chaiml-mn24b-v2preferwi_87788

developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn24b-v2preferwi_87788_v5
model_name: chaiml-mn24b-v2preferwi_87788_v5
model_group: ChaiML/mn24b_v2preferwin
status: torndown
timestamp: 2025-09-17T01:54:15+00:00
num_battles: 5673
num_wins: 3007
celo_rating: 1280.18
family_friendly_score: 0.5846
family_friendly_standard_error: 0.006969115295358515
submission_type: basic
model_repo: ChaiML/mn24b_v2preferwin2_qwen_bo4_tune1
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': 0.5453014606894507, 'latency_mean': 1.8337212359905244, 'latency_p50': 1.8538211584091187, 'latency_p90': 2.0368550062179565}, {'batch_size': 3, 'throughput': 1.087842855957036, 'latency_mean': 2.7424019598960876, 'latency_p50': 2.7566407918930054, 'latency_p90': 3.170415925979614}, {'batch_size': 5, 'throughput': 1.4251963710042252, 'latency_mean': 3.498502925634384, 'latency_p50': 3.4598331451416016, 'latency_p90': 4.001840376853942}, {'batch_size': 6, 'throughput': 1.5123303082585449, 'latency_mean': 3.9417560648918153, 'latency_p50': 3.9395880699157715, 'latency_p90': 4.463779354095459}, {'batch_size': 8, 'throughput': 1.6624681257773044, 'latency_mean': 4.77716821193695, 'latency_p50': 4.788872480392456, 'latency_p90': 5.3310247421264645}, {'batch_size': 10, 'throughput': 1.7354819483868127, 'latency_mean': 5.727500898838043, 'latency_p50': 5.727128744125366, 'latency_p90': 6.548437929153442}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn24b-v2preferwi_87788_v5
is_internal_developer: False
language_model: ChaiML/mn24b_v2preferwin2_qwen_bo4_tune1
model_size: 24B
ranking_group: single
throughput_3p7s: 1.47
us_pacific_date: 2025-09-16
win_ratio: 0.5300546448087432
generation_params: {'temperature': 0.8, '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': '\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-mn24b-v2preferwi-87788-v5-mkmlizer
Waiting for job on chaiml-mn24b-v2preferwi-87788-v5-mkmlizer to finish
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: Downloaded to shared memory in 57.499s
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: Checking if ChaiML/mn24b_v2preferwin2_qwen_bo4_tune1 already exists in ChaiML
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpdy6_woed, device:0
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: quantized model in 288.284s
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: Processed model ChaiML/mn24b_v2preferwin2_qwen_bo4_tune1 in 345.784s
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-87788-v5/nvidia
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-87788-v5/nvidia/config.json
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-87788-v5/nvidia/special_tokens_map.json
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-87788-v5/nvidia/tokenizer_config.json
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-87788-v5/nvidia/tokenizer.json
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-87788-v5/nvidia/flywheel_model.0.safetensors
