trace2333-dpo-v9-v2-reprompt

developer_uid: Trace2333
submission_id: trace2333-dpo-v9-v2-reprompt_v5
model_name: trace2333-dpo-v9-v2-reprompt_v5
model_group: Trace2333/dpo_v9_v2_repr
status: torndown
timestamp: 2024-08-27T12:35:27+00:00
num_battles: 11324
num_wins: 5958
celo_rating: 1254.4
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/dpo_v9_v2_reprompt
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: trace2333-dpo-v9-v2-reprompt_v5
is_internal_developer: False
language_model: Trace2333/dpo_v9_v2_reprompt
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-27
win_ratio: 0.526139173436948
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, '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
Running pipeline stage MKMLizer
Starting job with name trace2333-dpo-v9-v2-reprompt-v5-mkmlizer
Waiting for job on trace2333-dpo-v9-v2-reprompt-v5-mkmlizer to finish
Stopping job with name trace2333-dpo-v9-v2-reprompt-v5-mkmlizer
%s, retrying in %s seconds...
Starting job with name trace2333-dpo-v9-v2-reprompt-v5-mkmlizer
Waiting for job on trace2333-dpo-v9-v2-reprompt-v5-mkmlizer to finish
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║     _____            __           __                                ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║       /___/                                                         ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║                                                                     ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║                                                                     ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║  belonging to:                                                      ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║                                                                     ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ║                                                                     ║
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: Downloaded to shared memory in 46.432s
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3kih0x19, device:0
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: quantized model in 29.677s
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: Processed model Trace2333/dpo_v9_v2_reprompt in 76.110s
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: creating bucket guanaco-mkml-models
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-dpo-v9-v2-reprompt-v5
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-dpo-v9-v2-reprompt-v5/config.json
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-dpo-v9-v2-reprompt-v5/tokenizer.json
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-dpo-v9-v2-reprompt-v5/flywheel_model.0.safetensors
trace2333-dpo-v9-v2-reprompt-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 25.44it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:08, 33.73it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 31.57it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 34.01it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 31.76it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:07, 36.00it/s]
Loading 0:  12%|█▏        | 34/291 [00:01<00:10, 23.56it/s]
Loading 0:  13%|█▎        | 37/291 [00:01<00:10, 23.19it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 22.97it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:08, 30.09it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:08, 29.65it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:07, 32.34it/s]
Loading 0:  21%|██        | 61/291 [00:02<00:07, 31.22it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 33.36it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 31.99it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 31.66it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 31.76it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 21.46it/s]
Loading 0:  29%|██▉       | 85/291 [00:03<00:09, 22.56it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 26.50it/s]
Loading 0:  32%|███▏      | 93/291 [00:03<00:07, 25.49it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:06, 30.81it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 30.14it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 32.79it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 31.50it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 31.75it/s]
Loading 0:  42%|████▏     | 122/291 [00:04<00:04, 35.76it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 34.01it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 28.53it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 28.62it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 26.83it/s]
Loading 0:  50%|████▉     | 145/291 [00:04<00:05, 29.01it/s]
Loading 0:  51%|█████     | 149/291 [00:05<00:05, 27.10it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:03, 34.28it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:03, 33.02it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 34.87it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 33.24it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 35.26it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.09it/s]
Loading 0:  63%|██████▎   | 183/291 [00:06<00:02, 37.07it/s]
Loading 0:  64%|██████▍   | 187/291 [00:06<00:04, 25.56it/s]
Loading 0:  66%|██████▌   | 191/291 [00:06<00:03, 26.29it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:03, 25.44it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 30.60it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 30.23it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 33.31it/s]
Loading 0:  74%|███████▎  | 214/291 [00:07<00:02, 31.88it/s]
Loading 0:  75%|███████▌  | 219/291 [00:07<00:02, 33.60it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 32.32it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:02, 31.83it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 31.67it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 23.26it/s]
Loading 0:  82%|████████▏ | 239/291 [00:08<00:02, 23.68it/s]
Loading 0:  85%|████████▍ | 246/291 [00:08<00:01, 31.02it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 30.72it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 33.03it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:01, 31.80it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 34.14it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 32.71it/s]
Loading 0:  94%|█████████▍| 273/291 [00:09<00:00, 34.60it/s]
Loading 0:  95%|█████████▌| 277/291 [00:09<00:00, 32.93it/s]
Loading 0:  97%|█████████▋| 281/291 [00:09<00:00, 32.59it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.57it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.20it/s]
                                                            
Job trace2333-dpo-v9-v2-reprompt-v5-mkmlizer completed after 95.91s with status: succeeded
Stopping job with name trace2333-dpo-v9-v2-reprompt-v5-mkmlizer
Pipeline stage MKMLizer completed in 98.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-dpo-v9-v2-reprompt-v5
Waiting for inference service trace2333-dpo-v9-v2-reprompt-v5 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
Inference service trace2333-dpo-v9-v2-reprompt-v5 ready after 251.43554019927979s
Pipeline stage ISVCDeployer completed in 252.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4510772228240967s
Received healthy response to inference request in 1.7840862274169922s
Received healthy response to inference request in 1.7853121757507324s
Received healthy response to inference request in 1.9124090671539307s
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
Received healthy response to inference request in 1.7492456436157227s
5 requests
0 failed requests
5th percentile: 1.7562137603759767
10th percentile: 1.7631818771362304
20th percentile: 1.7771181106567382
30th percentile: 1.7843314170837403
40th percentile: 1.7848217964172364
50th percentile: 1.7853121757507324
60th percentile: 1.8361509323120118
70th percentile: 1.886989688873291
80th percentile: 2.220142698287964
90th percentile: 2.8356099605560305
95th percentile: 3.1433435916900634
99th percentile: 3.38953049659729
mean time: 2.136426067352295
Pipeline stage StressChecker completed in 13.77s
trace2333-dpo-v9-v2-reprompt_v5 status is now deployed due to DeploymentManager action
trace2333-dpo-v9-v2-reprompt_v5 status is now inactive due to auto deactivation removed underperforming models
trace2333-dpo-v9-v2-reprompt_v5 status is now torndown due to DeploymentManager action