chaiml-slerpv5-reward-d_98061

developer_uid: rirv938
submission_id: chaiml-slerpv5-reward-d_98061_v1
model_name: chaiml-slerpv5-reward-d_98061_v1
model_group: ChaiML/slerpv5_reward_dp
status: torndown
timestamp: 2025-06-12T01:14:25+00:00
num_battles: 8661
num_wins: 4586
celo_rating: 1306.51
family_friendly_score: 0.5724
family_friendly_standard_error: 0.006996545433283485
submission_type: basic
model_repo: ChaiML/slerpv5_reward_dpo_rl_ff
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-slerpv5-reward-d_98061_v1
is_internal_developer: True
language_model: ChaiML/slerpv5_reward_dpo_rl_ff
model_size: 24B
ranking_group: single
us_pacific_date: 2025-06-11
win_ratio: 0.5295000577300543
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>', '\n', '<|im_end|>', 'User:', '</s>', 'You:', 'Bot:', '####'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly\n', 'prompt_template': '', '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-slerpv5-reward-d-98061-v1-mkmlizer
Waiting for job on chaiml-slerpv5-reward-d-98061-v1-mkmlizer to finish
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║                                                                     ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║                                                                     ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║  Version: 0.27.1+vampire_v3                                         ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║                                                                     ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║                                                                     ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ║                                                                     ║
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-20250611-retune-u_1558_v2: HTTPConnectionPool(host='chaiml-20250611-retune-u-1558-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: Downloaded to shared memory in 429.494s
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpc7lp8u31, device:0
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: quantized model in 59.568s
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: Processed model ChaiML/slerpv5_reward_dpo_rl_ff in 489.063s
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-slerpv5-reward-d-98061-v1
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-slerpv5-reward-d-98061-v1/config.json
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-slerpv5-reward-d-98061-v1/special_tokens_map.json
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-slerpv5-reward-d-98061-v1/tokenizer_config.json
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-slerpv5-reward-d-98061-v1/tokenizer.json
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-slerpv5-reward-d-98061-v1/flywheel_model.1.safetensors
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-slerpv5-reward-d-98061-v1/flywheel_model.0.safetensors
chaiml-slerpv5-reward-d-98061-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 28.53it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.46it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 19.95it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:27, 12.85it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:32, 10.61it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 15.09it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:23, 14.58it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:27, 12.48it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:20, 16.40it/s]
Loading 0:   9%|▉         | 32/363 [00:02<00:16, 19.75it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:24, 13.44it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:25, 12.70it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:23, 13.56it/s]
Loading 0:  11%|█▏        | 41/363 [00:03<00:29, 11.09it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:19, 16.51it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 19.75it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:22, 13.68it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:23, 12.87it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:22, 13.73it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:26, 11.27it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 16.78it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 19.93it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:21, 13.75it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:22, 13.01it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:20, 13.90it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:25, 11.27it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 16.69it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:14, 19.73it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:19, 13.71it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:21, 12.92it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:16, 16.43it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:13, 19.53it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:14, 18.23it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:19, 13.49it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:20, 12.70it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.36it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.33it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 10.92it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:14, 16.61it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:12, 19.51it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:17, 13.92it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.29it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.20it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:20, 11.34it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:13, 16.92it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:11, 20.05it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.12it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:16, 13.43it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:15, 14.30it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:18, 11.66it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 17.22it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:10, 20.39it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 14.41it/s]
Loading 0:  45%|████▍     | 163/363 [00:11<00:14, 13.65it/s]
