developer_uid: azuruce
submission_id: chaiml-nitral-beta-4-40_74489_v2
model_name: chaiml-nitral-beta-4-40_74489_v2
model_group: ChaiML/nitral_beta_4_40k
status: torndown
timestamp: 2025-01-03T21:46:12+00:00
num_battles: 10140
num_wins: 5093
celo_rating: 1272.66
family_friendly_score: 0.5822
family_friendly_standard_error: 0.006974857131153297
submission_type: basic
model_repo: ChaiML/nitral_beta_4_40k_2496_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 1
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6658841924966726, 'latency_mean': 1.5016956877708436, 'latency_p50': 1.5031094551086426, 'latency_p90': 1.6586602210998536}, {'batch_size': 4, 'throughput': 1.6110167769455566, 'latency_mean': 2.4741159188747406, 'latency_p50': 2.4438390731811523, 'latency_p90': 2.8357064962387084}, {'batch_size': 5, 'throughput': 1.7948772285119299, 'latency_mean': 2.770314247608185, 'latency_p50': 2.76740300655365, 'latency_p90': 3.113442540168762}, {'batch_size': 8, 'throughput': 2.1823135226632155, 'latency_mean': 3.6476841378211975, 'latency_p50': 3.6421127319335938, 'latency_p90': 4.090059518814087}, {'batch_size': 10, 'throughput': 2.3382837923713566, 'latency_mean': 4.249395644664764, 'latency_p50': 4.251329660415649, 'latency_p90': 4.831773114204407}, {'batch_size': 12, 'throughput': 2.4644274314654595, 'latency_mean': 4.818886796236038, 'latency_p50': 4.80947744846344, 'latency_p90': 5.531383037567139}, {'batch_size': 15, 'throughput': 2.5784155984755364, 'latency_mean': 5.761207944154739, 'latency_p50': 5.703125834465027, 'latency_p90': 6.641900372505187}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nitral-beta-4-40_74489_v2
is_internal_developer: True
language_model: ChaiML/nitral_beta_4_40k_2496_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 2.21
us_pacific_date: 2025-01-03
win_ratio: 0.5022682445759369
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 1, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', '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 chaiml-nitral-beta-4-40-74489-v2-mkmlizer
Waiting for job on chaiml-nitral-beta-4-40-74489-v2-mkmlizer to finish
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ _____ __ __ ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ /___/ ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ belonging to: ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ║ ║
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-nitral-18k-1116-v2_v1: HTTPConnectionPool(host='chaiml-nitral-18k-1116-v2-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nitral-18k-1116-v2_v1: HTTPConnectionPool(host='chaiml-nitral-18k-1116-v2-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: Downloaded to shared memory in 65.044s
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjb8c65q8, device:0
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: quantized model in 42.260s
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: Processed model ChaiML/nitral_beta_4_40k_2496_v2 in 107.304s
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nitral-beta-4-40-74489-v2
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nitral-beta-4-40-74489-v2/config.json
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nitral-beta-4-40-74489-v2/special_tokens_map.json
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nitral-beta-4-40-74489-v2/tokenizer_config.json
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nitral-beta-4-40-74489-v2/tokenizer.json
chaiml-nitral-beta-4-40-74489-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nitral-beta-4-40-74489-v2/flywheel_model.0.safetensors
Job chaiml-nitral-beta-4-40-74489-v2-mkmlizer completed after 176.03s with status: succeeded
Stopping job with name chaiml-nitral-beta-4-40-74489-v2-mkmlizer
Pipeline stage MKMLizer completed in 181.58s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nitral-beta-4-40-74489-v2
Waiting for inference service chaiml-nitral-beta-4-40-74489-v2 to be ready
Inference service chaiml-nitral-beta-4-40-74489-v2 ready after 331.4824674129486s
Pipeline stage MKMLDeployer completed in 332.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7636184692382812s
Received healthy response to inference request in 1.2678821086883545s
Received healthy response to inference request in 1.4542920589447021s
Received healthy response to inference request in 1.2635235786437988s
Received healthy response to inference request in 1.2601556777954102s
5 requests
0 failed requests
5th percentile: 1.260829257965088
10th percentile: 1.2615028381347657
20th percentile: 1.262849998474121
30th percentile: 1.26439528465271
40th percentile: 1.2661386966705321
50th percentile: 1.2678821086883545
60th percentile: 1.3424460887908936
70th percentile: 1.4170100688934326
80th percentile: 1.516157341003418
90th percentile: 1.6398879051208497
95th percentile: 1.7017531871795655
99th percentile: 1.751245412826538
mean time: 1.4018943786621094
Pipeline stage StressChecker completed in 8.36s
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 0.62s
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 0.68s
Shutdown handler de-registered
chaiml-nitral-beta-4-40_74489_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-nitral-beta-4-40-74489-v2-profiler
Waiting for inference service chaiml-nitral-beta-4-40-74489-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 2258.17s
Shutdown handler de-registered
chaiml-nitral-beta-4-40_74489_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-nitral-beta-4-40_74489_v2 status is now torndown due to DeploymentManager action
chaiml-nitral-beta-4-40_74489_v2 status is now torndown due to DeploymentManager action
chaiml-nitral-beta-4-40_74489_v2 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1