rirv938-dpo-to-compare-_68956

developer_uid: rirv938

submission_id: rirv938-dpo-to-compare-_68956_v1

model_name: rirv938-dpo-to-compare-_68956_v1

model_group: rirv938/dpo_to_compare_t

status: torndown

timestamp: 2025-04-27T03:45:49+00:00

num_battles: 8981

num_wins: 4529

celo_rating: 1292.13

family_friendly_score: 0.5456

family_friendly_standard_error: 0.007041599818223129

submission_type: basic

model_repo: rirv938/dpo_to_compare_to_grpo_10k_cp186_b2_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': 0.5335522704888912, 'latency_mean': 1.8741760635375977, 'latency_p50': 1.8708962202072144, 'latency_p90': 2.0825090169906617}, {'batch_size': 3, 'throughput': 1.0787183102172961, 'latency_mean': 2.7720075500011445, 'latency_p50': 2.7819820642471313, 'latency_p90': 3.0307551860809325}, {'batch_size': 5, 'throughput': 1.3942891608623142, 'latency_mean': 3.576122941970825, 'latency_p50': 3.5484730005264282, 'latency_p90': 4.048906683921814}, {'batch_size': 6, 'throughput': 1.4959994127290361, 'latency_mean': 3.9739699828624726, 'latency_p50': 3.983788847923279, 'latency_p90': 4.447196221351623}, {'batch_size': 8, 'throughput': 1.641876982362086, 'latency_mean': 4.838544355630875, 'latency_p50': 4.806112051010132, 'latency_p90': 5.470020341873169}, {'batch_size': 10, 'throughput': 1.7364519184610352, 'latency_mean': 5.701370824575424, 'latency_p50': 5.626520037651062, 'latency_p90': 6.376654267311096}]

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

display_name: rirv938-dpo-to-compare-_68956_v1

is_internal_developer: True

language_model: rirv938/dpo_to_compare_to_grpo_10k_cp186_b2_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.44

