rirv938-tune-mistral-gr_43026

developer_uid: rirv938

submission_id: rirv938-tune-mistral-gr_43026_v1

model_name: rirv938-tune-mistral-gr_43026_v1

model_group: rirv938/tune_mistral_grp

status: torndown

timestamp: 2025-04-30T23:58:46+00:00

num_battles: 7604

num_wins: 3907

celo_rating: 1297.6

family_friendly_score: 0.5614

family_friendly_standard_error: 0.007017549999821875

submission_type: basic

model_repo: rirv938/tune_mistral_grpo_cp888_92ff_v3_run3_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': 0.5533724603514446, 'latency_mean': 1.8070444500446319, 'latency_p50': 1.8133842945098877, 'latency_p90': 1.9992748022079467}, {'batch_size': 4, 'throughput': 1.3729075238124664, 'latency_mean': 2.891770985126495, 'latency_p50': 2.9017398357391357, 'latency_p90': 3.1920761346817015}, {'batch_size': 5, 'throughput': 1.5484664420972214, 'latency_mean': 3.2121582674980163, 'latency_p50': 3.203019857406616, 'latency_p90': 3.556063485145569}, {'batch_size': 8, 'throughput': 1.8762818344853849, 'latency_mean': 4.238983241319656, 'latency_p50': 4.252681016921997, 'latency_p90': 4.756486511230468}, {'batch_size': 10, 'throughput': 2.0068135376575347, 'latency_mean': 4.942008452415466, 'latency_p50': 4.97931969165802, 'latency_p90': 5.644401907920837}, {'batch_size': 12, 'throughput': 2.0770153157437115, 'latency_mean': 5.713575476408005, 'latency_p50': 5.7168227434158325, 'latency_p90': 6.439941072463989}, {'batch_size': 15, 'throughput': 2.138265510800239, 'latency_mean': 6.904585081338882, 'latency_p50': 6.958195924758911, 'latency_p90': 7.761381602287292}]

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

display_name: rirv938-tune-mistral-gr_43026_v1

is_internal_developer: True

language_model: rirv938/tune_mistral_grpo_cp888_92ff_v3_run3_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.74

