stark2000s-ultrachat-v1-3

developer_uid: stark2000s

submission_id: stark2000s-ultrachat-v1-3_v2

model_name: stark2000s-ultrachat-v1-3_v2

model_group: stark2000s/ultrachat-v1.

status: inactive

timestamp: 2024-11-28T12:32:46+00:00

num_battles: 15640

num_wins: 5436

celo_rating: 1142.12

family_friendly_score: 0.5818

family_friendly_standard_error: 0.006975797588806602

submission_type: basic

model_repo: stark2000s/ultrachat-v1.3

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8677103683819759, 'latency_mean': 1.1523699688911437, 'latency_p50': 1.1599743366241455, 'latency_p90': 1.2746998071670532}, {'batch_size': 4, 'throughput': 1.8516847082066672, 'latency_mean': 2.1521247470378877, 'latency_p50': 2.1389882564544678, 'latency_p90': 2.4263577222824098}, {'batch_size': 5, 'throughput': 2.007010841111635, 'latency_mean': 2.482645583152771, 'latency_p50': 2.487602114677429, 'latency_p90': 2.7607784986495973}, {'batch_size': 8, 'throughput': 2.254343579209336, 'latency_mean': 3.5305535686016083, 'latency_p50': 3.499014735221863, 'latency_p90': 4.005006742477417}, {'batch_size': 10, 'throughput': 2.27819347419725, 'latency_mean': 4.361198182106018, 'latency_p50': 4.381679058074951, 'latency_p90': 4.9021652936935425}, {'batch_size': 12, 'throughput': 2.314348721051384, 'latency_mean': 5.124931577444077, 'latency_p50': 5.140003561973572, 'latency_p90': 5.666735053062439}, {'batch_size': 15, 'throughput': 2.325192673001844, 'latency_mean': 6.360520738363266, 'latency_p50': 6.421892166137695, 'latency_p90': 7.08577606678009}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: stark2000s-ultrachat-v1-3_v2

is_internal_developer: False

language_model: stark2000s/ultrachat-v1.3

model_size: 8B

ranking_group: single

throughput_3p7s: 2.27

us_pacific_date: 2024-11-28

win_ratio: 0.3475703324808184

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 stark2000s-ultrachat-v1-3-v2-mkmlizer
Waiting for job on stark2000s-ultrachat-v1-3-v2-mkmlizer to finish
stark2000s-ultrachat-v1-3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║     _____            __           __                                ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║       /___/                                                         ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║                                                                     ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║  https://mk1.ai                                                     ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║                                                                     ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║  belonging to:                                                      ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║                                                                     ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║  Chai Research Corp.                                                ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ║                                                                     ║
stark2000s-ultrachat-v1-3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
stark2000s-ultrachat-v1-3-v2-mkmlizer: Downloaded to shared memory in 34.093s
stark2000s-ultrachat-v1-3-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpes0izi15, device:0
stark2000s-ultrachat-v1-3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
stark2000s-ultrachat-v1-3-v2-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.
stark2000s-ultrachat-v1-3-v2-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
stark2000s-ultrachat-v1-3-v2-mkmlizer: quantized model in 27.868s
stark2000s-ultrachat-v1-3-v2-mkmlizer: Processed model stark2000s/ultrachat-v1.3 in 61.961s
stark2000s-ultrachat-v1-3-v2-mkmlizer: creating bucket guanaco-mkml-models
stark2000s-ultrachat-v1-3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
stark2000s-ultrachat-v1-3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/stark2000s-ultrachat-v1-3-v2
stark2000s-ultrachat-v1-3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/stark2000s-ultrachat-v1-3-v2/config.json
stark2000s-ultrachat-v1-3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/stark2000s-ultrachat-v1-3-v2/special_tokens_map.json
stark2000s-ultrachat-v1-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/stark2000s-ultrachat-v1-3-v2/tokenizer_config.json
stark2000s-ultrachat-v1-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/stark2000s-ultrachat-v1-3-v2/tokenizer.json
stark2000s-ultrachat-v1-3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/stark2000s-ultrachat-v1-3-v2/flywheel_model.0.safetensors
stark2000s-ultrachat-v1-3-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 48.08it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:03, 73.06it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 75.19it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 77.44it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 74.22it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 77.56it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 75.80it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 79.05it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 75.05it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:11, 18.23it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:08, 22.10it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:06, 28.36it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:05, 34.41it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:04, 39.64it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:03, 43.13it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 46.83it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 51.54it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 54.06it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 55.33it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 56.63it/s]
Loading 0:  63%|██████▎   | 182/291 [00:03<00:01, 56.13it/s]
Loading 0:  65%|██████▍   | 188/291 [00:05<00:07, 13.88it/s]
Loading 0:  67%|██████▋   | 196/291 [00:05<00:05, 18.45it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:03, 24.43it/s]
Loading 0:  73%|███████▎  | 212/291 [00:05<00:02, 29.47it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 36.36it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 44.39it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:01, 52.81it/s]
Loading 0:  85%|████████▍ | 247/291 [00:06<00:00, 58.88it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 65.36it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 70.74it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 75.02it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 76.31it/s]
                                                            
Job stark2000s-ultrachat-v1-3-v2-mkmlizer completed after 83.64s with status: succeeded
Stopping job with name stark2000s-ultrachat-v1-3-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.16s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service stark2000s-ultrachat-v1-3-v2
Waiting for inference service stark2000s-ultrachat-v1-3-v2 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 stark2000s-ultrachat-v1-3-v2 ready after 130.46511054039001s
Pipeline stage MKMLDeployer completed in 131.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7998621463775635s
Received healthy response to inference request in 1.6004679203033447s
Received healthy response to inference request in 1.1933667659759521s
Received healthy response to inference request in 1.3404805660247803s
Received healthy response to inference request in 1.2053215503692627s
5 requests
0 failed requests
5th percentile: 1.1957577228546143
10th percentile: 1.1981486797332763
20th percentile: 1.2029305934906005
30th percentile: 1.2323533535003661
40th percentile: 1.2864169597625732
50th percentile: 1.3404805660247803
60th percentile: 1.4444755077362061
70th percentile: 1.5484704494476318
80th percentile: 1.6403467655181885
90th percentile: 1.720104455947876
95th percentile: 1.7599833011627197
99th percentile: 1.7918863773345948
mean time: 1.4278997898101806
Pipeline stage StressChecker completed in 8.79s
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 2.17s
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 1.99s
Shutdown handler de-registered
stark2000s-ultrachat-v1-3_v2 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 2693.54s
Shutdown handler de-registered
stark2000s-ultrachat-v1-3_v2 status is now inactive due to auto deactivation removed underperforming models