chaiml-exp-grpo-cp312-_36146

developer_uid: NischayDnk
submission_id: chaiml-exp-grpo-cp312-_36146_v21
model_name: chaiml-exp-grpo-cp312-_36146_v21
model_group: ChaiML/exp_grpo_cp312_96
status: torndown
timestamp: 2025-08-19T00:13:39+00:00
num_battles: 5336
num_wins: 2967
celo_rating: 1296.55
family_friendly_score: 0.5324
family_friendly_standard_error: 0.007056206346189147
submission_type: basic
model_repo: ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: chaiml-exp-grpo-cp312-_36146_v21
ineligible_reason: num_battles<10000
is_internal_developer: False
language_model: ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged
model_size: 24B
ranking_group: single
us_pacific_date: 2025-08-18
win_ratio: 0.5560344827586207
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['You:', '\n', '###', '</s>'], '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 chaiml-exp-grpo-cp312-36146-v21-mkmlizer
Waiting for job on chaiml-exp-grpo-cp312-36146-v21-mkmlizer to finish
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: Downloaded to shared memory in 128.433s
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: Checking if ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged already exists in ChaiML
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmptr365gss, device:0
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: quantized model in 289.902s
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: Processed model ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged in 418.335s
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v21/nvidia
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v21/nvidia/config.json
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v21/nvidia/special_tokens_map.json
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v21/nvidia/tokenizer_config.json
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v21/nvidia/tokenizer.json
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v21/nvidia/flywheel_model.1.safetensors
chaiml-exp-grpo-cp312-36146-v21-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:02<04:04,  1.47it/s]
Loading 0:   1%|          | 4/363 [00:04<06:36,  1.10s/it]
Loading 0:   1%|▏         | 5/363 [00:06<08:26,  1.41s/it]
Loading 0:   2%|▏         | 8/363 [00:06<03:55,  1.51it/s]
Loading 0:   2%|▏         | 9/363 [00:06<03:26,  1.71it/s]
Loading 0:   3%|▎         | 10/363 [00:06<02:48,  2.10it/s]
Loading 0:   3%|▎         | 11/363 [00:07<02:28,  2.37it/s]
Loading 0:   3%|▎         | 12/363 [00:07<02:02,  2.87it/s]
Loading 0:   4%|▎         | 13/363 [00:09<04:41,  1.24it/s]
Loading 0:   4%|▍         | 14/363 [00:11<06:38,  1.14s/it]
Loading 0:   4%|▍         | 15/363 [00:13<08:10,  1.41s/it]
Loading 0:   5%|▍         | 18/363 [00:13<03:58,  1.45it/s]
Loading 0:   5%|▌         | 19/363 [00:13<03:16,  1.75it/s]
Loading 0:   6%|▌         | 21/363 [00:15<04:10,  1.37it/s]
Loading 0:   6%|▌         | 22/363 [00:17<05:40,  1.00it/s]
Loading 0:   6%|▋         | 23/363 [00:19<07:04,  1.25s/it]
Loading 0:   7%|▋         | 26/363 [00:20<03:48,  1.47it/s]
Loading 0:   7%|▋         | 27/363 [00:20<03:20,  1.67it/s]