Loading 0:  45%|████▌     | 165/363 [00:11<00:13, 14.46it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:16, 11.74it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:10, 17.38it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 20.42it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:12, 14.37it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:13, 13.49it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:12, 14.40it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:15, 11.65it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.35it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.51it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:11, 14.13it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:12, 13.38it/s]
Loading 0:  55%|█████▌    | 201/363 [00:28<04:46,  1.77s/it]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:39,  1.37s/it]
Loading 0:  57%|█████▋    | 207/363 [00:29<02:07,  1.22it/s]
Loading 0:  58%|█████▊    | 210/363 [00:29<01:29,  1.72it/s]
Loading 0:  59%|█████▊    | 213/363 [00:29<01:05,  2.28it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:53,  2.77it/s]
Loading 0:  60%|█████▉    | 217/363 [00:29<00:43,  3.37it/s]
Loading 0:  60%|██████    | 219/363 [00:30<00:33,  4.28it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:29,  4.86it/s]
Loading 0:  62%|██████▏   | 226/363 [00:30<00:16,  8.56it/s]
Loading 0:  63%|██████▎   | 230/363 [00:30<00:11, 11.66it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:12, 10.56it/s]
Loading 0:  65%|██████▌   | 236/363 [00:31<00:10, 11.84it/s]
Loading 0:  66%|██████▌   | 238/363 [00:31<00:10, 11.40it/s]
Loading 0:  66%|██████▌   | 240/363 [00:31<00:10, 11.50it/s]
Loading 0:  67%|██████▋   | 244/363 [00:31<00:07, 15.52it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:06, 18.97it/s]
Loading 0:  69%|██████▉   | 251/363 [00:32<00:07, 14.07it/s]
Loading 0:  70%|██████▉   | 253/363 [00:32<00:08, 13.60it/s]
Loading 0:  70%|███████   | 255/363 [00:32<00:07, 14.60it/s]
Loading 0:  71%|███████   | 257/363 [00:32<00:08, 11.93it/s]
Loading 0:  72%|███████▏  | 262/363 [00:32<00:05, 17.78it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:04, 20.62it/s]
Loading 0:  74%|███████▍  | 269/363 [00:33<00:06, 14.86it/s]
Loading 0:  75%|███████▍  | 271/363 [00:33<00:06, 14.16it/s]
Loading 0:  75%|███████▌  | 273/363 [00:33<00:05, 15.07it/s]
Loading 0:  76%|███████▌  | 275/363 [00:33<00:07, 12.25it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 17.84it/s]
Loading 0:  78%|███████▊  | 284/363 [00:33<00:03, 21.23it/s]
Loading 0:  79%|███████▉  | 287/363 [00:34<00:05, 15.02it/s]
Loading 0:  80%|███████▉  | 290/363 [00:34<00:04, 15.81it/s]
Loading 0:  80%|████████  | 292/363 [00:34<00:04, 14.21it/s]
Loading 0:  81%|████████  | 294/363 [00:34<00:05, 13.65it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:03, 17.65it/s]
Loading 0:  83%|████████▎ | 302/363 [00:35<00:02, 21.20it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:03, 14.95it/s]
Loading 0:  85%|████████▍ | 307/363 [00:35<00:03, 14.36it/s]
Loading 0:  85%|████████▌ | 309/363 [00:35<00:03, 15.21it/s]
Loading 0:  86%|████████▌ | 311/363 [00:35<00:04, 12.07it/s]
Loading 0:  87%|████████▋ | 316/363 [00:36<00:02, 18.01it/s]
Loading 0:  88%|████████▊ | 320/363 [00:36<00:02, 21.40it/s]
Loading 0:  89%|████████▉ | 323/363 [00:36<00:02, 14.39it/s]
Loading 0:  90%|████████▉ | 326/363 [00:36<00:02, 15.03it/s]
Loading 0:  90%|█████████ | 328/363 [00:36<00:02, 13.18it/s]
Loading 0:  91%|█████████ | 330/363 [00:37<00:02, 12.67it/s]
Loading 0:  92%|█████████▏| 334/363 [00:37<00:01, 16.89it/s]
Loading 0:  93%|█████████▎| 338/363 [00:37<00:01, 20.46it/s]
Loading 0:  94%|█████████▍| 341/363 [00:37<00:01, 13.32it/s]
Loading 0:  94%|█████████▍| 343/363 [00:38<00:01, 12.95it/s]
Loading 0:  95%|█████████▌| 345/363 [00:38<00:01, 13.84it/s]
Loading 0:  96%|█████████▌| 347/363 [00:38<00:01, 11.33it/s]
Loading 0:  97%|█████████▋| 352/363 [00:38<00:00, 17.26it/s]
Loading 0:  98%|█████████▊| 356/363 [00:38<00:00, 20.69it/s]
Loading 0:  99%|█████████▉| 359/363 [00:39<00:00, 10.41it/s]
Loading 0:  99%|█████████▉| 361/363 [00:39<00:00,  9.73it/s]
                                                            
Job chaiml-slerpv5-reward-d-98061-v1-mkmlizer completed after 513.62s with status: succeeded
Stopping job with name chaiml-slerpv5-reward-d-98061-v1-mkmlizer
Pipeline stage MKMLizer completed in 514.16s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-slerpv5-reward-d-98061-v1
Waiting for inference service chaiml-slerpv5-reward-d-98061-v1 to be ready
Inference service chaiml-slerpv5-reward-d-98061-v1 ready after 110.45704054832458s
Pipeline stage MKMLDeployer completed in 111.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6337826251983643s
Received healthy response to inference request in 2.067610263824463s
Received healthy response to inference request in 1.8725309371948242s
Received healthy response to inference request in 1.9984865188598633s
Received healthy response to inference request in 2.1277265548706055s
5 requests
0 failed requests
5th percentile: 1.897722053527832
10th percentile: 1.92291316986084
20th percentile: 1.9732954025268554
30th percentile: 2.012311267852783
40th percentile: 2.039960765838623
50th percentile: 2.067610263824463
60th percentile: 2.09165678024292
70th percentile: 2.115703296661377
80th percentile: 2.228937768936157
90th percentile: 2.431360197067261
95th percentile: 2.5325714111328126
99th percentile: 2.613540382385254
mean time: 2.140027379989624
Pipeline stage StressChecker completed in 12.38s
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 0.72s
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 0.71s
Shutdown handler de-registered
chaiml-slerpv5-reward-d_98061_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 0.14s
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-slerpv5-reward-d-98061-v1-profiler
Waiting for inference service chaiml-slerpv5-reward-d-98061-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3002.97s
Shutdown handler de-registered
chaiml-slerpv5-reward-d_98061_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-slerpv5-reward-d_98061_v1 status is now protected due to ABTestQueueItem
chaiml-slerpv5-reward-d_98061_v1 status is now inactive due to ABTestQueueItem
chaiml-slerpv5-reward-d_98061_v1 status is now torndown due to DeploymentManager action