trace2333-dpo-v9-v1-reprompt

submission_id: trace2333-dpo-v9-v1-reprompt_v1

developer_uid: Trace2333

best_of: 16

celo_rating: 1232.15

display_name: trace2333-dpo-v9-v1-reprompt_v1

family_friendly_score: 0.0

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{bot_name}:', 'truncate_by_message': False}

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}

is_internal_developer: False

language_model: Trace2333/dpo_v9_v1_reprompt

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Trace2333/dpo_v9_v1_repr

model_name: trace2333-dpo-v9-v1-reprompt_v1

model_num_parameters: 8030261248.0

model_repo: Trace2333/dpo_v9_v1_reprompt

model_size: 8B

num_battles: 11433

num_wins: 5633

ranking_group: single

status: torndown

submission_type: basic

timestamp: 2024-08-26T03:17:39+00:00

us_pacific_date: 2024-08-25

win_ratio: 0.4926965800752208

Resubmit model

Running pipeline stage MKMLizer
Starting job with name trace2333-dpo-v9-v1-reprompt-v1-mkmlizer
Waiting for job on trace2333-dpo-v9-v1-reprompt-v1-mkmlizer to finish
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║       /___/                                                         ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║                                                                     ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║                                                                     ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║                                                                     ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ║                                                                     ║
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: Downloaded to shared memory in 60.734s
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpl1rsr4_0, device:0
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: quantized model in 29.518s
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: Processed model Trace2333/dpo_v9_v1_reprompt in 90.252s
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-dpo-v9-v1-reprompt-v1
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-dpo-v9-v1-reprompt-v1/config.json
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-dpo-v9-v1-reprompt-v1/tokenizer_config.json
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-dpo-v9-v1-reprompt-v1/special_tokens_map.json
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-dpo-v9-v1-reprompt-v1/tokenizer.json
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-dpo-v9-v1-reprompt-v1/flywheel_model.0.safetensors
trace2333-dpo-v9-v1-reprompt-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 25.63it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:06, 40.35it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:07, 38.40it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:07, 37.07it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:07, 37.67it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:06, 38.90it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 23.80it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 25.91it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 32.98it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 32.62it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 35.70it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.31it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 35.16it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 33.51it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 33.42it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 33.56it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 23.28it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 26.18it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:07, 28.44it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 28.51it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:06, 31.81it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 31.55it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 34.78it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 33.39it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 32.99it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 37.53it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 35.07it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 29.61it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 29.70it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 28.41it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 32.97it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 32.09it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 34.39it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:04, 32.33it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 34.51it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 32.79it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 34.74it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.28it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 39.06it/s]
Loading 0:  65%|██████▍   | 189/291 [00:06<00:04, 23.10it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 24.29it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 30.71it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 30.55it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 32.94it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 31.57it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:02, 34.35it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 33.03it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 32.74it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 32.27it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 22.99it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 23.30it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 30.57it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 30.53it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 33.74it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 33.04it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 35.00it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 33.54it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 34.53it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 33.61it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 33.51it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.55it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.17it/s]
                                                            
Job trace2333-dpo-v9-v1-reprompt-v1-mkmlizer completed after 116.36s with status: succeeded
Stopping job with name trace2333-dpo-v9-v1-reprompt-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.36s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.21s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-dpo-v9-v1-reprompt-v1
Waiting for inference service trace2333-dpo-v9-v1-reprompt-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
Inference service trace2333-dpo-v9-v1-reprompt-v1 ready after 161.06301069259644s
Pipeline stage ISVCDeployer completed in 161.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.968388557434082s
Received healthy response to inference request in 1.5601160526275635s
Received healthy response to inference request in 2.1195733547210693s
Received healthy response to inference request in 1.6590547561645508s
Received healthy response to inference request in 1.6634252071380615s
5 requests
0 failed requests
5th percentile: 1.579903793334961
10th percentile: 1.5996915340423583
20th percentile: 1.6392670154571534
30th percentile: 1.659928846359253
40th percentile: 1.6616770267486571
50th percentile: 1.6634252071380615
60th percentile: 1.7854105472564696
70th percentile: 1.907395887374878
80th percentile: 1.9986255168914795
90th percentile: 2.0590994358062744
95th percentile: 2.089336395263672
99th percentile: 2.11352596282959
mean time: 1.7941115856170655
Pipeline stage StressChecker completed in 10.38s
trace2333-dpo-v9-v1-reprompt_v1 status is now deployed due to DeploymentManager action
trace2333-dpo-v9-v1-reprompt_v1 status is now inactive due to auto deactivation removed underperforming models
trace2333-dpo-v9-v1-reprompt_v1 status is now torndown due to DeploymentManager action