Loading 0:   8%|▊         | 28/363 [00:20<02:45,  2.02it/s]
Loading 0:   8%|▊         | 30/363 [00:20<02:01,  2.74it/s]
Loading 0:   9%|▊         | 31/363 [00:21<01:53,  2.93it/s]
Loading 0:   9%|▉         | 32/363 [00:21<01:35,  3.46it/s]
Loading 0:   9%|▉         | 33/363 [00:21<01:21,  4.05it/s]
Loading 0:   9%|▉         | 34/363 [00:23<03:53,  1.41it/s]
Loading 0:  10%|▉         | 35/363 [00:25<05:48,  1.06s/it]
Loading 0:  10%|▉         | 36/363 [00:27<07:19,  1.35s/it]
Loading 0:  11%|█         | 39/363 [00:29<05:15,  1.03it/s]
Loading 0:  11%|█         | 40/363 [00:31<06:22,  1.19s/it]
Loading 0:  11%|█▏        | 41/363 [00:33<07:28,  1.39s/it]
Loading 0:  12%|█▏        | 44/363 [00:33<04:01,  1.32it/s]
Loading 0:  12%|█▏        | 45/363 [00:34<03:30,  1.51it/s]
Loading 0:  13%|█▎        | 46/363 [00:34<02:52,  1.84it/s]
Loading 0:  13%|█▎        | 48/363 [00:34<02:05,  2.52it/s]
Loading 0:  13%|█▎        | 49/363 [00:34<01:55,  2.73it/s]
Loading 0:  14%|█▍        | 50/363 [00:34<01:36,  3.24it/s]
Loading 0:  14%|█▍        | 51/363 [00:35<01:21,  3.82it/s]
Loading 0:  14%|█▍        | 52/363 [00:37<03:43,  1.39it/s]
Loading 0:  15%|█▍        | 53/363 [00:39<05:31,  1.07s/it]
Loading 0:  15%|█▍        | 54/363 [00:41<06:57,  1.35s/it]
Loading 0:  16%|█▌        | 57/363 [00:43<05:00,  1.02it/s]
Loading 0:  16%|█▌        | 58/363 [00:45<06:03,  1.19s/it]
Loading 0:  16%|█▋        | 59/363 [00:47<07:03,  1.39s/it]
Loading 0:  17%|█▋        | 62/363 [00:47<03:47,  1.32it/s]
Loading 0:  17%|█▋        | 63/363 [00:47<03:18,  1.51it/s]
Loading 0:  18%|█▊        | 64/363 [00:47<02:43,  1.83it/s]
Loading 0:  18%|█▊        | 66/363 [00:48<01:58,  2.51it/s]
Loading 0:  18%|█▊        | 67/363 [00:48<01:48,  2.73it/s]
Loading 0:  19%|█▊        | 68/363 [00:48<01:30,  3.25it/s]
Loading 0:  19%|█▉        | 69/363 [00:48<01:16,  3.83it/s]
Loading 0:  19%|█▉        | 70/363 [00:50<03:31,  1.39it/s]
Loading 0:  20%|█▉        | 71/363 [00:52<05:12,  1.07s/it]
Loading 0:  20%|█▉        | 72/363 [00:54<06:33,  1.35s/it]
Loading 0:  21%|██        | 75/363 [00:56<04:42,  1.02it/s]
Loading 0:  21%|██        | 76/363 [00:58<05:41,  1.19s/it]
Loading 0:  21%|██        | 77/363 [01:00<06:36,  1.39s/it]
Loading 0:  22%|██▏       | 80/363 [01:01<03:33,  1.32it/s]
Loading 0:  22%|██▏       | 81/363 [01:01<03:05,  1.52it/s]
Loading 0:  23%|██▎       | 82/363 [01:01<02:32,  1.84it/s]
Loading 0:  23%|██▎       | 84/363 [01:01<01:50,  2.51it/s]
Loading 0:  23%|██▎       | 85/363 [01:02<01:41,  2.73it/s]
Loading 0:  24%|██▎       | 86/363 [01:02<01:25,  3.25it/s]
Loading 0:  24%|██▍       | 87/363 [01:02<01:11,  3.84it/s]
Loading 0:  24%|██▍       | 88/363 [01:04<03:17,  1.39it/s]
Loading 0:  25%|██▍       | 89/363 [01:06<04:52,  1.07s/it]
Loading 0:  25%|██▍       | 90/363 [01:08<06:08,  1.35s/it]
Loading 0:  26%|██▌       | 93/363 [01:08<03:00,  1.49it/s]
Loading 0:  26%|██▌       | 94/363 [01:08<02:36,  1.71it/s]
Loading 0:  26%|██▌       | 95/363 [01:09<02:07,  2.10it/s]
Loading 0:  27%|██▋       | 97/363 [01:09<01:33,  2.86it/s]
Loading 0:  27%|██▋       | 98/363 [01:09<01:27,  3.04it/s]
Loading 0:  27%|██▋       | 99/363 [01:09<01:13,  3.58it/s]
