rirv938-tune-mistral-gr_66976

developer_uid: rirv938

submission_id: rirv938-tune-mistral-gr_66976_v1

model_name: rirv938-tune-mistral-gr_66976_v1

model_group: rirv938/tune_mistral_grp

status: torndown

timestamp: 2025-04-29T20:11:40+00:00

num_battles: 7460

num_wins: 3773

celo_rating: 1303.89

family_friendly_score: 0.5716

family_friendly_standard_error: 0.006998191766449387

submission_type: basic

model_repo: rirv938/tune_mistral_grpo_cp62_92ff_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': 0.5568287587490837, 'latency_mean': 1.7958178544044494, 'latency_p50': 1.783462405204773, 'latency_p90': 1.996580719947815}, {'batch_size': 4, 'throughput': 1.3913521968805103, 'latency_mean': 2.851620901823044, 'latency_p50': 2.8422495126724243, 'latency_p90': 3.1623645782470704}, {'batch_size': 5, 'throughput': 1.534191223755682, 'latency_mean': 3.2376993346214293, 'latency_p50': 3.2309526205062866, 'latency_p90': 3.612534689903259}, {'batch_size': 8, 'throughput': 1.8768967536002084, 'latency_mean': 4.233991762399674, 'latency_p50': 4.219288229942322, 'latency_p90': 4.80478572845459}, {'batch_size': 10, 'throughput': 1.981571436288455, 'latency_mean': 5.004686012268066, 'latency_p50': 4.998006820678711, 'latency_p90': 5.641991591453552}, {'batch_size': 12, 'throughput': 2.071117856959616, 'latency_mean': 5.735924737453461, 'latency_p50': 5.7316882610321045, 'latency_p90': 6.53752715587616}, {'batch_size': 15, 'throughput': 2.125800445362954, 'latency_mean': 6.959497158527374, 'latency_p50': 7.054508090019226, 'latency_p90': 7.880904579162597}]

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

display_name: rirv938-tune-mistral-gr_66976_v1

is_internal_developer: True

language_model: rirv938/tune_mistral_grpo_cp62_92ff_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.73

us_pacific_date: 2025-04-29

win_ratio: 0.5057640750670241

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-tune-mistral-gr-66976-v1-mkmlizer
Waiting for job on rirv938-tune-mistral-gr-66976-v1-mkmlizer to finish
Unable to record family friendly update due to error: ('http://chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:44726->127.0.0.1:8080: read: connection reset by peer\n')
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║       /___/                                                         ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-66976-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-tune-mistral-gr-66976-v1-mkmlizer: Downloaded to shared memory in 176.932s
rirv938-tune-mistral-gr-66976-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnw82314y, device:0
rirv938-tune-mistral-gr-66976-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-tune-mistral-gr-66976-v1-mkmlizer: quantized model in 63.415s
rirv938-tune-mistral-gr-66976-v1-mkmlizer: Processed model rirv938/tune_mistral_grpo_cp62_92ff_merged in 240.347s
rirv938-tune-mistral-gr-66976-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-tune-mistral-gr-66976-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-tune-mistral-gr-66976-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-tune-mistral-gr-66976-v1
rirv938-tune-mistral-gr-66976-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-66976-v1/config.json
rirv938-tune-mistral-gr-66976-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-66976-v1/special_tokens_map.json
rirv938-tune-mistral-gr-66976-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-66976-v1/tokenizer_config.json
rirv938-tune-mistral-gr-66976-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-66976-v1/tokenizer.json
rirv938-tune-mistral-gr-66976-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-66976-v1/flywheel_model.1.safetensors
rirv938-tune-mistral-gr-66976-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-66976-v1/flywheel_model.0.safetensors
rirv938-tune-mistral-gr-66976-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.41it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:24, 14.39it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:16, 21.61it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:24, 14.44it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:25, 13.38it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:21, 16.21it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:21, 15.66it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:23, 14.55it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 18.80it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.47it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.46it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 16.11it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:22, 14.20it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:23, 13.50it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.58it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.15it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 14.78it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:21, 14.06it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:20, 15.01it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:25, 12.13it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.04it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.18it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 15.19it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.61it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:20, 13.98it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:21, 13.45it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 17.58it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 21.09it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 15.06it/s]
Loading 0:  25%|██▌       | 91/363 [00:05<00:19, 14.30it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:14, 18.28it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:12, 21.59it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.75it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:17, 15.05it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.92it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.56it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.46it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:20, 11.98it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.27it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.86it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.42it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.20it/s]
Loading 0:  36%|███▌      | 130/363 [00:08<00:15, 14.61it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:16, 13.77it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.99it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.54it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.29it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:15, 14.47it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:14, 15.35it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:17, 12.37it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.52it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.99it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:13, 15.35it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 16.03it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.59it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.58it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:09, 20.60it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.89it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.62it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 12.67it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 17.59it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:08, 20.71it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 15.42it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 15.85it/s]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:45,  1.41s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:25,  1.07it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:46,  1.43it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:19,  1.88it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<01:05,  2.27it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:52,  2.79it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:40,  3.53it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:34,  4.10it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:19,  7.13it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:13,  9.79it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:13,  9.34it/s]
Loading 0:  65%|██████▍   | 235/363 [00:29<00:13,  9.77it/s]
Loading 0:  65%|██████▌   | 237/363 [00:29<00:11, 11.02it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:12,  9.96it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 15.54it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 18.96it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.19it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 14.99it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:07, 13.63it/s]
Loading 0:  71%|███████   | 258/363 [00:30<00:07, 13.19it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:05, 17.50it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 20.79it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 14.68it/s]
Loading 0:  75%|███████▍  | 271/363 [00:31<00:06, 13.95it/s]
Loading 0:  75%|███████▌  | 273/363 [00:31<00:06, 14.84it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:07, 12.19it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.79it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 20.17it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:05, 14.81it/s]
Loading 0:  80%|███████▉  | 289/363 [00:32<00:05, 14.46it/s]
Loading 0:  80%|████████  | 292/363 [00:33<00:04, 15.01it/s]
Loading 0:  81%|████████  | 294/363 [00:33<00:04, 14.46it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 18.87it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 22.64it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 16.05it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 16.66it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:03, 13.09it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 18.26it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:01, 21.55it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 15.74it/s]
Loading 0:  90%|████████▉ | 326/363 [00:34<00:02, 16.32it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 12.76it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.68it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 20.91it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.57it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 16.21it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 12.84it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 17.84it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 20.86it/s]
Loading 0:  99%|█████████▉| 359/363 [00:43<00:02,  1.60it/s]
Loading 0:  99%|█████████▉| 361/363 [00:43<00:01,  1.89it/s]
                                                            
