bbchicago-brt-8b-l3-v1-_4895

developer_uid: Bbbrun0

submission_id: bbchicago-brt-8b-l3-v1-_4895_v35

model_name: brt-v1_7-dpo-s2500-format

model_group: BBChicago/Brt-8B-L3_v1.7

status: torndown

timestamp: 2024-07-30T04:34:49+00:00

num_battles: 12216

num_wins: 6552

celo_rating: 1219.08

family_friendly_score: 0.0

submission_type: basic

model_repo: BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500

model_architecture: LlamaForCausalLM

reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: brt-v1_7-dpo-s2500-format

is_internal_developer: False

language_model: BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-29

win_ratio: 0.5363457760314342

generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>', '\n\n{user_name}'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}

formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are an expert actor that can fully immerse yourself into any role given. Currently your role is {bot_name}. {bot_name}'s persona: {memory}. Please complete the actual conversation in an exceptionally high-quality manner to demonstrate your excellent role-playing capabilities. Respond with a brief, in-character, descriptive response.", 'prompt_template': "{bot_name}'s example conversation:\n{prompt}\n{bot_name}'s actual conversation:\n", '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|>Response:\n{bot_name}:', 'truncate_by_message': False}

reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer to finish
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║     _____            __           __                                ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║       /___/                                                         ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║                                                                     ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║  Version: 0.9.7                                                     ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║                                                                     ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║  belonging to:                                                      ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║                                                                     ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ║                                                                     ║
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: Downloaded to shared memory in 40.977s
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj8c84zph, device:0
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: quantized model in 30.533s
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500 in 71.510s
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v35
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v35/config.json
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v35/special_tokens_map.json
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v35/tokenizer_config.json
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v35/tokenizer.json
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v35/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 25.45it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:08, 34.62it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 32.24it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 34.40it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 32.16it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:07, 36.18it/s]
Loading 0:  12%|█▏        | 34/291 [00:01<00:11, 22.93it/s]
Loading 0:  13%|█▎        | 37/291 [00:01<00:11, 22.75it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 22.84it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:08, 29.91it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:08, 29.61it/s]
Loading 0:  19%|█▉        | 56/291 [00:01<00:07, 31.51it/s]
Loading 0:  21%|██        | 60/291 [00:02<00:08, 28.52it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 33.39it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 31.65it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 31.36it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 31.41it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 20.95it/s]
Loading 0:  29%|██▉       | 85/291 [00:03<00:09, 22.44it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 26.75it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:07, 26.96it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:06, 30.38it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 29.49it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 31.37it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 30.40it/s]
Loading 0:  40%|███▉      | 116/291 [00:04<00:05, 30.88it/s]
Loading 0:  42%|████▏     | 122/291 [00:04<00:04, 34.88it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 32.83it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 27.83it/s]
Loading 0:  47%|████▋     | 136/291 [00:04<00:05, 26.58it/s]
Loading 0:  48%|████▊     | 140/291 [00:04<00:05, 25.81it/s]
Loading 0:  51%|█████     | 147/291 [00:05<00:04, 32.75it/s]
Loading 0:  52%|█████▏    | 151/291 [00:05<00:04, 31.47it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:04, 32.68it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:04, 30.79it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 33.23it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 31.92it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 34.20it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 32.98it/s]
Loading 0:  63%|██████▎   | 183/291 [00:06<00:02, 36.83it/s]
Loading 0:  64%|██████▍   | 187/291 [00:06<00:04, 25.48it/s]
Loading 0:  66%|██████▌   | 191/291 [00:06<00:03, 26.86it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:03, 25.57it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 30.89it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 30.86it/s]
Loading 0:  72%|███████▏  | 210/291 [00:07<00:02, 33.55it/s]
Loading 0:  74%|███████▎  | 214/291 [00:07<00:02, 32.37it/s]
Loading 0:  75%|███████▌  | 219/291 [00:07<00:02, 34.84it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 33.08it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 33.40it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 33.85it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 24.97it/s]
Loading 0:  82%|████████▏ | 239/291 [00:08<00:02, 25.18it/s]
Loading 0:  85%|████████▍ | 246/291 [00:08<00:01, 33.11it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 32.73it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 35.23it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 34.01it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 35.17it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 28.34it/s]
Loading 0:  94%|█████████▍| 273/291 [00:09<00:00, 30.96it/s]
Loading 0:  95%|█████████▌| 277/291 [00:09<00:00, 29.92it/s]
Loading 0:  97%|█████████▋| 281/291 [00:09<00:00, 30.59it/s]
Loading 0:  98%|█████████▊| 286/291 [00:15<00:02,  2.47it/s]
Loading 0:  99%|█████████▉| 289/291 [00:15<00:00,  3.07it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer:   warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer:   warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer:   warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: Saving duration: 1.395s
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.070s
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v35_reward
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v35_reward/config.json
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v35_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v35_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v35_reward/merges.txt
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v35_reward/vocab.json
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v35_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v35_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer completed after 115.23s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-4895-v35-mkmlizer
Pipeline stage MKMLizer completed in 116.33s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-4895-v35
Waiting for inference service bbchicago-brt-8b-l3-v1-4895-v35 to be ready
Inference service bbchicago-brt-8b-l3-v1-4895-v35 ready after 120.76272487640381s
Pipeline stage ISVCDeployer completed in 122.60s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3583195209503174s
Received healthy response to inference request in 1.4470324516296387s
Received healthy response to inference request in 1.4471192359924316s
Received healthy response to inference request in 1.3522107601165771s
Received healthy response to inference request in 1.4836664199829102s
5 requests
0 failed requests
5th percentile: 1.3711750984191895
10th percentile: 1.3901394367218018
20th percentile: 1.4280681133270263
30th percentile: 1.4470498085021972
40th percentile: 1.4470845222473145
50th percentile: 1.4471192359924316
60th percentile: 1.461738109588623
70th percentile: 1.4763569831848145
80th percentile: 1.6585970401763919
90th percentile: 2.0084582805633544
95th percentile: 2.1833889007568357
99th percentile: 2.323333396911621
mean time: 1.617669677734375
Pipeline stage StressChecker completed in 8.77s
bbchicago-brt-8b-l3-v1-_4895_v35 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-_4895_v35 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-_4895_v35
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-4895-v35 is running
Tearing down inference service bbchicago-brt-8b-l3-v1-4895-v35
Service bbchicago-brt-8b-l3-v1-4895-v35 has been torndown
Pipeline stage ISVCDeleter completed in 4.63s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-4895-v35/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v35/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v35/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v35/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v35/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-4895-v35_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v35_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v35_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v35_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v35_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v35_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v35_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.50s
bbchicago-brt-8b-l3-v1-_4895_v35 status is now torndown due to DeploymentManager action