Loading 0:  28%|██▊       | 101/363 [01:11<02:29,  1.75it/s]
Loading 0:  28%|██▊       | 102/363 [01:13<03:52,  1.12it/s]
Loading 0:  28%|██▊       | 103/363 [01:15<05:05,  1.18s/it]
Loading 0:  29%|██▉       | 105/363 [01:15<03:05,  1.39it/s]
Loading 0:  29%|██▉       | 106/363 [01:17<04:19,  1.01s/it]
Loading 0:  29%|██▉       | 107/363 [01:19<05:19,  1.25s/it]
Loading 0:  30%|██▉       | 108/363 [01:21<06:12,  1.46s/it]
Loading 0:  31%|███       | 111/363 [01:23<04:23,  1.04s/it]
Loading 0:  31%|███       | 112/363 [01:25<05:09,  1.23s/it]
Loading 0:  31%|███       | 113/363 [01:28<05:54,  1.42s/it]
Loading 0:  32%|███▏      | 116/363 [01:28<03:12,  1.29it/s]
Loading 0:  32%|███▏      | 117/363 [01:28<02:46,  1.47it/s]
Loading 0:  33%|███▎      | 118/363 [01:28<02:17,  1.79it/s]
Loading 0:  33%|███▎      | 120/363 [01:29<01:39,  2.45it/s]
Loading 0:  33%|███▎      | 121/363 [01:29<01:30,  2.67it/s]
Loading 0:  34%|███▎      | 122/363 [01:29<01:16,  3.17it/s]
Loading 0:  34%|███▍      | 123/363 [01:29<01:03,  3.78it/s]
Loading 0:  34%|███▍      | 124/363 [01:31<02:52,  1.39it/s]
Loading 0:  34%|███▍      | 125/363 [01:33<04:14,  1.07s/it]
Loading 0:  35%|███▍      | 126/363 [01:35<05:19,  1.35s/it]
Loading 0:  36%|███▌      | 129/363 [01:37<03:48,  1.02it/s]
Loading 0:  36%|███▌      | 130/363 [01:39<04:36,  1.19s/it]
Loading 0:  36%|███▌      | 131/363 [01:41<05:22,  1.39s/it]
Loading 0:  37%|███▋      | 134/363 [01:42<02:53,  1.32it/s]
Loading 0:  37%|███▋      | 135/363 [01:42<02:30,  1.51it/s]
Loading 0:  37%|███▋      | 136/363 [01:42<02:03,  1.83it/s]
Loading 0:  38%|███▊      | 138/363 [01:42<01:29,  2.51it/s]
Loading 0:  38%|███▊      | 139/363 [01:42<01:22,  2.72it/s]
Loading 0:  39%|███▊      | 140/363 [01:43<01:09,  3.23it/s]
Loading 0:  39%|███▉      | 141/363 [01:43<00:58,  3.81it/s]
Loading 0:  39%|███▉      | 142/363 [01:45<02:39,  1.39it/s]
Loading 0:  39%|███▉      | 143/363 [01:47<03:55,  1.07s/it]
Loading 0:  40%|███▉      | 144/363 [01:49<04:55,  1.35s/it]
Loading 0:  40%|████      | 147/363 [01:51<03:31,  1.02it/s]
Loading 0:  41%|████      | 148/363 [01:53<04:15,  1.19s/it]
Loading 0:  41%|████      | 149/363 [01:55<04:57,  1.39s/it]
Loading 0:  42%|████▏     | 152/363 [01:55<02:39,  1.32it/s]
Loading 0:  42%|████▏     | 153/363 [01:55<02:18,  1.51it/s]
Loading 0:  42%|████▏     | 154/363 [01:56<01:53,  1.84it/s]
Loading 0:  43%|████▎     | 156/363 [01:56<01:22,  2.51it/s]
Loading 0:  43%|████▎     | 157/363 [01:56<01:15,  2.73it/s]
Loading 0:  44%|████▎     | 158/363 [01:56<01:03,  3.25it/s]
Loading 0:  44%|████▍     | 159/363 [01:56<00:53,  3.83it/s]
Loading 0:  44%|████▍     | 160/363 [01:58<02:26,  1.39it/s]
Loading 0:  44%|████▍     | 161/363 [02:00<03:35,  1.07s/it]
Loading 0:  45%|████▍     | 162/363 [02:02<04:30,  1.34s/it]
Loading 0:  45%|████▌     | 165/363 [02:04<03:13,  1.02it/s]
Loading 0:  46%|████▌     | 166/363 [02:06<03:53,  1.19s/it]
Loading 0:  46%|████▌     | 167/363 [02:08<04:31,  1.39s/it]
Loading 0:  47%|████▋     | 170/363 [02:09<02:25,  1.33it/s]
Loading 0:  47%|████▋     | 171/363 [02:09<02:06,  1.52it/s]
Loading 0:  47%|████▋     | 172/363 [02:09<01:43,  1.84it/s]
