developer_uid: PawanOsman
submission_id: pawankrd-cosmosrp-3-5_v2
model_name: pawankrd-cosmosrp-3-5_v2
model_group: PawanKrd/cosmosrp-3.5
status: torndown
timestamp: 2025-01-13T20:43:10+00:00
num_battles: 12595
num_wins: 6133
celo_rating: 1250.82
family_friendly_score: 0.5853999999999999
family_friendly_standard_error: 0.006967163554847841
submission_type: basic
model_repo: PawanKrd/cosmosrp-3.5
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.8586794242249486, 'latency_mean': 1.1644861686229706, 'latency_p50': 1.1666321754455566, 'latency_p90': 1.2862580060958861}, {'batch_size': 4, 'throughput': 1.870207266816883, 'latency_mean': 2.1289025807380675, 'latency_p50': 2.1193286180496216, 'latency_p90': 2.3867884635925294}, {'batch_size': 5, 'throughput': 2.020173885206795, 'latency_mean': 2.4646202170848848, 'latency_p50': 2.4705121517181396, 'latency_p90': 2.746478724479675}, {'batch_size': 8, 'throughput': 2.2348965346809475, 'latency_mean': 3.5531506288051604, 'latency_p50': 3.538758635520935, 'latency_p90': 4.047113752365112}, {'batch_size': 10, 'throughput': 2.28683666274763, 'latency_mean': 4.338855987787246, 'latency_p50': 4.350090742111206, 'latency_p90': 4.845914220809936}, {'batch_size': 12, 'throughput': 2.3418643154043055, 'latency_mean': 5.086624164581298, 'latency_p50': 5.0758957862854, 'latency_p90': 5.7869021654129025}, {'batch_size': 15, 'throughput': 2.3657710221353505, 'latency_mean': 6.262823024988174, 'latency_p50': 6.293484807014465, 'latency_p90': 6.9290804147720335}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: pawankrd-cosmosrp-3-5_v2
is_internal_developer: False
language_model: PawanKrd/cosmosrp-3.5
model_size: 8B
ranking_group: single
throughput_3p7s: 2.26
us_pacific_date: 2025-01-13
win_ratio: 0.4869392616117507
generation_params: {'temperature': 0.7, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, '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': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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 pawankrd-cosmosrp-3-5-v2-mkmlizer
Waiting for job on pawankrd-cosmosrp-3-5-v2-mkmlizer to finish
pawankrd-cosmosrp-3-5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ Version: 0.11.12 ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-3-5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-3-5-v2-mkmlizer: Downloaded to shared memory in 31.469s
pawankrd-cosmosrp-3-5-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjmjwd0eh, device:0
pawankrd-cosmosrp-3-5-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-3-5-v2-mkmlizer: quantized model in 25.950s
pawankrd-cosmosrp-3-5-v2-mkmlizer: Processed model PawanKrd/cosmosrp-3.5 in 57.419s
pawankrd-cosmosrp-3-5-v2-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-3-5-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-3-5-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-3-5-v2
pawankrd-cosmosrp-3-5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-3-5-v2/special_tokens_map.json
pawankrd-cosmosrp-3-5-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-3-5-v2/config.json
pawankrd-cosmosrp-3-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-3-5-v2/tokenizer_config.json
pawankrd-cosmosrp-3-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-3-5-v2/tokenizer.json
pawankrd-cosmosrp-3-5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-3-5-v2/flywheel_model.0.safetensors
pawankrd-cosmosrp-3-5-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:27, 2.38s/it] Loading 0: 2%|▏ | 6/291 [00:04<03:03, 1.55it/s] Loading 0: 4%|▍ | 11/291 [00:05<01:20, 3.46it/s] Loading 0: 5%|▌ | 15/291 [00:05<00:51, 5.37it/s] Loading 0: 8%|▊ | 23/291 [00:05<00:25, 10.54it/s] Loading 0: 10%|▉ | 29/291 [00:05<00:18, 14.45it/s] Loading 0: 12%|█▏ | 34/291 [00:05<00:14, 17.85it/s] Loading 0: 14%|█▍ | 42/291 [00:05<00:10, 23.95it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:07, 31.71it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:06, 34.53it/s] Loading 0: 21%|██▏ | 62/291 [00:06<00:07, 28.93it/s] Loading 0: 23%|██▎ | 68/291 [00:06<00:06, 33.11it/s] Loading 0: 25%|██▌ | 74/291 [00:06<00:06, 34.89it/s] Loading 0: 27%|██▋ | 79/291 [00:06<00:05, 