rirv938-tune-mistral-gr_79261

developer_uid: rirv938

submission_id: rirv938-tune-mistral-gr_79261_v1

model_name: rirv938-tune-mistral-gr_79261_v1

model_group: rirv938/tune_mistral_grp

status: torndown

timestamp: 2025-05-01T16:32:24+00:00

num_battles: 6134

num_wins: 3471

celo_rating: 1329.79

family_friendly_score: 0.5953999999999999

family_friendly_standard_error: 0.006941164743758788

submission_type: basic

model_repo: rirv938/tune_mistral_grpo_cp888_92ff_new_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': 0.5569969474012134, 'latency_mean': 1.7952819299697875, 'latency_p50': 1.7992990016937256, 'latency_p90': 2.0030115842819214}, {'batch_size': 4, 'throughput': 1.395652505165158, 'latency_mean': 2.857780497074127, 'latency_p50': 2.8425376415252686, 'latency_p90': 3.2019176721572875}, {'batch_size': 5, 'throughput': 1.5619034683393955, 'latency_mean': 3.1823765552043914, 'latency_p50': 3.14986515045166, 'latency_p90': 3.5233656406402587}, {'batch_size': 8, 'throughput': 1.857416809744707, 'latency_mean': 4.270727840662002, 'latency_p50': 4.2930474281311035, 'latency_p90': 4.719552206993103}, {'batch_size': 10, 'throughput': 2.0084509384514333, 'latency_mean': 4.932819572687149, 'latency_p50': 4.911081433296204, 'latency_p90': 5.565258955955505}, {'batch_size': 12, 'throughput': 2.0879793657078385, 'latency_mean': 5.676122238636017, 'latency_p50': 5.705782771110535, 'latency_p90': 6.400121974945068}, {'batch_size': 15, 'throughput': 2.170152939213315, 'latency_mean': 6.812314027547837, 'latency_p50': 6.767083168029785, 'latency_p90': 7.833149671554565}]

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

display_name: rirv938-tune-mistral-gr_79261_v1

is_internal_developer: True

language_model: rirv938/tune_mistral_grpo_cp888_92ff_new_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.74