Loading 0:  48%|████▊     | 174/363 [02:09<01:14,  2.53it/s]
Loading 0:  48%|████▊     | 175/363 [02:10<01:08,  2.74it/s]
Loading 0:  48%|████▊     | 176/363 [02:10<00:57,  3.23it/s]
Loading 0:  49%|████▉     | 177/363 [02:10<00:48,  3.82it/s]
Loading 0:  49%|████▉     | 178/363 [02:12<02:12,  1.39it/s]
Loading 0:  49%|████▉     | 179/363 [02:14<03:15,  1.06s/it]
Loading 0:  50%|████▉     | 180/363 [02:16<04:05,  1.34s/it]
Loading 0:  50%|█████     | 183/363 [02:18<02:55,  1.03it/s]
Loading 0:  51%|█████     | 184/363 [02:20<03:31,  1.18s/it]
Loading 0:  51%|█████     | 185/363 [02:22<04:05,  1.38s/it]
Loading 0:  52%|█████▏    | 188/363 [02:22<02:11,  1.33it/s]
Loading 0:  52%|█████▏    | 189/363 [02:23<01:54,  1.53it/s]
Loading 0:  52%|█████▏    | 190/363 [02:23<01:33,  1.84it/s]
Loading 0:  53%|█████▎    | 192/363 [02:23<01:07,  2.53it/s]
Loading 0:  53%|█████▎    | 193/363 [02:23<01:02,  2.74it/s]
Loading 0:  53%|█████▎    | 194/363 [02:23<00:51,  3.26it/s]
Loading 0:  54%|█████▎    | 195/363 [02:23<00:43,  3.89it/s]
Loading 0:  54%|█████▍    | 196/363 [02:25<01:58,  1.40it/s]
Loading 0:  54%|█████▍    | 197/363 [02:27<02:55,  1.06s/it]
Loading 0:  55%|█████▍    | 198/363 [02:30<03:40,  1.34s/it]
Loading 0:  55%|█████▌    | 201/363 [02:32<02:37,  1.03it/s]
Loading 0:  56%|█████▌    | 202/363 [02:33<03:09,  1.18s/it]
Loading 0:  56%|█████▌    | 203/363 [02:36<03:40,  1.38s/it]
Loading 0:  57%|█████▋    | 206/363 [02:36<01:57,  1.33it/s]
Loading 0:  57%|█████▋    | 207/363 [02:36<01:42,  1.53it/s]
Loading 0:  57%|█████▋    | 208/363 [02:36<01:23,  1.85it/s]
Loading 0:  58%|█████▊    | 210/363 [02:37<01:00,  2.54it/s]
Loading 0:  58%|█████▊    | 211/363 [02:37<00:55,  2.75it/s]
Loading 0:  58%|█████▊    | 212/363 [02:37<00:46,  3.27it/s]
Loading 0:  59%|█████▊    | 213/363 [02:37<00:38,  3.85it/s]
Loading 0:  59%|█████▉    | 214/363 [02:39<01:46,  1.40it/s]
Loading 0:  59%|█████▉    | 215/363 [02:41<02:37,  1.06s/it]
Loading 0:  60%|█████▉    | 216/363 [02:43<03:17,  1.34s/it]
Loading 0:  60%|██████    | 219/363 [02:45<02:19,  1.03it/s]
Loading 0:  61%|██████    | 220/363 [02:47<02:48,  1.18s/it]
Loading 0:  61%|██████    | 221/363 [02:49<03:16,  1.38s/it]
Loading 0:  62%|██████▏   | 224/363 [02:49<01:44,  1.33it/s]
Loading 0:  62%|██████▏   | 225/363 [02:50<01:30,  1.52it/s]
Loading 0:  62%|██████▏   | 226/363 [02:50<01:14,  1.85it/s]
Loading 0:  63%|██████▎   | 228/363 [02:50<00:53,  2.52it/s]
Loading 0:  63%|██████▎   | 229/363 [02:50<00:48,  2.74it/s]
Loading 0:  63%|██████▎   | 230/363 [02:50<00:40,  3.25it/s]
Loading 0:  64%|██████▎   | 231/363 [02:51<00:34,  3.84it/s]
Loading 0:  64%|██████▍   | 232/363 [02:53<01:33,  1.40it/s]
Loading 0:  64%|██████▍   | 233/363 [02:55<02:17,  1.06s/it]
Loading 0:  64%|██████▍   | 234/363 [02:57<02:52,  1.33s/it]
Loading 0:  65%|██████▌   | 237/363 [02:59<02:02,  1.03it/s]
Loading 0:  66%|██████▌   | 238/363 [03:01<02:27,  1.18s/it]
Loading 0:  66%|██████▌   | 239/363 [03:03<02:50,  1.38s/it]
Loading 0:  67%|██████▋   | 242/363 [03:03<01:30,  1.33it/s]
Loading 0:  67%|██████▋   | 243/363 [03:03<01:18,  1.53it/s]
Loading 0:  67%|██████▋   | 244/363 [03:03<01:04,  1.85it/s]
