developer_uid: Riverise
submission_id: rica40325-nsfw-free-sft_v9
model_name: rica40325-nsfw-free-sft_v3
model_group: rica40325/nsfw_free_sft
status: torndown
timestamp: 2024-11-12T11:03:59+00:00
num_battles: 13617
num_wins: 7078
celo_rating: 1259.47
family_friendly_score: 0.5700000000000001
family_friendly_standard_error: 0.007001428425685719
submission_type: basic
model_repo: rica40325/nsfw_free_sft
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6172159914531935, 'latency_mean': 1.6200761711597442, 'latency_p50': 1.6239418983459473, 'latency_p90': 1.8022317171096802}, {'batch_size': 3, 'throughput': 1.1186573879526125, 'latency_mean': 2.6718269205093383, 'latency_p50': 2.660520315170288, 'latency_p90': 2.949961042404175}, {'batch_size': 5, 'throughput': 1.3495868182583635, 'latency_mean': 3.680965209007263, 'latency_p50': 3.695152521133423, 'latency_p90': 4.086542773246765}, {'batch_size': 6, 'throughput': 1.4264154421235793, 'latency_mean': 4.181519145965576, 'latency_p50': 4.175674676895142, 'latency_p90': 4.572725939750671}, {'batch_size': 8, 'throughput': 1.4802894327832798, 'latency_mean': 5.364565552473068, 'latency_p50': 5.343740463256836, 'latency_p90': 6.102934765815735}, {'batch_size': 10, 'throughput': 1.5157793836763351, 'latency_mean': 6.554271522760391, 'latency_p50': 6.552666664123535, 'latency_p90': 7.35331780910492}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rica40325-nsfw-free-sft_v3
is_internal_developer: False
language_model: rica40325/nsfw_free_sft
model_size: 13B
ranking_group: single
throughput_3p7s: 1.36
us_pacific_date: 2024-11-12
win_ratio: 0.5197914371741206
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 rica40325-nsfw-free-sft-v9-mkmlizer
Waiting for job on rica40325-nsfw-free-sft-v9-mkmlizer to finish
rica40325-nsfw-free-sft-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-nsfw-free-sft-v9-mkmlizer: ║ _____ __ __ ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ /___/ ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ Version: 0.11.33 ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ https://mk1.ai ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ belonging to: ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ Chai Research Corp. ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rica40325-nsfw-free-sft-v9-mkmlizer: ║ ║
rica40325-nsfw-free-sft-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-nsfw-free-sft-v9-mkmlizer: Downloaded to shared memory in 44.626s
rica40325-nsfw-free-sft-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg9zcd21r, device:0
rica40325-nsfw-free-sft-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-nsfw-free-sft-v9-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
rica40325-nsfw-free-sft-v9-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rica40325-nsfw-free-sft-v9-mkmlizer: quantized model in 37.246s
rica40325-nsfw-free-sft-v9-mkmlizer: Processed model rica40325/nsfw_free_sft in 81.873s
rica40325-nsfw-free-sft-v9-mkmlizer: creating bucket guanaco-mkml-models
rica40325-nsfw-free-sft-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-nsfw-free-sft-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v9
rica40325-nsfw-free-sft-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v9/special_tokens_map.json
rica40325-nsfw-free-sft-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v9/tokenizer.json
rica40325-nsfw-free-sft-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v9/flywheel_model.0.safetensors
