developer_uid: rirv938
submission_id: chaiml-exp-grpo-cp312-_36146_v53
model_name: chaiml-exp-grpo-cp312-_36146_v53
model_group: ChaiML/exp_grpo_cp312_96
status: torndown
timestamp: 2025-10-21T04:14:06+00:00
num_battles: 6299
num_wins: 3447
celo_rating: 1300.11
family_friendly_score: 0.5138
family_friendly_standard_error: 0.007068374070463447
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: 16
max_input_tokens: 1280
max_output_tokens: 64
reward_model: chaiml-llama31-mer-v2-_44570_v27
latencies: [{'batch_size': 1, 'throughput': 0.4993539023493701, 'latency_mean': 2.002481943368912, 'latency_p50': 1.9919185638427734, 'latency_p90': 2.2205841541290283}, {'batch_size': 3, 'throughput': 0.8734485702922722, 'latency_mean': 3.422098070383072, 'latency_p50': 3.424204111099243, 'latency_p90': 3.829989695549011}, {'batch_size': 5, 'throughput': 1.0164608200160858, 'latency_mean': 4.8925782907009125, 'latency_p50': 4.847097635269165, 'latency_p90': 5.5306176185607905}, {'batch_size': 6, 'throughput': 1.0533688043590355, 'latency_mean': 5.673512459993362, 'latency_p50': 5.709998250007629, 'latency_p90': 6.360808563232422}, {'batch_size': 10, 'throughput': 1.0974093167712011, 'latency_mean': 9.035869966745377, 'latency_p50': 9.116668820381165, 'latency_p90': 10.173586869239807}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-exp-grpo-cp312-_36146_v53
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 0.91
us_pacific_date: 2025-10-20
win_ratio: 0.5472297190030163
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': ['\n'], 'max_input_tokens': 1280, 'best_of': 16, '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-v53-mkmlizer
Waiting for job on chaiml-exp-grpo-cp312-36146-v53-mkmlizer to finish
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ Version: 0.30.2 ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ https://mk1.ai ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ belonging to: ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ Chai Research Corp. ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ║ ║
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: Downloaded to shared memory in 86.220s
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: Checking if ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged already exists in ChaiML
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpdr268x0_, device:0
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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', '')
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: quantized model in 288.570s
