developer_uid: rirv938
submission_id: rirv938-mistral-24b-grp_36770_v1
model_name: rirv938-mistral-24b-grp_36770_v1
model_group: rirv938/mistral_24b_grpo
status: torndown
timestamp: 2025-04-29T01:12:52+00:00
num_battles: 10014
num_wins: 5307
celo_rating: 1309.0
family_friendly_score: 0.5916
family_friendly_standard_error: 0.006951394680206268
submission_type: basic
model_repo: rirv938/mistral_24b_grpo_40k_cp296_92ff_merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5280049901289484, 'latency_mean': 1.8938670456409454, 'latency_p50': 1.8935308456420898, 'latency_p90': 2.0768609046936035}, {'batch_size': 3, 'throughput': 1.0901954231200148, 'latency_mean': 2.739693092107773, 'latency_p50': 2.750479817390442, 'latency_p90': 2.990677738189697}, {'batch_size': 5, 'throughput': 1.403717074274546, 'latency_mean': 3.533731541633606, 'latency_p50': 3.5262417793273926, 'latency_p90': 3.916527771949768}, {'batch_size': 6, 'throughput': 1.5164692852632324, 'latency_mean': 3.933795644044876, 'latency_p50': 3.9433590173721313, 'latency_p90': 4.41655478477478}, {'batch_size': 8, 'throughput': 1.6708927948189984, 'latency_mean': 4.757147077322006, 'latency_p50': 4.7055017948150635, 'latency_p90': 5.3490437269210815}, {'batch_size': 10, 'throughput': 1.753188258296278, 'latency_mean': 5.6483115339279175, 'latency_p50': 5.6289896965026855, 'latency_p90': 6.284256076812744}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-mistral-24b-grp_36770_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_grpo_40k_cp296_92ff_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.46
us_pacific_date: 2025-04-28
win_ratio: 0.5299580587177951
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': ['###', '\n', 'You:', '</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 rirv938-mistral-24b-grp-36770-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-grp-36770-v1-mkmlizer to finish
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ /___/ ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ belonging to: ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ║ ║
rirv938-mistral-24b-grp-36770-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-grp-36770-v1-mkmlizer: Downloaded to shared memory in 166.655s
rirv938-mistral-24b-grp-36770-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5k5bydzo, device:0
rirv938-mistral-24b-grp-36770-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-grp-36770-v1-mkmlizer: quantized model in 60.360s
rirv938-mistral-24b-grp-36770-v1-mkmlizer: Processed model rirv938/mistral_24b_grpo_40k_cp296_92ff_merged in 227.016s
rirv938-mistral-24b-grp-36770-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-grp-36770-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-grp-36770-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v1
rirv938-mistral-24b-grp-36770-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v1/config.json
rirv938-mistral-24b-grp-36770-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v1/special_tokens_map.json
rirv938-mistral-24b-grp-36770-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v1/tokenizer_config.json
rirv938-mistral-24b-grp-36770-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v1/tokenizer.json
