submission_id: rica40325-feedback-and-dpo_v1
developer_uid: rica40325
alignment_samples: 11447
alignment_score: 0.9017426032470925
best_of: 1
celo_rating: 1145.39
display_name: rica40325-feedback-and-dpo_v1
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', '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': 1, '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: 11447
num_wins: 4285
propriety_score: 0.7393075356415478
propriety_total_count: 982.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-09-01T07:57:36+00:00
us_pacific_date: 2024-09-01
win_ratio: 0.37433388660784483
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rica40325-feedback-and-dpo-v1-mkmlizer
Waiting for job on rica40325-feedback-and-dpo-v1-mkmlizer to finish
Stopping job with name rica40325-feedback-and-dpo-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name rica40325-feedback-and-dpo-v1-mkmlizer
Waiting for job on rica40325-feedback-and-dpo-v1-mkmlizer to finish
rica40325-feedback-and-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-feedback-and-dpo-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║       /___/                                                         ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-feedback-and-dpo-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-and-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-feedback-and-dpo-v1-mkmlizer: Downloaded to shared memory in 35.241s
rica40325-feedback-and-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq_zw5rs2, device:0
rica40325-feedback-and-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-feedback-and-dpo-v1-mkmlizer: quantized model in 26.459s
rica40325-feedback-and-dpo-v1-mkmlizer: Processed model rica40325/feedback-and-dpo in 61.700s
rica40325-feedback-and-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-feedback-and-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-feedback-and-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-feedback-and-dpo-v1
rica40325-feedback-and-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-feedback-and-dpo-v1/config.json
rica40325-feedback-and-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-feedback-and-dpo-v1/special_tokens_map.json
rica40325-feedback-and-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-feedback-and-dpo-v1/tokenizer_config.json
rica40325-feedback-and-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-feedback-and-dpo-v1/tokenizer.json
rica40325-feedback-and-dpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 38.10it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 60.71it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 68.52it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 72.77it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 69.38it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 68.08it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 70.66it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:03, 68.20it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:02, 72.27it/s]
Loading 0:  29%|██▉       | 84/291 [00:02<00:09, 20.85it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:08, 24.10it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:06, 28.92it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 36.01it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 43.86it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 48.90it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:02, 53.95it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:02, 59.15it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 60.71it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:01, 66.89it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 70.43it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 74.83it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 21.76it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 27.78it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 33.60it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 40.61it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 47.41it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 53.19it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 57.19it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 58.26it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 60.97it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 63.40it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 66.11it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 65.53it/s]
                                                            

Job rica40325-feedback-and-dpo-v1-mkmlizer completed after 84.66s with status: succeeded
Stopping job with name rica40325-feedback-and-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.33s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-feedback-and-dpo-v1
Waiting for inference service rica40325-feedback-and-dpo-v1 to be ready
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
Inference service rica40325-feedback-and-dpo-v1 ready after 190.76501083374023s
Pipeline stage MKMLDeployer completed in 191.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7466349601745605s
Received healthy response to inference request in 1.4651010036468506s
Received healthy response to inference request in 1.5152759552001953s
Received healthy response to inference request in 0.5985317230224609s
Received healthy response to inference request in 1.6226458549499512s
5 requests
0 failed requests
5th percentile: 0.7718455791473389
10th percentile: 0.9451594352722168
20th percentile: 1.2917871475219727
30th percentile: 1.4751359939575195
40th percentile: 1.4952059745788575
50th percentile: 1.5152759552001953
60th percentile: 1.5582239151000976
70th percentile: 1.601171875
80th percentile: 1.647443675994873
90th percentile: 1.6970393180847168
95th percentile: 1.7218371391296388
99th percentile: 1.7416753959655762
mean time: 1.3896378993988037
Pipeline stage StressChecker completed in 7.66s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.58s
rica40325-feedback-and-dpo_v1 status is now deployed due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-feedback-and-dpo-v1-profiler
Waiting for inference service rica40325-feedback-and-dpo-v1-profiler to be ready
Inference service rica40325-feedback-and-dpo-v1-profiler ready after 190.43865394592285s
Pipeline stage MKMLProfilerDeployer completed in 190.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.47s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-feedback-and-dpo-v1-profiler is running
Tearing down inference service rica40325-feedback-and-dpo-v1-profiler
Service rica40325-feedback-and-dpo-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.98s
rica40325-feedback-and-dpo_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics