developer_uid: rirv938
submission_id: rirv938-tune-mistral-gr_11107_v1
model_name: rirv938-tune-mistral-gr_11107_v1
model_group: rirv938/tune_mistral_grp
status: torndown
timestamp: 2025-04-30T23:58:50+00:00
num_battles: 8783
num_wins: 4666
celo_rating: 1308.78
family_friendly_score: 0.5668
family_friendly_standard_error: 0.007007678074797671
submission_type: basic
model_repo: rirv938/tune_mistral_grpo_cp1184_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': 0.562263906198437, 'latency_mean': 1.7784703600406646, 'latency_p50': 1.7705754041671753, 'latency_p90': 1.9998779296875}, {'batch_size': 3, 'throughput': 1.1728155385956867, 'latency_mean': 2.5500979232788086, 'latency_p50': 2.5586094856262207, 'latency_p90': 2.855044388771057}, {'batch_size': 5, 'throughput': 1.5454516479846012, 'latency_mean': 3.2231448006629946, 'latency_p50': 3.2273426055908203, 'latency_p90': 3.6259641408920285}, {'batch_size': 6, 'throughput': 1.6888041951397514, 'latency_mean': 3.5401665222644807, 'latency_p50': 3.535766124725342, 'latency_p90': 3.941975784301758}, {'batch_size': 8, 'throughput': 1.841928327915698, 'latency_mean': 4.289693439006806, 'latency_p50': 4.337603211402893, 'latency_p90': 4.810695767402649}, {'batch_size': 10, 'throughput': 1.9696654759327106, 'latency_mean': 5.023455069065094, 'latency_p50': 5.048202753067017, 'latency_p90': 5.5952483177185055}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-tune-mistral-gr_11107_v1
is_internal_developer: True
language_model: rirv938/tune_mistral_grpo_cp1184_92ff_v3_run3_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.74
us_pacific_date: 2025-04-30
win_ratio: 0.5312535580097917
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-11107-v1-mkmlizer
Waiting for job on rirv938-tune-mistral-gr-11107-v1-mkmlizer to finish
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ _____ __ __ ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ /___/ ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ belonging to: ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ║ ║
rirv938-tune-mistral-gr-11107-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-tune-mistral-gr-11107-v1-mkmlizer: Downloaded to shared memory in 187.882s
rirv938-tune-mistral-gr-11107-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpznen90rz, device:0
rirv938-tune-mistral-gr-11107-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-tune-mistral-gr-11107-v1-mkmlizer: quantized model in 64.626s
rirv938-tune-mistral-gr-11107-v1-mkmlizer: Processed model rirv938/tune_mistral_grpo_cp1184_92ff_v3_run3_merged in 252.509s
rirv938-tune-mistral-gr-11107-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-tune-mistral-gr-11107-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-tune-mistral-gr-11107-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-tune-mistral-gr-11107-v1
rirv938-tune-mistral-gr-11107-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-11107-v1/config.json
rirv938-tune-mistral-gr-11107-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-11107-v1/special_tokens_map.json
rirv938-tune-mistral-gr-11107-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-11107-v1/tokenizer_config.json
rirv938-tune-mistral-gr-11107-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-11107-v1/tokenizer.json
rirv938-tune-mistral-gr-11107-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-11107-v1/flywheel_model.1.safetensors
rirv938-tune-mistral-gr-11107-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-11107-v1/flywheel_model.0.safetensors
