riverise-feedback-dpo-merged

developer_uid: Riverise
submission_id: riverise-feedback-dpo-merged_v4
model_name: riverise-feedback-dpo-merged_v1
model_group: Riverise/feedback_dpo_me
status: torndown
timestamp: 2024-09-07T14:10:58+00:00
num_battles: 14951
num_wins: 2299
celo_rating: 944.17
family_friendly_score: 0.0
submission_type: basic
model_repo: Riverise/feedback_dpo_merged
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
display_name: riverise-feedback-dpo-merged_v1
is_internal_developer: False
language_model: Riverise/feedback_dpo_merged
model_size: 8B
ranking_group: single
us_pacific_date: 2024-09-07
win_ratio: 0.15376897866363454
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}
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}
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 riverise-feedback-dpo-merged-v4-mkmlizer
Waiting for job on riverise-feedback-dpo-merged-v4-mkmlizer to finish
riverise-feedback-dpo-merged-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-feedback-dpo-merged-v4-mkmlizer: ║     _____            __           __                                ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║       /___/                                                         ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║                                                                     ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║  Version: 0.10.1                                                    ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║  https://mk1.ai                                                     ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║                                                                     ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║  belonging to:                                                      ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║                                                                     ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║  Chai Research Corp.                                                ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
riverise-feedback-dpo-merged-v4-mkmlizer: ║                                                                     ║
riverise-feedback-dpo-merged-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
riverise-feedback-dpo-merged-v4-mkmlizer: Downloaded to shared memory in 60.913s
riverise-feedback-dpo-merged-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpes7dhti5, device:0
riverise-feedback-dpo-merged-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
riverise-feedback-dpo-merged-v4-mkmlizer: quantized model in 28.457s
riverise-feedback-dpo-merged-v4-mkmlizer: Processed model Riverise/feedback_dpo_merged in 89.371s
riverise-feedback-dpo-merged-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-feedback-dpo-merged-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-feedback-dpo-merged-v4
riverise-feedback-dpo-merged-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-feedback-dpo-merged-v4/config.json
riverise-feedback-dpo-merged-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-feedback-dpo-merged-v4/tokenizer_config.json
riverise-feedback-dpo-merged-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-feedback-dpo-merged-v4/special_tokens_map.json
riverise-feedback-dpo-merged-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-feedback-dpo-merged-v4/tokenizer.json
riverise-feedback-dpo-merged-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-feedback-dpo-merged-v4/flywheel_model.0.safetensors
riverise-feedback-dpo-merged-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 28.30it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 38.12it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:07, 35.15it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:06, 38.72it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 36.34it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 42.78it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:09, 25.52it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 26.78it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 33.91it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:06, 34.52it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 34.72it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.80it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 35.38it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 33.57it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 32.08it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 32.79it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 24.10it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 24.90it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 29.38it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 30.09it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 34.04it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 33.46it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 36.51it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 35.01it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 33.88it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 38.33it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 35.74it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 31.13it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 30.71it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 29.08it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.66it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 32.64it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 34.81it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 33.90it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 35.83it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 34.44it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 37.10it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 35.22it/s]
Loading 0:  63%|██████▎   | 183/291 [00:05<00:02, 38.71it/s]
Loading 0:  64%|██████▍   | 187/291 [00:05<00:03, 26.85it/s]
Loading 0:  66%|██████▌   | 191/291 [00:05<00:03, 27.97it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:03, 27.17it/s]
Loading 0:  68%|██████▊   | 199/291 [00:06<00:03, 29.85it/s]
Loading 0:  70%|██████▉   | 203/291 [00:06<00:03, 28.25it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 35.98it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.13it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.54it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.90it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 34.33it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 33.82it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 26.13it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:01, 26.02it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 34.05it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 33.32it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 34.31it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 33.57it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 35.90it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 34.38it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 34.93it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 33.82it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 34.29it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.63it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.27it/s]
                                                            
Job riverise-feedback-dpo-merged-v4-mkmlizer completed after 106.72s with status: succeeded
Stopping job with name riverise-feedback-dpo-merged-v4-mkmlizer
Pipeline stage MKMLizer completed in 107.71s
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 riverise-feedback-dpo-merged-v4
Waiting for inference service riverise-feedback-dpo-merged-v4 to be ready
Failed to get response for submission blend_sehof_2024-08-22: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:54488->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission blend_jerun_2024-08-22: ('http://chaiml-lexical-nemo-v4-1k1e5-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:51492->127.0.0.1:8080: read: connection reset by peer\n')
Inference service riverise-feedback-dpo-merged-v4 ready after 291.36574482917786s
Pipeline stage MKMLDeployer completed in 291.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7004420757293701s
Received healthy response to inference request in 0.9910845756530762s
Received healthy response to inference request in 0.4761941432952881s
Received healthy response to inference request in 0.39516711235046387s
Received healthy response to inference request in 0.41515636444091797s
5 requests
0 failed requests
5th percentile: 0.3991649627685547
10th percentile: 0.4031628131866455
20th percentile: 0.41115851402282716
30th percentile: 0.427363920211792
40th percentile: 0.45177903175354006
50th percentile: 0.4761941432952881
60th percentile: 0.6821503162384033
70th percentile: 0.8881064891815185
80th percentile: 1.132956075668335
90th percentile: 1.4166990756988527
95th percentile: 1.5585705757141113
99th percentile: 1.6720677757263183
mean time: 0.7956088542938232
Pipeline stage StressChecker completed in 4.67s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.84s
Shutdown handler de-registered
riverise-feedback-dpo-merged_v4 status is now deployed due to DeploymentManager action
Shutdown handler registered
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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service riverise-feedback-dpo-merged-v4-profiler
Waiting for inference service riverise-feedback-dpo-merged-v4-profiler to be ready
Tearing down inference service riverise-feedback-dpo-merged-v4-profiler
%s, retrying in %s seconds...
Creating inference service riverise-feedback-dpo-merged-v4-profiler
Waiting for inference service riverise-feedback-dpo-merged-v4-profiler to be ready
Tearing down inference service riverise-feedback-dpo-merged-v4-profiler
%s, retrying in %s seconds...
Creating inference service riverise-feedback-dpo-merged-v4-profiler
Waiting for inference service riverise-feedback-dpo-merged-v4-profiler to be ready
Tearing down inference service riverise-feedback-dpo-merged-v4-profiler
clean up pipeline due to error=%s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.12s
Shutdown handler de-registered
riverise-feedback-dpo-merged_v4 status is now inactive due to auto deactivation removed underperforming models
riverise-feedback-dpo-merged_v4 status is now torndown due to DeploymentManager action
riverise-feedback-dpo-merged_v4 status is now torndown due to DeploymentManager action