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: Processed model ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged in 374.790s
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v53/nvidia
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v53/nvidia/config.json
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v53/nvidia/special_tokens_map.json
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v53/nvidia/tokenizer_config.json
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v53/nvidia/tokenizer.json
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v53/nvidia/flywheel_model.1.safetensors
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v53/nvidia/flywheel_model.0.safetensors
chaiml-exp-grpo-cp312-36146-v53-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:02<04:20, 1.38it/s] Loading 0: 1%| | 4/363 [00:04<06:44, 1.13s/it] Loading 0: 1%|▏ | 5/363 [00:06<08:28, 1.42s/it] Loading 0: 2%|▏ | 8/363 [00:06<03:55, 1.50it/s] Loading 0: 2%|▏ | 9/363 [00:06<03:26, 1.72it/s] Loading 0: 3%|▎ | 10/363 [00:06<02:47, 2.11it/s] Loading 0: 3%|▎ | 11/363 [00:07<02:27, 2.39it/s] Loading 0: 3%|▎ | 12/363 [00:07<02:02, 2.86it/s] Loading 0: 4%|▎ | 13/363 [00:09<04:38, 1.26it/s] Loading 0: 4%|▍ | 14/363 [00:11<06:32, 1.13s/it] Loading 0: 4%|▍ | 15/363 [00:13<08:03, 1.39s/it] Loading 0: 5%|▍ | 18/363 [00:13<03:54, 1.47it/s] Loading 0: 5%|▌ | 19/363 [00:13<03:13, 1.78it/s] Loading 0: 6%|▌ | 21/363 [00:15<04:06, 1.39it/s] Loading 0: 6%|▌ | 22/363 [00:17<05:35, 1.02it/s] Loading 0: 6%|▋ | 23/363 [00:19<06:56, 1.23s/it] Loading 0: 7%|▋ | 26/363 [00:20<03:43, 1.51it/s] Loading 0: 7%|▋ | 27/363 [00:20<03:16, 1.71it/s] Loading 0: 8%|▊ | 28/363 [00:20<02:41, 2.07it/s] Loading 0: 8%|▊ | 30/363 [00:20<01:57, 2.82it/s] Loading 0: 9%|▊ | 31/363 [00:20<01:48, 3.05it/s] Loading 0: 9%|▉ | 32/363 [00:21<01:32, 3.57it/s] Loading 0: 9%|▉ | 33/363 [00:21<01:19, 4.17it/s] Loading 0: 9%|▉ | 34/363 [00:23<03:49, 1.44it/s] Loading 0: 10%|▉ | 35/363 [00:25<05:42, 1.04s/it] Loading 0: 10%|▉ | 36/363 [00:27<07:11, 1.32s/it] Loading 0: 11%|█ | 39/363 [00:29<05:12, 1.04it/s] Loading 0: 11%|█ | 40/363 [00:31<06:18, 1.17s/it] Loading 0: 11%|█▏ | 41/363 [00:33<07:22, 1.37s/it] Loading 0: 12%|█▏ | 44/363 [00:33<03:58, 1.34it/s] Loading 0: 12%|█▏ | 45/363 [00:33<03:27, 1.53it/s] Loading 0: 13%|█▎ | 46/363 [00:33<02:50, 1.86it/s] Loading 0: 13%|█▎ | 48/363 [00:34<02:02, 2.58it/s] Loading 0: 13%|█▎ | 49/363 [00:34<01:52, 2.79it/s] Loading 0: 14%|█▍ | 50/363 [00:34<01:34, 3.32it/s] Loading 0: 14%|█▍ | 51/363 [00:34<01:20, 3.88it/s] Loading 0: 14%|█▍ | 52/363 [00:36<03:40, 1.41it/s] Loading 0: 15%|█▍ | 53/363 [00:38<05:26, 1.05s/it] Loading 