chaiml-mn24b-v2preferwi-87788-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:02<04:03,  1.48it/s]
Loading 0:   1%|          | 4/363 [00:04<06:34,  1.10s/it]
Loading 0:   1%|▏         | 5/363 [00:06<08:23,  1.41s/it]
Loading 0:   2%|▏         | 8/363 [00:06<03:54,  1.51it/s]
Loading 0:   2%|▏         | 9/363 [00:06<03:25,  1.72it/s]
Loading 0:   3%|▎         | 10/363 [00:06<02:47,  2.10it/s]
Loading 0:   3%|▎         | 12/363 [00:08<04:00,  1.46it/s]
Loading 0:   4%|▎         | 13/363 [00:10<05:41,  1.03it/s]
Loading 0:   4%|▍         | 14/363 [00:12<07:12,  1.24s/it]
Loading 0:   5%|▍         | 17/363 [00:13<03:49,  1.51it/s]
Loading 0:   5%|▍         | 18/363 [00:13<03:21,  1.71it/s]
Loading 0:   5%|▌         | 19/363 [00:13<02:47,  2.05it/s]
Loading 0:   6%|▌         | 21/363 [00:15<03:53,  1.46it/s]
Loading 0:   6%|▌         | 22/363 [00:17<05:28,  1.04it/s]
Loading 0:   6%|▋         | 23/363 [00:19<06:56,  1.23s/it]
Loading 0:   7%|▋         | 26/363 [00:19<03:43,  1.51it/s]
Loading 0:   7%|▋         | 27/363 [00:20<03:15,  1.72it/s]
Loading 0:   8%|▊         | 28/363 [00:20<02:41,  2.07it/s]
Loading 0:   8%|▊         | 30/363 [00:20<01:58,  2.80it/s]
Loading 0:   9%|▊         | 31/363 [00:20<01:51,  2.99it/s]
Loading 0:   9%|▉         | 32/363 [00:21<01:33,  3.53it/s]
Loading 0:   9%|▉         | 33/363 [00:21<01:22,  3.98it/s]
Loading 0:   9%|▉         | 34/363 [00:23<03:53,  1.41it/s]
Loading 0:  10%|▉         | 35/363 [00:25<05:47,  1.06s/it]
Loading 0:  10%|▉         | 36/363 [00:27<07:24,  1.36s/it]
Loading 0:  11%|█         | 39/363 [00:29<05:17,  1.02it/s]
Loading 0:  11%|█         | 40/363 [00:31<06:23,  1.19s/it]
Loading 0:  11%|█▏        | 41/363 [00:33<07:26,  1.39s/it]
Loading 0:  12%|█▏        | 44/363 [00:33<04:00,  1.33it/s]
Loading 0:  12%|█▏        | 45/363 [00:33<03:29,  1.52it/s]
Loading 0:  13%|█▎        | 46/363 [00:34<02:52,  1.84it/s]
Loading 0:  13%|█▎        | 48/363 [00:36<03:45,  1.40it/s]
Loading 0:  13%|█▎        | 49/363 [00:37<05:09,  1.02it/s]
Loading 0:  14%|█▍        | 50/363 [00:40<06:26,  1.23s/it]
Loading 0:  15%|█▍        | 53/363 [00:40<03:27,  1.50it/s]
Loading 0:  15%|█▍        | 54/363 [00:40<03:01,  1.70it/s]
Loading 0:  15%|█▌        | 55/363 [00:40<02:29,  2.05it/s]
Loading 0:  16%|█▌        | 57/363 [00:42<03:29,  1.46it/s]
Loading 0:  16%|█▌        | 58/363 [00:44<04:53,  1.04it/s]
Loading 0:  16%|█▋        | 59/363 [00:46<06:11,  1.22s/it]
Loading 0:  17%|█▋        | 62/363 [00:47<03:19,  1.51it/s]
Loading 0:  17%|█▋        | 63/363 [00:47<02:55,  1.71it/s]
Loading 0:  18%|█▊        | 64/363 [00:47<02:24,  2.07it/s]
Loading 0:  18%|█▊        | 65/363 [00:49<04:09,  1.19it/s]
Loading 0:  18%|█▊        | 67/363 [00:49<02:46,  1.77it/s]
Loading 0:  19%|█▊        | 68/363 [00:50<02:25,  2.02it/s]
Loading 0:  19%|█▉        | 69/363 [00:50<01:59,  2.47it/s]
Loading 0:  19%|█▉        | 70/363 [00:50<01:38,  2.96it/s]
