rirv938-grpo-to-compare_34174

developer_uid: rirv938

submission_id: rirv938-grpo-to-compare_34174_v1

model_name: rirv938-grpo-to-compare_34174_v1

model_group: rirv938/grpo_to_compare_

status: torndown

timestamp: 2025-04-26T07:10:45+00:00

num_battles: 11379

num_wins: 5943

celo_rating: 1303.28

family_friendly_score: 0.5571999999999999

family_friendly_standard_error: 0.007024644617345421

submission_type: basic

model_repo: rirv938/grpo_to_compare_to_dpo_10k_cp312_lr8_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': 0.5297077879997615, 'latency_mean': 1.887766765356064, 'latency_p50': 1.8849256038665771, 'latency_p90': 2.104369354248047}, {'batch_size': 3, 'throughput': 1.0785139857472055, 'latency_mean': 2.7739807605743407, 'latency_p50': 2.795102834701538, 'latency_p90': 3.0435335874557494}, {'batch_size': 5, 'throughput': 1.401494280912709, 'latency_mean': 3.552708990573883, 'latency_p50': 3.569620728492737, 'latency_p90': 3.9828147649765016}, {'batch_size': 6, 'throughput': 1.507393778660486, 'latency_mean': 3.9589658749103545, 'latency_p50': 3.974922776222229, 'latency_p90': 4.408943939208984}, {'batch_size': 8, 'throughput': 1.6589646554758928, 'latency_mean': 4.7807218921184536, 'latency_p50': 4.815690040588379, 'latency_p90': 5.385302448272705}, {'batch_size': 10, 'throughput': 1.754911780757197, 'latency_mean': 5.649211046695709, 'latency_p50': 5.645291566848755, 'latency_p90': 6.376655888557434}]

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

display_name: rirv938-grpo-to-compare_34174_v1

is_internal_developer: True

language_model: rirv938/grpo_to_compare_to_dpo_10k_cp312_lr8_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.45