0: 15%|█▍ | 54/363 [00:40<06:51, 1.33s/it] Loading 0: 16%|█▌ | 57/363 [00:42<04:55, 1.04it/s] Loading 0: 16%|█▌ | 58/363 [00:44<05:57, 1.17s/it] Loading 0: 16%|█▋ | 59/363 [00:46<06:57, 1.37s/it] Loading 0: 17%|█▋ | 62/363 [00:46<03:44, 1.34it/s] Loading 0: 17%|█▋ | 63/363 [00:47<03:13, 1.55it/s] Loading 0: 18%|█▊ | 64/363 [00:47<02:39, 1.88it/s] Loading 0: 18%|█▊ | 66/363 [00:47<01:54, 2.60it/s] Loading 0: 18%|█▊ | 67/363 [00:47<01:45, 2.81it/s] Loading 0: 19%|█▊ | 68/363 [00:47<01:28, 3.34it/s] Loading 0: 19%|█▉ | 69/363 [00:47<01:15, 3.91it/s] Loading 0: 19%|█▉ | 70/363 [00:49<03:27, 1.41it/s] Loading 0: 20%|█▉ | 71/363 [00:51<05:08, 1.06s/it] Loading 0: 20%|█▉ | 72/363 [00:54<06:28, 1.34s/it] Loading 0: 21%|██ | 75/363 [00:55<04:38, 1.03it/s] Loading 0: 21%|██ | 76/363 [00:57<05:36, 1.17s/it] Loading 0: 21%|██ | 77/363 [00:59<06:31, 1.37s/it] Loading 0: 22%|██▏ | 80/363 [01:00<03:31, 1.34it/s] Loading 0: 22%|██▏ | 81/363 [01:00<03:03, 1.53it/s] Loading 0: 23%|██▎ | 82/363 [01:00<02:31, 1.86it/s] Loading 0: 23%|██▎ | 84/363 [01:00<01:48, 2.57it/s] Loading 0: 23%|██▎ | 85/363 [01:01<01:39, 2.79it/s] Loading 0: 24%|██▎ | 86/363 [01:01<01:23, 3.31it/s] Loading 0: 24%|██▍ | 87/363 [01:01<01:10, 3.89it/s] Loading 0: 24%|██▍ | 88/363 [01:03<03:14, 1.41it/s] Loading 0: 25%|██▍ | 89/363 [01:05<04:48, 1.05s/it] Loading 0: 25%|██▍ | 90/363 [01:07<06:03, 1.33s/it] Loading 0: 26%|██▌ | 93/363 [01:07<02:57, 1.52it/s] Loading 0: 26%|██▌ | 94/363 [01:07<02:33, 1.75it/s] Loading 0: 26%|██▌ | 95/363 [01:08<02:05, 2.13it/s] Loading 0: 27%|██▋ | 97/363 [01:08<01:30, 2.94it/s] Loading 0: 27%|██▋ | 98/363 [01:08<01:24, 3.13it/s] Loading 0: 27%|██▋ | 99/363 [01:08<01:11, 3.70it/s] Loading 0: 28%|██▊ | 101/363 [01:10<02:27, 1.78it/s] Loading 0: 28%|██▊ | 102/363 [01:12<03:49, 1.14it/s] Loading 0: 28%|██▊ | 103/363 [01:14<05:02, 1.16s/it] Loading 0: 29%|██▉ | 105/363 [01:14<03:03, 1.40it/s] Loading 0: 29%|██▉ | 106/363 [01:16<04:16, 1.00it/s] Loading 0: 29%|██▉ | 107/363 [01:18<05:16, 1.24s/it] Loading 0: 30%|██▉ | 108/363 [01:20<06:08, 1.44s/it] Loading 0: 31%|███ | 111/363 [01:22<04:20, 1.03s/it] Loading 0: 31%|███ | 112/363 [01:24<05:06, 1.22s/it] Loading 0: 31%|███ | 113/363 [01:26<05:50, 1.40s/it] Loading 0: 32%|███▏ | 116/363 [01:27<03:10, 1.30it/s] Loading 0: 32%|███▏ | 117/363 [01:27<02:45, 1.49it/s] Loading 0: 33%|███▎ | 118/363 [01:27<02:15, 1.80it/s] Loading 0: 33%|███▎ | 120/363 [01:27<01:36, 2.51it/s] Loading 0: 33%|███▎ | 121/363 [01:28<01:28, 2.73it/s] Loading 0: 34%|███▎ | 122/363 [01:28<01:14, 3.24it/s] Loading 0: 34%|███▍ | 123/363 [01:28<01:03, 3.81it/s] Loading 0: 34%|███▍ | 