developer_uid: zonemercy
submission_id: chaiml-augment-ensemble_v3
model_name: chaiml-augment-ensemble_v3
model_group: ChaiML/augment-ensemble
status: torndown
timestamp: 2024-07-12T23:06:50+00:00
num_battles: 30991
num_wins: 19290
celo_rating: 1261.97
family_friendly_score: 0.0
submission_type: basic
model_repo: ChaiML/augment-ensemble
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: chaiml-augment-ensemble_v3
is_internal_developer: True
language_model: ChaiML/augment-ensemble
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-12
win_ratio: 0.6224387725468684
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, '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': "<|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}
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 chaiml-augment-ensemble-v3-mkmlizer
Waiting for job on chaiml-augment-ensemble-v3-mkmlizer to finish
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
chaiml-augment-ensemble-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-augment-ensemble-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-augment-ensemble-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-augment-ensemble-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-augment-ensemble-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-augment-ensemble-v3-mkmlizer: ║       /___/                                                         ║
chaiml-augment-ensemble-v3-mkmlizer: ║                                                                     ║
chaiml-augment-ensemble-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
chaiml-augment-ensemble-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-augment-ensemble-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-augment-ensemble-v3-mkmlizer: ║                                                                     ║
chaiml-augment-ensemble-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-augment-ensemble-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-augment-ensemble-v3-mkmlizer: ║                                                                     ║
chaiml-augment-ensemble-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-augment-ensemble-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-augment-ensemble-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-augment-ensemble-v3-mkmlizer: ║                                                                     ║
chaiml-augment-ensemble-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-augment-ensemble-v3-mkmlizer: Downloaded to shared memory in 46.232s
chaiml-augment-ensemble-v3-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-augment-ensemble-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-augment-ensemble-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:06, 44.77it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:04, 59.61it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:04, 63.70it/s]
Loading 0:  11%|█▏        | 33/291 [00:00<00:07, 36.80it/s]
Loading 0:  13%|█▎        | 38/291 [00:00<00:06, 38.88it/s]
Loading 0:  15%|█▍        | 43/291 [00:01<00:06, 40.53it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:05, 44.42it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 51.36it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:03, 56.34it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 61.96it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 33.27it/s]
Loading 0:  31%|███▏      | 91/291 [00:02<00:04, 40.69it/s]
Loading 0:  34%|███▍      | 99/291 [00:02<00:04, 47.94it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:03, 52.44it/s]
Loading 0:  39%|███▉      | 113/291 [00:02<00:03, 53.88it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:02, 60.32it/s]
Loading 0:  44%|████▍     | 129/291 [00:02<00:02, 59.48it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:04, 32.05it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:04, 33.83it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 39.73it/s]
Loading 0:  54%|█████▎    | 156/291 [00:03<00:02, 47.20it/s]
Loading 0:  56%|█████▌    | 162/291 [00:03<00:02, 49.74it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 49.82it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 53.64it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:02, 35.78it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 37.10it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 38.65it/s]
Loading 0:  70%|██████▉   | 203/291 [00:04<00:02, 42.48it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:01, 49.22it/s]
Loading 0:  76%|███████▌  | 221/291 [00:04<00:01, 53.99it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 59.63it/s]
Loading 0:  81%|████████  | 236/291 [00:05<00:01, 35.80it/s]
Loading 0:  83%|████████▎ | 242/291 [00:05<00:01, 38.45it/s]
Loading 0:  85%|████████▌ | 248/291 [00:05<00:01, 41.08it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 48.24it/s]
Loading 0:  91%|█████████ | 264/291 [00:05<00:00, 55.10it/s]
Loading 0:  94%|█████████▍| 273/291 [00:05<00:00, 58.91it/s]
Loading 0:  97%|█████████▋| 281/291 [00:06<00:00, 59.27it/s]
Loading 0:  99%|█████████▉| 288/291 [00:13<00:00,  3.50it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaiml-augment-ensemble-v3-mkmlizer: quantized model in 31.546s
chaiml-augment-ensemble-v3-mkmlizer: Processed model ChaiML/augment-ensemble in 77.778s
chaiml-augment-ensemble-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-augment-ensemble-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-augment-ensemble-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-augment-ensemble-v3