Loading 0:  68%|██████▊   | 246/363 [03:04<00:46,  2.54it/s]
Loading 0:  68%|██████▊   | 247/363 [03:04<00:42,  2.76it/s]
Loading 0:  68%|██████▊   | 248/363 [03:04<00:35,  3.28it/s]
Loading 0:  69%|██████▊   | 249/363 [03:04<00:29,  3.90it/s]
Loading 0:  69%|██████▉   | 250/363 [03:06<01:20,  1.40it/s]
Loading 0:  69%|██████▉   | 251/363 [03:08<01:58,  1.06s/it]
Loading 0:  69%|██████▉   | 252/363 [03:10<02:28,  1.34s/it]
Loading 0:  70%|███████   | 255/363 [03:12<01:44,  1.03it/s]
Loading 0:  71%|███████   | 256/363 [03:14<02:06,  1.18s/it]
Loading 0:  71%|███████   | 257/363 [03:16<02:25,  1.37s/it]
Loading 0:  72%|███████▏  | 260/363 [03:16<01:17,  1.33it/s]
Loading 0:  72%|███████▏  | 261/363 [03:17<01:06,  1.53it/s]
Loading 0:  72%|███████▏  | 262/363 [03:17<00:54,  1.85it/s]
Loading 0:  73%|███████▎  | 264/363 [03:17<00:39,  2.54it/s]
Loading 0:  73%|███████▎  | 265/363 [03:17<00:35,  2.75it/s]
Loading 0:  73%|███████▎  | 266/363 [03:17<00:29,  3.28it/s]
Loading 0:  74%|███████▎  | 267/363 [03:18<00:24,  3.86it/s]
Loading 0:  74%|███████▍  | 268/363 [03:20<01:07,  1.40it/s]
Loading 0:  74%|███████▍  | 269/363 [03:22<01:39,  1.06s/it]
Loading 0:  74%|███████▍  | 270/363 [03:24<02:04,  1.34s/it]
Loading 0:  75%|███████▌  | 273/363 [03:39<04:58,  3.32s/it]
Loading 0:  75%|███████▌  | 274/363 [03:41<04:30,  3.04s/it]
Loading 0:  76%|███████▌  | 275/363 [03:43<04:08,  2.82s/it]
Loading 0:  77%|███████▋  | 278/363 [03:43<02:06,  1.48s/it]
Loading 0:  77%|███████▋  | 279/363 [03:43<01:44,  1.24s/it]
Loading 0:  77%|███████▋  | 280/363 [03:43<01:23,  1.00s/it]
Loading 0:  78%|███████▊  | 282/363 [03:44<00:54,  1.48it/s]
Loading 0:  78%|███████▊  | 283/363 [03:44<00:46,  1.72it/s]
Loading 0:  78%|███████▊  | 284/363 [03:44<00:37,  2.12it/s]
Loading 0:  79%|███████▊  | 285/363 [03:44<00:29,  2.61it/s]
Loading 0:  79%|███████▉  | 286/363 [03:46<01:00,  1.28it/s]
Loading 0:  79%|███████▉  | 287/363 [03:48<01:24,  1.11s/it]
Loading 0:  79%|███████▉  | 288/363 [03:50<01:42,  1.37s/it]
Loading 0:  80%|████████  | 291/363 [03:52<01:09,  1.04it/s]
Loading 0:  80%|████████  | 292/363 [03:54<01:22,  1.17s/it]
Loading 0:  81%|████████  | 293/363 [03:56<01:35,  1.37s/it]
Loading 0:  82%|████████▏ | 296/363 [03:56<00:49,  1.35it/s]
Loading 0:  82%|████████▏ | 297/363 [03:56<00:42,  1.56it/s]
Loading 0:  82%|████████▏ | 298/363 [03:56<00:34,  1.90it/s]
Loading 0:  83%|████████▎ | 300/363 [03:57<00:24,  2.61it/s]
Loading 0:  83%|████████▎ | 301/363 [03:57<00:21,  2.88it/s]
Loading 0:  83%|████████▎ | 302/363 [03:57<00:17,  3.41it/s]
Loading 0:  83%|████████▎ | 303/363 [03:57<00:15,  3.99it/s]
Loading 0:  84%|████████▎ | 304/363 [03:59<00:40,  1.47it/s]
Loading 0:  84%|████████▍ | 305/363 [04:01<00:59,  1.03s/it]
Loading 0:  84%|████████▍ | 306/363 [04:03<01:15,  1.32s/it]
Loading 0:  85%|████████▌ | 309/363 [04:05<00:50,  1.07it/s]
Loading 0:  85%|████████▌ | 310/363 [04:07<01:00,  1.15s/it]
Loading 0:  86%|████████▌ | 311/363 [04:09<01:10,  1.35s/it]
Loading 0:  87%|████████▋ | 314/363 [04:09<00:35,  1.37it/s]
Loading 0:  87%|████████▋ | 315/363 [04:09<00:30,  1.57it/s]
Loading 0:  87%|████████▋ | 316/363 [04:10<00:24,  1.91it/s]