us_pacific_date: 2025-04-26

win_ratio: 0.5042868277474669

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': 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-dpo-to-compare-68956-v1-mkmlizer
Waiting for job on rirv938-dpo-to-compare-68956-v1-mkmlizer to finish
rirv938-dpo-to-compare-68956-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║       /___/                                                         ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║                                                                     ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║                                                                     ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║                                                                     ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ║                                                                     ║
rirv938-dpo-to-compare-68956-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-dpo-to-compare-68956-v1-mkmlizer: Downloaded to shared memory in 171.155s
rirv938-dpo-to-compare-68956-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmps5pzbr_n, device:0
rirv938-dpo-to-compare-68956-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-dpo-to-compare-68956-v1-mkmlizer: quantized model in 77.890s
rirv938-dpo-to-compare-68956-v1-mkmlizer: Processed model rirv938/dpo_to_compare_to_grpo_10k_cp186_b2_merged in 249.046s
rirv938-dpo-to-compare-68956-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-dpo-to-compare-68956-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-dpo-to-compare-68956-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-dpo-to-compare-68956-v1
rirv938-dpo-to-compare-68956-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-dpo-to-compare-68956-v1/config.json
rirv938-dpo-to-compare-68956-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-dpo-to-compare-68956-v1/special_tokens_map.json
rirv938-dpo-to-compare-68956-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-dpo-to-compare-68956-v1/tokenizer_config.json
rirv938-dpo-to-compare-68956-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-dpo-to-compare-68956-v1/tokenizer.json
rirv938-dpo-to-compare-68956-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-dpo-to-compare-68956-v1/flywheel_model.1.safetensors
rirv938-dpo-to-compare-68956-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-dpo-to-compare-68956-v1/flywheel_model.0.safetensors
rirv938-dpo-to-compare-68956-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:56,  6.41it/s]
Loading 0:   1%|          | 4/363 [00:00<01:31,  3.92it/s]
Loading 0:   1%|▏         | 5/363 [00:01<01:51,  3.22it/s]
Loading 0:   3%|▎         | 10/363 [00:01<00:41,  8.49it/s]
Loading 0:   3%|▎         | 12/363 [00:01<00:39,  8.98it/s]
Loading 0:   4%|▍         | 14/363 [00:01<00:40,  8.54it/s]
Loading 0:   4%|▍         | 16/363 [00:02<00:37,  9.21it/s]
Loading 0:   5%|▌         | 19/363 [00:02<00:27, 12.40it/s]
Loading 0:   6%|▌         | 21/363 [00:02<00:25, 13.39it/s]
Loading 0:   6%|▋         | 23/363 [00:02<00:31, 10.84it/s]
Loading 0:   8%|▊         | 28/363 [00:02<00:19, 17.00it/s]
Loading 0:   9%|▉         | 32/363 [00:02<00:16, 20.43it/s]
Loading 0:  10%|▉         | 35/363 [00:03<00:23, 13.93it/s]
Loading 0:  10%|█         | 37/363 [00:03<00:24, 13.34it/s]
Loading 0:  11%|█         | 39/363 [00:03<00:22, 14.14it/s]
Loading 0:  11%|█▏        | 41/363 [00:03<00:28, 11.41it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:18, 17.03it/s]
Loading 0:  14%|█▍        | 50/363 [00:04<00:15, 20.39it/s]
Loading 0:  15%|█▍        | 53/363 [00:04<00:22, 13.98it/s]
Loading 0:  15%|█▌        | 55/363 [00:04<00:24, 12.75it/s]
Loading 0:  16%|█▌        | 57/363 [00:04<00:22, 13.72it/s]
Loading 0:  16%|█▋        | 59/363 [00:05<00:27, 11.01it/s]
Loading 0:  18%|█▊        | 64/363 [00:05<00:18, 16.40it/s]
Loading 0:  19%|█▊        | 68/363 [00:05<00:15, 19.39it/s]
Loading 0:  20%|█▉        | 71/363 [00:05<00:21, 13.56it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:22, 12.98it/s]
Loading 0:  21%|██        | 75/363 [00:06<00:20, 13.83it/s]
Loading 0:  21%|██        | 77/363 [00:06<00:25, 11.30it/s]
Loading 0:  23%|██▎       | 82/363 [00:06<00:16, 16.84it/s]
Loading 0:  24%|██▎       | 86/363 [00:06<00:13, 20.00it/s]
Loading 0:  25%|██▍       | 89/363 [00:07<00:19, 14.09it/s]
Loading 0:  25%|██▌       | 91/363 [00:07<00:20, 13.45it/s]
Loading 0:  26%|██▌       | 95/363 [00:07<00:15, 17.18it/s]
Loading 0:  27%|██▋       | 99/363 [00:07<00:12, 20.32it/s]
Loading 0:  28%|██▊       | 102/363 [00:07<00:14, 18.51it/s]
Loading 0:  29%|██▉       | 105/363 [00:08<00:19, 13.50it/s]
Loading 0:  29%|██▉       | 107/363 [00:08<00:20, 12.70it/s]
Loading 0:  30%|███       | 109/363 [00:08<00:20, 12.37it/s]
Loading 0:  31%|███       | 111/363 [00:08<00:18, 13.36it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:22, 11.06it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:14, 16.77it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:12, 19.95it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:17, 13.98it/s]
