rica40325-llama31

developer_uid: rica40325

submission_id: rica40325-llama31_v1

model_name: rica40325-llama31_v1

model_group: rica40325/llama31

status: torndown

timestamp: 2025-03-10T02:39:30+00:00

num_battles: 11705

num_wins: 5010

celo_rating: 1224.42

family_friendly_score: 0.6056

family_friendly_standard_error: 0.006911564801114144

submission_type: basic

model_repo: rica40325/llama31

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8354878195397113, 'latency_mean': 1.1968320739269256, 'latency_p50': 1.2038493156433105, 'latency_p90': 1.3135340213775635}, {'batch_size': 4, 'throughput': 1.780393042475295, 'latency_mean': 2.239917196035385, 'latency_p50': 2.24077570438385, 'latency_p90': 2.486193299293518}, {'batch_size': 5, 'throughput': 1.9083304584952125, 'latency_mean': 2.607230907678604, 'latency_p50': 2.6225383281707764, 'latency_p90': 2.883942484855652}, {'batch_size': 8, 'throughput': 2.1209184715580696, 'latency_mean': 3.740253839492798, 'latency_p50': 3.764721155166626, 'latency_p90': 4.3092519521713255}, {'batch_size': 10, 'throughput': 2.1845434254688456, 'latency_mean': 4.542845802307129, 'latency_p50': 4.519011616706848, 'latency_p90': 5.136232447624207}, {'batch_size': 12, 'throughput': 2.220131511714598, 'latency_mean': 5.352204493284225, 'latency_p50': 5.331102013587952, 'latency_p90': 6.082779717445374}, {'batch_size': 15, 'throughput': 2.222590006946945, 'latency_mean': 6.663750411272049, 'latency_p50': 6.6706753969192505, 'latency_p90': 7.538991403579712}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-llama31_v1

is_internal_developer: False

language_model: rica40325/llama31

model_size: 8B

ranking_group: single

throughput_3p7s: 2.13

us_pacific_date: 2025-03-09

win_ratio: 0.4280222127296027

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 rica40325-llama31-v1-mkmlizer
Waiting for job on rica40325-llama31-v1-mkmlizer to finish
rica40325-llama31-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-llama31-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-llama31-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-llama31-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-llama31-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-llama31-v1-mkmlizer: ║       /___/                                                         ║
rica40325-llama31-v1-mkmlizer: ║                                                                     ║
rica40325-llama31-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rica40325-llama31-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-llama31-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-llama31-v1-mkmlizer: ║                                                                     ║
rica40325-llama31-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-llama31-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-llama31-v1-mkmlizer: ║                                                                     ║
rica40325-llama31-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-llama31-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-llama31-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rica40325-llama31-v1-mkmlizer: ║                                                                     ║
rica40325-llama31-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-llama31-v1-mkmlizer: Downloaded to shared memory in 36.545s
rica40325-llama31-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjclfr5dg, device:0
rica40325-llama31-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-llama31-v1-mkmlizer: quantized model in 25.889s
rica40325-llama31-v1-mkmlizer: Processed model rica40325/llama31 in 62.435s
rica40325-llama31-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-llama31-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-llama31-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-llama31-v1
rica40325-llama31-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-llama31-v1/config.json
rica40325-llama31-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-llama31-v1/special_tokens_map.json
rica40325-llama31-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-llama31-v1/tokenizer_config.json
rica40325-llama31-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-llama31-v1/tokenizer.json
rica40325-llama31-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-llama31-v1/flywheel_model.0.safetensors
rica40325-llama31-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 34.17it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 48.58it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 53.31it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:04, 55.29it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 56.53it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 57.40it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 56.50it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 59.88it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:03, 54.56it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:03, 54.37it/s]
Loading 0:  30%|██▉       | 86/291 [00:01<00:05, 36.08it/s]
Loading 0:  33%|███▎      | 95/291 [00:01<00:04, 41.28it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:03, 48.61it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:03, 48.10it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 50.04it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:03, 47.69it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:02, 53.72it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 50.56it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 51.83it/s]
Loading 0:  51%|█████     | 149/291 [00:02<00:02, 48.98it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 55.11it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 52.24it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 51.90it/s]
Loading 0:  61%|██████    | 177/291 [00:03<00:02, 53.11it/s]
Loading 0:  63%|██████▎   | 183/291 [00:03<00:02, 52.06it/s]
Loading 0:  65%|██████▍   | 189/291 [00:03<00:02, 35.64it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:02, 37.66it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 44.17it/s]
Loading 0:  71%|███████   | 207/291 [00:04<00:01, 45.77it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 40.49it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 45.76it/s]
Loading 0:  78%|███████▊  | 226/291 [00:04<00:01, 45.43it/s]
Loading 0:  79%|███████▉  | 231/291 [00:04<00:01, 46.02it/s]
Loading 0:  82%|████████▏ | 238/291 [00:04<00:01, 51.53it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:00, 47.84it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 49.05it/s]
Loading 0:  88%|████████▊ | 257/291 [00:05<00:00, 45.99it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 52.05it/s]
Loading 0:  93%|█████████▎| 271/291 [00:05<00:00, 45.33it/s]
Loading 0:  95%|█████████▍| 276/291 [00:05<00:00, 45.83it/s]
Loading 0:  97%|█████████▋| 282/291 [00:05<00:00, 43.81it/s]
Loading 0:  99%|█████████▊| 287/291 [00:11<00:01,  3.35it/s]
                                                            
Job rica40325-llama31-v1-mkmlizer completed after 83.3s with status: succeeded
Stopping job with name rica40325-llama31-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-llama31-v1
Waiting for inference service rica40325-llama31-v1 to be ready
Inference service rica40325-llama31-v1 ready after 90.32693552970886s
Pipeline stage MKMLDeployer completed in 90.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9418003559112549s
Received healthy response to inference request in 1.3257484436035156s
Received healthy response to inference request in 1.3721191883087158s
Received healthy response to inference request in 1.2393617630004883s
Received healthy response to inference request in 1.3083655834197998s
5 requests
0 failed requests
5th percentile: 1.2531625270843505
10th percentile: 1.266963291168213
20th percentile: 1.2945648193359376
30th percentile: 1.311842155456543
40th percentile: 1.3187952995300294
50th percentile: 1.3257484436035156
60th percentile: 1.3442967414855957
70th percentile: 1.3628450393676759
80th percentile: 1.4860554218292237
90th percentile: 1.7139278888702394
95th percentile: 1.827864122390747
99th percentile: 1.9190131092071534
mean time: 1.437479066848755
Pipeline stage StressChecker completed in 8.46s
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 0.73s
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 0.87s
Shutdown handler de-registered
rica40325-llama31_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3885.88s
Shutdown handler de-registered
rica40325-llama31_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-llama31_v1 status is now torndown due to DeploymentManager action