Job rirv938-tune-mistral-gr-66976-v1-mkmlizer completed after 271.33s with status: succeeded
Stopping job with name rirv938-tune-mistral-gr-66976-v1-mkmlizer
Pipeline stage MKMLizer completed in 271.82s
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 rirv938-tune-mistral-gr-66976-v1
Waiting for inference service rirv938-tune-mistral-gr-66976-v1 to be ready
Inference service rirv938-tune-mistral-gr-66976-v1 ready after 150.48362350463867s
Pipeline stage MKMLDeployer completed in 150.96s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.4851441383361816s
Received healthy response to inference request in 1.8582797050476074s
Received healthy response to inference request in 2.0227785110473633s
Received healthy response to inference request in 2.064683675765991s
5 requests
1 failed requests
5th percentile: 1.8911794662475585
10th percentile: 1.9240792274475098
20th percentile: 1.9898787498474122
30th percentile: 2.031159543991089
40th percentile: 2.04792160987854
50th percentile: 2.064683675765991
60th percentile: 2.2328678607940673
70th percentile: 2.4010520458221434
80th percentile: 6.015981769561771
90th percentile: 13.07765703201294
95th percentile: 16.608494663238524
99th percentile: 19.433164768218994
mean time: 5.714043664932251
%s, retrying in %s seconds...
Received healthy response to inference request in 2.078922986984253s
Received healthy response to inference request in 1.856839656829834s
Received healthy response to inference request in 2.1446890830993652s
Received healthy response to inference request in 1.9500532150268555s
Received healthy response to inference request in 2.015535354614258s
5 requests
0 failed requests
5th percentile: 1.8754823684692383
10th percentile: 1.8941250801086427
20th percentile: 1.9314105033874511
30th percentile: 1.963149642944336
40th percentile: 1.989342498779297
50th percentile: 2.015535354614258
60th percentile: 2.040890407562256
70th percentile: 2.066245460510254
80th percentile: 2.0920762062072753
90th percentile: 2.1183826446533205
95th percentile: 2.131535863876343
99th percentile: 2.1420584392547606
mean time: 2.009208059310913
Pipeline stage StressChecker completed in 41.23s
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 0.70s
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 0.68s
Shutdown handler de-registered
rirv938-tune-mistral-gr_66976_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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-tune-mistral-gr-66976-v1-profiler
Waiting for inference service rirv938-tune-mistral-gr-66976-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 3157.71s
Shutdown handler de-registered
rirv938-tune-mistral-gr_66976_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-tune-mistral-gr_66976_v1 status is now torndown due to DeploymentManager action