us_pacific_date: 2025-05-01

win_ratio: 0.5658624062601891

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:', '\n', '</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-79261-v1-mkmlizer
Waiting for job on rirv938-tune-mistral-gr-79261-v1-mkmlizer to finish
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║       /___/                                                         ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-79261-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-tune-mistral-gr-79261-v1-mkmlizer: Downloaded to shared memory in 172.746s
rirv938-tune-mistral-gr-79261-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp00i7n5aq, device:0
rirv938-tune-mistral-gr-79261-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-tune-mistral-gr-79261-v1-mkmlizer: quantized model in 66.887s
rirv938-tune-mistral-gr-79261-v1-mkmlizer: Processed model rirv938/tune_mistral_grpo_cp888_92ff_new_merged in 239.633s
rirv938-tune-mistral-gr-79261-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-tune-mistral-gr-79261-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-tune-mistral-gr-79261-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-tune-mistral-gr-79261-v1
rirv938-tune-mistral-gr-79261-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-79261-v1/config.json
rirv938-tune-mistral-gr-79261-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-79261-v1/special_tokens_map.json
rirv938-tune-mistral-gr-79261-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-79261-v1/tokenizer_config.json
rirv938-tune-mistral-gr-79261-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-79261-v1/tokenizer.json
rirv938-tune-mistral-gr-79261-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-79261-v1/flywheel_model.1.safetensors
rirv938-tune-mistral-gr-79261-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-79261-v1/flywheel_model.0.safetensors
rirv938-tune-mistral-gr-79261-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.27it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.57it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 20.65it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:25, 13.57it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:31, 11.11it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:21, 15.95it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:22, 15.29it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:21, 15.55it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.09it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.92it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.75it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 15.53it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:23, 13.86it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:24, 13.27it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.39it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:14, 21.19it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.75it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.97it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:20, 14.84it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:25, 11.96it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 18.06it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.53it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.94it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.59it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:20, 13.94it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:21, 13.41it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 17.62it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 21.21it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 14.82it/s]
Loading 0:  25%|██▌       | 91/363 [00:05<00:19, 13.93it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:15, 17.85it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 21.33it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.67it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:17, 14.35it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 13.36it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:19, 12.93it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.85it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.46it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 17.67it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.25it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.06it/s]
Loading 0:  35%|███▌      | 128/363 [00:08<00:15, 15.62it/s]
Loading 0:  36%|███▌      | 130/363 [00:08<00:16, 13.97it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:17, 13.36it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.64it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.31it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 14.94it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:15, 13.93it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:14, 14.66it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:18, 11.83it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.65it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 20.97it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 14.68it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 14.05it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:13, 14.85it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:16, 12.05it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.08it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 21.49it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 15.05it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.63it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:12, 13.98it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:13, 13.33it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 17.27it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.84it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.76it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:11, 14.04it/s]
Loading 0:  55%|█████▌    | 201/363 [00:29<05:31,  2.04s/it]
Loading 0:  56%|█████▌    | 203/363 [00:30<04:11,  1.57s/it]
Loading 0:  57%|█████▋    | 207/363 [00:30<02:25,  1.07it/s]
Loading 0:  58%|█████▊    | 210/363 [00:30<01:40,  1.52it/s]
Loading 0:  59%|█████▊    | 213/363 [00:30<01:13,  2.04it/s]
Loading 0:  59%|█████▉    | 215/363 [00:30<00:59,  2.50it/s]
Loading 0:  60%|█████▉    | 217/363 [00:31<00:47,  3.09it/s]
Loading 0:  60%|██████    | 219/363 [00:31<00:36,  3.93it/s]
Loading 0:  61%|██████    | 221/363 [00:31<00:31,  4.51it/s]
Loading 0:  62%|██████▏   | 226/363 [00:31<00:17,  8.01it/s]
Loading 0:  63%|██████▎   | 230/363 [00:31<00:12, 10.97it/s]
Loading 0:  64%|██████▍   | 233/363 [00:32<00:12, 10.06it/s]
Loading 0:  65%|██████▍   | 235/363 [00:32<00:12, 10.40it/s]
Loading 0:  65%|██████▌   | 237/363 [00:32<00:10, 11.66it/s]
Loading 0:  66%|██████▌   | 239/363 [00:32<00:12, 10.29it/s]
Loading 0:  67%|██████▋   | 244/363 [00:32<00:07, 15.64it/s]
Loading 0:  68%|██████▊   | 248/363 [00:32<00:06, 19.04it/s]
Loading 0:  69%|██████▉   | 251/363 [00:33<00:07, 14.27it/s]
Loading 0:  70%|██████▉   | 254/363 [00:33<00:07, 14.98it/s]
Loading 0:  71%|███████   | 256/363 [00:33<00:07, 13.55it/s]
Loading 0:  71%|███████   | 258/363 [00:33<00:07, 13.20it/s]
Loading 0:  72%|███████▏  | 262/363 [00:33<00:05, 17.32it/s]
Loading 0:  73%|███████▎  | 266/363 [00:34<00:04, 20.85it/s]
Loading 0:  74%|███████▍  | 269/363 [00:34<00:06, 14.83it/s]
Loading 0:  75%|███████▍  | 271/363 [00:34<00:06, 14.13it/s]
Loading 0:  75%|███████▌  | 273/363 [00:34<00:05, 15.01it/s]
Loading 0:  76%|███████▌  | 275/363 [00:34<00:07, 11.97it/s]
Loading 0:  77%|███████▋  | 280/363 [00:35<00:04, 18.00it/s]
Loading 0:  78%|███████▊  | 284/363 [00:35<00:03, 21.43it/s]
Loading 0:  79%|███████▉  | 287/363 [00:35<00:05, 15.18it/s]
Loading 0:  80%|███████▉  | 290/363 [00:35<00:04, 15.96it/s]
Loading 0:  80%|████████  | 292/363 [00:35<00:05, 14.10it/s]
Loading 0:  81%|████████  | 294/363 [00:36<00:05, 13.42it/s]
Loading 0:  82%|████████▏ | 298/363 [00:36<00:03, 17.67it/s]
Loading 0:  83%|████████▎ | 302/363 [00:36<00:02, 21.29it/s]
Loading 0:  84%|████████▍ | 305/363 [00:36<00:03, 14.81it/s]
Loading 0:  85%|████████▍ | 307/363 [00:36<00:03, 14.18it/s]
Loading 0:  85%|████████▌ | 309/363 [00:36<00:03, 14.83it/s]
Loading 0:  86%|████████▌ | 311/363 [00:37<00:04, 12.15it/s]
Loading 0:  87%|████████▋ | 316/363 [00:37<00:02, 18.22it/s]
Loading 0:  88%|████████▊ | 320/363 [00:37<00:01, 21.60it/s]
Loading 0:  89%|████████▉ | 323/363 [00:37<00:02, 15.17it/s]
Loading 0:  90%|████████▉ | 326/363 [00:37<00:02, 15.93it/s]
Loading 0:  90%|█████████ | 328/363 [00:38<00:02, 14.22it/s]
Loading 0:  91%|█████████ | 330/363 [00:38<00:02, 13.68it/s]
Loading 0:  92%|█████████▏| 334/363 [00:38<00:01, 17.88it/s]
Loading 0:  93%|█████████▎| 338/363 [00:38<00:01, 21.31it/s]
Loading 0:  94%|█████████▍| 341/363 [00:38<00:01, 14.94it/s]
Loading 0:  94%|█████████▍| 343/363 [00:39<00:01, 14.01it/s]
Loading 0:  95%|█████████▌| 345/363 [00:39<00:01, 14.88it/s]
Loading 0:  96%|█████████▌| 347/363 [00:39<00:01, 11.97it/s]
Loading 0:  97%|█████████▋| 352/363 [00:39<00:00, 18.00it/s]
Loading 0:  98%|█████████▊| 356/363 [00:39<00:00, 21.42it/s]
Loading 0:  99%|█████████▉| 359/363 [00:46<00:02,  1.47it/s]
Loading 0:  99%|█████████▉| 361/363 [00:47<00:01,  1.76it/s]
                                                            
