developer_uid: noumanjavaid
submission_id: riverise-lima-safe-sft_v3
model_name: riverise-lima-safe-sft_v1
model_group: Riverise/lima_safe_sft
status: inactive
timestamp: 2025-02-02T14:04:48+00:00
num_battles: 5881
num_wins: 2788
celo_rating: 1252.02
family_friendly_score: 0.5851999999999999
family_friendly_standard_error: 0.006967653263474008
submission_type: basic
model_repo: Riverise/lima_safe_sft
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: riverise-lima-safe-sft_v1
is_internal_developer: False
language_model: Riverise/lima_safe_sft
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-02
win_ratio: 0.474069035878252
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 riverise-lima-safe-sft-v3-mkmlizer
Waiting for job on riverise-lima-safe-sft-v3-mkmlizer to finish
riverise-lima-safe-sft-v3-mkmlizer: Downloaded to shared memory in 103.300s
riverise-lima-safe-sft-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzvqi5fad, device:0
riverise-lima-safe-sft-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
riverise-lima-safe-sft-v3-mkmlizer: quantized model in 44.287s
riverise-lima-safe-sft-v3-mkmlizer: Processed model Riverise/lima_safe_sft in 147.587s
riverise-lima-safe-sft-v3-mkmlizer: creating bucket guanaco-mkml-models
riverise-lima-safe-sft-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-lima-safe-sft-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-lima-safe-sft-v3
riverise-lima-safe-sft-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-lima-safe-sft-v3/config.json
riverise-lima-safe-sft-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-lima-safe-sft-v3/special_tokens_map.json
riverise-lima-safe-sft-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-lima-safe-sft-v3/tokenizer_config.json
riverise-lima-safe-sft-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-lima-safe-sft-v3/tokenizer.json
riverise-lima-safe-sft-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-lima-safe-sft-v3/flywheel_model.0.safetensors
riverise-lima-safe-sft-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:17, 21.01it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:13, 25.82it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:15, 22.65it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:11, 28.72it/s] Loading 0: 6%|▋ | 23/363 [00:01<00:16, 20.82it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:18, 18.57it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:13, 24.11it/s] Loading 0: 9%|▉ | 34/363 [00:01<00:13, 23.81it/s] Loading 0: 10%|█ | 37/363 [00:01<00:13, 24.85it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:14, 22.37it/s] Loading 0: 13%|█▎ | 46/363 [00:01<00:11, 27.63it/s] Loading 0: 14%|█▍ | 50/363 [00:02<00:13, 24.02it/s] Loading 0: 15%|█▌ | 55/363 [00:02<00:10, 28.47it/s] Loading 0: 17%|█▋ | 60/363 [00:02<00:10, 29.26it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:15, 19.00it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:12, 23.34it/s] Loading 0: 20%|██ | 73/363 [00:03<00:12, 23.24it/s] Loading 0: 21%|██ | 77/363 [00:03<00:12, 22.07it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:10, 26.50it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:11, 24.02it/s] Loading 0: 25%|██▌ | 91/363 [00:03<00:09, 28.52it/s] Loading 0: 26%|██▌ | 95/363 [00:03<00:10, 24.77it/s] Loading 0: 28%|██▊ | 100/363 [00:04<00:09, 29.17it/s] Loading 0: 29%|██▊ | 104/363 [00:04<00:14, 17.84it/s] Loading 0: 30%|███ | 109/363 [00:04<00:11, 22.18it/s] Loading 0: 31%|███ | 113/363 [00:04<00:11, 20.98it/s] Loading 0: 33%|███▎ | 118/363 [00:04<00:09, 25.38it/s] Loading 0: 34%|███▎ | 122/363 [00:05<00:10, 22.97it/s] Loading 0: 35%|███▍ | 127/363 [00:05<00:08, 27.28it/s] Loading 0: 36%|███▌ | 131/363 [00:05<00:09, 24.25it/s] Loading 0: 37%|███▋ | 136/363 [00:05<00:07, 28.46it/s] Loading 0: 39%|███▉ | 141/363 [00:05<00:07, 29.02it/s] Loading 0: 40%|███▉ | 145/363 [00:06<00:10, 20.41it/s] Loading 0: 41%|████ | 149/363 [00:06<00:10, 19.95it/s] Loading 0: 42%|████▏ | 154/363 [00:06<00:08, 24.24it/s] Loading 0: 43%|████▎ | 157/363 [00:06<00:08, 25.25it/s] Loading 0: 44%|████▍ | 160/363 [00:06<00:08, 24.56it/s] Loading 0: 45%|████▍ | 163/363 [00:06<00:07, 25.56it/s] Loading 0: 46%|████▌ | 167/363 [00:07<00:08, 23.06it/s] Loading 0: 47%|████▋ | 172/363 [00:07<00:06, 28.12it/s] Loading 0: 48%|████▊ | 176/363 [00:07<00:07, 24.90it/s] Loading 0: 50%|████▉ | 