Loading 0:  35%|███▍      | 127/363 [00:09<00:17, 13.24it/s]
Loading 0:  36%|███▌      | 129/363 [00:09<00:16, 14.17it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:20, 11.54it/s]
Loading 0:  37%|███▋      | 136/363 [00:10<00:13, 17.19it/s]
Loading 0:  39%|███▊      | 140/363 [00:10<00:11, 20.17it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:15, 14.43it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:15, 13.73it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:14, 14.60it/s]
Loading 0:  41%|████      | 149/363 [00:11<00:18, 11.80it/s]
Loading 0:  42%|████▏     | 154/363 [00:11<00:11, 17.62it/s]
Loading 0:  44%|████▎     | 158/363 [00:11<00:09, 20.83it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:13, 14.61it/s]
Loading 0:  45%|████▍     | 163/363 [00:11<00:14, 13.86it/s]
Loading 0:  45%|████▌     | 165/363 [00:12<00:13, 14.76it/s]
Loading 0:  46%|████▌     | 167/363 [00:12<00:16, 12.02it/s]
Loading 0:  47%|████▋     | 172/363 [00:12<00:10, 17.78it/s]
Loading 0:  48%|████▊     | 176/363 [00:12<00:08, 21.10it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:12, 14.94it/s]
Loading 0:  50%|█████     | 182/363 [00:13<00:11, 15.54it/s]
Loading 0:  51%|█████     | 184/363 [00:13<00:12, 13.79it/s]
Loading 0:  51%|█████     | 186/363 [00:13<00:13, 13.21it/s]
Loading 0:  52%|█████▏    | 190/363 [00:13<00:09, 17.33it/s]
Loading 0:  53%|█████▎    | 194/363 [00:13<00:08, 20.67it/s]
Loading 0:  54%|█████▍    | 197/363 [00:14<00:11, 14.30it/s]
Loading 0:  55%|█████▍    | 199/363 [00:14<00:12, 13.58it/s]
Loading 0:  55%|█████▌    | 200/363 [00:34<00:12, 13.58it/s]
Loading 0:  55%|█████▌    | 201/363 [00:34<06:18,  2.34s/it]
Loading 0:  56%|█████▌    | 203/363 [00:34<04:47,  1.80s/it]
Loading 0:  57%|█████▋    | 207/363 [00:34<02:45,  1.06s/it]
Loading 0:  58%|█████▊    | 210/363 [00:34<01:54,  1.33it/s]
Loading 0:  59%|█████▊    | 213/363 [00:34<01:22,  1.81it/s]
Loading 0:  59%|█████▉    | 215/363 [00:35<01:06,  2.22it/s]
Loading 0:  60%|█████▉    | 217/363 [00:35<00:53,  2.73it/s]
Loading 0:  60%|██████    | 219/363 [00:35<00:41,  3.51it/s]
Loading 0:  61%|██████    | 221/363 [00:35<00:34,  4.10it/s]
Loading 0:  62%|██████▏   | 226/363 [00:35<00:18,  7.36it/s]
Loading 0:  63%|██████▎   | 230/363 [00:35<00:13, 10.19it/s]
Loading 0:  64%|██████▍   | 233/363 [00:36<00:13,  9.67it/s]
Loading 0:  65%|██████▍   | 235/363 [00:36<00:12, 10.07it/s]
Loading 0:  65%|██████▌   | 237/363 [00:36<00:11, 11.28it/s]
Loading 0:  66%|██████▌   | 239/363 [00:36<00:12, 10.08it/s]
Loading 0:  67%|██████▋   | 244/363 [00:36<00:07, 15.59it/s]
Loading 0:  68%|██████▊   | 248/363 [00:37<00:05, 19.36it/s]
Loading 0:  69%|██████▉   | 251/363 [00:37<00:07, 14.61it/s]
Loading 0:  70%|██████▉   | 254/363 [00:37<00:07, 15.33it/s]
Loading 0:  71%|███████   | 257/363 [00:37<00:08, 12.29it/s]
Loading 0:  72%|███████▏  | 262/363 [00:38<00:05, 17.24it/s]
Loading 0:  73%|███████▎  | 266/363 [00:38<00:04, 20.34it/s]
Loading 0:  74%|███████▍  | 269/363 [00:38<00:06, 15.16it/s]
Loading 0:  75%|███████▍  | 272/363 [00:38<00:05, 15.73it/s]
Loading 0:  76%|███████▌  | 275/363 [00:39<00:07, 12.45it/s]
Loading 0:  77%|███████▋  | 280/363 [00:39<00:04, 17.27it/s]
Loading 0:  78%|███████▊  | 284/363 [00:39<00:03, 20.40it/s]
Loading 0:  79%|███████▉  | 287/363 [00:39<00:05, 15.18it/s]
Loading 0:  80%|███████▉  | 290/363 [00:39<00:04, 15.85it/s]
Loading 0:  81%|████████  | 293/363 [00:40<00:05, 12.06it/s]
Loading 0:  82%|████████▏ | 298/363 [00:40<00:03, 16.64it/s]
Loading 0:  83%|████████▎ | 302/363 [00:40<00:03, 19.60it/s]
Loading 0:  84%|████████▍ | 305/363 [00:40<00:03, 14.52it/s]
Loading 0:  85%|████████▍ | 308/363 [00:40<00:03, 15.08it/s]
Loading 0:  85%|████████▌ | 310/363 [00:41<00:03, 13.59it/s]
Loading 0:  86%|████████▌ | 312/363 [00:41<00:03, 13.08it/s]
Loading 0:  87%|████████▋ | 316/363 [00:41<00:02, 17.13it/s]
Loading 0:  88%|████████▊ | 320/363 [00:41<00:02, 20.72it/s]
Loading 0:  89%|████████▉ | 323/363 [00:41<00:02, 14.62it/s]
Loading 0:  90%|████████▉ | 325/363 [00:42<00:02, 13.88it/s]
Loading 0:  90%|█████████ | 327/363 [00:42<00:02, 14.59it/s]
Loading 0:  91%|█████████ | 329/363 [00:42<00:02, 11.69it/s]
Loading 0:  92%|█████████▏| 334/363 [00:42<00:01, 17.30it/s]
Loading 0:  93%|█████████▎| 338/363 [00:42<00:01, 20.11it/s]
Loading 0:  94%|█████████▍| 341/363 [00:43<00:01, 13.53it/s]
Loading 0:  94%|█████████▍| 343/363 [00:43<00:01, 12.93it/s]
Loading 0:  95%|█████████▌| 345/363 [00:43<00:01, 13.74it/s]
Loading 0:  96%|█████████▌| 347/363 [00:43<00:01, 11.12it/s]
Loading 0:  97%|█████████▋| 352/363 [00:43<00:00, 16.77it/s]
Loading 0:  98%|█████████▊| 356/363 [00:44<00:00, 20.06it/s]
Loading 0:  99%|█████████▉| 359/363 [00:51<00:02,  1.40it/s]
Loading 0:  99%|█████████▉| 361/363 [00:51<00:01,  1.67it/s]
                                                            
