stark2000s-ultra-du-v1-4

developer_uid: stark2000s

submission_id: stark2000s-ultra-du-v1-4_v3

model_name: stark2000s-ultra-du-v1-4_v1

model_group: stark2000s/ultra_du-v1.4

status: torndown

timestamp: 2024-11-10T10:16:37+00:00

num_battles: 17254

num_wins: 8279

celo_rating: 1225.7

family_friendly_score: 0.5562

family_friendly_standard_error: 0.007026258748437891

submission_type: basic

model_repo: stark2000s/ultra_du-v1.4

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.867615305590257, 'latency_mean': 1.1525259733200073, 'latency_p50': 1.1455847024917603, 'latency_p90': 1.299885845184326}, {'batch_size': 3, 'throughput': 1.5305129410907141, 'latency_mean': 1.9525896859169007, 'latency_p50': 1.9361205101013184, 'latency_p90': 2.1817604303359985}, {'batch_size': 5, 'throughput': 1.716732407485963, 'latency_mean': 2.8970349872112275, 'latency_p50': 2.89507520198822, 'latency_p90': 3.2214731216430663}, {'batch_size': 6, 'throughput': 1.7730861109251599, 'latency_mean': 3.3646963620185852, 'latency_p50': 3.3577311038970947, 'latency_p90': 3.75382604598999}, {'batch_size': 8, 'throughput': 1.8181445074250562, 'latency_mean': 4.366348620653152, 'latency_p50': 4.384349346160889, 'latency_p90': 4.819197130203247}, {'batch_size': 10, 'throughput': 1.8601502600210886, 'latency_mean': 5.331108210086822, 'latency_p50': 5.289233207702637, 'latency_p90': 6.160974717140197}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: stark2000s-ultra-du-v1-4_v1

is_internal_developer: False

language_model: stark2000s/ultra_du-v1.4

model_size: 8B

ranking_group: single

throughput_3p7s: 1.8

us_pacific_date: 2024-11-10

win_ratio: 0.47983076388083923

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': 512, 'best_of': 16, '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-ultra-du-v1-4-v3-mkmlizer
Waiting for job on stark2000s-ultra-du-v1-4-v3-mkmlizer to finish
stark2000s-ultra-du-v1-4-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║     _____            __           __                                ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║       /___/                                                         ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║                                                                     ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║  Version: 0.11.33                                                   ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║  https://mk1.ai                                                     ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║                                                                     ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║  belonging to:                                                      ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║                                                                     ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║  Chai Research Corp.                                                ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ║                                                                     ║
stark2000s-ultra-du-v1-4-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
stark2000s-ultra-du-v1-4-v3-mkmlizer: Downloaded to shared memory in 22.011s
stark2000s-ultra-du-v1-4-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw4doxkr6, device:0
stark2000s-ultra-du-v1-4-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
stark2000s-ultra-du-v1-4-v3-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-ultra-du-v1-4-v3-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
stark2000s-ultra-du-v1-4-v3-mkmlizer: quantized model in 26.877s
stark2000s-ultra-du-v1-4-v3-mkmlizer: Processed model stark2000s/ultra_du-v1.4 in 48.889s
stark2000s-ultra-du-v1-4-v3-mkmlizer: creating bucket guanaco-mkml-models
stark2000s-ultra-du-v1-4-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
stark2000s-ultra-du-v1-4-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/stark2000s-ultra-du-v1-4-v3
stark2000s-ultra-du-v1-4-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/stark2000s-ultra-du-v1-4-v3/config.json
stark2000s-ultra-du-v1-4-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/stark2000s-ultra-du-v1-4-v3/special_tokens_map.json
stark2000s-ultra-du-v1-4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/stark2000s-ultra-du-v1-4-v3/tokenizer_config.json
stark2000s-ultra-du-v1-4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/stark2000s-ultra-du-v1-4-v3/tokenizer.json
stark2000s-ultra-du-v1-4-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 39.75it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 67.19it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 75.44it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 77.79it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 79.12it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 72.38it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 75.97it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 78.83it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:02, 78.63it/s]
Loading 0:  29%|██▉       | 84/291 [00:02<00:10, 20.09it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:08, 22.64it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 27.00it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 33.18it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 40.98it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 47.74it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 51.98it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:02, 58.38it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 59.96it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 63.78it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 66.23it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 68.75it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:05, 20.38it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 25.25it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:02, 31.12it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:02, 36.45it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 43.37it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 47.74it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 54.89it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 61.43it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 67.01it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 69.22it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 73.19it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 75.48it/s]
                                                            
Job stark2000s-ultra-du-v1-4-v3-mkmlizer completed after 73.9s with status: succeeded
Stopping job with name stark2000s-ultra-du-v1-4-v3-mkmlizer
Pipeline stage MKMLizer completed in 74.44s
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 stark2000s-ultra-du-v1-4-v3
Waiting for inference service stark2000s-ultra-du-v1-4-v3 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
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
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-ultra-du-v1-4-v3 ready after 180.63420009613037s
Pipeline stage MKMLDeployer completed in 181.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0050861835479736s
Received healthy response to inference request in 1.5002286434173584s
Received healthy response to inference request in 2.0896077156066895s
Received healthy response to inference request in 1.2657980918884277s
Received healthy response to inference request in 1.3459370136260986s
5 requests
0 failed requests
5th percentile: 1.281825876235962
10th percentile: 1.297853660583496
20th percentile: 1.3299092292785644
30th percentile: 1.3767953395843506
40th percentile: 1.4385119915008544
50th percentile: 1.5002286434173584
60th percentile: 1.7021716594696044
70th percentile: 1.9041146755218505
80th percentile: 2.021990489959717
90th percentile: 2.055799102783203
95th percentile: 2.072703409194946
99th percentile: 2.086226854324341
mean time: 1.6413315296173097
Pipeline stage StressChecker completed in 9.64s
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
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 5.94s
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 2.44s
Shutdown handler de-registered
stark2000s-ultra-du-v1-4_v3 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 2725.58s
Shutdown handler de-registered
stark2000s-ultra-du-v1-4_v3 status is now inactive due to auto deactivation removed underperforming models
stark2000s-ultra-du-v1-4_v3 status is now torndown due to DeploymentManager action