trace2333-dpo-v9-v2-reprompt

developer_uid: Trace2333

submission_id: trace2333-dpo-v9-v2-reprompt_v3

model_name: trace2333-dpo-v9-v2-reprompt_v3

model_group: Trace2333/dpo_v9_v2_repr

status: torndown

timestamp: 2024-08-26T09:04:33+00:00

num_battles: 11745

num_wins: 6185

celo_rating: 1253.06

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_v3

is_internal_developer: False

language_model: Trace2333/dpo_v9_v2_reprompt

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-26

win_ratio: 0.5266070668369519

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, '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-v3-mkmlizer
Waiting for job on trace2333-dpo-v9-v2-reprompt-v3-mkmlizer to finish
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║     _____            __           __                                ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║       /___/                                                         ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║                                                                     ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║                                                                     ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║  belonging to:                                                      ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║                                                                     ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ║                                                                     ║
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: Downloaded to shared memory in 39.639s
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9vrpwvkn, device:0
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: quantized model in 28.685s
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: Processed model Trace2333/dpo_v9_v2_reprompt in 68.324s
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: creating bucket guanaco-mkml-models
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-dpo-v9-v2-reprompt-v3
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-dpo-v9-v2-reprompt-v3/config.json
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-dpo-v9-v2-reprompt-v3/special_tokens_map.json
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-dpo-v9-v2-reprompt-v3/tokenizer_config.json
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-dpo-v9-v2-reprompt-v3/tokenizer.json
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-dpo-v9-v2-reprompt-v3/flywheel_model.0.safetensors
trace2333-dpo-v9-v2-reprompt-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.99it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 35.96it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 32.48it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 35.33it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 33.67it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 40.06it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 23.85it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 25.20it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 31.92it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 31.40it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 33.98it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.05it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 35.91it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 33.62it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 33.67it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 34.00it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 23.81it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 26.51it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 28.94it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 29.44it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 32.78it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 31.60it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 34.80it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 33.39it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 33.74it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 38.20it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 35.82it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 30.67it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 31.13it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 28.65it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.61it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 32.92it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 34.90it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:03, 33.60it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 36.12it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 34.36it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 36.34it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.86it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 39.92it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:04, 24.95it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 26.47it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.15it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 32.38it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.47it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 33.27it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.09it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.78it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 33.56it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 33.91it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.39it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 25.48it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 32.72it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 32.23it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 34.00it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 32.81it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 35.21it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 33.80it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 35.71it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 34.08it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 33.77it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.61it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.25it/s]
                                                            
Job trace2333-dpo-v9-v2-reprompt-v3-mkmlizer completed after 96.31s with status: succeeded
Stopping job with name trace2333-dpo-v9-v2-reprompt-v3-mkmlizer
Pipeline stage MKMLizer completed in 97.13s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-dpo-v9-v2-reprompt-v3
Waiting for inference service trace2333-dpo-v9-v2-reprompt-v3 to be ready
Inference service trace2333-dpo-v9-v2-reprompt-v3 ready after 151.21194291114807s
Pipeline stage ISVCDeployer completed in 152.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9169917106628418s
Received healthy response to inference request in 1.6940157413482666s
Received healthy response to inference request in 1.8840382099151611s
Received healthy response to inference request in 1.5671601295471191s
Received healthy response to inference request in 2.5795464515686035s
5 requests
0 failed requests
5th percentile: 1.5925312519073487
10th percentile: 1.6179023742675782
20th percentile: 1.668644618988037
30th percentile: 1.7320202350616456
40th percentile: 1.8080292224884034
50th percentile: 1.8840382099151611
60th percentile: 1.8972196102142334
70th percentile: 1.9104010105133056
80th percentile: 2.0495026588439944
90th percentile: 2.3145245552062987
95th percentile: 2.447035503387451
99th percentile: 2.553044261932373
mean time: 1.9283504486083984
Pipeline stage StressChecker completed in 10.60s
trace2333-dpo-v9-v2-reprompt_v3 status is now deployed due to DeploymentManager action
trace2333-dpo-v9-v2-reprompt_v3 status is now inactive due to auto deactivation removed underperforming models
trace2333-dpo-v9-v2-reprompt_v3 status is now torndown due to DeploymentManager action