124/363 [01:30<02:50, 1.40it/s] Loading 0: 34%|███▍ | 125/363 [01:32<04:11, 1.06s/it] Loading 0: 35%|███▍ | 126/363 [01:34<05:16, 1.34s/it] Loading 0: 36%|███▌ | 129/363 [01:36<03:46, 1.03it/s] Loading 0: 36%|███▌ | 130/363 [01:38<04:33, 1.17s/it] Loading 0: 36%|███▌ | 131/363 [01:40<05:18, 1.37s/it] Loading 0: 37%|███▋ | 134/363 [01:40<02:51, 1.34it/s] Loading 0: 37%|███▋ | 135/363 [01:40<02:28, 1.53it/s] Loading 0: 37%|███▋ | 136/363 [01:40<02:02, 1.86it/s] Loading 0: 38%|███▊ | 138/363 [01:41<01:28, 2.55it/s] Loading 0: 38%|███▊ | 139/363 [01:41<01:20, 2.77it/s] Loading 0: 39%|███▊ | 140/363 [01:41<01:07, 3.29it/s] Loading 0: 39%|███▉ | 141/363 [01:41<00:57, 3.86it/s] Loading 0: 39%|███▉ | 142/363 [01:43<02:37, 1.41it/s] Loading 0: 39%|███▉ | 143/363 [01:45<03:51, 1.05s/it] Loading 0: 40%|███▉ | 144/363 [01:47<04:51, 1.33s/it] Loading 0: 40%|████ | 147/363 [01:49<03:28, 1.04it/s] Loading 0: 41%|████ | 148/363 [01:51<04:12, 1.17s/it] Loading 0: 41%|████ | 149/363 [01:53<04:54, 1.38s/it] Loading 0: 42%|████▏ | 152/363 [01:54<02:37, 1.34it/s] Loading 0: 42%|████▏ | 153/363 [01:54<02:17, 1.53it/s] Loading 0: 42%|████▏ | 154/363 [01:54<01:52, 1.86it/s] Loading 0: 43%|████▎ | 156/363 [01:54<01:21, 2.55it/s] Loading 0: 43%|████▎ | 157/363 [01:55<01:14, 2.77it/s] Loading 0: 44%|████▎ | 158/363 [01:55<01:02, 3.29it/s] Loading 0: 44%|████▍ | 159/363 [01:55<00:52, 3.86it/s] Loading 0: 44%|████▍ | 160/363 [01:57<02:24, 1.41it/s] Loading 0: 44%|████▍ | 161/363 [01:59<03:33, 1.05s/it] Loading 0: 45%|████▍ | 162/363 [02:01<04:27, 1.33s/it] Loading 0: 45%|████▌ | 165/363 [02:03<03:11, 1.04it/s] Loading 0: 46%|████▌ | 166/363 [02:05<03:51, 1.17s/it] Loading 0: 46%|████▌ | 167/363 [02:07<04:29, 1.37s/it] Loading 0: 47%|████▋ | 170/363 [02:07<02:24, 1.34it/s] Loading 0: 47%|████▋ | 171/363 [02:07<02:05, 1.53it/s] Loading 0: 47%|████▋ | 172/363 [02:07<01:42, 1.86it/s] Loading 0: 48%|████▊ | 174/363 [02:08<01:14, 2.55it/s] Loading 0: 48%|████▊ | 175/363 [02:08<01:07, 2.77it/s] Loading 0: 48%|████▊ | 176/363 [02:08<00:56, 3.28it/s] Loading 0: 49%|████▉ | 177/363 [02:08<00:48, 3.85it/s] Loading 0: 49%|████▉ | 178/363 [02:10<02:11, 1.41it/s] Loading 0: 49%|████▉ | 179/363 [02:12<03:14, 1.05s/it] Loading 0: 50%|████▉ | 180/363 [02:14<04:03, 1.33s/it] Loading 0: 50%|█████ | 183/363 [02:16<02:53, 1.04it/s] Loading 0: 51%|█████ | 184/363 [02:18<03:29, 1.17s/it] Loading 0: 51%|█████ | 185/363 [02:20<04:04, 1.37s/it] Loading 0: 52%|█████▏ | 188/363 [02:21<02:10, 1.34it/s] Loading 0: 52%|█████▏ | 189/363 [02:21<01:53, 1.53it/s] Loading 0: 52%|█████▏ | 190/363 [02:21<01:33, 1.86it/s] Loading 0: 53%|█████▎ | 192/363 [02:21<01:06, 2.58it/s] Loading 0: 53%|█████▎ | 193/363 [02:21<01:00, 2.79it/s] Loading 0: 53%|█████▎ | 194/363 [02:22<00:51, 3.31it/s] Loading 0: 54%|█████▎ | 195/363 [02:22<00:43, 3.88it/s] Loading 0: 54%|█████▍ | 196/363 [02:24<01:58, 1.41it/s] Loading 0: 54%|█████▍ | 197/363 [02:26<02:54, 1.05s/it] Loading 0: 55%|█████▍ | 198/363 [02:28<03:39, 1.33s/it] Loading 0: 55%|█████▌ | 201/363 [02:30<02:36, 1.04it/s] Loading 0: 56%|█████▌ | 202/363 [02:32<03:08, 1.17s/it] Loading 0: 56%|█████▌ | 203/363 [02:34<03:39, 1.37s/it] Loading 0: 57%|█████▋ | 206/363 [02:34<01:57, 1.34it/s] Loading 0: 57%|█████▋ | 207/363 [02:34<01:41, 1.54it/s] Loading 0: 57%|█████▋ | 208/363 [02:34<01:23, 1.86it/s] Loading 0: 58%|█████▊ | 210/363 [02:35<00:59, 2.56it/s] Loading 0: 58%|█████▊ | 211/363 [02:35<00:54, 2.78it/s] Loading 0: 58%|█████▊ | 212/363 [02:35<00:45, 3.30it/s] Loading 0: 59%|█████▊ | 213/363 [02:35<00:38, 3.87it/s] Loading 0: 59%|█████▉ | 214/363 [02:37<01:45, 1.41it/s] Loading 0: 59%|█████▉ | 215/363 [02:39<02:35, 1.05s/it] Loading 0: 60%|█████▉ | 216/363 [02:41<03:14, 1.32s/it] Loading 0: 60%|██████ | 219/363 [02:43<02:18, 1.04it/s] Loading 0: 61%|██████ | 220/363 [02:45<02:47, 1.17s/it] Loading 0: 61%|██████ | 221/363 [02:47<03:14, 1.37s/it] Loading 0: 62%|██████▏ | 224/363 [02:47<01:43, 1.34it/s] Loading 0: 62%|██████▏ | 225/363 [02:48<01:29, 1.54it/s] Loading 0: 62%|██████▏ | 226/363 [02:48<01:13, 1.86it/s] Loading 0: 63%|██████▎ | 228/363 [02:48<00:53, 2.55it/s] Loading 0: 63%|██████▎ | 229/363 [02:48<00:48, 2.76it/s] Loading 0: 63%|██████▎ | 230/363 [02:48<00:40, 3.28it/s] Loading 0: 64%|██████▎ | 231/363 [02:49<00:34, 3.85it/s] Loading 0: 64%|██████▍ | 232/363 [02:51<01:32, 1.41it/s] Loading 0: 64%|██████▍ | 233/363 [02:52<02:16, 1.05s/it] Loading 0: 64%|██████▍ | 234/363 [02:55<02:50, 1.33s/it] Loading 0: 65%|██████▌ | 237/363 [02:56<02:01, 1.04it/s] Loading 0: 66%|██████▌ | 238/363 [02:58<02:26, 1.17s/it] Loading 0: 66%|██████▌ | 239/363 [03:01<02:50, 1.37s/it] Loading 0: 67%|██████▋ | 242/363 [03:01<01:30, 1.34it/s] Loading 0: 67%|██████▋ | 243/363 [03:01<01:18, 1.54it/s] Loading 0: 67%|██████▋ | 244/363 [03:01<01:03, 1.86it/s] Loading 0: 68%|██████▊ | 246/363 [03:02<00:45, 2.55it/s] Loading 0: 68%|██████▊ | 247/363 [03:02<00:41, 2.77it/s] Loading 0: 68%|██████▊ | 248/363 [03:02<00:34, 3.29it/s] Loading 0: 69%|██████▊ | 249/363 [03:02<00:29, 3.87it/s] Loading 0: 69%|██████▉ | 250/363 [03:04<01:20, 1.41it/s] Loading 0: 69%|██████▉ | 251/363 [03:06<01:57, 1.05s/it] Loading 0: 69%|██████▉ | 252/363 [03:08<02:27, 1.33s/it] Loading 0: 70%|███████ | 255/363 [03:10<01:43, 