37.22it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:04, 43.79it/s] Loading 0: 32%|███▏ | 92/291 [00:06<00:04, 41.64it/s] Loading 0: 33%|███▎ | 97/291 [00:06<00:04, 41.91it/s] Loading 0: 36%|███▌ | 104/291 [00:07<00:03, 48.19it/s] Loading 0: 38%|███▊ | 110/291 [00:07<00:03, 45.76it/s] Loading 0: 40%|███▉ | 115/291 [00:07<00:03, 45.44it/s] Loading 0: 42%|████▏ | 122/291 [00:07<00:03, 50.65it/s] Loading 0: 44%|████▍ | 128/291 [00:07<00:03, 48.02it/s] Loading 0: 46%|████▌ | 133/291 [00:07<00:03, 47.60it/s] Loading 0: 48%|████▊ | 139/291 [00:07<00:03, 49.93it/s] Loading 0: 50%|████▉ | 145/291 [00:07<00:02, 52.19it/s] Loading 0: 52%|█████▏ | 151/291 [00:08<00:02, 48.75it/s] Loading 0: 55%|█████▍ | 159/291 [00:08<00:02, 49.73it/s] Loading 0: 57%|█████▋ | 166/291 [00:08<00:02, 42.38it/s] Loading 0: 59%|█████▉ | 171/291 [00:08<00:02, 43.90it/s] Loading 0: 61%|██████ | 177/291 [00:08<00:02, 40.47it/s] Loading 0: 64%|██████▎ | 185/291 [00:08<00:02, 47.95it/s] Loading 0: 66%|██████▌ | 191/291 [00:08<00:02, 46.14it/s] Loading 0: 67%|██████▋ | 196/291 [00:09<00:02, 45.82it/s] Loading 0: 70%|██████▉ | 203/291 [00:09<00:01, 51.54it/s] Loading 0: 72%|███████▏ | 209/291 [00:09<00:01, 48.19it/s] Loading 0: 74%|███████▍ | 215/291 [00:09<00:01, 49.13it/s] Loading 0: 76%|███████▋ | 222/291 [00:09<00:01, 46.10it/s] Loading 0: 79%|███████▉ | 230/291 [00:09<00:01, 53.28it/s] Loading 0: 81%|████████ | 236/291 [00:09<00:01, 48.98it/s] Loading 0: 84%|████████▎ | 243/291 [00:09<00:00, 53.79it/s] Loading 0: 86%|████████▌ | 249/291 [00:10<00:00, 49.26it/s] Loading 0: 88%|████████▊ | 257/291 [00:10<00:00, 56.17it/s] Loading 0: 90%|█████████ | 263/291 [00:10<00:00, 52.10it/s] Loading 0: 92%|█████████▏| 269/291 [00:10<00:00, 38.56it/s] Loading 0: 95%|█████████▍| 276/291 [00:10<00:00, 39.66it/s] Loading 0: 98%|█████████▊| 284/291 [00:10<00:00, 47.57it/s] Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 46.44it/s]
Job pawankrd-cosmosrp-3-5-v2-mkmlizer completed after 83.71s with status: succeeded
Stopping job with name pawankrd-cosmosrp-3-5-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.21s
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 pawankrd-cosmosrp-3-5-v2
Waiting for inference service pawankrd-cosmosrp-3-5-v2 to be ready
Failed to get response for submission pawankrd-cosmosrp-3-5_v1: HTTPConnectionPool(host='pawankrd-cosmosrp-3-5-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission pawankrd-cosmosrp-3-5_v1: HTTPConnectionPool(host='pawankrd-cosmosrp-3-5-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service pawankrd-cosmosrp-3-5-v2 ready after 361.8720235824585s
Pipeline stage MKMLDeployer completed in 362.38s
run pipeline stage %s
Running pipeline stage StressChecker
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.7745656967163086s
Received healthy response to inference request in 1.2364907264709473s
Received healthy response to inference request in 1.3314688205718994s
Received healthy response to inference request in 1.7021737098693848s
Received healthy response to inference request in 1.3723323345184326s
5 requests
0 failed requests
5th percentile: 1.2554863452911378
10th percentile: 1.274481964111328
20th percentile: 1.312473201751709
30th percentile: 1.339641523361206
40th percentile: 1.3559869289398194
50th percentile: 1.3723323345184326
60th percentile: 1.5042688846588135
70th percentile: 1.6362054347991943
80th percentile: 1.7166521072387695
90th percentile: 1.7456089019775392
95th percentile: 1.7600872993469239
99th percentile: 1.7716700172424316
mean time: 1.4834062576293945
Pipeline stage StressChecker completed in 8.78s
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 1.09s
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 0.76s
Shutdown handler de-registered
pawankrd-cosmosrp-3-5_v2 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service pawankrd-cosmosrp-3-5-v2-profiler
Waiting for inference service pawankrd-cosmosrp-3-5-v2-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 2363.49s
Shutdown handler de-registered
pawankrd-cosmosrp-3-5_v2 status is now inactive due to auto deactivation removed underperforming models
pawankrd-cosmosrp-3-5_v2 status is now torndown due to DeploymentManager action