jic062-dpo-v1

developer_uid: chace9580

submission_id: jic062-dpo-v1_v2

model_name: jic062-dpo-v1_v2

model_group: jic062/dpo-v1

status: torndown

timestamp: 2024-08-23T03:51:12+00:00

num_battles: 11241

num_wins: 5820

celo_rating: 1248.69

family_friendly_score: 0.0

submission_type: basic

model_repo: jic062/dpo-v1

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: jic062-dpo-v1_v2

is_internal_developer: False

language_model: jic062/dpo-v1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-22

win_ratio: 0.5177475313584201

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', '<|end_of_text|>', '|eot_id|'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': "<|begin_of_text|><|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\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name jic062-dpo-v1-v2-mkmlizer
Waiting for job on jic062-dpo-v1-v2-mkmlizer to finish
jic062-dpo-v1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-dpo-v1-v2-mkmlizer: ║     _____            __           __                                ║
jic062-dpo-v1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-dpo-v1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-dpo-v1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-dpo-v1-v2-mkmlizer: ║       /___/                                                         ║
jic062-dpo-v1-v2-mkmlizer: ║                                                                     ║
jic062-dpo-v1-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
jic062-dpo-v1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-dpo-v1-v2-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-dpo-v1-v2-mkmlizer: ║                                                                     ║
jic062-dpo-v1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-dpo-v1-v2-mkmlizer: ║  belonging to:                                                      ║
jic062-dpo-v1-v2-mkmlizer: ║                                                                     ║
jic062-dpo-v1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-dpo-v1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-dpo-v1-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-dpo-v1-v2-mkmlizer: ║                                                                     ║
jic062-dpo-v1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-dpo-v1-v2-mkmlizer: Downloaded to shared memory in 36.396s
jic062-dpo-v1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk_ti1i1h, device:0
jic062-dpo-v1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-dpo-v1-v2-mkmlizer: quantized model in 26.120s
jic062-dpo-v1-v2-mkmlizer: Processed model jic062/dpo-v1 in 62.516s
jic062-dpo-v1-v2-mkmlizer: creating bucket guanaco-mkml-models
jic062-dpo-v1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-dpo-v1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-dpo-v1-v2
jic062-dpo-v1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-dpo-v1-v2/config.json
jic062-dpo-v1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-dpo-v1-v2/special_tokens_map.json
jic062-dpo-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-dpo-v1-v2/tokenizer_config.json
jic062-dpo-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-dpo-v1-v2/tokenizer.json
jic062-dpo-v1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-dpo-v1-v2/flywheel_model.0.safetensors
jic062-dpo-v1-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 35.56it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 46.90it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 50.05it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 58.50it/s]
Loading 0:  13%|█▎        | 38/291 [00:00<00:04, 55.12it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:04, 52.87it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:05, 46.45it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 48.99it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 55.28it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 51.81it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:04, 52.23it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:05, 37.85it/s]
Loading 0:  31%|███▏      | 91/291 [00:01<00:05, 38.86it/s]
Loading 0:  33%|███▎      | 96/291 [00:02<00:04, 40.29it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 46.24it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:04, 45.12it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:03, 45.09it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 50.52it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 48.21it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:03, 47.09it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 52.10it/s]
Loading 0:  50%|████▉     | 145/291 [00:03<00:03, 48.36it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:03, 46.97it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 51.60it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 48.63it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 46.96it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:02, 54.81it/s]
Loading 0:  63%|██████▎   | 182/291 [00:03<00:02, 47.87it/s]
Loading 0:  65%|██████▍   | 188/291 [00:04<00:02, 37.18it/s]
Loading 0:  66%|██████▋   | 193/291 [00:04<00:02, 38.28it/s]
Loading 0:  68%|██████▊   | 199/291 [00:04<00:02, 39.25it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:02, 40.32it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 46.71it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 46.04it/s]
Loading 0:  76%|███████▋  | 222/291 [00:04<00:01, 45.36it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 50.69it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 48.40it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 47.32it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 51.16it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 48.62it/s]
Loading 0:  89%|████████▊ | 258/291 [00:05<00:00, 47.49it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 52.04it/s]
Loading 0:  93%|█████████▎| 271/291 [00:05<00:00, 49.60it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 50.01it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 45.76it/s]
Loading 0:  99%|█████████▉| 288/291 [00:11<00:00,  3.34it/s]
                                                            
Job jic062-dpo-v1-v2-mkmlizer completed after 85.0s with status: succeeded
Stopping job with name jic062-dpo-v1-v2-mkmlizer
Pipeline stage MKMLizer completed in 86.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service jic062-dpo-v1-v2
Waiting for inference service jic062-dpo-v1-v2 to be ready
Inference service jic062-dpo-v1-v2 ready after 191.6017713546753s
Pipeline stage ISVCDeployer completed in 192.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.304492950439453s
Received healthy response to inference request in 1.7007813453674316s
Received healthy response to inference request in 1.7137396335601807s
Received healthy response to inference request in 1.5139024257659912s
Received healthy response to inference request in 2.1511311531066895s
5 requests
0 failed requests
5th percentile: 1.5512782096862794
10th percentile: 1.5886539936065673
20th percentile: 1.6634055614471435
30th percentile: 1.7033730030059815
40th percentile: 1.708556318283081
50th percentile: 1.7137396335601807
60th percentile: 1.8886962413787842
70th percentile: 2.063652849197388
80th percentile: 2.181803512573242
90th percentile: 2.2431482315063476
95th percentile: 2.2738205909729006
99th percentile: 2.2983584785461426
mean time: 1.8768095016479491
Pipeline stage StressChecker completed in 10.15s
jic062-dpo-v1_v2 status is now deployed due to DeploymentManager action
jic062-dpo-v1_v2 status is now inactive due to auto deactivation removed underperforming models
jic062-dpo-v1_v2 status is now torndown due to DeploymentManager action