rirv938-mistral-24b-grp_30204

developer_uid: rirv938

submission_id: rirv938-mistral-24b-grp_30204_v1

model_name: rirv938-mistral-24b-grp_30204_v1

model_group: rirv938/mistral_24b_grpo

status: torndown

timestamp: 2025-04-29T17:20:07+00:00

num_battles: 6181

num_wins: 3221

celo_rating: 1322.55

family_friendly_score: 0.5449999999999999

family_friendly_standard_error: 0.0070423717595707765

submission_type: basic

model_repo: rirv938/mistral_24b_grpo_40k_cp592_95ff_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5481953118243885, 'latency_mean': 1.824052027463913, 'latency_p50': 1.8182893991470337, 'latency_p90': 2.0249824285507203}, {'batch_size': 4, 'throughput': 1.3728213813012937, 'latency_mean': 2.905943270921707, 'latency_p50': 2.9133516550064087, 'latency_p90': 3.2090110778808594}, {'batch_size': 5, 'throughput': 1.5176645804723707, 'latency_mean': 3.278971310853958, 'latency_p50': 3.270708680152893, 'latency_p90': 3.670007753372192}, {'batch_size': 8, 'throughput': 1.8468040493743514, 'latency_mean': 4.297327629327774, 'latency_p50': 4.31901216506958, 'latency_p90': 4.811813020706176}, {'batch_size': 10, 'throughput': 1.9822423851851894, 'latency_mean': 4.994623479843139, 'latency_p50': 4.989474058151245, 'latency_p90': 5.7275807619094845}, {'batch_size': 12, 'throughput': 2.0405924004904676, 'latency_mean': 5.809320353269577, 'latency_p50': 5.882104277610779, 'latency_p90': 6.511421036720276}, {'batch_size': 15, 'throughput': 2.1029627489456804, 'latency_mean': 7.01272219657898, 'latency_p50': 7.0352360010147095, 'latency_p90': 7.98844850063324}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: rirv938-mistral-24b-grp_30204_v1

is_internal_developer: True

language_model: rirv938/mistral_24b_grpo_40k_cp592_95ff_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.69