us_pacific_date: 2025-04-26

win_ratio: 0.5222778803058266

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': 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-grpo-to-compare-34174-v1-mkmlizer
Waiting for job on rirv938-grpo-to-compare-34174-v1-mkmlizer to finish
rirv938-grpo-to-compare-34174-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║       /___/                                                         ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-34174-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-grpo-to-compare-34174-v1-mkmlizer: Downloaded to shared memory in 156.183s
rirv938-grpo-to-compare-34174-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdl1gx3sa, device:0
rirv938-grpo-to-compare-34174-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-grpo-to-compare-34174-v1-mkmlizer: quantized model in 66.734s
rirv938-grpo-to-compare-34174-v1-mkmlizer: Processed model rirv938/grpo_to_compare_to_dpo_10k_cp312_lr8_merged in 222.918s
rirv938-grpo-to-compare-34174-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-grpo-to-compare-34174-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-grpo-to-compare-34174-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v1
rirv938-grpo-to-compare-34174-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v1/config.json
rirv938-grpo-to-compare-34174-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v1/special_tokens_map.json
rirv938-grpo-to-compare-34174-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v1/tokenizer_config.json
rirv938-grpo-to-compare-34174-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v1/tokenizer.json
rirv938-grpo-to-compare-34174-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v1/flywheel_model.1.safetensors
rirv938-grpo-to-compare-34174-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-34174-v1/flywheel_model.0.safetensors
rirv938-grpo-to-compare-34174-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 27.81it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.41it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 20.87it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:27, 12.79it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:27, 12.65it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.33it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:26, 12.88it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.15it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.18it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.79it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:21, 15.31it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:24, 13.45it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:24, 13.11it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 17.70it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:14, 21.95it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 14.90it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 15.36it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:22, 13.43it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:24, 12.49it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:18, 16.39it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:15, 19.59it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:21, 13.28it/s]
Loading 0:  20%|██        | 73/363 [00:04<00:22, 12.68it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:21, 13.37it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:26, 10.99it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 16.66it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:14, 19.71it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:20, 13.49it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:21, 12.70it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:16, 16.33it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:13, 19.43it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:14, 17.46it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:19, 13.02it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:21, 12.04it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:21, 11.69it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:19, 12.61it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:23, 10.60it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.01it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.29it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:15, 14.97it/s]
Loading 0:  35%|███▌      | 128/363 [00:08<00:14, 15.81it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.47it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.83it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:10, 21.61it/s]
Loading 0:  40%|███▉      | 144/363 [00:09<00:16, 13.42it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:14, 15.22it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:15, 13.81it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 17.28it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 20.56it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 14.57it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:13, 15.16it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:16, 11.85it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 16.40it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 19.37it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:13, 14.14it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:12, 14.70it/s]
Loading 0:  51%|█████     | 184/363 [00:12<00:13, 12.96it/s]
Loading 0:  51%|█████     | 186/363 [00:12<00:14, 12.08it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 15.94it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 19.36it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:12, 13.26it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:13, 12.49it/s]
Loading 0:  55%|█████▌    | 201/363 [00:28<04:55,  1.82s/it]
Loading 0:  56%|█████▌    | 202/363 [00:28<04:14,  1.58s/it]
Loading 0:  56%|█████▌    | 204/363 [00:28<03:03,  1.16s/it]
Loading 0:  57%|█████▋    | 207/363 [00:29<01:53,  1.37it/s]
Loading 0:  58%|█████▊    | 210/363 [00:29<01:14,  2.05it/s]
Loading 0:  58%|█████▊    | 212/363 [00:29<00:57,  2.62it/s]
Loading 0:  59%|█████▉    | 214/363 [00:29<00:47,  3.16it/s]
Loading 0:  60%|█████▉    | 216/363 [00:29<00:39,  3.72it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:26,  5.42it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:24,  5.72it/s]
Loading 0:  62%|██████▏   | 226/363 [00:30<00:14,  9.74it/s]
Loading 0:  63%|██████▎   | 230/363 [00:30<00:10, 12.95it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:12, 10.81it/s]
Loading 0:  65%|██████▍   | 235/363 [00:31<00:11, 10.86it/s]
Loading 0:  65%|██████▌   | 237/363 [00:31<00:10, 11.86it/s]
Loading 0:  66%|██████▌   | 239/363 [00:31<00:12, 10.22it/s]
Loading 0:  67%|██████▋   | 244/363 [00:31<00:08, 14.85it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:06, 18.02it/s]
Loading 0:  69%|██████▉   | 251/363 [00:32<00:08, 12.92it/s]
Loading 0:  70%|██████▉   | 253/363 [00:32<00:08, 12.57it/s]
Loading 0:  70%|███████   | 255/363 [00:32<00:08, 13.39it/s]
Loading 0:  71%|███████   | 257/363 [00:32<00:09, 11.32it/s]
Loading 0:  72%|███████▏  | 262/363 [00:32<00:05, 17.66it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:04, 21.83it/s]
Loading 0:  74%|███████▍  | 269/363 [00:33<00:06, 15.37it/s]
Loading 0:  75%|███████▍  | 272/363 [00:33<00:05, 16.02it/s]
Loading 0:  76%|███████▌  | 275/363 [00:33<00:07, 12.45it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 17.43it/s]
Loading 0:  78%|███████▊  | 284/363 [00:34<00:03, 20.02it/s]
Loading 0:  79%|███████▉  | 287/363 [00:34<00:05, 13.58it/s]
Loading 0:  80%|███████▉  | 290/363 [00:34<00:05, 14.06it/s]
Loading 0:  80%|████████  | 292/363 [00:34<00:05, 12.66it/s]
Loading 0:  81%|████████  | 294/363 [00:35<00:05, 12.31it/s]
Loading 0:  82%|████████▏ | 298/363 [00:35<00:04, 16.04it/s]
Loading 0:  83%|████████▎ | 302/363 [00:35<00:03, 19.32it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:04, 13.18it/s]
Loading 0:  85%|████████▍ | 307/363 [00:35<00:04, 12.70it/s]
Loading 0:  85%|████████▌ | 309/363 [00:36<00:04, 13.48it/s]
Loading 0:  86%|████████▌ | 311/363 [00:36<00:04, 10.97it/s]
Loading 0:  87%|████████▋ | 316/363 [00:36<00:02, 16.54it/s]
Loading 0:  88%|████████▊ | 320/363 [00:36<00:02, 19.55it/s]
Loading 0:  89%|████████▉ | 323/363 [00:37<00:02, 13.83it/s]
Loading 0:  90%|████████▉ | 325/363 [00:37<00:02, 13.36it/s]
Loading 0:  90%|█████████ | 327/363 [00:37<00:02, 14.12it/s]
Loading 0:  91%|█████████ | 329/363 [00:37<00:02, 11.53it/s]
Loading 0:  92%|█████████▏| 334/363 [00:37<00:01, 17.59it/s]
Loading 0:  93%|█████████▎| 338/363 [00:37<00:01, 21.10it/s]
Loading 0:  94%|█████████▍| 341/363 [00:38<00:01, 15.00it/s]
Loading 0:  95%|█████████▍| 344/363 [00:38<00:01, 15.71it/s]
Loading 0:  96%|█████████▌| 347/363 [00:38<00:01, 12.17it/s]
Loading 0:  97%|█████████▋| 352/363 [00:38<00:00, 16.87it/s]
Loading 0:  98%|█████████▊| 356/363 [00:39<00:00, 19.67it/s]
Loading 0:  99%|█████████▉| 359/363 [00:46<00:02,  1.53it/s]
Loading 0:  99%|█████████▉| 361/363 [00:46<00:01,  1.81it/s]
                                                            
Job rirv938-grpo-to-compare-34174-v1-mkmlizer completed after 269.64s with status: succeeded
Stopping job with name rirv938-grpo-to-compare-34174-v1-mkmlizer
Pipeline stage MKMLizer completed in 270.13s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-grpo-to-compare-34174-v1
Waiting for inference service rirv938-grpo-to-compare-34174-v1 to be ready
Inference service rirv938-grpo-to-compare-34174-v1 ready after 140.48445534706116s
Pipeline stage MKMLDeployer completed in 140.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.228882312774658s
Received healthy response to inference request in 1.9354777336120605s
Received healthy response to inference request in 2.104870557785034s
Received healthy response to inference request in 2.1842386722564697s
Received healthy response to inference request in 1.9717366695404053s
5 requests
0 failed requests
5th percentile: 1.9427295207977295
10th percentile: 1.9499813079833985
20th percentile: 1.9644848823547363
30th percentile: 1.998363447189331
40th percentile: 2.0516170024871827
50th percentile: 2.104870557785034
60th percentile: 2.1366178035736083
70th percentile: 2.1683650493621824
80th percentile: 2.3931674003601078
90th percentile: 2.811024856567383
95th percentile: 3.01995358467102
99th percentile: 3.1870965671539304
mean time: 2.2850411891937257
Pipeline stage StressChecker completed in 12.77s
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 0.76s
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 0.65s
Shutdown handler de-registered
rirv938-grpo-to-compare_34174_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 0.13s
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-grpo-to-compare-34174-v1-profiler
Waiting for inference service rirv938-grpo-to-compare-34174-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 4805.75s
Shutdown handler de-registered
rirv938-grpo-to-compare_34174_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-grpo-to-compare_34174_v1 status is now torndown due to DeploymentManager action