Job rirv938-dpo-to-compare-68956-v1-mkmlizer completed after 278.9s with status: succeeded
Stopping job with name rirv938-dpo-to-compare-68956-v1-mkmlizer
Pipeline stage MKMLizer completed in 279.40s
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-dpo-to-compare-68956-v1
Waiting for inference service rirv938-dpo-to-compare-68956-v1 to be ready
Inference service rirv938-dpo-to-compare-68956-v1 ready after 120.68441915512085s
Pipeline stage MKMLDeployer completed in 121.12s
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 2.9112560749053955s
Received healthy response to inference request in 2.0641109943389893s
Received healthy response to inference request in 2.1516168117523193s
Received healthy response to inference request in 1.7150335311889648s
5 requests
1 failed requests
5th percentile: 1.7848490238189698
10th percentile: 1.8546645164489746
20th percentile: 1.9942955017089843
30th percentile: 2.081612157821655
40th percentile: 2.116614484786987
50th percentile: 2.1516168117523193
60th percentile: 2.4554725170135496
70th percentile: 2.75932822227478
80th percentile: 6.354795026779177
90th percentile: 13.241872930526736
95th percentile: 16.68541188240051
99th percentile: 19.440243043899535
mean time: 5.7941936492919925
%s, retrying in %s seconds...
Received healthy response to inference request in 1.7666897773742676s
Received healthy response to inference request in 2.273136854171753s
Received healthy response to inference request in 2.1310653686523438s
Received healthy response to inference request in 1.7697296142578125s
Received healthy response to inference request in 2.0465614795684814s
5 requests
0 failed requests
5th percentile: 1.7672977447509766
10th percentile: 1.7679057121276855
20th percentile: 1.7691216468811035
30th percentile: 1.8250959873199464
40th percentile: 1.935828733444214
50th percentile: 2.0465614795684814
60th percentile: 2.0803630352020264
70th percentile: 2.1141645908355713
80th percentile: 2.1594796657562254
90th percentile: 2.216308259963989
95th percentile: 2.2447225570678713
99th percentile: 2.2674539947509764
mean time: 1.9974366188049317
Pipeline stage StressChecker completed in 41.51s
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 0.72s
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 0.66s
Shutdown handler de-registered
rirv938-dpo-to-compare-_68956_v1 status is now deployed due to DeploymentManager action
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 4994.83s
Shutdown handler de-registered
rirv938-dpo-to-compare-_68956_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-dpo-to-compare-_68956_v1 status is now torndown due to DeploymentManager action