chaiml-augment-ensemble-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-augment-ensemble-v3/config.json
chaiml-augment-ensemble-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-augment-ensemble-v3/tokenizer_config.json
chaiml-augment-ensemble-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-augment-ensemble-v3/special_tokens_map.json
chaiml-augment-ensemble-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-augment-ensemble-v3/tokenizer.json
chaiml-augment-ensemble-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-augment-ensemble-v3/flywheel_model.0.safetensors
chaiml-augment-ensemble-v3-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-augment-ensemble-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-augment-ensemble-v3-mkmlizer:   warnings.warn(
chaiml-augment-ensemble-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
chaiml-augment-ensemble-v3-mkmlizer:   warnings.warn(
chaiml-augment-ensemble-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-augment-ensemble-v3-mkmlizer:   warnings.warn(
chaiml-augment-ensemble-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-augment-ensemble-v3-mkmlizer:   warnings.warn(
chaiml-augment-ensemble-v3-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:07<00:07,  7.40s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.28s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.74s/it]
chaiml-augment-ensemble-v3-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.64it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.68it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.45it/s]
chaiml-augment-ensemble-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-augment-ensemble-v3-mkmlizer: Saving duration: 2.152s
chaiml-augment-ensemble-v3-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.910s
chaiml-augment-ensemble-v3-mkmlizer: creating bucket guanaco-reward-models
chaiml-augment-ensemble-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-augment-ensemble-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-augment-ensemble-v3_reward
chaiml-augment-ensemble-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-augment-ensemble-v3_reward/config.json
chaiml-augment-ensemble-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-augment-ensemble-v3_reward/special_tokens_map.json
chaiml-augment-ensemble-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-augment-ensemble-v3_reward/tokenizer_config.json
chaiml-augment-ensemble-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-augment-ensemble-v3_reward/vocab.json
chaiml-augment-ensemble-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-augment-ensemble-v3_reward/merges.txt
chaiml-augment-ensemble-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-augment-ensemble-v3_reward/tokenizer.json
chaiml-augment-ensemble-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-augment-ensemble-v3_reward/reward.tensors
Job chaiml-augment-ensemble-v3-mkmlizer completed after 144.41s with status: succeeded
Stopping job with name chaiml-augment-ensemble-v3-mkmlizer
Pipeline stage MKMLizer completed in 145.34s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-augment-ensemble-v3
Waiting for inference service chaiml-augment-ensemble-v3 to be ready
Inference service chaiml-augment-ensemble-v3 ready after 40.33279299736023s
Pipeline stage ISVCDeployer completed in 47.13s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9994843006134033s
Received healthy response to inference request in 6.597512722015381s
Received healthy response to inference request in 1.8796648979187012s
Received healthy response to inference request in 1.5098254680633545s
Received healthy response to inference request in 3.4390532970428467s
5 requests
0 failed requests
5th percentile: 1.5837933540344238
10th percentile: 1.657761240005493
20th percentile: 1.8056970119476319
30th percentile: 2.1036287784576415
40th percentile: 2.5515565395355226
50th percentile: 2.9994843006134033
60th percentile: 3.1753118991851808
70th percentile: 3.3511394977569577
80th percentile: 4.070745182037354
90th percentile: 5.334128952026368
95th percentile: 5.965820837020874
99th percentile: 6.471174345016479
mean time: 3.285108137130737
Pipeline stage StressChecker completed in 17.13s
chaiml-augment-ensemble_v3 status is now deployed due to DeploymentManager action
chaiml-augment-ensemble_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-augment-ensemble_v3
Running pipeline stage ISVCDeleter
Checking if service chaiml-augment-ensemble-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.03s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-augment-ensemble-v3/config.json from bucket guanaco-mkml-models
Deleting key chaiml-augment-ensemble-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-augment-ensemble-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-augment-ensemble-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-augment-ensemble-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-augment-ensemble-v3_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-augment-ensemble-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-augment-ensemble-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-augment-ensemble-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-augment-ensemble-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-augment-ensemble-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-augment-ensemble-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.51s
chaiml-augment-ensemble_v3 status is now torndown due to DeploymentManager action