1.04it/s] Loading 0: 71%|███████ | 256/363 [03:12<02:05, 1.17s/it] Loading 0: 71%|███████ | 257/363 [03:14<02:25, 1.37s/it] Loading 0: 72%|███████▏ | 260/363 [03:14<01:16, 1.34it/s] Loading 0: 72%|███████▏ | 261/363 [03:15<01:06, 1.54it/s] Loading 0: 72%|███████▏ | 262/363 [03:15<00:54, 1.87it/s] Loading 0: 73%|███████▎ | 264/363 [03:15<00:38, 2.56it/s] Loading 0: 73%|███████▎ | 265/363 [03:15<00:35, 2.77it/s] Loading 0: 73%|███████▎ | 266/363 [03:15<00:29, 3.29it/s] Loading 0: 74%|███████▎ | 267/363 [03:15<00:24, 3.89it/s] Loading 0: 74%|███████▍ | 268/363 [03:17<01:07, 1.42it/s] Loading 0: 74%|███████▍ | 269/363 [03:19<01:38, 1.05s/it] Loading 0: 74%|███████▍ | 270/363 [03:21<02:03, 1.33s/it] Loading 0: 75%|███████▌ | 273/363 [03:37<05:02, 3.36s/it] Loading 0: 75%|███████▌ | 274/363 [03:38<04:33, 3.07s/it] Loading 0: 76%|███████▌ | 275/363 [03:41<04:10, 2.85s/it] Loading 0: 77%|███████▋ | 278/363 [03:41<02:07, 1.50s/it] Loading 0: 77%|███████▋ | 279/363 [03:41<01:45, 1.25s/it] Loading 0: 77%|███████▋ | 280/363 [03:41<01:23, 1.01s/it] Loading 0: 78%|███████▊ | 282/363 [03:42<00:55, 1.47it/s] Loading 0: 78%|███████▊ | 283/363 [03:42<00:46, 1.72it/s] Loading 0: 78%|███████▊ | 284/363 [03:42<00:37, 2.11it/s] Loading 0: 79%|███████▊ | 285/363 [03:42<00:30, 2.60it/s] Loading 0: 79%|███████▉ | 286/363 [03:44<01:01, 1.25it/s] Loading 0: 79%|███████▉ | 287/363 [03:46<01:25, 1.12s/it] Loading 0: 79%|███████▉ | 288/363 [03:48<01:43, 1.38s/it] Loading 0: 80%|████████ | 291/363 [03:50<01:11, 1.01it/s] Loading 0: 80%|████████ | 292/363 [03:52<01:24, 1.19s/it] Loading 0: 81%|████████ | 293/363 [03:54<01:36, 1.38s/it] Loading 0: 82%|████████▏ | 296/363 [03:54<00:49, 1.35it/s] Loading 0: 82%|████████▏ | 297/363 [03:54<00:42, 1.55it/s] Loading 0: 82%|████████▏ | 298/363 [03:55<00:34, 1.88it/s] Loading 0: 83%|████████▎ | 300/363 [03:55<00:24, 2.61it/s] Loading 0: 83%|████████▎ | 301/363 [03:55<00:21, 2.84it/s] Loading 0: 83%|████████▎ | 302/363 [03:55<00:18, 3.37it/s] Loading 0: 83%|████████▎ | 303/363 [03:55<00:15, 3.98it/s] Loading 0: 84%|████████▎ | 304/363 [03:57<00:41, 1.43it/s] Loading 0: 84%|████████▍ | 305/363 [03:59<01:00, 1.05s/it] Loading 0: 84%|████████▍ | 306/363 [04:01<01:15, 1.33s/it] Loading 0: 85%|████████▌ | 309/363 [04:03<00:51, 1.04it/s] Loading 0: 85%|████████▌ | 310/363 [04:05<01:01, 1.17s/it] Loading 0: 86%|████████▌ | 311/363 [04:07<01:11, 1.37s/it] Loading 0: 87%|████████▋ | 314/363 [04:08<00:36, 1.35it/s] Loading 0: 87%|████████▋ | 315/363 [04:08<00:30, 1.56it/s] Loading 0: 87%|████████▋ | 316/363 [04:08<00:24, 1.89it/s] Loading 0: 88%|████████▊ | 318/363 [04:08<00:17, 