rica40325-nsfw-free-sft-v9-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:07, 49.88it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:05, 65.71it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:04, 72.57it/s] Loading 0: 9%|▉ | 34/363 [00:00<00:04, 72.93it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:04, 75.05it/s] Loading 0: 14%|█▍ | 52/363 [00:00<00:03, 78.86it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:15, 19.34it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:11, 25.38it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:08, 32.16it/s] Loading 0: 24%|██▍ | 88/363 [00:02<00:07, 38.92it/s] Loading 0: 27%|██▋ | 97/363 [00:02<00:06, 44.27it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:05, 50.37it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 56.29it/s] Loading 0: 34%|███▍ | 124/363 [00:02<00:03, 59.86it/s] Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 61.60it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:11, 19.04it/s] Loading 0: 42%|████▏ | 151/363 [00:04<00:08, 24.47it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 30.56it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 37.45it/s] Loading 0: 49%|████▉ | 178/363 [00:04<00:04, 44.12it/s] Loading 0: 52%|█████▏ | 187/363 [00:04<00:03, 48.83it/s] Loading 0: 54%|█████▍ | 196/363 [00:04<00:03, 53.14it/s] Loading 0: 56%|█████▋ | 205/363 [00:04<00:02, 59.74it/s] Loading 0: 59%|█████▉ | 214/363 [00:05<00:02, 64.97it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:07, 18.00it/s] Loading 0: 64%|██████▍ | 232/363 [00:06<00:05, 23.10it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:04, 28.80it/s] Loading 0: 69%|██████▉ | 250/363 [00:06<00:03, 35.22it/s] Loading 0: 71%|███████▏ | 259/363 [00:06<00:02, 42.04it/s] Loading 0: 74%|███████▍ | 268/363 [00:07<00:01, 47.52it/s] Loading 0: 76%|███████▋ | 277/363 [00:07<00:01, 53.16it/s] Loading 0: 79%|███████▉ | 286/363 [00:07<00:01, 59.81it/s] Loading 0: 81%|████████▏ | 295/363 [00:07<00:01, 65.94it/s] Loading 0: 84%|████████▎ | 304/363 [00:08<00:02, 20.21it/s] Loading 0: 86%|████████▌ | 313/363 [00:08<00:01, 26.16it/s] Loading 0: 89%|████████▊ | 322/363 [00:08<00:01, 31.83it/s] Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 39.25it/s] Loading 0: 94%|█████████▎| 340/363 [00:09<00:00, 46.20it/s] Loading 0: 96%|█████████▌| 349/363 [00:09<00:00, 51.87it/s] Loading 0: 99%|█████████▊| 358/363 [00:09<00:00, 55.01it/s]
Job rica40325-nsfw-free-sft-v9-mkmlizer completed after 114.88s with status: succeeded
Stopping job with name rica40325-nsfw-free-sft-v9-mkmlizer
Pipeline stage MKMLizer completed in 115.39s
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 rica40325-nsfw-free-sft-v9
Waiting for inference service rica40325-nsfw-free-sft-v9 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rica40325-nsfw-free-sft-v9 ready after 200.68566823005676s
Pipeline stage MKMLDeployer completed in 201.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.262726306915283s
Received healthy response to inference request in 1.0903899669647217s
Received healthy response to inference request in 1.7942183017730713s
Received healthy response to inference request in 1.4917182922363281s
Received healthy response to inference request in 1.901897668838501s
5 requests
0 failed requests
5th percentile: 1.1706556320190429
10th percentile: 1.2509212970733643
20th percentile: 1.411452627182007
30th percentile: 1.5522182941436768
40th percentile: 1.673218297958374
50th percentile: 1.7942183017730713
60th percentile: 1.8372900485992432
70th percentile: 1.880361795425415
80th percentile: 1.9740633964538574
90th percentile: 2.1183948516845703
95th percentile: 2.1905605792999268
99th percentile: 2.248293161392212
mean time: 1.708190107345581
Pipeline stage StressChecker completed in 9.72s
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 2.18s
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 2.08s
Shutdown handler de-registered
rica40325-nsfw-free-sft_v9 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-nsfw-free-sft-v9-profiler
Waiting for inference service rica40325-nsfw-free-sft-v9-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 2962.88s
Shutdown handler de-registered
rica40325-nsfw-free-sft_v9 status is now inactive due to auto deactivation removed underperforming models
rica40325-nsfw-free-sft_v9 status is now torndown due to DeploymentManager action