rirv938-tune-mistral-gr-11107-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:00<00:13, 27.25it/s] Loading 0: 2%|▏ | 6/363 [00:00<00:27, 12.86it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:17, 19.75it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:26, 13.04it/s] Loading 0: 4%|▍ | 15/363 [00:01<00:32, 10.82it/s] Loading 0: 6%|▌ | 21/363 [00:01<00:21, 15.89it/s] Loading 0: 6%|▋ | 23/363 [00:01<00:27, 12.44it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:18, 17.81it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:15, 21.02it/s] Loading 0: 10%|▉ | 35/363 [00:02<00:22, 14.53it/s] Loading 0: 10%|█ | 38/363 [00:02<00:21, 14.97it/s] Loading 0: 11%|█ | 40/363 [00:02<00:24, 13.25it/s] Loading 0: 12%|█▏ | 42/363 [00:02<00:25, 12.82it/s] Loading 0: 13%|█▎ | 46/363 [00:03<00:18, 17.21it/s] Loading 0: 14%|█▍ | 50/363 [00:03<00:14, 21.32it/s] Loading 0: 15%|█▍ | 53/363 [00:03<00:20, 14.84it/s] Loading 0: 15%|█▌ | 56/363 [00:03<00:19, 15.46it/s] Loading 0: 16%|█▌ | 58/363 [00:03<00:22, 13.64it/s] Loading 0: 17%|█▋ | 60/363 [00:04<00:23, 13.07it/s] Loading 0: 18%|█▊ | 64/363 [00:04<00:17, 17.37it/s] Loading 0: 19%|█▊ | 68/363 [00:04<00:13, 21.53it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:19, 15.07it/s] Loading 0: 20%|██ | 74/363 [00:04<00:18, 15.65it/s] Loading 0: 21%|██ | 76/363 [00:04<00:20, 13.82it/s] Loading 0: 21%|██▏ | 78/363 [00:05<00:21, 13.24it/s] Loading 0: 23%|██▎ | 82/363 [00:05<00:15, 17.68it/s] Loading 0: 24%|██▎ | 86/363 [00:05<00:12, 22.16it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:17, 15.56it/s] Loading 0: 25%|██▌ | 92/363 [00:05<00:17, 15.87it/s] Loading 0: 26%|██▋ | 96/363 [00:05<00:13, 20.08it/s] Loading 0: 28%|██▊ | 101/363 [00:06<00:11, 21.99it/s] Loading 0: 29%|██▊ | 104/363 [00:06<00:14, 18.24it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:17, 14.30it/s] Loading 0: 30%|███ | 109/363 [00:06<00:18, 13.69it/s] Loading 0: 31%|███ | 111/363 [00:07<00:17, 14.41it/s] Loading 0: 31%|███ | 113/363 [00:07<00:21, 11.70it/s] Loading 0: 33%|███▎ | 118/363 [00:07<00:13, 17.87it/s] Loading 0: 34%|███▎ | 122/363 [00:07<00:11, 21.78it/s] Loading 0: 34%|███▍ | 125/363 [00:07<00:15, 15.25it/s] Loading 0: 35%|███▌ | 128/363 [00:08<00:14, 15.85it/s] Loading 0: 36%|███▌ | 131/363 [00:08<00:19, 12.14it/s] Loading 0: 37%|███▋ | 136/363 [00:08<00:13, 17.02it/s] Loading 0: 39%|███▊ | 140/363 [00:08<00:11, 20.24it/s] Loading 0: 39%|███▉ | 143/363 [00:09<00:14, 14.78it/s] Loading 0: 40%|████ | 146/363 [00:09<00:14, 15.47it/s] Loading 0: 41%|████ | 149/363 [00:09<00:17, 12.26it/s] Loading 0: 42%|████▏ | 154/363 [00:09<00:12, 17.26it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:10, 20.40it/s] Loading 0: 44%|████▍ | 161/363 [00:10<00:13, 15.03it/s] Loading 0: 45%|████▌ | 164/363 [00:10<00:12, 15.52it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:16, 12.03it/s] Loading 0: 47%|████▋ | 172/363 [00:10<00:11, 16.36it/s] Loading 0: 48%|████▊ | 176/363 [00:11<00:09, 19.27it/s] Loading 0: 49%|████▉ | 179/363 [00:11<00:12, 14.38it/s] Loading 0: 50%|█████ | 182/363 [00:11<00:12, 14.80it/s] Loading 0: 51%|█████ | 184/363 [00:11<00:13, 13.25it/s] Loading 0: 51%|█████ | 186/363 [00:11<00:13, 12.66it/s] Loading 0: 52%|█████▏ | 190/363 [00:12<00:10, 16.64it/s] Loading 0: 53%|█████▎ | 194/363 [00:12<00:08, 20.19it/s] Loading 0: 54%|█████▍ | 197/363 [00:12<00:11, 14.25it/s] Loading 0: 55%|█████▍ | 199/363 [00:12<00:12, 13.41it/s] Loading 0: 55%|█████▌ | 201/363 [00:27<04:50, 1.79s/it] Loading 0: 56%|█████▌ | 203/363 [00:28<03:42, 1.39s/it] Loading 0: 57%|█████▋ | 207/363 [00:28<02:08, 1.21it/s] Loading 0: 58%|█████▊ | 210/363 [00:28<01:29, 1.71it/s] Loading 0: 59%|█████▊ | 213/363 [00:28<01:05, 2.30it/s] Loading 0: 59%|█████▉ | 215/363 [00:28<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, 4.32it/s] Loading 0: 61%|██████ | 221/363 [00:29<00:28, 4.93it/s] Loading 0: 63%|██████▎ | 227/363 [00:29<00:14, 9.60it/s] Loading 0: 64%|██████▎ | 231/363 [00:29<00:11, 11.17it/s] Loading 0: 64%|██████▍ | 234/363 [00:30<00:12, 10.20it/s] Loading 0: 65%|██████▌ | 237/363 [00:30<00:10, 12.35it/s] Loading 0: 66%|██████▌ | 240/363 [00:30<00:10, 12.11it/s] Loading 0: 67%|██████▋ | 245/363 [00:30<00:06, 