submission_id: rica40325-feedback-and-dpo_v3
developer_uid: rica40325
alignment_samples: 12508
alignment_score: 0.2909737750127793
best_of: 16
celo_rating: 1151.63
display_name: rica40325-feedback-and-dpo_v1
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\nYou: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n', 'truncate_by_message': False}
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': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: rica40325/feedback-and-dpo
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: rica40325/feedback-and-d
model_name: rica40325-feedback-and-dpo_v1
model_num_parameters: 8030261248.0
model_repo: rica40325/feedback-and-dpo
model_size: 8B
num_battles: 12508
num_wins: 4710
propriety_score: 0.7404214559386973
propriety_total_count: 1044.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-09-03T12:01:03+00:00
us_pacific_date: 2024-09-03
win_ratio: 0.3765590022385673
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rica40325-feedback-and-dpo-v3-mkmlizer
Waiting for job on rica40325-feedback-and-dpo-v3-mkmlizer to finish
rica40325-feedback-and-dpo-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-feedback-and-dpo-v3-mkmlizer: ║ _____ __ __ ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ /___/ ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ Version: 0.10.1 ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ https://mk1.ai ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ belonging to: ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ Chai Research Corp. ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
rica40325-feedback-and-dpo-v3-mkmlizer: ║ ║
rica40325-feedback-and-dpo-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-feedback-and-dpo-v3-mkmlizer: Downloaded to shared memory in 34.564s
rica40325-feedback-and-dpo-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb5vr9t6p, device:0
rica40325-feedback-and-dpo-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-feedback-and-dpo-v3-mkmlizer: quantized model in 26.261s
rica40325-feedback-and-dpo-v3-mkmlizer: Processed model rica40325/feedback-and-dpo in 60.825s
rica40325-feedback-and-dpo-v3-mkmlizer: creating bucket guanaco-mkml-models
rica40325-feedback-and-dpo-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-feedback-and-dpo-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-feedback-and-dpo-v3
rica40325-feedback-and-dpo-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-feedback-and-dpo-v3/config.json
rica40325-feedback-and-dpo-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-feedback-and-dpo-v3/special_tokens_map.json
rica40325-feedback-and-dpo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-feedback-and-dpo-v3/tokenizer_config.json
rica40325-feedback-and-dpo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-feedback-and-dpo-v3/tokenizer.json
rica40325-feedback-and-dpo-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-feedback-and-dpo-v3/flywheel_model.0.safetensors
rica40325-feedback-and-dpo-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 39.56it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:03, 74.92it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:03, 70.82it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 72.83it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:03, 73.65it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:03, 74.46it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:03, 75.83it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:03, 70.36it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:02, 74.53it/s] Loading 0: 29%|██▉ | 84/291 [00:02<00:09, 21.22it/s] Loading 0: 31%|███ | 90/291 [00:02<00:08, 24.31it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:06, 29.01it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 43.42it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 49.99it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:02, 53.72it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 60.30it/s] Loading 0: 52%|█████▏ | 151/291 [00:03<00:02, 64.48it/s] Loading 0: 55%|█████▍ | 160/291 [00:03<00:01, 66.04it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:01, 70.26it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 71.20it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 21.55it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:03, 27.54it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:02, 39.39it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 44.31it/s] Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 49.06it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:00, 55.36it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 57.51it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 59.86it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 62.06it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 61.48it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 67.37it/s] Loading 0: 100%|██████████| 291/291 [00:11<00:00, 5.18it/s]
Job rica40325-feedback-and-dpo-v3-mkmlizer completed after 84.84s with status: succeeded
Stopping job with name rica40325-feedback-and-dpo-v3-mkmlizer
Pipeline stage MKMLizer completed in 85.85s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-feedback-and-dpo-v3
Waiting for inference service rica40325-feedback-and-dpo-v3 to be ready
Inference service rica40325-feedback-and-dpo-v3 ready after 150.52303624153137s
Pipeline stage MKMLDeployer completed in 150.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.208981990814209s
Received healthy response to inference request in 2.3963754177093506s
Received healthy response to inference request in 1.8023455142974854s
Received healthy response to inference request in 1.4244415760040283s
Received healthy response to inference request in 1.6714506149291992s
5 requests
0 failed requests
5th percentile: 1.4738433837890625
10th percentile: 1.5232451915740968
20th percentile: 1.622048807144165
30th percentile: 1.6976295948028564
40th percentile: 1.7499875545501709
50th percentile: 1.8023455142974854
60th percentile: 1.9650001049041748
70th percentile: 2.127654695510864
80th percentile: 2.2464606761932373
90th percentile: 2.321418046951294
95th percentile: 2.3588967323303223
99th percentile: 2.388879680633545
mean time: 1.9007190227508546
Pipeline stage StressChecker completed in 10.40s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.33s
rica40325-feedback-and-dpo_v3 status is now deployed due to DeploymentManager action
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 0.19s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-feedback-and-dpo-v3-profiler
Waiting for inference service rica40325-feedback-and-dpo-v3-profiler to be ready
Inference service rica40325-feedback-and-dpo-v3-profiler ready after 240.5431318283081s
Pipeline stage MKMLProfilerDeployer completed in 241.04s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-feedback-ae2cc9d1e18e98ceb0ed0cbb2e28e6d15-deploqrqzf:/code/chaiverse_profiler_1725365403 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-feedback-ae2cc9d1e18e98ceb0ed0cbb2e28e6d15-deploqrqzf --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725365403 && chmod +x profiles.py && python profiles.py profile --best_of_n 16 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725365403/summary.json'
rica40325-feedback-and-dpo_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics