developer_uid: rirv938
submission_id: rirv938-dpo-to-compare-_51776_v1
model_name: rirv938-dpo-to-compare-_51776_v1
model_group: rirv938/dpo_to_compare_t
status: torndown
timestamp: 2025-04-25T17:31:16+00:00
num_battles: 6679
num_wins: 3393
celo_rating: 1289.09
family_friendly_score: 0.55
family_friendly_standard_error: 0.007035623639735145
submission_type: basic
model_repo: rirv938/dpo_to_compare_to_grpo_10k_cp248_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': 0.5263679416053336, 'latency_mean': 1.8997577559947967, 'latency_p50': 1.9019994735717773, 'latency_p90': 2.087495136260986}, {'batch_size': 3, 'throughput': 1.0865031972792822, 'latency_mean': 2.7500111198425294, 'latency_p50': 2.7313318252563477, 'latency_p90': 3.067477250099182}, {'batch_size': 5, 'throughput': 1.398788413539436, 'latency_mean': 3.5555703949928286, 'latency_p50': 3.5738720893859863, 'latency_p90': 3.8894737720489503}, {'batch_size': 6, 'throughput': 1.5116528454041827, 'latency_mean': 3.9397326207160948, 'latency_p50': 3.9515795707702637, 'latency_p90': 4.479708957672119}, {'batch_size': 8, 'throughput': 1.6614214407644603, 'latency_mean': 4.781732993125916, 'latency_p50': 4.8203898668289185, 'latency_p90': 5.385911202430725}, {'batch_size': 10, 'throughput': 1.7594884080592328, 'latency_mean': 5.628157602548599, 'latency_p50': 5.606758713722229, 'latency_p90': 6.3297295570373535}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-dpo-to-compare-_51776_v1
is_internal_developer: True
language_model: rirv938/dpo_to_compare_to_grpo_10k_cp248_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.45
us_pacific_date: 2025-04-25
win_ratio: 0.5080101811648451
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': ['\n', '###', '</s>', 'You:'], '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-51776-v1-mkmlizer
Waiting for job on rirv938-dpo-to-compare-51776-v1-mkmlizer to finish
rirv938-dpo-to-compare-51776-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ _____ __ __ ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ /___/ ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ belonging to: ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ║ ║
rirv938-dpo-to-compare-51776-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-dpo-to-compare-51776-v1-mkmlizer: Downloaded to shared memory in 190.629s
rirv938-dpo-to-compare-51776-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0vpji938, device:0
rirv938-dpo-to-compare-51776-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-dpo-to-compare-51776-v1-mkmlizer: quantized model in 65.088s
rirv938-dpo-to-compare-51776-v1-mkmlizer: Processed model rirv938/dpo_to_compare_to_grpo_10k_cp248_merged in 255.727s
rirv938-dpo-to-compare-51776-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-dpo-to-compare-51776-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-dpo-to-compare-51776-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-dpo-to-compare-51776-v1
rirv938-dpo-to-compare-51776-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-dpo-to-compare-51776-v1/config.json
