chaiml-rob-script-short-dpo

developer_uid: azuruce

submission_id: chaiml-rob-script-short-dpo_v1

model_name: chaiml-rob-script-short-dpo_v1

model_group: ChaiML/rob-script-short-

status: torndown

timestamp: 2025-01-03T18:41:29+00:00

num_battles: 18677

num_wins: 8486

celo_rating: 1229.21

family_friendly_score: 0.5958

family_friendly_standard_error: 0.0069400628239231375

submission_type: basic

model_repo: ChaiML/rob-script-short-dpo

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.632528122091978, 'latency_mean': 1.580868089199066, 'latency_p50': 1.5723295211791992, 'latency_p90': 1.7437089920043944}, {'batch_size': 3, 'throughput': 1.2664312814103957, 'latency_mean': 2.36109548330307, 'latency_p50': 2.3468167781829834, 'latency_p90': 2.6216304063797}, {'batch_size': 5, 'throughput': 1.5917456671328074, 'latency_mean': 3.1263257551193235, 'latency_p50': 3.1199162006378174, 'latency_p90': 3.510972785949707}, {'batch_size': 6, 'throughput': 1.696781780502709, 'latency_mean': 3.509906643629074, 'latency_p50': 3.5018080472946167, 'latency_p90': 3.973581314086914}, {'batch_size': 8, 'throughput': 1.8579407531551209, 'latency_mean': 4.283155379295349, 'latency_p50': 4.304851651191711, 'latency_p90': 4.748753905296326}, {'batch_size': 10, 'throughput': 1.9469777917159234, 'latency_mean': 5.092410025596618, 'latency_p50': 5.087021350860596, 'latency_p90': 5.778284692764282}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-rob-script-short-dpo_v1

is_internal_developer: False

language_model: ChaiML/rob-script-short-dpo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.75

us_pacific_date: 2025-01-03

win_ratio: 0.45435562456497297

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': ['Bot:', '<|eot_id|>', '####', 'User:', 'You:', '<|im_end|>', '</s>', '\n'], '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-rob-script-short-dpo-v1-mkmlizer
Waiting for job on chaiml-rob-script-short-dpo-v1-mkmlizer to finish
chaiml-rob-script-short-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-rob-script-short-dpo-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║       /___/                                                         ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-rob-script-short-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-rob-script-short-dpo-v1-mkmlizer: Downloaded to shared memory in 41.675s
chaiml-rob-script-short-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpetg5um4d, device:0
chaiml-rob-script-short-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-rob-script-short-dpo-v1-mkmlizer: quantized model in 35.459s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-rob-script-short-dpo-v1-mkmlizer: Processed model ChaiML/rob-script-short-dpo in 77.135s
chaiml-rob-script-short-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-rob-script-short-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-rob-script-short-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-rob-script-short-dpo-v1
chaiml-rob-script-short-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-rob-script-short-dpo-v1/config.json
chaiml-rob-script-short-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-rob-script-short-dpo-v1/special_tokens_map.json
chaiml-rob-script-short-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-rob-script-short-dpo-v1/tokenizer_config.json
chaiml-rob-script-short-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-rob-script-short-dpo-v1/tokenizer.json
chaiml-rob-script-short-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-rob-script-short-dpo-v1/flywheel_model.0.safetensors
Job chaiml-rob-script-short-dpo-v1-mkmlizer completed after 104.55s with status: succeeded
Stopping job with name chaiml-rob-script-short-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.07s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-rob-script-short-dpo-v1
Waiting for inference service chaiml-rob-script-short-dpo-v1 to be ready
Inference service chaiml-rob-script-short-dpo-v1 ready after 321.55566239356995s
Pipeline stage MKMLDeployer completed in 322.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3360514640808105s
Received healthy response to inference request in 0.6728365421295166s
Received healthy response to inference request in 1.3768346309661865s
Received healthy response to inference request in 1.237849473953247s
Received healthy response to inference request in 0.7659702301025391s
5 requests
0 failed requests
5th percentile: 0.6914632797241211
10th percentile: 0.7100900173187256
20th percentile: 0.7473434925079345
30th percentile: 0.8603460788726807
40th percentile: 1.0490977764129639
50th percentile: 1.237849473953247
60th percentile: 1.293443536758423
70th percentile: 1.3490375995635986
80th percentile: 1.5686779975891114
90th percentile: 1.952364730834961
95th percentile: 2.1442080974578857
99th percentile: 2.2976827907562254
mean time: 1.2779084682464599
Pipeline stage StressChecker completed in 8.24s
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 0.89s
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 0.90s
Shutdown handler de-registered
chaiml-rob-script-short-dpo_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 5711.78s
Shutdown handler de-registered
chaiml-rob-script-short-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-rob-script-short-dpo_v1 status is now torndown due to DeploymentManager action
chaiml-rob-script-short-dpo_v1 status is now torndown due to DeploymentManager action
chaiml-rob-script-short-dpo_v1 status is now torndown due to DeploymentManager action