2.62it/s] Loading 0: 88%|████████▊ | 319/363 [04:08<00:15, 2.89it/s] Loading 0: 88%|████████▊ | 320/363 [04:08<00:12, 3.42it/s] Loading 0: 88%|████████▊ | 321/363 [04:09<00:10, 3.99it/s] Loading 0: 89%|████████▊ | 322/363 [04:11<00:28, 1.42it/s] Loading 0: 89%|████████▉ | 323/363 [04:13<00:41, 1.05s/it] Loading 0: 89%|████████▉ | 324/363 [04:15<00:51, 1.32s/it] Loading 0: 90%|█████████ | 327/363 [04:17<00:34, 1.04it/s] Loading 0: 90%|█████████ | 328/363 [04:19<00:40, 1.17s/it] Loading 0: 91%|█████████ | 329/363 [04:21<00:46, 1.37s/it] Loading 0: 91%|█████████▏| 332/363 [04:21<00:22, 1.35it/s] Loading 0: 92%|█████████▏| 333/363 [04:21<00:19, 1.55it/s] Loading 0: 92%|█████████▏| 334/363 [04:21<00:15, 1.88it/s] Loading 0: 93%|█████████▎| 336/363 [04:21<00:10, 2.61it/s] Loading 0: 93%|█████████▎| 337/363 [04:22<00:09, 2.83it/s] Loading 0: 93%|█████████▎| 338/363 [04:22<00:07, 3.29it/s] Loading 0: 93%|█████████▎| 339/363 [04:22<00:06, 3.86it/s] Loading 0: 94%|█████████▎| 340/363 [04:24<00:16, 1.41it/s] Loading 0: 94%|█████████▍| 341/363 [04:26<00:23, 1.05s/it] Loading 0: 94%|█████████▍| 342/363 [04:28<00:27, 1.33s/it] Loading 0: 95%|█████████▌| 345/363 [04:30<00:17, 1.03it/s] Loading 0: 95%|█████████▌| 346/363 [04:32<00:19, 1.17s/it] Loading 0: 96%|█████████▌| 347/363 [04:34<00:21, 1.37s/it] Loading 0: 96%|█████████▋| 350/363 [04:34<00:09, 1.34it/s] Loading 0: 97%|█████████▋| 351/363 [04:35<00:07, 1.54it/s] Loading 0: 97%|█████████▋| 352/363 [04:35<00:05, 1.87it/s] Loading 0: 98%|█████████▊| 354/363 [04:35<00:03, 2.57it/s] Loading 0: 98%|█████████▊| 355/363 [04:35<00:02, 2.80it/s] Loading 0: 98%|█████████▊| 356/363 [04:35<00:02, 3.30it/s] Loading 0: 98%|█████████▊| 357/363 [04:36<00:02, 2.98it/s] Loading 0: 99%|█████████▉| 359/363 [04:38<00:02, 1.62it/s] Loading 0: 99%|█████████▉| 360/363 [04:40<00:02, 1.08it/s] Loading 0: 99%|█████████▉| 361/363 [04:42<00:02, 1.20s/it]
Job chaiml-exp-grpo-cp312-36146-v53-mkmlizer completed after 459.55s with status: succeeded
Stopping job with name chaiml-exp-grpo-cp312-36146-v53-mkmlizer
Pipeline stage MKMLizer completed in 460.18s
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-exp-grpo-cp312-36146-v53
Waiting for inference service chaiml-exp-grpo-cp312-36146-v53 to be ready
Inference service chaiml-exp-grpo-cp312-36146-v53 ready after 60.352354526519775s
Pipeline stage MKMLDeployer completed in 61.35s
run pipeline stage %s
Running pipeline stage StressChecker
{"detail":"HTTPConnectionPool(host='chaiml-llama31-mer-v2-44570-v27-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)"}
Received unhealthy response to inference request!