rirv938-dpo-to-compare-51776-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-dpo-to-compare-51776-v1/special_tokens_map.json
rirv938-dpo-to-compare-51776-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-dpo-to-compare-51776-v1/tokenizer_config.json
rirv938-dpo-to-compare-51776-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-dpo-to-compare-51776-v1/tokenizer.json
rirv938-dpo-to-compare-51776-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-dpo-to-compare-51776-v1/flywheel_model.1.safetensors
rirv938-dpo-to-compare-51776-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-dpo-to-compare-51776-v1/flywheel_model.0.safetensors
rirv938-dpo-to-compare-51776-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:18, 19.75it/s] Loading 0: 2%|▏ | 6/363 [00:00<00:26, 13.65it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:17, 20.08it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:24, 14.15it/s] Loading 0: 4%|▍ | 15/363 [00:01<00:30, 11.33it/s] Loading 0: 5%|▌ | 19/363 [00:01<00:21, 16.21it/s] Loading 0: 6%|▌ | 22/363 [00:01<00:22, 15.32it/s] Loading 0: 7%|▋ | 24/363 [00:01<00:24, 14.06it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:18, 18.35it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:15, 21.87it/s] Loading 0: 10%|▉ | 35/363 [00:02<00:22, 14.85it/s] Loading 0: 10%|█ | 38/363 [00:02<00:21, 15.25it/s] Loading 0: 11%|█ | 40/363 [00:02<00:23, 13.47it/s] Loading 0: 12%|█▏ | 42/363 [00:02<00:25, 12.70it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:18, 16.93it/s] Loading 0: 14%|█▍ | 50/363 [00:03<00:15, 20.74it/s] Loading 0: 15%|█▍ | 53/363 [00:03<00:21, 14.36it/s] Loading 0: 15%|█▌ | 55/363 [00:03<00:22, 13.64it/s] Loading 0: 16%|█▌ | 57/363 [00:03<00:21, 14.46it/s] Loading 0: 16%|█▋ | 59/363 [00:04<00:26, 11.29it/s] Loading 0: 18%|█▊ | 64/363 [00:04<00:17, 17.24it/s] Loading 0: 19%|█▊ | 68/363 [00:04<00:14, 20.94it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:19, 14.93it/s] Loading 0: 20%|██ | 74/363 [00:04<00:18, 15.23it/s] Loading 0: 21%|██ | 76/363 [00:05<00:21, 13.43it/s] Loading 0: 21%|██▏ | 78/363 [00:05<00:22, 12.88it/s] Loading 0: 23%|██▎ | 82/363 [00:05<00:16, 17.11it/s] Loading 0: 24%|██▎ | 86/363 [00:05<00:13, 20.75it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:18, 14.48it/s] Loading 0: 25%|██▌ | 91/363 [00:05<00:20, 13.49it/s] Loading 0: 26%|██▌ | 95/363 [00:06<00:15, 17.15it/s] Loading 0: 27%|██▋ | 99/363 [00:06<00:12, 20.43it/s] Loading 0: 28%|██▊ | 102/363 [00:06<00:14, 18.62it/s] Loading 0: 29%|██▉ | 105/363 [00:06<00:18, 14.07it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:19, 12.92it/s] Loading 0: 30%|███ | 109/363 [00:07<00:20, 12.33it/s] Loading 0: 31%|███ | 111/363 [00:07<00:19, 13.24it/s] Loading 0: 31%|███ | 113/363 [00:07<00:22, 11.05it/s] Loading 0: 33%|███▎ | 118/363 [00:07<00:14, 17.35it/s] Loading 0: 34%|███▎ | 122/363 [00:07<00:11, 21.09it/s] Loading 0: 34%|███▍ | 125/363 [00:08<00:15, 14.96it/s] Loading 0: 35%|███▌ | 128/363 [00:08<00:15, 15.40it/s] Loading 0: 36%|███▌ | 130/363 [00:08<00:17, 13.61it/s] Loading 0: 36%|███▋ | 132/363 [00:08<00:17, 13.13it/s] Loading 0: 37%|███▋ | 136/363 [00:08<00:13, 17.42it/s] Loading 0: 39%|███▊ | 140/363 [00:08<00:10, 21.11it/s] Loading 0: 39%|███▉ | 143/363 [00:09<00:14, 14.68it/s] Loading 0: 40%|███▉ | 145/363 [00:09<00:15, 13.76it/s] Loading 0: 40%|████ | 147/363 [00:09<00:14, 14.55it/s] Loading 0: 41%|████ | 149/363 [00:09<00:18, 11.49it/s] Loading 0: 42%|████▏ | 154/363 [00:09<00:11, 17.65it/s] Loading 0: 44%|████▎ | 158/363 [00:10<00:09, 21.16it/s] Loading 0: 44%|████▍ | 161/363 [00:10<00:13, 14.84it/s] Loading 0: 45%|████▌ | 164/363 [00:10<00:12, 15.40it/s] Loading 0: 46%|████▌ | 166/363 [00:10<00:14, 13.59it/s] Loading 0: 46%|████▋ | 168/363 [00:11<00:15, 13.00it/s] Loading 0: 47%|████▋ | 172/363 [00:11<00:10, 17.37it/s] Loading 0: 48%|████▊ | 176/363 [00:11<00:08, 21.25it/s] Loading 0: 49%|████▉ | 179/363 [00:11<00:12, 14.68it/s] Loading 0: 50%|█████ | 182/363 [00:11<00:11, 15.17it/s] Loading 0: 51%|█████ | 184/363 [00:12<00:13, 13.49it/s] Loading 0: 51%|█████ | 186/363 [00:12<00:13, 12.92it/s] Loading 0: 52%|█████▏ | 190/363 [00:12<00:09, 17.31it/s] Loading 0: 53%|█████▎ | 194/363 [00:12<00:07, 21.23it/s] Loading 0: 54%|█████▍ | 197/363 [00:12<00:11, 14.58it/s] Loading 0: 55%|█████▌ | 200/363 [00:12<00:10, 15.25it/s] Loading 0: 56%|█████▌ | 202/363 [00:27<04:25, 1.65s/it] Loading 0: 56%|█████▌ | 203/363 [00:28<03:53, 1.46s/it] Loading 0: 57%|█████▋ | 207/363 [00:28<02:11, 1.19it/s] Loading 0: 58%|█████▊ | 210/363 [00:28<01:30, 1.69it/s] Loading 0: 59%|█████▊ | 213/363 [00:28<01:05, 2.28it/s] Loading 0: 59%|█████▉ | 215/363 [00:28<00:53, 2.77it/s] Loading 0: 60%|█████▉ | 217/363 [00:29<00:43, 3.38it/s] Loading 0: 60%|██████ | 219/363 [00:29<00:33, 4.29it/s] Loading 0: 61%|██████ | 221/363 [00:29<00:29, 4.83it/s] Loading 0: 62%|██████▏ | 226/363 [00:29<00:16, 8.56it/s] Loading 0: 63%|██████▎ | 230/363 [00:29<00:11, 11.66it/s] Loading 0: 64%|██████▍ | 233/363 [00:30<00:12, 10.51it/s] Loading 0: 65%|██████▌ | 236/363 [00:30<00:10, 11.81it/s] Loading 0: 66%|██████▌ | 238/363 [00:30<00:11, 11.25it/s] Loading 0: 66%|██████▌ | 240/363 [00:30<00:10, 11.31it/s] Loading 0: 67%|██████▋ | 244/363 [00:30<00:07, 15.50it/s] Loading 0: 68%|██████▊ | 248/363 [00:30<00:05, 19.35it/s] Loading 0: 69%|██████▉ | 251/363 [00:31<00:07, 14.09it/s] Loading 0: 70%|██████▉ | 253/363 [00:31<00:08, 13.35it/s] Loading 0: 70%|███████ | 255/363 [00:31<00:07, 14.17it/s] Loading 0: 71%|███████ | 257/363 [00:31<00:09, 11.49it/s] Loading 0: 72%|███████▏ | 262/363 [00:31<00:05, 17.44it/s] Loading 0: 73%|███████▎ | 266/363 [00:31<00:04, 20.78it/s] Loading 0: 74%|███████▍ | 269/363 [00:32<00:06, 14.55it/s] Loading 0: 75%|███████▍ | 272/363 [00:32<00:06, 15.09it/s] Loading 0: 75%|███████▌ | 274/363 [00:32<00:06, 13.37it/s] Loading 0: 76%|███████▌ | 276/363 [00:32<00:06, 12.77it/s] Loading 0: 77%|███████▋ | 280/363 [00:33<00:04, 17.02it/s] Loading 0: 78%|███████▊ | 284/363 [00:33<00:03, 21.04it/s] Loading 0: 79%|███████▉ | 287/363 [00:33<00:05, 14.92it/s] Loading 0: 80%|███████▉ | 290/363 [00:33<00:04, 15.59it/s] Loading 0: 80%|████████ | 292/363 [00:33<00:05, 13.80it/s] Loading 0: 81%|████████ | 294/363 [00:34<00:05, 13.05it/s] Loading 