submission_id: rica40325-nsfw-free-sft_v8
developer_uid: Riverise
best_of: 8
celo_rating: 1260.01
display_name: rica40325-nsfw-free-sft_v3
family_friendly_score: 0.569
family_friendly_standard_error: 0.007003413453452538
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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: rica40325/nsfw_free_sft
latencies: [{'batch_size': 1, 'throughput': 0.6063277008594335, 'latency_mean': 1.6492127776145935, 'latency_p50': 1.6524103879928589, 'latency_p90': 1.8115062952041625}, {'batch_size': 3, 'throughput': 1.1153948523929111, 'latency_mean': 2.680571628808975, 'latency_p50': 2.688693046569824, 'latency_p90': 2.924085521697998}, {'batch_size': 5, 'throughput': 1.3394072165750506, 'latency_mean': 3.725456477403641, 'latency_p50': 3.7320693731307983, 'latency_p90': 4.139381623268127}, {'batch_size': 6, 'throughput': 1.3959650484673207, 'latency_mean': 4.2811883771419526, 'latency_p50': 4.311898469924927, 'latency_p90': 4.741449761390686}, {'batch_size': 8, 'throughput': 1.4588461021800916, 'latency_mean': 5.4394035196304324, 'latency_p50': 5.4698076248168945, 'latency_p90': 6.088140869140625}, {'batch_size': 10, 'throughput': 1.4968533437610128, 'latency_mean': 6.620052852630615, 'latency_p50': 6.599971413612366, 'latency_p90': 7.5549152135849}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: rica40325/nsfw_free_sft
model_name: rica40325-nsfw-free-sft_v3
model_num_parameters: 12772070400.0
model_repo: rica40325/nsfw_free_sft
model_size: 13B
num_battles: 16212
num_wins: 8459
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.34
timestamp: 2024-11-12T09:24:49+00:00
us_pacific_date: 2024-11-12
win_ratio: 0.5217739945719221
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-v8-mkmlizer
Waiting for job on rica40325-nsfw-free-sft-v8-mkmlizer to finish
rica40325-nsfw-free-sft-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-nsfw-free-sft-v8-mkmlizer: ║ _____ __ __ ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ /___/ ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ Version: 0.11.33 ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ https://mk1.ai ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ belonging to: ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ Chai Research Corp. ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rica40325-nsfw-free-sft-v8-mkmlizer: ║ ║
rica40325-nsfw-free-sft-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-nsfw-free-sft-v8-mkmlizer: Downloaded to shared memory in 47.010s
rica40325-nsfw-free-sft-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpo958edwv, device:0
rica40325-nsfw-free-sft-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-nsfw-free-sft-v8-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-v8-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rica40325-nsfw-free-sft-v8-mkmlizer: quantized model in 36.765s
rica40325-nsfw-free-sft-v8-mkmlizer: Processed model rica40325/nsfw_free_sft in 83.775s
rica40325-nsfw-free-sft-v8-mkmlizer: creating bucket guanaco-mkml-models
rica40325-nsfw-free-sft-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-nsfw-free-sft-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v8
rica40325-nsfw-free-sft-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v8/config.json
rica40325-nsfw-free-sft-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v8/special_tokens_map.json
rica40325-nsfw-free-sft-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v8/tokenizer_config.json
rica40325-nsfw-free-sft-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v8/tokenizer.json
rica40325-nsfw-free-sft-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-nsfw-free-sft-v8/flywheel_model.0.safetensors