Loading 0:  20%|█▉        | 71/363 [00:52<03:48,  1.28it/s]
Loading 0:  20%|█▉        | 72/363 [00:54<05:24,  1.11s/it]
Loading 0:  20%|██        | 73/363 [00:56<06:40,  1.38s/it]
Loading 0:  21%|██        | 76/363 [00:56<03:15,  1.47it/s]
Loading 0:  21%|██        | 77/363 [00:56<02:49,  1.69it/s]
Loading 0:  21%|██▏       | 78/363 [00:57<02:18,  2.06it/s]
Loading 0:  22%|██▏       | 79/363 [00:59<04:02,  1.17it/s]
Loading 0:  22%|██▏       | 80/363 [01:01<05:29,  1.16s/it]
Loading 0:  23%|██▎       | 82/363 [01:01<03:26,  1.36it/s]
Loading 0:  23%|██▎       | 83/363 [01:01<02:53,  1.61it/s]
Loading 0:  23%|██▎       | 84/363 [01:01<02:18,  2.02it/s]
Loading 0:  24%|██▎       | 86/363 [01:03<03:15,  1.42it/s]
Loading 0:  24%|██▍       | 87/363 [01:05<04:39,  1.01s/it]
Loading 0:  25%|██▍       | 90/363 [01:07<03:49,  1.19it/s]
Loading 0:  25%|██▌       | 91/363 [01:09<04:47,  1.06s/it]
Loading 0:  25%|██▌       | 92/363 [01:11<05:44,  1.27s/it]
Loading 0:  26%|██▌       | 95/363 [01:12<03:10,  1.40it/s]
Loading 0:  26%|██▋       | 96/363 [01:12<02:47,  1.60it/s]
Loading 0:  27%|██▋       | 97/363 [01:12<02:19,  1.91it/s]
Loading 0:  27%|██▋       | 99/363 [01:14<03:04,  1.43it/s]
Loading 0:  28%|██▊       | 100/363 [01:16<04:15,  1.03it/s]
Loading 0:  28%|██▊       | 101/363 [01:18<05:19,  1.22s/it]
Loading 0:  29%|██▊       | 104/363 [01:18<02:51,  1.51it/s]
Loading 0:  29%|██▉       | 105/363 [01:19<02:30,  1.71it/s]
Loading 0:  29%|██▉       | 106/363 [01:19<02:04,  2.06it/s]
Loading 0:  29%|██▉       | 107/363 [01:19<01:43,  2.48it/s]
Loading 0:  30%|██▉       | 108/363 [01:21<03:24,  1.25it/s]
Loading 0:  31%|███       | 111/363 [01:23<03:03,  1.37it/s]
Loading 0:  31%|███       | 112/363 [01:25<04:05,  1.02it/s]
Loading 0:  31%|███       | 113/363 [01:27<05:04,  1.22s/it]
Loading 0:  32%|███▏      | 116/363 [01:27<02:46,  1.48it/s]
Loading 0:  32%|███▏      | 117/363 [01:27<02:26,  1.68it/s]
Loading 0:  33%|███▎      | 118/363 [01:28<02:01,  2.02it/s]
Loading 0:  33%|███▎      | 120/363 [01:30<02:46,  1.46it/s]
Loading 0:  33%|███▎      | 121/363 [01:31<03:52,  1.04it/s]
Loading 0:  34%|███▎      | 122/363 [01:34<04:52,  1.21s/it]
Loading 0:  34%|███▍      | 125/363 [01:34<02:36,  1.52it/s]
Loading 0:  35%|███▍      | 126/363 [01:34<02:17,  1.72it/s]
Loading 0:  35%|███▍      | 127/363 [01:34<01:53,  2.08it/s]
Loading 0:  36%|███▌      | 129/363 [01:36<02:38,  1.47it/s]
Loading 0:  36%|███▌      | 130/363 [01:38<03:43,  1.04it/s]
Loading 0:  36%|███▌      | 131/363 [01:40<04:42,  1.22s/it]
Loading 0:  37%|███▋      | 134/363 [01:41<02:30,  1.52it/s]
Loading 0:  37%|███▋      | 135/363 [01:41<02:12,  1.72it/s]
Loading 0:  37%|███▋      | 136/363 [01:41<01:49,  2.08it/s]
Loading 0:  38%|███▊      | 138/363 [01:43<02:32,  1.48it/s]
Loading 0:  38%|███▊      | 139/363 [01:45<03:34,  1.04it/s]
Loading 0:  39%|███▊      | 140/363 [01:47<04:30,  1.21s/it]
Loading 0:  39%|███▉      | 143/363 [01:47<02:24,  1.52it/s]