Loading 0:  88%|████████▊ | 318/363 [04:10<00:17,  2.63it/s]
Loading 0:  88%|████████▊ | 319/363 [04:10<00:15,  2.88it/s]
Loading 0:  88%|████████▊ | 320/363 [04:10<00:12,  3.41it/s]
Loading 0:  88%|████████▊ | 321/363 [04:10<00:10,  3.99it/s]
Loading 0:  89%|████████▊ | 322/363 [04:12<00:28,  1.42it/s]
Loading 0:  89%|████████▉ | 323/363 [04:14<00:42,  1.05s/it]
Loading 0:  89%|████████▉ | 324/363 [04:16<00:51,  1.33s/it]
Loading 0:  90%|█████████ | 327/363 [04:18<00:34,  1.04it/s]
Loading 0:  90%|█████████ | 328/363 [04:20<00:41,  1.17s/it]
Loading 0:  91%|█████████ | 329/363 [04:22<00:46,  1.38s/it]
Loading 0:  91%|█████████▏| 332/363 [04:23<00:22,  1.35it/s]
Loading 0:  92%|█████████▏| 333/363 [04:23<00:19,  1.56it/s]
Loading 0:  92%|█████████▏| 334/363 [04:23<00:15,  1.89it/s]
Loading 0:  93%|█████████▎| 336/363 [04:23<00:10,  2.61it/s]
Loading 0:  93%|█████████▎| 337/363 [04:23<00:09,  2.87it/s]
Loading 0:  93%|█████████▎| 338/363 [04:24<00:07,  3.40it/s]
Loading 0:  93%|█████████▎| 339/363 [04:24<00:06,  3.97it/s]
Loading 0:  94%|█████████▎| 340/363 [04:26<00:16,  1.41it/s]
Loading 0:  94%|█████████▍| 341/363 [04:28<00:23,  1.05s/it]
Loading 0:  94%|█████████▍| 342/363 [04:30<00:27,  1.33s/it]
Loading 0:  95%|█████████▌| 345/363 [04:32<00:17,  1.03it/s]
Loading 0:  95%|█████████▌| 346/363 [04:34<00:19,  1.18s/it]
Loading 0:  96%|█████████▌| 347/363 [04:36<00:21,  1.37s/it]
Loading 0:  96%|█████████▋| 350/363 [04:36<00:09,  1.35it/s]
Loading 0:  97%|█████████▋| 351/363 [04:36<00:07,  1.56it/s]
Loading 0:  97%|█████████▋| 352/363 [04:36<00:05,  1.89it/s]
Loading 0:  98%|█████████▊| 354/363 [04:37<00:03,  2.61it/s]
Loading 0:  98%|█████████▊| 355/363 [04:37<00:02,  2.85it/s]
Loading 0:  98%|█████████▊| 356/363 [04:37<00:02,  3.38it/s]
Loading 0:  98%|█████████▊| 357/363 [04:37<00:02,  2.96it/s]
Loading 0:  99%|█████████▉| 359/363 [04:39<00:02,  1.61it/s]
Loading 0:  99%|█████████▉| 360/363 [04:41<00:02,  1.07it/s]
Loading 0:  99%|█████████▉| 361/363 [04:43<00:02,  1.21s/it]
                                                            
Job chaiml-exp-grpo-cp312-36146-v21-mkmlizer completed after 458.63s with status: succeeded
Stopping job with name chaiml-exp-grpo-cp312-36146-v21-mkmlizer
Pipeline stage MKMLizer completed in 459.71s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v21
Waiting for inference service chaiml-exp-grpo-cp312-36146-v21 to be ready
Inference service chaiml-exp-grpo-cp312-36146-v21 ready after 70.26456904411316s
Pipeline stage MKMLDeployer completed in 70.67s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.1883740425109863s
Received healthy response to inference request in 2.3237509727478027s
Received healthy response to inference request in 3.617770195007324s
Received healthy response to inference request in 1.738215684890747s
5 requests
1 failed requests
5th percentile: 1.828247356414795
10th percentile: 1.9182790279388429
20th percentile: 2.0983423709869387
30th percentile: 2.2154494285583497
40th percentile: 2.269600200653076
50th percentile: 2.3237509727478027
60th percentile: 2.8413586616516113
70th percentile: 3.35896635055542
80th percentile: 6.926855087280277
