1-tune9-v1-mkmlizer completed after 267.94s with status: succeeded
Stopping job with name chaiml-mn12b-syn1-tune9-v1-mkmlizer
Pipeline stage MKMLizer completed in 268.37s
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 chaiml-mn12b-syn1-tune9-v1
Waiting for inference service chaiml-mn12b-syn1-tune9-v1 to be ready
Failed to get response for submission blend_milen_2025-09-03: HTTPConnectionPool(host='guanaco-model-mesh-load-balancer.model-mesh.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-mn12b-syn1-tune9-v1 ready after 60.045005083084106s
Pipeline stage MKMLDeployer completed in 60.52s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7319345474243164s
Received healthy response to inference request in 1.0553054809570312s
Received healthy response to inference request in 0.9800834655761719s
Received healthy response to inference request in 1.3886439800262451s
Received healthy response to inference request in 0.8867995738983154s
5 requests
0 failed requests
5th percentile: 0.9054563522338868
10th percentile: 0.924113130569458
20th percentile: 0.9614266872406005
30th percentile: 0.9951278686523437
40th percentile: 1.0252166748046876
50th percentile: 1.0553054809570312
60th percentile: 1.1886408805847168
70th percentile: 1.3219762802124022
80th percentile: 1.4573020935058594
90th percentile: 1.594618320465088
95th percentile: 1.6632764339447021
99th percentile: 1.7182029247283936
mean time: 1.208553409576416
Pipeline stage StressChecker completed in 7.85s
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 0.63s
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 0.63s
Shutdown handler de-registered
chaiml-mn12b-syn1-tune9_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 0.15s
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 chaiml-mn12b-syn1-tune9-v1-profiler
Waiting for inference service chaiml-mn12b-syn1-tune9-v1-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
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-mn12b-syn1-tune9-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.62s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.41s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mn12b-syn1-tune9-v1-profiler
Waiting for inference service chaiml-mn12b-syn1-tune9-v1-profiler to be ready
Inference service chaiml-mn12b-syn1-tune9-v1-profiler ready after 71.11954641342163s
Pipeline stage MKMLProfilerDeployer completed in 175.64s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /opt/project/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-mn12b-syn1-tune9-v1-profiler-predictor-00001-deployhjrnz:/code/chaiverse_profiler_1757023053 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
Received signal 15, running shutdown handler
run pipeline stage %s
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-mn12b-syn1-tune9-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.61s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.56s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mn12b-syn1-tune9-v1-profiler
Waiting for inference service chaiml-mn12b-syn1-tune9-v1-profiler to be ready
Inference service chaiml-mn12b-syn1-tune9-v1-profiler ready after 61.01500058174133s
Pipeline stage MKMLProfilerDeployer completed in 62.36s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /opt/project/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-mn12b-syn1-tune9-v1-profiler-predictor-00001-deploymtg2x:/code/chaiverse_profiler_1757023349 --namespace tenant-chaiml-guanaco
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-mn12b-syn1-tune9-v1-profiler is running
Tearing down inference service chaiml-mn12b-syn1-tune9-v1-profiler
Service chaiml-mn12b-syn1-tune9-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.85s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.54s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mn12b-syn1-tune9-v1-profiler
Waiting for inference service chaiml-mn12b-syn1-tune9-v1-profiler to be ready
Inference service chaiml-mn12b-syn1-tune9-v1-profiler ready after 50.90232443809509s
Pipeline stage MKMLProfilerDeployer completed in 52.69s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /opt/project/guanaco_services/resources/cks_kube_config cp /opt/project/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-mn12b-syn1-tune9-v1-profiler-predictor-00001-deploy86xlv:/code/chaiverse_profiler_1757023524 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /opt/project/guanaco_services/resources/cks_kube_config exec -it chaiml-mn12b-syn1-tune9-v1-profiler-predictor-00001-deploy86xlv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1757023524 && 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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1757023524/summary.json'
kubectl --kubeconfig /opt/project/guanaco_services/resources/cks_kube_config exec -it chaiml-mn12b-syn1-tune9-v1-profiler-predictor-00001-deploy86xlv --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1757023524/summary.json'
Pipeline stage MKMLProfilerRunner completed in 494.65s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-mn12b-syn1-tune9-v1-profiler is running
Tearing down inference service chaiml-mn12b-syn1-tune9-v1-profiler
Service chaiml-mn12b-syn1-tune9-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.59s
Shutdown handler de-registered
chaiml-mn12b-syn1-tune9_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mn12b-syn1-tune9_v1 status is now torndown due to DeploymentManager action