Loading 0:  40%|███▉      | 144/363 [01:48<02:06,  1.73it/s]
Loading 0:  40%|███▉      | 145/363 [01:48<01:44,  2.08it/s]
Loading 0:  40%|████      | 147/363 [01:48<01:16,  2.81it/s]
Loading 0:  41%|████      | 148/363 [01:48<01:11,  3.00it/s]
Loading 0:  41%|████      | 149/363 [01:48<01:00,  3.53it/s]
Loading 0:  41%|████▏     | 150/363 [01:48<00:52,  4.09it/s]
Loading 0:  42%|████▏     | 151/363 [01:50<02:29,  1.42it/s]
Loading 0:  42%|████▏     | 152/363 [01:52<03:42,  1.06s/it]
Loading 0:  42%|████▏     | 153/363 [01:55<04:41,  1.34s/it]
Loading 0:  43%|████▎     | 156/363 [01:57<03:20,  1.03it/s]
Loading 0:  43%|████▎     | 157/363 [01:58<04:02,  1.18s/it]
Loading 0:  44%|████▎     | 158/363 [02:01<04:42,  1.38s/it]
Loading 0:  44%|████▍     | 161/363 [02:01<02:30,  1.34it/s]
Loading 0:  45%|████▍     | 162/363 [02:01<02:11,  1.53it/s]
Loading 0:  45%|████▍     | 163/363 [02:01<01:48,  1.85it/s]
Loading 0:  45%|████▌     | 165/363 [02:03<02:21,  1.40it/s]
Loading 0:  46%|████▌     | 166/363 [02:05<03:14,  1.01it/s]
Loading 0:  46%|████▌     | 167/363 [02:07<04:01,  1.23s/it]
Loading 0:  47%|████▋     | 170/363 [02:08<02:08,  1.50it/s]
Loading 0:  47%|████▋     | 171/363 [02:08<01:52,  1.70it/s]
Loading 0:  47%|████▋     | 172/363 [02:08<01:32,  2.05it/s]
Loading 0:  48%|████▊     | 174/363 [02:10<02:08,  1.47it/s]
Loading 0:  48%|████▊     | 175/363 [02:12<03:00,  1.04it/s]
Loading 0:  48%|████▊     | 176/363 [02:14<03:47,  1.22s/it]
Loading 0:  49%|████▉     | 179/363 [02:14<02:01,  1.52it/s]
Loading 0:  50%|████▉     | 180/363 [02:15<01:46,  1.72it/s]
Loading 0:  50%|████▉     | 181/363 [02:15<01:27,  2.07it/s]
Loading 0:  50%|█████     | 182/363 [02:17<02:31,  1.19it/s]
Loading 0:  51%|█████     | 184/363 [02:17<01:40,  1.78it/s]
Loading 0:  51%|█████     | 185/363 [02:17<01:27,  2.03it/s]
Loading 0:  51%|█████     | 186/363 [02:17<01:12,  2.45it/s]
Loading 0:  52%|█████▏    | 187/363 [02:17<00:59,  2.96it/s]
Loading 0:  52%|█████▏    | 188/363 [02:19<02:16,  1.28it/s]
Loading 0:  52%|█████▏    | 189/363 [02:22<03:16,  1.13s/it]
Loading 0:  53%|█████▎    | 192/363 [02:23<02:29,  1.14it/s]
Loading 0:  53%|█████▎    | 193/363 [02:25<03:07,  1.10s/it]
Loading 0:  53%|█████▎    | 194/363 [02:28<03:42,  1.32s/it]
Loading 0:  54%|█████▍    | 197/363 [02:28<01:59,  1.39it/s]
Loading 0:  55%|█████▍    | 198/363 [02:28<01:43,  1.59it/s]
Loading 0:  55%|█████▍    | 199/363 [02:28<01:25,  1.92it/s]
Loading 0:  55%|█████▌    | 201/363 [02:30<01:53,  1.43it/s]
Loading 0:  56%|█████▌    | 202/363 [02:32<02:36,  1.03it/s]
Loading 0:  56%|█████▌    | 203/363 [02:34<03:16,  1.23s/it]
Loading 0:  57%|█████▋    | 206/363 [02:35<01:44,  1.50it/s]
Loading 0:  57%|█████▋    | 207/363 [02:35<01:31,  1.71it/s]
Loading 0:  57%|█████▋    | 208/363 [02:35<01:15,  2.06it/s]
Loading 0:  58%|█████▊    | 210/363 [02:37<01:43,  1.48it/s]
Loading 0:  58%|█████▊    | 211/363 [02:39<02:25,  1.05it/s]
Loading 0:  58%|█████▊    | 212/363 [02:41<03:02,  1.21s/it]
