rirv938-tune-mistral-gr_63526

developer_uid: rirv938

submission_id: rirv938-tune-mistral-gr_63526_v1

model_name: rirv938-tune-mistral-gr_63526_v1

model_group: rirv938/tune_mistral_grp

status: torndown

timestamp: 2025-04-30T23:58:37+00:00

num_battles: 6313

num_wins: 3119

celo_rating: 1285.47

family_friendly_score: 0.563

family_friendly_standard_error: 0.007014713108887633

submission_type: basic

model_repo: rirv938/tune_mistral_grpo_cp296_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': 0.556866424657898, 'latency_mean': 1.7957070422172547, 'latency_p50': 1.801342248916626, 'latency_p90': 2.022750449180603}, {'batch_size': 3, 'throughput': 1.1860329624948136, 'latency_mean': 2.5234951186180115, 'latency_p50': 2.526082992553711, 'latency_p90': 2.7781014680862426}, {'batch_size': 5, 'throughput': 1.5522133018450543, 'latency_mean': 3.2085040283203123, 'latency_p50': 3.207013249397278, 'latency_p90': 3.575408959388733}, {'batch_size': 6, 'throughput': 1.6747551430597114, 'latency_mean': 3.5581014800071715, 'latency_p50': 3.543629288673401, 'latency_p90': 3.981654739379883}, {'batch_size': 8, 'throughput': 1.8565092888029668, 'latency_mean': 4.262762326002121, 'latency_p50': 4.3367698192596436, 'latency_p90': 4.779521751403808}, {'batch_size': 10, 'throughput': 1.9734395140612973, 'latency_mean': 5.014775149822235, 'latency_p50': 5.064401626586914, 'latency_p90': 5.600607562065124}]

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

display_name: rirv938-tune-mistral-gr_63526_v1

is_internal_developer: True

language_model: rirv938/tune_mistral_grpo_cp296_92ff_v3_run3_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.73

