stark2000s-hope

developer_uid: stark2000s

submission_id: stark2000s-hope_v1

model_name: stark2000s-hope_v1

model_group: stark2000s/hope

status: inactive

timestamp: 2024-12-13T01:10:17+00:00

num_battles: 6422

num_wins: 2964

celo_rating: 1227.85

family_friendly_score: 0.5778

family_friendly_standard_error: 0.006984943235273999

submission_type: basic

model_repo: stark2000s/hope

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8544438713401309, 'latency_mean': 1.1702843022346496, 'latency_p50': 1.1693644523620605, 'latency_p90': 1.279345440864563}, {'batch_size': 4, 'throughput': 1.8552854818199624, 'latency_mean': 2.1504862093925476, 'latency_p50': 2.1595901250839233, 'latency_p90': 2.426830458641052}, {'batch_size': 5, 'throughput': 1.9807801883974094, 'latency_mean': 2.5025163817405702, 'latency_p50': 2.512291193008423, 'latency_p90': 2.7587140798568726}, {'batch_size': 8, 'throughput': 2.218668448751431, 'latency_mean': 3.5827272868156435, 'latency_p50': 3.5611127614974976, 'latency_p90': 3.988461470603943}, {'batch_size': 10, 'throughput': 2.266452322504451, 'latency_mean': 4.380869263410569, 'latency_p50': 4.409461259841919, 'latency_p90': 4.971794629096985}, {'batch_size': 12, 'throughput': 2.2869906140916183, 'latency_mean': 5.18996046423912, 'latency_p50': 5.249191403388977, 'latency_p90': 5.860607051849366}, {'batch_size': 15, 'throughput': 2.29899346464469, 'latency_mean': 6.444931961297989, 'latency_p50': 6.391374945640564, 'latency_p90': 7.221031379699707}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: stark2000s-hope_v1

is_internal_developer: False

language_model: stark2000s/hope

model_size: 8B

ranking_group: single

throughput_3p7s: 2.24

us_pacific_date: 2024-12-12

win_ratio: 0.46153846153846156

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-hope-v1-mkmlizer
Waiting for job on stark2000s-hope-v1-mkmlizer to finish
stark2000s-hope-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
stark2000s-hope-v1-mkmlizer: ║     _____            __           __                                ║
stark2000s-hope-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
stark2000s-hope-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
stark2000s-hope-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
stark2000s-hope-v1-mkmlizer: ║       /___/                                                         ║
stark2000s-hope-v1-mkmlizer: ║                                                                     ║
stark2000s-hope-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
stark2000s-hope-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
stark2000s-hope-v1-mkmlizer: ║  https://mk1.ai                                                     ║
stark2000s-hope-v1-mkmlizer: ║                                                                     ║
stark2000s-hope-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
stark2000s-hope-v1-mkmlizer: ║  belonging to:                                                      ║
stark2000s-hope-v1-mkmlizer: ║                                                                     ║
stark2000s-hope-v1-mkmlizer: ║  Chai Research Corp.                                                ║
stark2000s-hope-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
stark2000s-hope-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
stark2000s-hope-v1-mkmlizer: ║                                                                     ║
stark2000s-hope-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
stark2000s-hope-v1-mkmlizer: quantized model in 27.168s
stark2000s-hope-v1-mkmlizer: Processed model stark2000s/hope in 60.590s
stark2000s-hope-v1-mkmlizer: creating bucket guanaco-mkml-models
stark2000s-hope-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
stark2000s-hope-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/stark2000s-hope-v1
stark2000s-hope-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/stark2000s-hope-v1/config.json
stark2000s-hope-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/stark2000s-hope-v1/special_tokens_map.json
stark2000s-hope-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/stark2000s-hope-v1/tokenizer_config.json
stark2000s-hope-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/stark2000s-hope-v1/tokenizer.json
stark2000s-hope-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/stark2000s-hope-v1/flywheel_model.0.safetensors
stark2000s-hope-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 39.86it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 62.81it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 63.00it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 67.65it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 70.97it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 72.75it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 72.08it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:03, 72.55it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:02, 74.04it/s]
Loading 0:  29%|██▉       | 84/291 [00:02<00:10, 19.33it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:09, 22.07it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 25.76it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 32.93it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 40.91it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 47.23it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:02, 54.02it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:02, 60.28it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 65.40it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 65.15it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 68.43it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 71.57it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:05, 20.22it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 26.14it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:02, 32.90it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:01, 40.15it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 44.88it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 50.01it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 56.16it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 62.64it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 65.49it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 65.53it/s]
Loading 0:  95%|█████████▌| 277/291 [00:06<00:00, 70.60it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 74.34it/s]
                                                            
Job stark2000s-hope-v1-mkmlizer completed after 84.05s with status: succeeded
Stopping job with name stark2000s-hope-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.60s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service stark2000s-hope-v1
Waiting for inference service stark2000s-hope-v1 to be ready
Inference service stark2000s-hope-v1 ready after 201.04425072669983s
Pipeline stage MKMLDeployer completed in 201.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7917039394378662s
Received healthy response to inference request in 1.3702096939086914s
Received healthy response to inference request in 1.7212605476379395s
Received healthy response to inference request in 1.1847403049468994s
Received healthy response to inference request in 1.382000207901001s
5 requests
0 failed requests
5th percentile: 1.2218341827392578
10th percentile: 1.2589280605316162
20th percentile: 1.333115816116333
30th percentile: 1.3725677967071532
40th percentile: 1.377284002304077
50th percentile: 1.382000207901001
60th percentile: 1.5177043437957765
70th percentile: 1.6534084796905517
80th percentile: 1.7353492259979248
90th percentile: 1.7635265827178954
95th percentile: 1.7776152610778808
99th percentile: 1.788886203765869
mean time: 1.4899829387664796
Pipeline stage StressChecker completed in 8.87s
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 2.55s
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 2.25s
Shutdown handler de-registered
stark2000s-hope_v1 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 2100.23s
Shutdown handler de-registered
stark2000s-hope_v1 status is now inactive due to auto deactivation removed underperforming models