181/363 [00:07<00:06, 29.41it/s] Loading 0: 51%|█████ | 185/363 [00:07<00:10, 17.66it/s] Loading 0: 52%|█████▏ | 190/363 [00:08<00:07, 21.79it/s] Loading 0: 53%|█████▎ | 194/363 [00:08<00:08, 20.80it/s] Loading 0: 55%|█████▍ | 199/363 [00:08<00:06, 23.57it/s] Loading 0: 56%|█████▌ | 203/363 [00:08<00:07, 21.85it/s] Loading 0: 57%|█████▋ | 208/363 [00:08<00:05, 26.44it/s] Loading 0: 58%|█████▊ | 212/363 [00:08<00:06, 23.80it/s] Loading 0: 60%|█████▉ | 217/363 [00:09<00:05, 28.32it/s] Loading 0: 61%|██████ | 222/363 [00:09<00:04, 29.40it/s] Loading 0: 62%|██████▏ | 226/363 [00:09<00:06, 20.17it/s] Loading 0: 63%|██████▎ | 230/363 [00:09<00:06, 19.89it/s] Loading 0: 65%|██████▍ | 235/363 [00:09<00:05, 24.22it/s] Loading 0: 66%|██████▌ | 239/363 [00:10<00:05, 22.36it/s] Loading 0: 67%|██████▋ | 244/363 [00:10<00:04, 26.74it/s] Loading 0: 68%|██████▊ | 248/363 [00:10<00:04, 23.65it/s] Loading 0: 70%|██████▉ | 253/363 [00:10<00:04, 27.49it/s] Loading 0: 71%|███████ | 257/363 [00:10<00:04, 23.24it/s] Loading 0: 72%|███████▏ | 262/363 [00:10<00:03, 26.19it/s] Loading 0: 73%|███████▎ | 265/363 [00:11<00:04, 19.79it/s] Loading 0: 74%|███████▍ | 268/363 [00:11<00:04, 20.48it/s] Loading 0: 75%|███████▌ | 273/363 [00:11<00:03, 23.87it/s] Loading 0: 76%|███████▌ | 276/363 [00:11<00:03, 22.35it/s] Loading 0: 77%|███████▋ | 280/363 [00:11<00:03, 25.40it/s] Loading 0: 78%|███████▊ | 283/363 [00:11<00:03, 26.28it/s] Loading 0: 79%|███████▉ | 286/363 [00:11<00:03, 25.14it/s] Loading 0: 80%|████████ | 291/363 [00:12<00:02, 27.58it/s] Loading 0: 81%|████████ | 294/363 [00:12<00:02, 23.66it/s] Loading 0: 82%|████████▏ | 298/363 [00:12<00:02, 25.72it/s] Loading 0: 83%|████████▎ | 303/363 [00:12<00:02, 27.33it/s] Loading 0: 84%|████████▍ | 306/363 [00:12<00:03, 17.84it/s] Loading 0: 86%|████████▌ | 311/363 [00:13<00:02, 19.40it/s] Loading 0: 87%|████████▋ | 316/363 [00:13<00:02, 23.45it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:01, 21.75it/s] Loading 0: 90%|████████▉ | 325/363 [00:13<00:01, 26.00it/s] Loading 0: 91%|█████████ | 329/363 [00:13<00:01, 23.19it/s] Loading 0: 92%|█████████▏| 334/363 [00:13<00:01, 27.31it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 24.41it/s] Loading 0: 95%|█████████▍| 344/363 [00:21<00:08, 2.19it/s] Loading 0: 96%|█████████▌| 348/363 [00:21<00:05, 2.85it/s] Loading 0: 97%|█████████▋| 353/363 [00:21<00:02, 4.00it/s] Loading 0: 98%|█████████▊| 357/363 [00:21<00:01, 5.08it/s] Loading 0: 100%|█████████▉| 362/363 [00:21<00:00, 7.13it/s]
Job riverise-lima-safe-sft-v3-mkmlizer completed after 174.78s with status: succeeded
Stopping job with name riverise-lima-safe-sft-v3-mkmlizer
Pipeline stage MKMLizer completed in 175.22s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service riverise-lima-safe-sft-v3
Waiting for inference service riverise-lima-safe-sft-v3 to be ready
Inference service riverise-lima-safe-sft-v3 ready after 170.58608841896057s
Pipeline stage MKMLDeployer completed in 171.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.194403886795044s
Received healthy response to inference request in 1.8374111652374268s
Received healthy response to inference request in 1.8170366287231445s
Received healthy response to inference request in 2.0083534717559814s
Received healthy response to inference request in 1.8497178554534912s
5 requests
0 failed requests
5th percentile: 1.821111536026001
10th percentile: 1.8251864433288574
20th percentile: 1.8333362579345702
30th percentile: 1.8398725032806396
40th percentile: 1.8447951793670654
50th percentile: 1.8497178554534912
60th percentile: 1.9131721019744874
70th percentile: 1.9766263484954834
80th percentile: 2.045563554763794
90th percentile: 2.1199837207794188
95th percentile: 2.1571938037872314
99th percentile: 2.1869618701934814
mean time: 1.9413846015930176
Pipeline stage StressChecker completed in 10.84s
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 0.69s
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 0.57s
Shutdown handler de-registered
riverise-lima-safe-sft_v3 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service riverise-lima-safe-sft-v3-profiler
Waiting for inference service riverise-lima-safe-sft-v3-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 2545.07s
Shutdown handler de-registered
riverise-lima-safe-sft_v3 status is now inactive due to auto deactivation removed underperforming models