us_pacific_date: 2025-04-30

win_ratio: 0.5138085218306154

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': 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-tune-mistral-gr-43026-v1-mkmlizer
Waiting for job on rirv938-tune-mistral-gr-43026-v1-mkmlizer to finish
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║       /___/                                                         ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-43026-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-tune-mistral-gr-43026-v1-mkmlizer: Downloaded to shared memory in 146.648s
rirv938-tune-mistral-gr-43026-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprrpw1lcc, device:0
rirv938-tune-mistral-gr-43026-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_luleb_2025-04-14: ('http://rirv938-anthropic-40k-2-43413-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'readfrom tcp 127.0.0.1:40760->127.0.0.1:8080: write tcp 127.0.0.1:40760->127.0.0.1:8080: use of closed network connection\n')
rirv938-tune-mistral-gr-43026-v1-mkmlizer: quantized model in 65.156s
rirv938-tune-mistral-gr-43026-v1-mkmlizer: Processed model rirv938/tune_mistral_grpo_cp888_92ff_v3_run3_merged in 211.805s
rirv938-tune-mistral-gr-43026-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-tune-mistral-gr-43026-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-tune-mistral-gr-43026-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-tune-mistral-gr-43026-v1
rirv938-tune-mistral-gr-43026-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-43026-v1/config.json
rirv938-tune-mistral-gr-43026-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-43026-v1/special_tokens_map.json
rirv938-tune-mistral-gr-43026-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-43026-v1/tokenizer_config.json
rirv938-tune-mistral-gr-43026-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-43026-v1/tokenizer.json
rirv938-tune-mistral-gr-43026-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-43026-v1/flywheel_model.1.safetensors
rirv938-tune-mistral-gr-43026-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-43026-v1/flywheel_model.0.safetensors
rirv938-tune-mistral-gr-43026-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:13, 26.11it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:27, 13.04it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 19.82it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:27, 12.67it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:33, 10.44it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:23, 14.93it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:23, 14.34it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:25, 13.28it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:19, 17.12it/s]
Loading 0:   9%|▉         | 32/363 [00:02<00:16, 20.18it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:24, 13.32it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:25, 12.80it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:23, 13.56it/s]
Loading 0:  11%|█▏        | 41/363 [00:03<00:29, 10.85it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:19, 16.38it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:16, 19.55it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:23, 13.45it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:23, 12.85it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:22, 13.77it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:26, 11.58it/s]
Loading 0:  18%|█▊        | 65/363 [00:04<00:15, 19.43it/s]
Loading 0:  19%|█▉        | 69/363 [00:04<00:16, 18.04it/s]
Loading 0:  20%|█▉        | 72/363 [00:04<00:21, 13.66it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:18, 15.86it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:19, 14.45it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 17.94it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 21.08it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 14.56it/s]
Loading 0:  25%|██▌       | 92/363 [00:06<00:18, 14.96it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.27it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 20.83it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:14, 18.45it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:18, 13.74it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:20, 12.65it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.31it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:19, 13.23it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:23, 10.83it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 16.73it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.16it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.40it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.57it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.36it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:20, 11.29it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:13, 17.12it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:10, 20.28it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.04it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:16, 13.27it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:15, 13.99it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:18, 11.47it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 17.39it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 20.88it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 14.61it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:13, 15.16it/s]
Loading 0:  46%|████▌     | 166/363 [00:11<00:14, 13.40it/s]
Loading 0:  46%|████▋     | 168/363 [00:11<00:14, 13.04it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:10, 17.70it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 20.98it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.92it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:12, 14.28it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:11, 15.06it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:14, 12.04it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.89it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.91it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:11, 14.19it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:12, 13.51it/s]
Loading 0:  55%|█████▌    | 201/363 [00:28<04:44,  1.76s/it]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:37,  1.36s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:06,  1.23it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:27,  1.74it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:03,  2.35it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:52,  2.85it/s]
Loading 0:  60%|█████▉    | 217/363 [00:29<00:41,  3.49it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:32,  4.41it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:28,  4.92it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:15,  8.72it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:11, 12.03it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:12, 10.77it/s]
Loading 0:  65%|██████▌   | 236/363 [00:30<00:10, 11.96it/s]
Loading 0:  66%|██████▌   | 239/363 [00:30<00:11, 10.38it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:08, 14.82it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:06, 17.92it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:08, 13.76it/s]
Loading 0:  70%|██████▉   | 254/363 [00:31<00:07, 14.52it/s]
Loading 0:  71%|███████   | 256/363 [00:31<00:08, 13.08it/s]
Loading 0:  71%|███████   | 258/363 [00:32<00:08, 12.67it/s]
Loading 0:  72%|███████▏  | 262/363 [00:32<00:06, 16.71it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:04, 20.21it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:06, 14.18it/s]
Loading 0:  75%|███████▍  | 271/363 [00:32<00:06, 13.51it/s]
Loading 0:  75%|███████▌  | 273/363 [00:32<00:06, 14.19it/s]
Loading 0:  76%|███████▌  | 275/363 [00:33<00:07, 11.54it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 17.45it/s]
Loading 0:  78%|███████▊  | 284/363 [00:33<00:03, 20.68it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 14.05it/s]
Loading 0:  80%|███████▉  | 289/363 [00:34<00:05, 13.31it/s]
Loading 0:  80%|████████  | 291/363 [00:34<00:05, 14.16it/s]
Loading 0:  81%|████████  | 293/363 [00:34<00:06, 11.45it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:03, 17.06it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:02, 20.47it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:04, 14.22it/s]
Loading 0:  85%|████████▍ | 307/363 [00:35<00:04, 13.51it/s]
Loading 0:  85%|████████▌ | 309/363 [00:35<00:03, 14.22it/s]
Loading 0:  86%|████████▌ | 311/363 [00:35<00:04, 11.38it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 17.06it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:02, 20.50it/s]
Loading 0:  89%|████████▉ | 323/363 [00:36<00:02, 14.63it/s]
Loading 0:  90%|████████▉ | 326/363 [00:36<00:02, 15.36it/s]
Loading 0:  90%|█████████ | 328/363 [00:36<00:02, 13.57it/s]
Loading 0:  91%|█████████ | 330/363 [00:36<00:02, 13.15it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 17.65it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 22.11it/s]
Loading 0:  94%|█████████▍| 341/363 [00:37<00:01, 15.51it/s]
Loading 0:  95%|█████████▍| 344/363 [00:37<00:01, 16.30it/s]
Loading 0:  96%|█████████▌| 347/363 [00:37<00:01, 12.62it/s]
Loading 0:  97%|█████████▋| 352/363 [00:37<00:00, 17.85it/s]
Loading 0:  98%|█████████▊| 356/363 [00:38<00:00, 21.54it/s]
Loading 0:  99%|█████████▉| 359/363 [00:45<00:02,  1.56it/s]
Loading 0: 100%|█████████▉| 362/363 [00:45<00:00,  2.02it/s]
                                                            
Job rirv938-tune-mistral-gr-43026-v1-mkmlizer completed after 258.21s with status: succeeded
Stopping job with name rirv938-tune-mistral-gr-43026-v1-mkmlizer
Pipeline stage MKMLizer completed in 258.68s
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 rirv938-tune-mistral-gr-43026-v1
Waiting for inference service rirv938-tune-mistral-gr-43026-v1 to be ready
Inference service rirv938-tune-mistral-gr-43026-v1 ready after 140.5571312904358s
Pipeline stage MKMLDeployer completed in 141.10s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.582247495651245s
Received healthy response to inference request in 1.9152874946594238s
Received healthy response to inference request in 1.8764142990112305s
Received healthy response to inference request in 1.8025240898132324s
Received healthy response to inference request in 1.9213628768920898s
5 requests
0 failed requests
5th percentile: 1.817302131652832
10th percentile: 1.8320801734924317
20th percentile: 1.861636257171631
30th percentile: 1.8841889381408692
40th percentile: 1.8997382164001464
50th percentile: 1.9152874946594238
60th percentile: 1.9177176475524902
70th percentile: 1.9201478004455566
80th percentile: 2.053539800643921
90th percentile: 2.317893648147583
95th percentile: 2.450070571899414
99th percentile: 2.5558121109008787
mean time: 2.0195672512054443
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 0.71s
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 0.78s
Shutdown handler de-registered
rirv938-tune-mistral-gr_43026_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-tune-mistral-gr-43026-v1-profiler
Waiting for inference service rirv938-tune-mistral-gr-43026-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 4851.74s
Shutdown handler de-registered
rirv938-tune-mistral-gr_43026_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-tune-mistral-gr_43026_v1 status is now torndown due to DeploymentManager action