Loading 0:  59%|█████▉    | 215/363 [02:41<01:36,  1.53it/s]
Loading 0:  60%|█████▉    | 216/363 [02:41<01:24,  1.73it/s]
Loading 0:  60%|█████▉    | 217/363 [02:42<01:10,  2.08it/s]
Loading 0:  60%|██████    | 218/363 [02:44<02:00,  1.20it/s]
Loading 0:  60%|██████    | 219/363 [02:46<02:44,  1.14s/it]
Loading 0:  61%|██████    | 221/363 [02:46<01:43,  1.37it/s]
Loading 0:  61%|██████    | 222/363 [02:46<01:27,  1.62it/s]
Loading 0:  61%|██████▏   | 223/363 [02:46<01:09,  2.01it/s]
Loading 0:  62%|██████▏   | 224/363 [02:46<00:55,  2.49it/s]
Loading 0:  62%|██████▏   | 225/363 [02:48<01:54,  1.20it/s]
Loading 0:  63%|██████▎   | 228/363 [02:50<01:39,  1.36it/s]
Loading 0:  63%|██████▎   | 229/363 [02:52<02:12,  1.01it/s]
Loading 0:  63%|██████▎   | 230/363 [02:54<02:43,  1.23s/it]
Loading 0:  64%|██████▍   | 233/363 [02:55<01:27,  1.48it/s]
Loading 0:  64%|██████▍   | 234/363 [02:55<01:16,  1.68it/s]
Loading 0:  65%|██████▍   | 235/363 [02:55<01:03,  2.02it/s]
Loading 0:  65%|██████▌   | 237/363 [02:57<01:25,  1.47it/s]
Loading 0:  66%|██████▌   | 238/363 [02:59<01:59,  1.04it/s]
Loading 0:  66%|██████▌   | 239/363 [03:01<02:30,  1.21s/it]
Loading 0:  67%|██████▋   | 242/363 [03:01<01:19,  1.52it/s]
Loading 0:  67%|██████▋   | 243/363 [03:02<01:09,  1.73it/s]
Loading 0:  67%|██████▋   | 244/363 [03:02<00:57,  2.08it/s]
Loading 0:  68%|██████▊   | 246/363 [03:04<01:19,  1.48it/s]
Loading 0:  68%|██████▊   | 247/363 [03:06<01:50,  1.05it/s]
Loading 0:  68%|██████▊   | 248/363 [03:08<02:18,  1.21s/it]
Loading 0:  69%|██████▉   | 251/363 [03:08<01:13,  1.53it/s]
Loading 0:  69%|██████▉   | 252/363 [03:08<01:03,  1.74it/s]
Loading 0:  70%|██████▉   | 253/363 [03:08<00:52,  2.09it/s]
Loading 0:  70%|███████   | 255/363 [03:10<01:12,  1.48it/s]
Loading 0:  71%|███████   | 256/363 [03:12<01:41,  1.05it/s]
Loading 0:  71%|███████   | 257/363 [03:14<02:08,  1.21s/it]
Loading 0:  72%|███████▏  | 260/363 [03:15<01:07,  1.52it/s]
Loading 0:  72%|███████▏  | 261/363 [03:15<00:58,  1.73it/s]
Loading 0:  72%|███████▏  | 262/363 [03:15<00:48,  2.08it/s]
Loading 0:  73%|███████▎  | 264/363 [03:15<00:35,  2.80it/s]
Loading 0:  73%|███████▎  | 265/363 [03:16<00:32,  3.00it/s]
Loading 0:  73%|███████▎  | 266/363 [03:16<00:27,  3.53it/s]
Loading 0:  74%|███████▎  | 267/363 [03:16<00:23,  4.08it/s]
Loading 0:  74%|███████▍  | 268/363 [03:18<01:06,  1.42it/s]
Loading 0:  74%|███████▍  | 269/363 [03:20<01:38,  1.05s/it]
Loading 0:  74%|███████▍  | 270/363 [03:22<02:03,  1.33s/it]
Loading 0:  75%|███████▌  | 273/363 [03:37<05:00,  3.34s/it]
Loading 0:  75%|███████▌  | 274/363 [03:39<04:31,  3.05s/it]
Loading 0:  76%|███████▌  | 275/363 [03:41<04:09,  2.84s/it]
Loading 0:  77%|███████▋  | 278/363 [03:41<02:06,  1.48s/it]
Loading 0:  77%|███████▋  | 279/363 [03:42<01:44,  1.24s/it]
Loading 0:  77%|███████▋  | 280/363 [03:42<01:23,  1.00s/it]
Loading 0:  78%|███████▊  | 282/363 [03:44<01:20,  1.00it/s]