{"detail":"HTTPConnectionPool(host='chaiml-llama31-mer-v2-44570-v27-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)"}
Received unhealthy response to inference request!
{"detail":"HTTPConnectionPool(host='chaiml-llama31-mer-v2-44570-v27-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)"}
Received unhealthy response to inference request!
{"detail":"HTTPConnectionPool(host='chaiml-llama31-mer-v2-44570-v27-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)"}
Received unhealthy response to inference request!
{"detail":"HTTPConnectionPool(host='chaiml-llama31-mer-v2-44570-v27-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)"}
Received unhealthy response to inference request!
5 requests
5 failed requests
5th percentile: 13.912455749511718
10th percentile: 13.914543533325196
20th percentile: 13.91871910095215
30th percentile: 13.968413925170898
40th percentile: 14.063628005981446
50th percentile: 14.158842086791992
60th percentile: 14.280485534667969
70th percentile: 14.402128982543946
80th percentile: 14.469955778121948
90th percentile: 14.483965921401978
95th percentile: 14.490970993041993
99th percentile: 14.496575050354004
mean time: 14.19018874168396
%s, retrying in %s seconds...
{"detail":"HTTPConnectionPool(host='chaiml-llama31-mer-v2-44570-v27-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)"}
Received unhealthy response to inference request!
{"detail":"HTTPConnectionPool(host='chaiml-llama31-mer-v2-44570-v27-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)"}
Received unhealthy response to inference request!
{"detail":"HTTPConnectionPool(host='chaiml-llama31-mer-v2-44570-v27-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)"}
Received unhealthy response to inference request!
{"detail":"HTTPConnectionPool(host='chaiml-llama31-mer-v2-44570-v27-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)"}
Received unhealthy response to inference request!
Received healthy response to inference request in 7.143011569976807s
5 requests
4 failed requests
5th percentile: 8.504571628570556
10th percentile: 9.866131687164307
20th percentile: 12.589251804351807
30th percentile: 14.002259159088135
40th percentile: 14.10515375137329
50th percentile: 14.208048343658447
60th percentile: 14.286520385742188
70th percentile: 14.364992427825928
80th percentile: 14.431649732589722
90th percentile: 14.48649230003357
95th percentile: 14.513913583755492
99th percentile: 14.535850610733032
mean time: 12.849487018585204
%s, retrying in %s seconds...
Received healthy response to inference request in 1.914273738861084s
Received healthy response to inference request in 2.0085766315460205s
Received healthy response to inference request in 2.594057321548462s
Received healthy response to inference request in 2.1165876388549805s
Received healthy response to inference request in 1.8425636291503906s
5 requests
0 failed requests
5th percentile: 1.8569056510925293
10th percentile: 1.8712476730346679
20th percentile: 1.8999317169189454
30th percentile: 1.9331343173980713
40th percentile: 1.970855474472046
50th percentile: 2.0085766315460205
60th percentile: 2.0517810344696046
70th percentile: 2.0949854373931887
80th percentile: 2.2120815753936767
90th percentile: 2.4030694484710695
95th percentile: 2.4985633850097657
99th percentile: 2.574958534240723
mean time: 2.0952117919921873
Pipeline stage StressChecker completed in 149.54s
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 0.64s
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 0.66s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v53 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v53-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v53-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 2890.14s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v53 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp-grpo-cp312-_36146_v53 status is now torndown due to DeploymentManager action