chaiml-mistral-nemo-simp_2753

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-simp_2753_v1

model_name: chaiml-mistral-nemo-simp_2753_v1

model_group: ChaiML/mistral_nemo_simp

status: inactive

timestamp: 2024-12-13T20:22:29+00:00

num_battles: 15100

num_wins: 7522

celo_rating: 1259.33

family_friendly_score: 0.5840000000000001

family_friendly_standard_error: 0.006970566691453429

submission_type: basic

model_repo: ChaiML/mistral_nemo_simpo_baseline_albert_241212_v1_rerun

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6279697727562922, 'latency_mean': 1.592344835996628, 'latency_p50': 1.594525933265686, 'latency_p90': 1.7526936531066895}, {'batch_size': 3, 'throughput': 1.2509888944739709, 'latency_mean': 2.3887100899219513, 'latency_p50': 2.3851003646850586, 'latency_p90': 2.6233269453048704}, {'batch_size': 5, 'throughput': 1.5743412683697253, 'latency_mean': 3.1534293842315675, 'latency_p50': 3.1625874042510986, 'latency_p90': 3.50885751247406}, {'batch_size': 6, 'throughput': 1.6826634040553898, 'latency_mean': 3.5392816853523255, 'latency_p50': 3.548252820968628, 'latency_p90': 4.018147444725036}, {'batch_size': 8, 'throughput': 1.826091326731232, 'latency_mean': 4.344062205553055, 'latency_p50': 4.314359784126282, 'latency_p90': 4.946746492385865}, {'batch_size': 10, 'throughput': 1.9047062429488346, 'latency_mean': 5.213087855577469, 'latency_p50': 5.277239441871643, 'latency_p90': 5.773696637153625}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-simp_2753_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_simpo_baseline_albert_241212_v1_rerun

model_size: 13B

ranking_group: single

throughput_3p7s: 1.73

us_pacific_date: 2024-12-13

win_ratio: 0.4981456953642384

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': 4, '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-mistral-nemo-simp-2753-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-simp-2753-v1-mkmlizer to finish
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: Downloaded to shared memory in 50.100s
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2cxl2l5g, device:0
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2753-v1
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2753-v1/special_tokens_map.json
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2753-v1/config.json
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2753-v1/tokenizer_config.json
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2753-v1/tokenizer.json
chaiml-mistral-nemo-simp-2753-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-2753-v1/flywheel_model.0.safetensors
Job chaiml-mistral-nemo-simp-2753-v1-mkmlizer completed after 115.06s with status: succeeded
Stopping job with name chaiml-mistral-nemo-simp-2753-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.55s
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-mistral-nemo-simp-2753-v1
Waiting for inference service chaiml-mistral-nemo-simp-2753-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-mistral-nemo-simp-2753-v1 ready after 190.674818277359s
Pipeline stage MKMLDeployer completed in 191.09s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.593919277191162s
Received healthy response to inference request in 1.3336286544799805s
Received healthy response to inference request in 1.0256049633026123s
Received healthy response to inference request in 1.1592061519622803s
5 requests
1 failed requests
5th percentile: 1.0523252010345459
10th percentile: 1.0790454387664794
20th percentile: 1.1324859142303467
30th percentile: 1.1940906524658204
40th percentile: 1.2638596534729003
50th percentile: 1.3336286544799805
60th percentile: 1.4377449035644532
70th percentile: 1.5418611526489256
80th percentile: 5.299019050598147
90th percentile: 12.70921859741211
95th percentile: 16.41431837081909
99th percentile: 19.378398189544676
mean time: 5.046355438232422
%s, retrying in %s seconds...
Received healthy response to inference request in 1.3474762439727783s
Received healthy response to inference request in 1.2128493785858154s
Received healthy response to inference request in 0.7265849113464355s
Received healthy response to inference request in 1.3076989650726318s
Received healthy response to inference request in 1.2227182388305664s
5 requests
0 failed requests
5th percentile: 0.8238378047943116
10th percentile: 0.9210906982421875
20th percentile: 1.1155964851379394
30th percentile: 1.2148231506347655
40th percentile: 1.218770694732666
50th percentile: 1.2227182388305664
60th percentile: 1.2567105293273926
70th percentile: 1.2907028198242188
80th percentile: 1.315654420852661
90th percentile: 1.3315653324127197
95th percentile: 1.3395207881927491
99th percentile: 1.3458851528167726
mean time: 1.1634655475616456
Pipeline stage StressChecker completed in 33.99s
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 2.14s
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 2.62s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_2753_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 2614.48s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_2753_v1 status is now inactive due to auto deactivation removed underperforming models