rirv938-mistral-24b-grp-36770-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-grp-36770-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-grp-36770-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-grp-36770-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:15, 22.55it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:18, 19.30it/s] Loading 0: 3%|▎ | 11/363 [00:00<00:15, 23.12it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:23, 14.57it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:24, 14.19it/s] Loading 0: 6%|▌ | 21/363 [00:01<00:19, 17.97it/s] Loading 0: 6%|▋ | 23/363 [00:01<00:23, 14.40it/s] Loading 0: 8%|▊ | 29/363 [00:01<00:15, 22.12it/s] Loading 0: 9%|▉ | 33/363 [00:01<00:16, 20.04it/s] Loading 0: 10%|▉ | 36/363 [00:02<00:21, 15.36it/s] Loading 0: 11%|█ | 40/363 [00:02<00:19, 16.88it/s] Loading 0: 12%|█▏ | 43/363 [00:02<00:18, 17.29it/s] Loading 0: 13%|█▎ | 47/363 [00:02<00:14, 21.17it/s] Loading 0: 14%|█▍ | 51/363 [00:02<00:16, 19.17it/s] Loading 0: 15%|█▍ | 54/363 [00:03<00:20, 14.96it/s] Loading 0: 16%|█▌ | 57/363 [00:03<00:17, 17.20it/s] Loading 0: 17%|█▋ | 60/363 [00:03<00:19, 15.58it/s] Loading 0: 18%|█▊ | 64/363 [00:03<00:15, 19.40it/s] Loading 0: 19%|█▊ | 68/363 [00:03<00:12, 22.98it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:17, 16.65it/s] Loading 0: 20%|██ | 74/363 [00:04<00:16, 17.43it/s] Loading 0: 21%|██ | 77/363 [00:04<00:20, 13.67it/s] Loading 0: 23%|██▎ | 82/363 [00:04<00:14, 19.05it/s] Loading 0: 24%|██▎ | 86/363 [00:04<00:12, 22.56it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:16, 16.67it/s] Loading 0: 25%|██▌ | 92/363 [00:05<00:15, 17.13it/s] Loading 0: 27%|██▋ | 97/363 [00:05<00:11, 22.18it/s] Loading 0: 28%|██▊ | 101/363 [00:05<00:11, 23.04it/s] Loading 0: 29%|██▊ | 104/363 [00:05<00:13, 19.04it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:17, 15.04it/s] Loading 0: 30%|███ | 109/363 [00:06<00:17, 14.50it/s] Loading 0: 31%|███ | 111/363 [00:06<00:16, 15.35it/s] Loading 0: 31%|███ | 113/363 [00:06<00:19, 12.77it/s] Loading 0: 33%|███▎ | 118/363 [00:06<00:12, 19.17it/s] Loading 0: 34%|███▎ | 122/363 [00:06<00:10, 23.02it/s] Loading 0: 34%|███▍ | 125/363 [00:07<00:14, 16.36it/s] Loading 0: 35%|███▌ | 128/363 [00:07<00:13, 17.32it/s] Loading 0: 36%|███▌ | 131/363 [00:07<00:17, 13.44it/s] Loading 0: 37%|███▋ | 136/363 [00:07<00:11, 18.99it/s] Loading 0: 39%|███▊ | 140/363 [00:07<00:09, 22.63it/s] Loading 0: 40%|███▉ | 144/363 [00:08<00:14, 14.92it/s] Loading 0: 41%|████ | 148/363 [00:08<00:13, 16.45it/s] Loading 0: 42%|████▏ | 151/363 [00:08<00:12, 16.84it/s] Loading 0: 43%|████▎ | 155/363 [00:08<00:10, 20.61it/s] Loading 0: 44%|████▎ | 158/363 [00:08<00:09, 22.21it/s] Loading 0: 44%|████▍ | 161/363 [00:09<00:12, 16.20it/s] Loading 0: 45%|████▌ | 164/363 [00:09<00:11, 17.09it/s] Loading 0: 46%|████▌ | 167/363 [00:09<00:14, 13.53it/s] Loading 0: 47%|████▋ | 172/363 [00:09<00:10, 18.88it/s] Loading 0: 48%|████▊ | 176/363 [00:09<00:08, 22.26it/s] Loading 0: 49%|████▉ | 179/363 [00:10<00:11, 16.36it/s] Loading 0: 50%|█████ | 182/363 [00:10<00:10, 17.15it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:13, 13.60it/s] Loading 0: 52%|█████▏ | 190/363 [00:10<00:09, 18.95it/s] Loading 0: 53%|█████▎ | 194/363 [00:10<00:07, 22.45it/s] Loading 0: 55%|█████▍ | 198/363 [00:11<00:11, 14.83it/s] Loading 0: 55%|█████▌ | 200/363 [00:25<00:10, 14.83it/s] Loading 0: 55%|█████▌ | 201/363 [00:25<03:16, 1.21s/it] Loading 0: 56%|█████▌ | 203/363 [00:25<02:41, 1.01s/it] Loading 0: 57%|█████▋ | 207/363 [00:25<01:43, 1.51it/s] Loading 0: 58%|█████▊ | 210/363 [00:25<01:15, 2.03it/s] Loading 0: 59%|█████▊ | 213/363 [00:26<00:56, 2.66it/s] Loading 0: 60%|█████▉ | 216/363 [00:26<00:43, 3.34it/s] Loading 0: 60%|██████ | 219/363 [00:26<00:31, 4.50it/s] Loading 0: 61%|██████ | 222/363 [00:26<00:25, 5.56it/s] Loading 0: 62%|██████▏ | 226/363 [00:26<00:17, 8.00it/s] Loading 0: 63%|██████▎ | 230/363 [00:27<00:12, 10.93it/s] Loading 0: 64%|██████▍ | 233/363 [00:27<00:12, 10.47it/s] Loading 0: 65%|██████▌ | 236/363 [00:27<00:10, 12.05it/s] Loading 0: 66%|██████▌ | 239/363 [00:27<00:11, 10.93it/s] Loading 0: 67%|██████▋ | 244/363 [00:27<00:07, 15.92it/s] Loading 0: 68%|██████▊ | 248/363 [00:28<00:05, 19.49it/s] Loading 0: 69%|██████▉ | 252/363 [00:28<00:07, 13.89it/s] Loading 0: 70%|███████ | 255/363 [00:28<00:06, 16.01it/s] Loading 0: 71%|███████ | 258/363 [00:28<00:07, 14.90it/s] Loading 0: 72%|███████▏ | 262/363 [00:29<00:05, 18.63it/s] Loading 0: 73%|███████▎ | 266/363 [00:29<00:04, 21.91it/s] Loading 0: 74%|███████▍ | 269/363 [00:29<00:05, 16.15it/s] Loading 0: 75%|███████▍ | 272/363 [00:29<00:05, 17.08it/s] Loading 0: 76%|███████▌ | 275/363 [00:29<00:06, 13.64it/s] Loading 0: 77%|███████▋ | 280/363 [00:30<00:04, 19.12it/s] Loading 0: 78%|███████▊ | 284/363 [00:30<00:03, 22.65it/s] Loading 0: 79%|███████▉ | 288/363 [00:30<00:05, 14.96it/s] Loading 0: 80%|████████ | 291/363 [00:30<00:04, 16.98it/s] Loading 0: 81%|████████ | 294/363 [00:30<00:04, 15.63it/s] Loading 0: 82%|████████▏ | 298/363 [00:31<00:03, 19.37it/s] Loading 0: 83%|████████▎ | 302/363 [00:31<00:02, 22.97it/s] Loading 0: 84%|████████▍ | 305/363 [00:31<00:03, 16.48it/s] Loading 0: 85%|████████▍ | 308/363 [00:31<00:03, 17.24it/s] Loading 0: 86%|████████▌ | 311/363 [00:31<00:03, 13.60it/s] Loading 0: 87%|████████▋ | 316/363 [00:32<00:02, 18.96it/s] Loading 0: 88%|████████▊ | 320/363 [00:32<00:01, 22.37it/s] Loading 0: 89%|████████▉ | 323/363 [00:32<00:02, 16.57it/s] Loading 0: 90%|████████▉ | 326/363 [00:32<00:02, 17.30it/s] Loading 0: 91%|█████████ | 329/363 [00:33<00:02, 13.81it/s] Loading 0: 92%|█████████▏| 334/363 [00:33<00:01, 18.98it/s] Loading 0: 93%|█████████▎| 338/363 [00:33<00:01, 22.38it/s] Loading 0: 94%|█████████▍| 341/363 [00:33<00:01, 16.48it/s] Loading 0: 95%|█████████▍| 344/363 [00:33<00:01, 17.26it/s] Loading 0: 96%|█████████▌| 347/363 [00:34<00:01, 13.76it/s] Loading 0: 97%|█████████▋| 352/363 [00:34<00:00, 19.09it/s] Loading 0: 98%|█████████▊| 356/363 [00:34<00:00, 22.76it/s] Loading 0: 99%|█████████▉| 360/363 [00:41<00:01, 1.75it/s] Loading 0: 100%|██████████| 363/363 [00:41<00:00, 2.26it/s]
Job rirv938-mistral-24b-grp-36770-v1-mkmlizer completed after 257.17s with status: succeeded
Stopping job with name rirv938-mistral-24b-grp-36770-v1-mkmlizer
Pipeline stage MKMLizer completed in 257.87s
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-36770-v1
Waiting for inference service rirv938-mistral-24b-grp-36770-v1 to be ready
Inference service rirv938-mistral-24b-grp-36770-v1 ready after 140.5112383365631s
Pipeline stage MKMLDeployer completed in 141.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0972557067871094s
Received healthy response to inference request in 2.2638282775878906s
Received healthy response to inference request in 1.886939525604248s
Received healthy response to inference request in 1.924748420715332s
Received healthy response to inference request in 2.1009790897369385s
5 requests
0 failed requests
5th percentile: 1.894501304626465
10th percentile: 1.9020630836486816
20th percentile: 1.9171866416931151
30th percentile: 1.9592498779296874
40th percentile: 2.0282527923583986
50th percentile: 2.0972557067871094
60th percentile: 2.098745059967041
70th percentile: 2.1002344131469726
80th percentile: 2.133548927307129
90th percentile: 2.19868860244751
95th percentile: 2.2312584400177
99th percentile: 2.2573143100738524
mean time: 2.0547502040863037
Pipeline stage StressChecker completed in 11.48s
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 0.61s
Shutdown handler de-registered
rirv938-mistral-24b-grp_36770_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-grp-36770-v1-profiler
Waiting for inference service rirv938-mistral-24b-grp-36770-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4993.96s
Shutdown handler de-registered
rirv938-mistral-24b-grp_36770_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-grp_36770_v1 status is now torndown due to DeploymentManager action