90th percentile: 13.545024871826174
95th percentile: 16.854109764099118
99th percentile: 19.50137767791748
mean time: 6.006261110305786
%s, retrying in %s seconds...
Received healthy response to inference request in 1.7110199928283691s
Received healthy response to inference request in 2.0582265853881836s
Received healthy response to inference request in 1.6970102787017822s
Received healthy response to inference request in 2.2470507621765137s
Received healthy response to inference request in 2.2854440212249756s
5 requests
0 failed requests
5th percentile: 1.6998122215270997
10th percentile: 1.702614164352417
20th percentile: 1.7082180500030517
30th percentile: 1.780461311340332
40th percentile: 1.9193439483642578
50th percentile: 2.0582265853881836
60th percentile: 2.1337562561035157
70th percentile: 2.209285926818848
80th percentile: 2.254729413986206
90th percentile: 2.270086717605591
95th percentile: 2.2777653694152833
99th percentile: 2.283908290863037
mean time: 1.9997503280639648
Pipeline stage StressChecker completed in 43.33s
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 0.70s
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-exp-grpo-cp312-_36146_v21 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 2.41s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v21-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v21-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 2842.60s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v21 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
chaiml-exp-grpo-cp312-_36146_v21 status is now protected due to ABTestQueueItem
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 0.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.51s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v21-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v21-profiler to be ready
Inference service chaiml-exp-grpo-cp312-36146-v21-profiler ready after 61.10212254524231s
Pipeline stage MKMLProfilerDeployer completed in 62.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/cks_kube_config cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-exp-grpo-cp3144b70fd7d331dbc6338eb064ed87288c-deplot7s6k:/code/chaiverse_profiler_1757708144 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/cks_kube_config exec -it chaiml-exp-grpo-cp3144b70fd7d331dbc6338eb064ed87288c-deplot7s6k --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1757708144 && 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_1757708144/summary.json'
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/cks_kube_config exec -it chaiml-exp-grpo-cp3144b70fd7d331dbc6338eb064ed87288c-deplot7s6k --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1757708144/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1058.51s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-exp-grpo-cp312-36146-v21-profiler is running
Tearing down inference service chaiml-exp-grpo-cp312-36146-v21-profiler
Service chaiml-exp-grpo-cp312-36146-v21-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.28s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v21 status is now torndown due to DeploymentManager action