0: 82%|████████▏ | 298/363 [00:34<00:03, 17.46it/s] Loading 0: 83%|████████▎ | 302/363 [00:34<00:02, 21.53it/s] Loading 0: 84%|████████▍ | 305/363 [00:34<00:03, 15.20it/s] Loading 0: 85%|████████▍ | 308/363 [00:34<00:03, 15.85it/s] Loading 0: 85%|████████▌ | 310/363 [00:35<00:03, 13.92it/s] Loading 0: 86%|████████▌ | 312/363 [00:35<00:03, 13.35it/s] Loading 0: 87%|████████▋ | 316/363 [00:35<00:02, 17.78it/s] Loading 0: 88%|████████▊ | 320/363 [00:35<00:02, 21.36it/s] Loading 0: 89%|████████▉ | 323/363 [00:35<00:02, 15.13it/s] Loading 0: 90%|████████▉ | 325/363 [00:35<00:02, 14.12it/s] Loading 0: 90%|█████████ | 327/363 [00:36<00:02, 14.74it/s] Loading 0: 91%|█████████ | 329/363 [00:36<00:02, 11.60it/s] Loading 0: 92%|█████████▏| 334/363 [00:36<00:01, 17.73it/s] Loading 0: 93%|█████████▎| 338/363 [00:36<00:01, 21.12it/s] Loading 0: 94%|█████████▍| 341/363 [00:36<00:01, 14.80it/s] Loading 0: 95%|█████████▍| 344/363 [00:37<00:01, 15.37it/s] Loading 0: 95%|█████████▌| 346/363 [00:37<00:01, 13.32it/s] Loading 0: 96%|█████████▌| 348/363 [00:37<00:01, 12.81it/s] Loading 0: 97%|█████████▋| 352/363 [00:37<00:00, 17.15it/s] Loading 0: 98%|█████████▊| 356/363 [00:37<00:00, 20.89it/s] Loading 0: 99%|█████████▉| 359/363 [00:44<00:02, 1.41it/s] Loading 0: 99%|█████████▉| 361/363 [00:45<00:01, 1.70it/s]
Job rirv938-dpo-to-compare-51776-v1-mkmlizer completed after 422.59s with status: succeeded
Stopping job with name rirv938-dpo-to-compare-51776-v1-mkmlizer
Pipeline stage MKMLizer completed in 423.12s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-dpo-to-compare-51776-v1
Waiting for inference service rirv938-dpo-to-compare-51776-v1 to be ready
Inference service rirv938-dpo-to-compare-51776-v1 ready after 140.5422556400299s
Pipeline stage MKMLDeployer completed in 141.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.044858932495117s
Received healthy response to inference request in 1.845047950744629s
Received healthy response to inference request in 2.0960144996643066s
Received healthy response to inference request in 2.0893218517303467s
Received healthy response to inference request in 1.880988597869873s
5 requests
0 failed requests
5th percentile: 1.8522360801696778
10th percentile: 1.8594242095947267
20th percentile: 1.8738004684448242
30th percentile: 1.913762664794922
40th percentile: 1.9793107986450196
50th percentile: 2.044858932495117
60th percentile: 2.062644100189209
70th percentile: 2.080429267883301
80th percentile: 2.0906603813171385
90th percentile: 2.0933374404907226
95th percentile: 2.094675970077515
99th percentile: 2.0957467937469483
mean time: 1.9912463665008544
Pipeline stage StressChecker completed in 11.57s
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 0.66s
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 0.74s
Shutdown handler de-registered
rirv938-dpo-to-compare-_51776_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3074.82s
Shutdown handler de-registered
rirv938-dpo-to-compare-_51776_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-dpo-to-compare-_51776_v1 status is now torndown due to DeploymentManager action