developer_uid: rirv938
submission_id: rirv938-mistral-24b-dpo_17146_v1
model_name: rirv938-mistral-24b-dpo_17146_v1
model_group: rirv938/mistral_24b_dpo_
status: torndown
timestamp: 2025-02-23T06:20:50+00:00
num_battles: 10496
num_wins: 5108
celo_rating: 1266.69
family_friendly_score: 0.6314
family_friendly_standard_error: 0.0068225221142917515
submission_type: basic
model_repo: rirv938/mistral_24b_dpo_40k_1250_v2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.38810903308602895, 'latency_mean': 2.576506391763687, 'latency_p50': 2.5617263317108154, 'latency_p90': 2.8838840246200563}, {'batch_size': 3, 'throughput': 0.79324086726602, 'latency_mean': 3.7686121749877928, 'latency_p50': 3.7450616359710693, 'latency_p90': 4.216191840171814}, {'batch_size': 5, 'throughput': 1.0508881654552449, 'latency_mean': 4.734060245752334, 'latency_p50': 4.695751190185547, 'latency_p90': 5.341121482849121}, {'batch_size': 6, 'throughput': 1.122677312627104, 'latency_mean': 5.317188427448273, 'latency_p50': 5.33551812171936, 'latency_p90': 5.980737495422363}, {'batch_size': 10, 'throughput': 1.2753096758196787, 'latency_mean': 7.75825187087059, 'latency_p50': 7.750021457672119, 'latency_p90': 8.660505437850953}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-dpo_17146_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_dpo_40k_1250_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.78
us_pacific_date: 2025-02-22
win_ratio: 0.48666158536585363
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '###', 'You:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{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 rirv938-mistral-24b-dpo-17146-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-17146-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ /___/ ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ belonging to: ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: Downloaded to shared memory in 189.157s
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsfipda9p, device:0
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: quantized model in 66.121s
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_40k_1250_v2 in 255.286s
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-17146-v1
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-17146-v1/config.json
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-17146-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-17146-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-17146-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-17146-v1/tokenizer.json
Job rirv938-mistral-24b-dpo-17146-v1-mkmlizer completed after 327.65s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-17146-v1-mkmlizer
Pipeline stage MKMLizer completed in 328.12s
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 rirv938-mistral-24b-dpo-17146-v1
Waiting for inference service rirv938-mistral-24b-dpo-17146-v1 to be ready
Inference service rirv938-mistral-24b-dpo-17146-v1 ready after 241.03766441345215s
Pipeline stage MKMLDeployer completed in 241.58s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7554383277893066s
Received healthy response to inference request in 2.028115749359131s
Received healthy response to inference request in 2.386444568634033s
Received healthy response to inference request in 2.0894598960876465s
Received healthy response to inference request in 2.308971405029297s
5 requests
0 failed requests
5th percentile: 2.040384578704834
10th percentile: 2.052653408050537
20th percentile: 2.0771910667419435
30th percentile: 2.1333621978759765
40th percentile: 2.221166801452637
50th percentile: 2.308971405029297
60th percentile: 2.3399606704711915
70th percentile: 2.370949935913086
80th percentile: 2.460243320465088
90th percentile: 2.607840824127197
95th percentile: 2.681639575958252
99th percentile: 2.7406785774230955
mean time: 2.313685989379883
Pipeline stage StressChecker completed in 12.88s
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 0.60s
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
rirv938-mistral-24b-dpo_17146_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 5426.32s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_17146_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_17146_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1