submission_id: invisietch-etherealrainb_9091_v3
developer_uid: invisietch
best_of: 4
celo_rating: 1178.03
display_name: invisietch-etherealrainbow-v0_3
family_friendly_score: 0.0
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}
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '\n\n{user_name}'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
is_internal_developer: False
language_model: invisietch/EtherealRainbow-v0.3-8B
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: invisietch/EtherealRainb
model_name: invisietch-etherealrainbow-v0_3
model_num_parameters: 8030261248.0
model_repo: invisietch/EtherealRainbow-v0.3-8B
model_size: 8B
num_battles: 31290
num_wins: 14833
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-08T04:00:11+00:00
us_pacific_date: 2024-07-07
win_ratio: 0.4740492170022371
Resubmit model
Running pipeline stage MKMLizer
Starting job with name invisietch-etherealrainb-9091-v3-mkmlizer
Waiting for job on invisietch-etherealrainb-9091-v3-mkmlizer to finish
invisietch-etherealrainb-9091-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
invisietch-etherealrainb-9091-v3-mkmlizer: ║ _____ __ __ ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ /___/ ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ Version: 0.8.14 ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ https://mk1.ai ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ The license key for the current software has been verified as ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ belonging to: ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ Chai Research Corp. ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
invisietch-etherealrainb-9091-v3-mkmlizer: ║ ║
invisietch-etherealrainb-9091-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
invisietch-etherealrainb-9091-v3-mkmlizer: Downloaded to shared memory in 28.052s
invisietch-etherealrainb-9091-v3-mkmlizer: quantizing model to /dev/shm/model_cache
invisietch-etherealrainb-9091-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
invisietch-etherealrainb-9091-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:52, 2.88s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:25, 3.23it/s] Loading 0: 8%|▊ | 22/291 [00:06<00:50, 5.37it/s] Loading 0: 11%|█▏ | 33/291 [00:06<00:26, 9.77it/s] Loading 0: 17%|█▋ | 49/291 [00:06<00:13, 18.26it/s] Loading 0: 21%|██ | 60/291 [00:06<00:09, 25.01it/s] Loading 0: 26%|██▌ | 76/291 [00:06<00:05, 37.75it/s] Loading 0: 30%|███ | 88/291 [00:06<00:05, 36.83it/s] Loading 0: 35%|███▌ | 103/291 [00:07<00:03, 49.74it/s] Loading 0: 39%|███▉ | 114/291 [00:07<00:03, 57.73it/s] Loading 0: 45%|████▍ | 130/291 [00:07<00:02, 74.28it/s] Loading 0: 49%|████▉ | 142/291 [00:07<00:02, 56.60it/s] Loading 0: 54%|█████▍ | 157/291 [00:07<00:01, 70.27it/s] Loading 0: 58%|█████▊ | 168/291 [00:07<00:01, 76.01it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 91.21it/s] Loading 0: 67%|██████▋ | 196/291 [00:08<00:00, 95.04it/s] Loading 0: 71%|███████▏ | 208/291 [00:08<00:01, 64.02it/s] Loading 0: 76%|███████▌ | 221/291 [00:08<00:00, 74.11it/s] Loading 0: 81%|████████ | 235/291 [00:08<00:00, 86.37it/s] Loading 0: 85%|████████▌ | 248/291 [00:08<00:00, 93.02it/s] Loading 0: 90%|████████▉ | 261/291 [00:08<00:00, 101.48it/s] Loading 0: 94%|█████████▍| 273/291 [00:09<00:00, 67.47it/s] Loading 0: 98%|█████████▊| 284/291 [00:09<00:00, 74.02it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
invisietch-etherealrainb-9091-v3-mkmlizer: quantized model in 30.790s
invisietch-etherealrainb-9091-v3-mkmlizer: Processed model invisietch/EtherealRainbow-v0.3-8B in 58.842s
invisietch-etherealrainb-9091-v3-mkmlizer: creating bucket guanaco-mkml-models
invisietch-etherealrainb-9091-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
invisietch-etherealrainb-9091-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/invisietch-etherealrainb-9091-v3
invisietch-etherealrainb-9091-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/invisietch-etherealrainb-9091-v3/config.json
invisietch-etherealrainb-9091-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/invisietch-etherealrainb-9091-v3/special_tokens_map.json
invisietch-etherealrainb-9091-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/invisietch-etherealrainb-9091-v3/tokenizer_config.json
invisietch-etherealrainb-9091-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/invisietch-etherealrainb-9091-v3/tokenizer.json
invisietch-etherealrainb-9091-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/invisietch-etherealrainb-9091-v3/flywheel_model.0.safetensors
invisietch-etherealrainb-9091-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
invisietch-etherealrainb-9091-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.