Loading 0:  78%|███████▊  | 283/363 [03:46<01:36,  1.21s/it]
Loading 0:  78%|███████▊  | 284/363 [03:48<01:50,  1.40s/it]
Loading 0:  79%|███████▉  | 287/363 [03:48<00:56,  1.34it/s]
Loading 0:  79%|███████▉  | 288/363 [03:48<00:48,  1.55it/s]
Loading 0:  80%|███████▉  | 289/363 [03:48<00:39,  1.88it/s]
Loading 0:  80%|████████  | 291/363 [03:50<00:50,  1.42it/s]
Loading 0:  80%|████████  | 292/363 [03:52<01:09,  1.03it/s]
Loading 0:  81%|████████  | 293/363 [03:54<01:25,  1.22s/it]
Loading 0:  82%|████████▏ | 296/363 [03:55<00:44,  1.52it/s]
Loading 0:  82%|████████▏ | 297/363 [03:55<00:37,  1.74it/s]
Loading 0:  82%|████████▏ | 298/363 [03:55<00:30,  2.11it/s]
Loading 0:  82%|████████▏ | 299/363 [03:57<00:53,  1.21it/s]
Loading 0:  83%|████████▎ | 301/363 [03:57<00:34,  1.82it/s]
Loading 0:  83%|████████▎ | 302/363 [03:57<00:29,  2.10it/s]
Loading 0:  83%|████████▎ | 303/363 [03:57<00:23,  2.57it/s]
Loading 0:  84%|████████▎ | 304/363 [03:58<00:19,  3.10it/s]
Loading 0:  84%|████████▍ | 305/363 [04:00<00:44,  1.31it/s]
Loading 0:  84%|████████▍ | 306/363 [04:02<01:03,  1.12s/it]
Loading 0:  85%|████████▌ | 309/363 [04:04<00:46,  1.15it/s]
Loading 0:  85%|████████▌ | 310/363 [04:06<00:57,  1.09s/it]
Loading 0:  86%|████████▌ | 311/363 [04:08<01:08,  1.31s/it]
Loading 0:  87%|████████▋ | 314/363 [04:08<00:34,  1.41it/s]
Loading 0:  87%|████████▋ | 315/363 [04:08<00:29,  1.62it/s]
Loading 0:  87%|████████▋ | 316/363 [04:08<00:23,  1.96it/s]
Loading 0:  88%|████████▊ | 318/363 [04:10<00:31,  1.44it/s]
Loading 0:  88%|████████▊ | 319/363 [04:12<00:42,  1.04it/s]
Loading 0:  88%|████████▊ | 320/363 [04:14<00:52,  1.21s/it]
Loading 0:  89%|████████▉ | 323/363 [04:14<00:26,  1.53it/s]
Loading 0:  89%|████████▉ | 324/363 [04:15<00:22,  1.76it/s]
Loading 0:  90%|████████▉ | 325/363 [04:15<00:17,  2.12it/s]
Loading 0:  90%|█████████ | 327/363 [04:17<00:24,  1.48it/s]
Loading 0:  90%|█████████ | 328/363 [04:19<00:33,  1.04it/s]
Loading 0:  91%|█████████ | 329/363 [04:21<00:41,  1.21s/it]
Loading 0:  91%|█████████▏| 332/363 [04:21<00:20,  1.53it/s]
Loading 0:  92%|█████████▏| 333/363 [04:21<00:17,  1.76it/s]
Loading 0:  92%|█████████▏| 334/363 [04:21<00:13,  2.11it/s]
Loading 0:  92%|█████████▏| 335/363 [04:23<00:23,  1.21it/s]
Loading 0:  93%|█████████▎| 336/363 [04:25<00:30,  1.13s/it]
Loading 0:  93%|█████████▎| 338/363 [04:26<00:17,  1.40it/s]
Loading 0:  93%|█████████▎| 339/363 [04:26<00:14,  1.67it/s]
Loading 0:  94%|█████████▎| 340/363 [04:26<00:11,  2.09it/s]
Loading 0:  94%|█████████▍| 341/363 [04:26<00:09,  2.33it/s]
Loading 0:  94%|█████████▍| 343/363 [04:28<00:13,  1.50it/s]
Loading 0:  95%|█████████▌| 346/363 [04:30<00:11,  1.51it/s]
Loading 0:  96%|█████████▌| 347/363 [04:32<00:14,  1.11it/s]
Loading 0:  96%|█████████▌| 348/363 [04:34<00:17,  1.14s/it]
Loading 0:  97%|█████████▋| 351/363 [04:35<00:07,  1.55it/s]
Loading 0:  97%|█████████▋| 352/363 [04:35<00:06,  1.76it/s]
Loading 0:  97%|█████████▋| 353/363 [04:35<00:04,  2.11it/s]