Job rirv938-tune-mistral-gr-79261-v1-mkmlizer completed after 268.61s with status: succeeded
Stopping job with name rirv938-tune-mistral-gr-79261-v1-mkmlizer
Pipeline stage MKMLizer completed in 269.13s
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-79261-v1
Waiting for inference service rirv938-tune-mistral-gr-79261-v1 to be ready
Failed to get response for submission bogoconic1-nemo-280k-s6_46455_v1: HTTPConnectionPool(host='bogoconic1-nemo-280k-s6-46455-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rirv938-tune-mistral-gr-79261-v1 ready after 160.6136176586151s
Pipeline stage MKMLDeployer completed in 161.34s
run pipeline stage %s
Running pipeline stage StressChecker
Failed to get response for submission bogoconic1-nemo-280k-s6_46455_v1: HTTPConnectionPool(host='bogoconic1-nemo-280k-s6-46455-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
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 2.8258159160614014s
Received healthy response to inference request in 2.0512404441833496s
Received healthy response to inference request in 1.8220534324645996s
Received healthy response to inference request in 1.8494393825531006s
5 requests
1 failed requests
5th percentile: 1.8275306224822998
10th percentile: 1.8330078125
20th percentile: 1.8439621925354004
30th percentile: 1.8897995948791504
40th percentile: 1.97052001953125
50th percentile: 2.0512404441833496
60th percentile: 2.3610706329345703
70th percentile: 2.670900821685791
80th percentile: 6.288386535644534
90th percentile: 13.213527774810792
95th percentile: 16.676098394393918
99th percentile: 19.446154890060424
mean time: 5.737443637847901
%s, retrying in %s seconds...
Received healthy response to inference request in 2.093130350112915s
Received healthy response to inference request in 2.2661194801330566s
Received healthy response to inference request in 1.9470102787017822s
Received healthy response to inference request in 2.174741268157959s
Received healthy response to inference request in 2.0095713138580322s
5 requests
0 failed requests
5th percentile: 1.9595224857330322
10th percentile: 1.9720346927642822
20th percentile: 1.9970591068267822
30th percentile: 2.026283121109009
40th percentile: 2.0597067356109617
50th percentile: 2.093130350112915
60th percentile: 2.1257747173309327
70th percentile: 2.1584190845489504
80th percentile: 2.1930169105529784
90th percentile: 2.2295681953430178
95th percentile: 2.247843837738037
99th percentile: 2.2624643516540526
mean time: 2.098114538192749
Pipeline stage StressChecker completed in 41.76s
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 0.89s
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 0.67s
Shutdown handler de-registered
rirv938-tune-mistral-gr_79261_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-tune-mistral-gr-79261-v1-profiler
Waiting for inference service rirv938-tune-mistral-gr-79261-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 3085.33s
Shutdown handler de-registered
rirv938-tune-mistral-gr_79261_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-tune-mistral-gr_79261_v1 status is now torndown due to DeploymentManager action