alexxi19-ft-v1-nemo-base

developer_uid: leosheng

submission_id: alexxi19-ft-v1-nemo-base_v6

model_name: alexxi19-ft-v1-nemo-base_v6

model_group: alexxi19/ft-v1-nemo-base

status: torndown

timestamp: 2025-02-27T08:14:27+00:00

num_battles: 8158

num_wins: 3809

celo_rating: 1247.9

family_friendly_score: 0.5494

family_friendly_standard_error: 0.007036471274722863

submission_type: basic

model_repo: alexxi19/ft-v1-nemo-base

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5938828310107733, 'latency_mean': 1.6837734866142273, 'latency_p50': 1.6816942691802979, 'latency_p90': 1.8560023784637452}, {'batch_size': 3, 'throughput': 1.0700421080416607, 'latency_mean': 2.796716763973236, 'latency_p50': 2.7907100915908813, 'latency_p90': 3.061349868774414}, {'batch_size': 5, 'throughput': 1.2740256428284833, 'latency_mean': 3.896996273994446, 'latency_p50': 3.9104163646698, 'latency_p90': 4.3596641540527346}, {'batch_size': 6, 'throughput': 1.337456437543136, 'latency_mean': 4.464743458032608, 'latency_p50': 4.485742211341858, 'latency_p90': 4.966731786727905}, {'batch_size': 8, 'throughput': 1.3812560183728644, 'latency_mean': 5.749557607173919, 'latency_p50': 5.69755220413208, 'latency_p90': 6.427060508728027}, {'batch_size': 10, 'throughput': 1.4298670134434899, 'latency_mean': 6.950194519758225, 'latency_p50': 6.960123538970947, 'latency_p90': 7.80998694896698}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-base_v6

is_internal_developer: False

language_model: alexxi19/ft-v1-nemo-base

model_size: 13B

ranking_group: single

throughput_3p7s: 1.25

us_pacific_date: 2025-02-27

win_ratio: 0.4669036528560922

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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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 alexxi19-ft-v1-nemo-base-v6-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-base-v6-mkmlizer to finish
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission mistralai-mistral-smal_78605_v18: HTTPConnectionPool(host='mistralai-mistral-smal-78605-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-base-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-base-v6-mkmlizer: Downloaded to shared memory in 68.942s
alexxi19-ft-v1-nemo-base-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvnfz7qpb, device:0
alexxi19-ft-v1-nemo-base-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-base-v6-mkmlizer: quantized model in 36.886s
alexxi19-ft-v1-nemo-base-v6-mkmlizer: Processed model alexxi19/ft-v1-nemo-base in 105.828s
alexxi19-ft-v1-nemo-base-v6-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-base-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-base-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-v6
alexxi19-ft-v1-nemo-base-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-v6/config.json
alexxi19-ft-v1-nemo-base-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-v6/special_tokens_map.json
alexxi19-ft-v1-nemo-base-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-v6/tokenizer_config.json
alexxi19-ft-v1-nemo-base-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-v6/tokenizer.json
alexxi19-ft-v1-nemo-base-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-v6/flywheel_model.0.safetensors
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Job alexxi19-ft-v1-nemo-base-v6-mkmlizer completed after 268.0s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-base-v6-mkmlizer
Pipeline stage MKMLizer completed in 268.47s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexxi19-ft-v1-nemo-base-v6
Waiting for inference service alexxi19-ft-v1-nemo-base-v6 to be ready
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service alexxi19-ft-v1-nemo-base-v6 ready after 292.3192801475525s
Pipeline stage MKMLDeployer completed in 292.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.275648832321167s
Received healthy response to inference request in 1.4549808502197266s
Received healthy response to inference request in 1.5523223876953125s
Received healthy response to inference request in 1.5217044353485107s
Received healthy response to inference request in 1.6969871520996094s
5 requests
0 failed requests
5th percentile: 1.4683255672454834
10th percentile: 1.4816702842712401
20th percentile: 1.508359718322754
30th percentile: 1.5278280258178711
40th percentile: 1.5400752067565917
50th percentile: 1.5523223876953125
60th percentile: 1.6101882934570313
70th percentile: 1.6680541992187499
80th percentile: 1.812719488143921
90th percentile: 2.044184160232544
95th percentile: 2.1599164962768556
99th percentile: 2.2525023651123046
mean time: 1.7003287315368651
Pipeline stage StressChecker completed in 10.03s
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 0.71s
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 0.63s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-base_v6 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 4484.75s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-base_v6 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-base_v6 status is now torndown due to DeploymentManager action