Loading 0:  98%|█████████▊| 355/363 [04:37<00:05,  1.49it/s]
Loading 0:  98%|█████████▊| 356/363 [04:39<00:06,  1.06it/s]
Loading 0:  98%|█████████▊| 357/363 [04:41<00:07,  1.20s/it]
Loading 0:  99%|█████████▉| 360/363 [04:41<00:01,  1.54it/s]
Loading 0:  99%|█████████▉| 361/363 [04:41<00:01,  1.76it/s]
Loading 0: 100%|█████████▉| 362/363 [04:42<00:00,  2.12it/s]
                                                            
Job chaiml-mn24b-v2preferwi-87788-v5-mkmlizer completed after 408.19s with status: succeeded
Stopping job with name chaiml-mn24b-v2preferwi-87788-v5-mkmlizer
Pipeline stage MKMLizer completed in 408.95s
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-mn24b-v2preferwi-87788-v5
Waiting for inference service chaiml-mn24b-v2preferwi-87788-v5 to be ready
Inference service chaiml-mn24b-v2preferwi-87788-v5 ready after 60.531620502471924s
Pipeline stage MKMLDeployer completed in 61.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8595659732818604s
Received healthy response to inference request in 2.010531187057495s
Received healthy response to inference request in 1.6097207069396973s
Received healthy response to inference request in 1.6335816383361816s
Received healthy response to inference request in 1.9027957916259766s
5 requests
0 failed requests
5th percentile: 1.6144928932189941
10th percentile: 1.619265079498291
20th percentile: 1.6288094520568848
30th percentile: 1.6787785053253175
40th percentile: 1.769172239303589
50th percentile: 1.8595659732818604
60th percentile: 1.8768579006195067
70th percentile: 1.8941498279571534
80th percentile: 1.9243428707122803
90th percentile: 1.9674370288848877
95th percentile: 1.9889841079711914
99th percentile: 2.0062217712402344
mean time: 1.8032390594482421
Pipeline stage StressChecker completed in 10.30s
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 0.69s
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 0.75s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_87788_v5 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mn24b-v2preferwi-87788-v5-profiler
Waiting for inference service chaiml-mn24b-v2preferwi-87788-v5-profiler to be ready
Inference service chaiml-mn24b-v2preferwi-87788-v5-profiler ready after 60.63367295265198s
Pipeline stage MKMLProfilerDeployer completed in 61.23s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-mn24b-v2prefe58dd258187a648fd3b4ad16c81401838-deplops5vz:/code/chaiverse_profiler_1758074692 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-mn24b-v2prefe58dd258187a648fd3b4ad16c81401838-deplops5vz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1758074692 && 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_1758074692/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 2449.54s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_87788_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-mn24b-v2preferwi_87788_v5 status is now torndown due to DeploymentManager action