us_pacific_date: 2025-04-29

win_ratio: 0.521113088497007

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.2, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['You:', '</s>', '\n', '###'], 'max_input_tokens': 768, '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 rirv938-mistral-24b-grp-30204-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-grp-30204-v1-mkmlizer to finish
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-grp-30204-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-grp-30204-v1-mkmlizer: Downloaded to shared memory in 171.692s
rirv938-mistral-24b-grp-30204-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmps6hlsn3_, device:0
rirv938-mistral-24b-grp-30204-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-grp-30204-v1-mkmlizer: quantized model in 66.298s
rirv938-mistral-24b-grp-30204-v1-mkmlizer: Processed model rirv938/mistral_24b_grpo_40k_cp592_95ff_merged in 237.990s
rirv938-mistral-24b-grp-30204-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-grp-30204-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-grp-30204-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-grp-30204-v1
rirv938-mistral-24b-grp-30204-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-30204-v1/config.json
rirv938-mistral-24b-grp-30204-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-30204-v1/special_tokens_map.json
rirv938-mistral-24b-grp-30204-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-30204-v1/tokenizer_config.json
rirv938-mistral-24b-grp-30204-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-30204-v1/tokenizer.json
rirv938-mistral-24b-grp-30204-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-grp-30204-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-grp-30204-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-grp-30204-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-grp-30204-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.72it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:27, 13.09it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:19, 18.49it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:27, 12.76it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:32, 10.67it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 15.34it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:22, 15.10it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:23, 14.36it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.40it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.79it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.53it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:23, 13.87it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:22, 14.72it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:26, 11.95it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 17.86it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:14, 21.19it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.50it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:20, 15.17it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:22, 13.67it/s]
Loading 0:  17%|█▋        | 60/363 [00:04<00:22, 13.34it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 17.69it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.52it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.97it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.83it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:20, 14.12it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:21, 13.23it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.20it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.30it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:19, 14.31it/s]
Loading 0:  25%|██▌       | 91/363 [00:05<00:20, 13.52it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.46it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 20.99it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.34it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:18, 14.21it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 13.22it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:19, 12.78it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.69it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 11.31it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.39it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.56it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.10it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.48it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.40it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:19, 11.67it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.57it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 20.80it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.44it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:14, 15.14it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:15, 13.57it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:16, 13.11it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:12, 17.07it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 20.52it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 14.27it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 13.58it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:13, 14.41it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:16, 11.92it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:10, 17.76it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 21.00it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.73it/s]
Loading 0:  50%|████▉     | 181/363 [00:11<00:13, 13.73it/s]
Loading 0:  50%|█████     | 183/363 [00:11<00:12, 14.62it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:14, 11.97it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.79it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 21.07it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.96it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 15.46it/s]
Loading 0:  56%|█████▌    | 202/363 [00:28<04:25,  1.65s/it]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:53,  1.46s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:12,  1.18it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:31,  1.67it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:06,  2.25it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:54,  2.73it/s]
Loading 0:  60%|█████▉    | 217/363 [00:29<00:43,  3.33it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:34,  4.22it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:29,  4.78it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:16,  8.44it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:11, 11.49it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:12, 10.23it/s]
Loading 0:  65%|██████▍   | 235/363 [00:30<00:12, 10.45it/s]
Loading 0:  65%|██████▌   | 237/363 [00:30<00:10, 11.53it/s]
Loading 0:  66%|██████▌   | 239/363 [00:30<00:12, 10.18it/s]
Loading 0:  67%|██████▋   | 244/363 [00:31<00:07, 15.83it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:06, 18.92it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:07, 14.04it/s]
Loading 0:  70%|██████▉   | 253/363 [00:31<00:08, 13.39it/s]
Loading 0:  70%|███████   | 255/363 [00:31<00:07, 14.18it/s]
Loading 0:  71%|███████   | 257/363 [00:32<00:08, 11.79it/s]
Loading 0:  72%|███████▏  | 262/363 [00:32<00:05, 17.65it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:04, 21.27it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:06, 15.16it/s]
Loading 0:  75%|███████▍  | 272/363 [00:32<00:05, 15.72it/s]
Loading 0:  75%|███████▌  | 274/363 [00:33<00:06, 13.94it/s]
Loading 0:  76%|███████▌  | 276/363 [00:33<00:06, 13.37it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 17.61it/s]
Loading 0:  78%|███████▊  | 284/363 [00:33<00:03, 21.00it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 14.58it/s]
Loading 0:  80%|███████▉  | 289/363 [00:33<00:05, 13.18it/s]
Loading 0:  80%|████████  | 291/363 [00:34<00:05, 14.12it/s]
Loading 0:  81%|████████  | 293/363 [00:34<00:06, 11.44it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:03, 17.24it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:02, 20.52it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:04, 14.46it/s]
Loading 0:  85%|████████▍ | 307/363 [00:35<00:04, 13.60it/s]
Loading 0:  85%|████████▌ | 309/363 [00:35<00:03, 14.39it/s]
Loading 0:  86%|████████▌ | 311/363 [00:35<00:04, 11.74it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 17.64it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:02, 20.91it/s]
Loading 0:  89%|████████▉ | 323/363 [00:36<00:02, 14.66it/s]
Loading 0:  90%|████████▉ | 326/363 [00:36<00:02, 15.28it/s]
Loading 0:  90%|█████████ | 328/363 [00:36<00:02, 13.67it/s]
Loading 0:  91%|█████████ | 330/363 [00:36<00:02, 13.12it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 17.08it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 20.56it/s]
Loading 0:  94%|█████████▍| 341/363 [00:37<00:01, 14.41it/s]
Loading 0:  94%|█████████▍| 343/363 [00:37<00:01, 13.73it/s]
Loading 0:  95%|█████████▌| 345/363 [00:37<00:01, 14.47it/s]
Loading 0:  96%|█████████▌| 347/363 [00:37<00:01, 11.91it/s]
Loading 0:  97%|█████████▋| 352/363 [00:38<00:00, 17.80it/s]
Loading 0:  98%|█████████▊| 356/363 [00:38<00:00, 21.04it/s]
Loading 0:  99%|█████████▉| 359/363 [00:45<00:02,  1.47it/s]
Loading 0:  99%|█████████▉| 361/363 [00:45<00:01,  1.75it/s]
                                                            
Job rirv938-mistral-24b-grp-30204-v1-mkmlizer completed after 288.87s with status: succeeded
Stopping job with name rirv938-mistral-24b-grp-30204-v1-mkmlizer
Pipeline stage MKMLizer completed in 289.33s
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 rirv938-mistral-24b-grp-30204-v1
Waiting for inference service rirv938-mistral-24b-grp-30204-v1 to be ready
Inference service rirv938-mistral-24b-grp-30204-v1 ready after 140.46925854682922s
Pipeline stage MKMLDeployer completed in 140.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7387585639953613s
Received healthy response to inference request in 2.0594358444213867s
Received healthy response to inference request in 2.2933077812194824s
Received healthy response to inference request in 2.117170810699463s
Received healthy response to inference request in 1.9538934230804443s
5 requests
0 failed requests
5th percentile: 1.975001907348633
10th percentile: 1.9961103916168212
20th percentile: 2.038327360153198
30th percentile: 2.070982837677002
40th percentile: 2.0940768241882326
50th percentile: 2.117170810699463
60th percentile: 2.187625598907471
70th percentile: 2.2580803871154784
80th percentile: 2.3823979377746585
90th percentile: 2.5605782508850097
95th percentile: 2.6496684074401853
99th percentile: 2.720940532684326
mean time: 2.2325132846832276
Pipeline stage StressChecker completed in 12.64s
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 0.86s
Shutdown handler de-registered
rirv938-mistral-24b-grp_30204_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 0.12s
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 rirv938-mistral-24b-grp-30204-v1-profiler
Waiting for inference service rirv938-mistral-24b-grp-30204-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 2886.96s
Shutdown handler de-registered
rirv938-mistral-24b-grp_30204_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-grp_30204_v1 status is now torndown due to DeploymentManager action