17.23it/s] Loading 0: 69%|██████▊ | 249/363 [00:30<00:06, 17.29it/s] Loading 0: 69%|██████▉ | 252/363 [00:31<00:08, 13.45it/s] Loading 0: 70%|███████ | 255/363 [00:31<00:06, 15.47it/s] Loading 0: 71%|███████ | 258/363 [00:31<00:07, 14.05it/s] Loading 0: 72%|███████▏ | 262/363 [00:31<00:05, 18.04it/s] Loading 0: 73%|███████▎ | 266/363 [00:31<00:04, 21.06it/s] Loading 0: 74%|███████▍ | 269/363 [00:32<00:06, 14.60it/s] Loading 0: 75%|███████▍ | 272/363 [00:32<00:05, 15.29it/s] Loading 0: 76%|███████▌ | 275/363 [00:32<00:07, 12.15it/s] Loading 0: 77%|███████▋ | 280/363 [00:32<00:04, 17.27it/s] Loading 0: 78%|███████▊ | 284/363 [00:33<00:03, 20.78it/s] Loading 0: 79%|███████▉ | 287/363 [00:33<00:05, 15.00it/s] Loading 0: 80%|███████▉ | 290/363 [00:33<00:04, 15.59it/s] Loading 0: 81%|████████ | 293/363 [00:33<00:05, 12.41it/s] Loading 0: 82%|████████▏ | 299/363 [00:34<00:03, 18.76it/s] Loading 0: 83%|████████▎ | 303/363 [00:34<00:03, 17.57it/s] Loading 0: 84%|████████▍ | 306/363 [00:34<00:04, 13.85it/s] Loading 0: 85%|████████▌ | 309/363 [00:34<00:03, 15.87it/s] Loading 0: 86%|████████▌ | 312/363 [00:35<00:03, 14.55it/s] Loading 0: 87%|████████▋ | 316/363 [00:35<00:02, 18.38it/s] Loading 0: 88%|████████▊ | 321/363 [00:35<00:02, 19.20it/s] Loading 0: 89%|████████▉ | 324/363 [00:35<00:02, 14.58it/s] Loading 0: 90%|█████████ | 327/363 [00:35<00:02, 16.52it/s] Loading 0: 91%|█████████ | 330/363 [00:36<00:02, 14.76it/s] Loading 0: 92%|█████████▏| 334/363 [00:36<00:01, 18.05it/s] Loading 0: 93%|█████████▎| 338/363 [00:36<00:01, 21.85it/s] Loading 0: 94%|█████████▍| 341/363 [00:36<00:01, 15.53it/s] Loading 0: 95%|█████████▍| 344/363 [00:36<00:01, 16.07it/s] Loading 0: 96%|█████████▌| 347/363 [00:37<00:01, 12.52it/s] Loading 0: 97%|█████████▋| 352/363 [00:37<00:00, 17.78it/s] Loading 0: 98%|█████████▊| 356/363 [00:37<00:00, 21.35it/s] Loading 0: 99%|█████████▉| 359/363 [00:44<00:02, 1.57it/s] Loading 0: 100%|█████████▉| 362/363 [00:44<00:00, 2.02it/s]
Job rirv938-tune-mistral-gr-11107-v1-mkmlizer completed after 288.66s with status: succeeded
Stopping job with name rirv938-tune-mistral-gr-11107-v1-mkmlizer
Pipeline stage MKMLizer completed in 289.13s
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-tune-mistral-gr-11107-v1
Waiting for inference service rirv938-tune-mistral-gr-11107-v1 to be ready
Inference service rirv938-tune-mistral-gr-11107-v1 ready after 150.51893591880798s
Pipeline stage MKMLDeployer completed in 151.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4536473751068115s
Received healthy response to inference request in 1.9510688781738281s
Received healthy response to inference request in 2.1345443725585938s
Received healthy response to inference request in 2.0528643131256104s
Received healthy response to inference request in 2.0028305053710938s
5 requests
0 failed requests
5th percentile: 1.9614212036132812
10th percentile: 1.9717735290527343
20th percentile: 1.9924781799316407
30th percentile: 2.012837266921997
40th percentile: 2.0328507900238035
50th percentile: 2.0528643131256104
60th percentile: 2.085536336898804
70th percentile: 2.1182083606719972
80th percentile: 2.1983649730682373
90th percentile: 2.3260061740875244
95th percentile: 2.389826774597168
99th percentile: 2.440883255004883
mean time: 2.1189910888671877
Pipeline stage StressChecker completed in 11.86s
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 0.69s
Shutdown handler de-registered
rirv938-tune-mistral-gr_11107_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-tune-mistral-gr-11107-v1-profiler
Waiting for inference service rirv938-tune-mistral-gr-11107-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 2940.79s
Shutdown handler de-registered
rirv938-tune-mistral-gr_11107_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-tune-mistral-gr_11107_v1 status is now torndown due to DeploymentManager action