us_pacific_date: 2025-04-30

win_ratio: 0.4940598764454301

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': ['###', '</s>', 'You:', '\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-63526-v1-mkmlizer
Waiting for job on rirv938-tune-mistral-gr-63526-v1-mkmlizer to finish
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║       /___/                                                         ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-63526-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-tune-mistral-gr-63526-v1-mkmlizer: Downloaded to shared memory in 184.818s
rirv938-tune-mistral-gr-63526-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmllhyql5, device:0
rirv938-tune-mistral-gr-63526-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-tune-mistral-gr-63526-v1-mkmlizer: quantized model in 66.446s
rirv938-tune-mistral-gr-63526-v1-mkmlizer: Processed model rirv938/tune_mistral_grpo_cp296_92ff_v3_run3_merged in 251.265s
rirv938-tune-mistral-gr-63526-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-tune-mistral-gr-63526-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-tune-mistral-gr-63526-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-tune-mistral-gr-63526-v1
rirv938-tune-mistral-gr-63526-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-63526-v1/config.json
rirv938-tune-mistral-gr-63526-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-63526-v1/special_tokens_map.json
rirv938-tune-mistral-gr-63526-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-63526-v1/tokenizer_config.json
rirv938-tune-mistral-gr-63526-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-63526-v1/tokenizer.json
rirv938-tune-mistral-gr-63526-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-63526-v1/flywheel_model.1.safetensors
rirv938-tune-mistral-gr-63526-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-63526-v1/flywheel_model.0.safetensors
rirv938-tune-mistral-gr-63526-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:13, 26.54it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:27, 12.95it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 20.09it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:28, 12.48it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:34, 10.20it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:23, 14.80it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:24, 14.08it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:26, 12.97it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:19, 16.78it/s]
Loading 0:   9%|▉         | 32/363 [00:02<00:16, 20.30it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:24, 13.25it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:26, 12.48it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:24, 13.25it/s]
Loading 0:  11%|█▏        | 41/363 [00:03<00:30, 10.47it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:19, 15.86it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:16, 18.98it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:24, 12.80it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:25, 12.09it/s]
Loading 0:  16%|█▌        | 57/363 [00:04<00:23, 12.81it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:29, 10.37it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:19, 15.62it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:15, 18.68it/s]
Loading 0:  20%|█▉        | 71/363 [00:05<00:23, 12.49it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:24, 11.86it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:22, 12.81it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:26, 10.71it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:17, 16.27it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 19.80it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:19, 14.16it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:20, 13.39it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.27it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 20.58it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 18.86it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:18, 14.21it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:19, 13.01it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.45it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.32it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:23, 10.84it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:14, 16.90it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:11, 20.65it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.47it/s]
Loading 0:  35%|███▌      | 128/363 [00:08<00:15, 15.11it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:17, 13.32it/s]
Loading 0:  36%|███▋      | 132/363 [00:09<00:18, 12.82it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:13, 16.90it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:10, 20.49it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.38it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:16, 13.55it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:15, 14.37it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:18, 11.60it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:11, 17.55it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 21.25it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:14, 14.34it/s]
Loading 0:  45%|████▌     | 164/363 [00:11<00:13, 14.73it/s]
Loading 0:  46%|████▌     | 166/363 [00:11<00:14, 13.19it/s]
Loading 0:  46%|████▋     | 168/363 [00:11<00:15, 12.66it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 16.79it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 20.48it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:12, 14.28it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:13, 13.52it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:12, 14.32it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:15, 11.65it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.38it/s]
Loading 0:  53%|█████▎    | 194/363 [00:13<00:08, 20.93it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:11, 14.83it/s]
Loading 0:  55%|█████▌    | 200/363 [00:13<00:10, 15.47it/s]
Loading 0:  56%|█████▌    | 202/363 [00:28<04:23,  1.64s/it]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:52,  1.45s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:11,  1.19it/s]
Loading 0:  58%|█████▊    | 210/363 [00:29<01:30,  1.69it/s]
Loading 0:  59%|█████▊    | 213/363 [00:29<01:05,  2.29it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:53,  2.78it/s]
Loading 0:  60%|█████▉    | 217/363 [00:29<00:42,  3.42it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:33,  4.34it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:29,  4.88it/s]
Loading 0:  62%|██████▏   | 226/363 [00:30<00:15,  8.66it/s]
Loading 0:  63%|██████▎   | 230/363 [00:30<00:11, 11.92it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:12, 10.66it/s]
Loading 0:  65%|██████▌   | 236/363 [00:30<00:10, 11.93it/s]
Loading 0:  66%|██████▌   | 238/363 [00:31<00:10, 11.37it/s]
Loading 0:  66%|██████▌   | 240/363 [00:31<00:10, 11.36it/s]
Loading 0:  67%|██████▋   | 244/363 [00:31<00:08, 14.81it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:06, 18.09it/s]
Loading 0:  69%|██████▉   | 251/363 [00:32<00:08, 12.56it/s]
Loading 0:  70%|██████▉   | 253/363 [00:32<00:09, 12.08it/s]
Loading 0:  70%|███████   | 255/363 [00:32<00:08, 12.94it/s]
Loading 0:  71%|███████   | 257/363 [00:32<00:09, 10.84it/s]
Loading 0:  72%|███████▏  | 262/363 [00:32<00:06, 16.61it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:04, 19.93it/s]
Loading 0:  74%|███████▍  | 269/363 [00:33<00:06, 14.17it/s]
Loading 0:  75%|███████▍  | 271/363 [00:33<00:06, 13.33it/s]
Loading 0:  75%|███████▌  | 273/363 [00:33<00:06, 14.17it/s]
Loading 0:  76%|███████▌  | 275/363 [00:33<00:07, 11.14it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 16.64it/s]
Loading 0:  78%|███████▊  | 284/363 [00:34<00:03, 20.02it/s]
Loading 0:  79%|███████▉  | 287/363 [00:34<00:05, 14.16it/s]
Loading 0:  80%|███████▉  | 289/363 [00:34<00:05, 13.41it/s]
Loading 0:  80%|████████  | 291/363 [00:34<00:05, 14.15it/s]
Loading 0:  81%|████████  | 293/363 [00:34<00:06, 11.54it/s]
Loading 0:  82%|████████▏ | 298/363 [00:35<00:03, 17.33it/s]
Loading 0:  83%|████████▎ | 302/363 [00:35<00:02, 20.75it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:03, 14.51it/s]
Loading 0:  85%|████████▍ | 308/363 [00:35<00:03, 14.48it/s]
Loading 0:  85%|████████▌ | 310/363 [00:36<00:04, 12.25it/s]
Loading 0:  86%|████████▌ | 312/363 [00:36<00:04, 11.60it/s]
Loading 0:  87%|████████▋ | 316/363 [00:36<00:03, 15.51it/s]
Loading 0:  88%|████████▊ | 320/363 [00:36<00:02, 19.30it/s]
Loading 0:  89%|████████▉ | 323/363 [00:36<00:02, 13.94it/s]
Loading 0:  90%|████████▉ | 325/363 [00:37<00:02, 12.90it/s]
Loading 0:  90%|█████████ | 327/363 [00:37<00:02, 13.73it/s]
Loading 0:  91%|█████████ | 329/363 [00:37<00:03, 10.69it/s]
Loading 0:  92%|█████████▏| 334/363 [00:37<00:01, 15.85it/s]
Loading 0:  93%|█████████▎| 338/363 [00:37<00:01, 19.10it/s]
Loading 0:  94%|█████████▍| 341/363 [00:38<00:01, 13.55it/s]
Loading 0:  94%|█████████▍| 343/363 [00:38<00:01, 13.02it/s]
Loading 0:  95%|█████████▌| 345/363 [00:38<00:01, 13.75it/s]
Loading 0:  96%|█████████▌| 347/363 [00:38<00:01, 11.29it/s]
Loading 0:  97%|█████████▋| 352/363 [00:38<00:00, 17.00it/s]
Loading 0:  98%|█████████▊| 356/363 [00:39<00:00, 20.00it/s]
Loading 0:  99%|█████████▉| 359/363 [00:46<00:02,  1.46it/s]
Loading 0:  99%|█████████▉| 361/363 [00:46<00:01,  1.75it/s]
                                                            
Job rirv938-tune-mistral-gr-63526-v1-mkmlizer completed after 288.7s with status: succeeded
Stopping job with name rirv938-tune-mistral-gr-63526-v1-mkmlizer
Pipeline stage MKMLizer completed in 289.38s
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-tune-mistral-gr-63526-v1
Waiting for inference service rirv938-tune-mistral-gr-63526-v1 to be ready
Inference service rirv938-tune-mistral-gr-63526-v1 ready after 150.75420665740967s
Pipeline stage MKMLDeployer completed in 151.16s
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 2.4234769344329834s
Received healthy response to inference request in 1.977815866470337s
Received healthy response to inference request in 1.866145133972168s
Received healthy response to inference request in 2.0099527835845947s
5 requests
1 failed requests
5th percentile: 1.8884792804718018
10th percentile: 1.9108134269714356
20th percentile: 1.955481719970703
30th percentile: 1.9842432498931886
40th percentile: 1.9970980167388916
50th percentile: 2.0099527835845947
60th percentile: 2.1753624439239503
70th percentile: 2.3407721042633054
80th percentile: 5.966663599014286
90th percentile: 13.053036928176882
95th percentile: 16.596223592758175
99th percentile: 19.430772924423216
mean time: 5.683360195159912
%s, retrying in %s seconds...
Received healthy response to inference request in 1.826247215270996s
Received healthy response to inference request in 2.3843114376068115s
Received healthy response to inference request in 2.146885633468628s
Received healthy response to inference request in 1.852534532546997s
Received healthy response to inference request in 2.034518241882324s
5 requests
0 failed requests
5th percentile: 1.8315046787261964
10th percentile: 1.8367621421813964
20th percentile: 1.8472770690917968
30th percentile: 1.8889312744140625
40th percentile: 1.9617247581481934
50th percentile: 2.034518241882324
60th percentile: 2.0794651985168455
70th percentile: 2.1244121551513673
80th percentile: 2.1943707942962645
90th percentile: 2.289341115951538
95th percentile: 2.336826276779175
99th percentile: 2.3748144054412843
mean time: 2.0488994121551514
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 0.75s
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 0.71s
Shutdown handler de-registered
rirv938-tune-mistral-gr_63526_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-tune-mistral-gr-63526-v1-profiler
Waiting for inference service rirv938-tune-mistral-gr-63526-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 2688.11s
Shutdown handler de-registered
rirv938-tune-mistral-gr_63526_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-tune-mistral-gr_63526_v1 status is now torndown due to DeploymentManager action