rica40325-nsfw-free-sft

submission_id: rica40325-nsfw-free-sft_v4

developer_uid: Riverise

best_of: 8

celo_rating: 1255.13

display_name: rica40325-nsfw-free-sft_v4

family_friendly_score: 0.7766

family_friendly_standard_error: 0.005890542250081905

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}

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}

is_internal_developer: False

language_model: rica40325/nsfw_free_sft

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: rica40325/nsfw_free_sft

model_name: rica40325-nsfw-free-sft_v4

model_num_parameters: 12772070400.0

model_repo: rica40325/nsfw_free_sft

model_size: 13B

num_battles: 12595

num_wins: 6484

ranking_group: single

status: inactive

submission_type: basic

timestamp: 2024-10-24T09:23:27+00:00

us_pacific_date: 2024-10-24

win_ratio: 0.514807463279079

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-v4-mkmlizer
Waiting for job on rica40325-nsfw-free-sft-v4-mkmlizer to finish
rica40325-nsfw-free-sft-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-nsfw-free-sft-v4-mkmlizer: ║     _____            __           __                                ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║       /___/                                                         ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║                                                                     ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║                                                                     ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║  belonging to:                                                      ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║                                                                     ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rica40325-nsfw-free-sft-v4-mkmlizer: ║                                                                     ║
rica40325-nsfw-free-sft-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-nsfw-free-sft-v4-mkmlizer: Downloaded to shared memory in 34.004s
rica40325-nsfw-free-sft-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprs5uu_5c, device:0
rica40325-nsfw-free-sft-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-nsfw-free-sft-v4-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-v4-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rica40325-nsfw-free-sft-v4-mkmlizer: quantized model in 36.236s
rica40325-nsfw-free-sft-v4-mkmlizer: Processed model rica40325/nsfw_free_sft in 70.240s
rica40325-nsfw-free-sft-v4-mkmlizer: creating bucket guanaco-mkml-models
rica40325-nsfw-free-sft-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v4/config.json
rica40325-nsfw-free-sft-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v4/special_tokens_map.json
rica40325-nsfw-free-sft-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v4/tokenizer_config.json
rica40325-nsfw-free-sft-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v4/tokenizer.json
rica40325-nsfw-free-sft-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v4/flywheel_model.0.safetensors
rica40325-nsfw-free-sft-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 48.49it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:05, 65.90it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:04, 72.72it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:04, 76.00it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:04, 77.44it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:04, 76.73it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:15, 19.52it/s]
Loading 0:  19%|█▉        | 70/363 [00:01<00:11, 25.57it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 31.77it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:07, 38.15it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:05, 45.58it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:04, 52.95it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 59.42it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 63.01it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 62.71it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:10, 21.06it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:07, 27.26it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 34.17it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:04, 40.36it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:03, 47.59it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 52.02it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 57.34it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 57.25it/s]
Loading 0:  59%|█████▉    | 214/363 [00:04<00:02, 61.95it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:06, 20.85it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:04, 26.99it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 33.47it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:02, 39.44it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 45.26it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 50.97it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 56.54it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 60.05it/s]
Loading 0:  81%|████████▏ | 295/363 [00:06<00:01, 66.07it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 21.81it/s]
Loading 0:  86%|████████▌ | 313/363 [00:08<00:01, 28.09it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 35.11it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 41.47it/s]
Loading 0:  94%|█████████▎| 340/363 [00:08<00:00, 48.66it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 55.89it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 62.38it/s]
                                                            
Job rica40325-nsfw-free-sft-v4-mkmlizer completed after 104.4s with status: succeeded
Stopping job with name rica40325-nsfw-free-sft-v4-mkmlizer
Pipeline stage MKMLizer completed in 104.95s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-nsfw-free-sft-v4
Waiting for inference service rica40325-nsfw-free-sft-v4 to be ready
Inference service rica40325-nsfw-free-sft-v4 ready after 130.48481345176697s
Pipeline stage MKMLDeployer completed in 131.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.169588327407837s
Received healthy response to inference request in 1.667564868927002s
Received healthy response to inference request in 1.7391581535339355s
Received healthy response to inference request in 2.1186394691467285s
Received healthy response to inference request in 1.9164955615997314s
5 requests
0 failed requests
5th percentile: 1.6818835258483886
10th percentile: 1.6962021827697753
20th percentile: 1.7248394966125489
30th percentile: 1.7746256351470948
40th percentile: 1.8455605983734131
50th percentile: 1.9164955615997314
60th percentile: 1.9973531246185303
70th percentile: 2.078210687637329
80th percentile: 2.12882924079895
90th percentile: 2.1492087841033936
95th percentile: 2.1593985557556152
99th percentile: 2.1675503730773924
mean time: 1.9222892761230468
Pipeline stage StressChecker completed in 11.28s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.40s
Shutdown handler de-registered
rica40325-nsfw-free-sft_v4 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 1984.12s
Shutdown handler de-registered
rica40325-nsfw-free-sft_v4 status is now inactive due to auto deactivation removed underperforming models