rica40325-nsfw-free-sft-v8-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 39.82it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:05, 66.86it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:04, 76.06it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:04, 80.73it/s] Loading 0: 11%|█ | 40/363 [00:00<00:03, 82.57it/s] Loading 0: 14%|█▍ | 51/363 [00:00<00:03, 91.12it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:14, 20.53it/s] Loading 0: 19%|█▉ | 70/363 [00:01<00:11, 25.70it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:08, 32.75it/s] Loading 0: 24%|██▍ | 88/363 [00:02<00:06, 40.40it/s] Loading 0: 27%|██▋ | 97/363 [00:02<00:05, 48.22it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:04, 54.24it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 61.38it/s] Loading 0: 34%|███▍ | 124/363 [00:02<00:03, 67.68it/s] Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 72.85it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:11, 20.03it/s] Loading 0: 42%|████▏ | 152/363 [00:04<00:07, 26.98it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 37.59it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 43.45it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:03, 48.89it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 55.71it/s] Loading 0: 56%|█████▌ | 203/363 [00:04<00:02, 64.29it/s] Loading 0: 58%|█████▊ | 212/363 [00:04<00:02, 67.35it/s] Loading 0: 61%|██████ | 221/363 [00:04<00:02, 70.99it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:06, 21.06it/s] Loading 0: 66%|██████▌ | 238/363 [00:06<00:04, 26.02it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 32.45it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 40.13it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 47.43it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 54.41it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 59.08it/s] Loading 0: 80%|████████ | 292/363 [00:06<00:01, 64.82it/s] Loading 0: 83%|████████▎ | 301/363 [00:06<00:00, 69.95it/s] Loading 0: 85%|████████▌ | 310/363 [00:08<00:02, 20.86it/s] Loading 0: 88%|████████▊ | 319/363 [00:08<00:01, 26.46it/s] Loading 0: 90%|█████████ | 328/363 [00:08<00:01, 33.15it/s] Loading 0: 93%|█████████▎| 337/363 [00:08<00:00, 39.37it/s] Loading 0: 95%|█████████▌| 346/363 [00:08<00:00, 45.72it/s] Loading 0: 98%|█████████▊| 355/363 [00:08<00:00, 50.94it/s] Loading 0: 100%|██████████| 363/363 [00:15<00:00, 4.17it/s]
Job rica40325-nsfw-free-sft-v8-mkmlizer completed after 114.72s with status: succeeded
Stopping job with name rica40325-nsfw-free-sft-v8-mkmlizer
Pipeline stage MKMLizer completed in 115.36s
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-v8
Waiting for inference service rica40325-nsfw-free-sft-v8 to be ready
Failed to get response for submission rica40325-linear-merge-1113_v1: ('http://rica40325-linear-merge-1113-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:56254->127.0.0.1:8080: read: connection reset by peer\n')
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
Inference service rica40325-nsfw-free-sft-v8 ready after 190.6870288848877s
Pipeline stage MKMLDeployer completed in 191.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1245028972625732s
Received healthy response to inference request in 1.643866777420044s
Received healthy response to inference request in 1.6076722145080566s
Received healthy response to inference request in 1.5319674015045166s
Received healthy response to inference request in 1.7219958305358887s
5 requests
0 failed requests
5th percentile: 1.5471083641052246
10th percentile: 1.5622493267059325
20th percentile: 1.5925312519073487
30th percentile: 1.6149111270904541
40th percentile: 1.629388952255249
50th percentile: 1.643866777420044
60th percentile: 1.6751183986663818
70th percentile: 1.7063700199127196
80th percentile: 1.8024972438812257
90th percentile: 1.9635000705718995
95th percentile: 2.0440014839172362
99th percentile: 2.1084026145935058
mean time: 1.7260010242462158
Pipeline stage StressChecker completed in 10.24s
run pipeline stage %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
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
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 3.02s
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 2.47s
Shutdown handler de-registered
rica40325-nsfw-free-sft_v8 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-nsfw-free-sft-v8-profiler
Waiting for inference service rica40325-nsfw-free-sft-v8-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 2982.56s
Shutdown handler de-registered
rica40325-nsfw-free-sft_v8 status is now inactive due to auto deactivation removed underperforming models
rica40325-nsfw-free-sft_v8 status is now torndown due to DeploymentManager action