invisietch-etherealrainb-9091-v3-mkmlizer: warnings.warn(
invisietch-etherealrainb-9091-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`.
invisietch-etherealrainb-9091-v3-mkmlizer: warnings.warn(
invisietch-etherealrainb-9091-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.
invisietch-etherealrainb-9091-v3-mkmlizer: warnings.warn(
invisietch-etherealrainb-9091-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.
invisietch-etherealrainb-9091-v3-mkmlizer: warnings.warn(
invisietch-etherealrainb-9091-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
invisietch-etherealrainb-9091-v3-mkmlizer: return self.fget.__get__(instance, owner)()
invisietch-etherealrainb-9091-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
invisietch-etherealrainb-9091-v3-mkmlizer: Saving duration: 0.631s
invisietch-etherealrainb-9091-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.817s
invisietch-etherealrainb-9091-v3-mkmlizer: creating bucket guanaco-reward-models
invisietch-etherealrainb-9091-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
invisietch-etherealrainb-9091-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/invisietch-etherealrainb-9091-v3_reward
invisietch-etherealrainb-9091-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/invisietch-etherealrainb-9091-v3_reward/special_tokens_map.json
invisietch-etherealrainb-9091-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/invisietch-etherealrainb-9091-v3_reward/merges.txt
invisietch-etherealrainb-9091-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/invisietch-etherealrainb-9091-v3_reward/tokenizer_config.json
invisietch-etherealrainb-9091-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/invisietch-etherealrainb-9091-v3_reward/config.json
invisietch-etherealrainb-9091-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/invisietch-etherealrainb-9091-v3_reward/vocab.json
invisietch-etherealrainb-9091-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/invisietch-etherealrainb-9091-v3_reward/tokenizer.json
invisietch-etherealrainb-9091-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/invisietch-etherealrainb-9091-v3_reward/reward.tensors
Job invisietch-etherealrainb-9091-v3-mkmlizer completed after 94.81s with status: succeeded
Stopping job with name invisietch-etherealrainb-9091-v3-mkmlizer
Pipeline stage MKMLizer completed in 95.66s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service invisietch-etherealrainb-9091-v3
Waiting for inference service invisietch-etherealrainb-9091-v3 to be ready
Inference service invisietch-etherealrainb-9091-v3 ready after 41.41933274269104s
Pipeline stage ISVCDeployer completed in 48.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8956756591796875s
Received healthy response to inference request in 1.112046241760254s
Received healthy response to inference request in 1.1228313446044922s
Received healthy response to inference request in 1.1119272708892822s
Received healthy response to inference request in 1.1214804649353027s
5 requests
0 failed requests
5th percentile: 1.1119510650634765
10th percentile: 1.1119748592376708
20th percentile: 1.1120224475860596
30th percentile: 1.1139330863952637
40th percentile: 1.1177067756652832
50th percentile: 1.1214804649353027
60th percentile: 1.1220208168029786
70th percentile: 1.1225611686706543
80th percentile: 1.2774002075195314
90th percentile: 1.5865379333496095
95th percentile: 1.7411067962646483
99th percentile: 1.8647618865966797
mean time: 1.2727921962738038
Pipeline stage StressChecker completed in 7.07s
invisietch-etherealrainb_9091_v3 status is now deployed due to DeploymentManager action
invisietch-etherealrainb_9091_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of invisietch-etherealrainb_9091_v3
Running pipeline stage ISVCDeleter
Checking if service invisietch-etherealrainb-9091-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.14s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key invisietch-etherealrainb-9091-v3/config.json from bucket guanaco-mkml-models
Deleting key invisietch-etherealrainb-9091-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key invisietch-etherealrainb-9091-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key invisietch-etherealrainb-9091-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key invisietch-etherealrainb-9091-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key invisietch-etherealrainb-9091-v3_reward/config.json from bucket guanaco-reward-models
Deleting key invisietch-etherealrainb-9091-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key invisietch-etherealrainb-9091-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key invisietch-etherealrainb-9091-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key invisietch-etherealrainb-9091-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key invisietch-etherealrainb-9091-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key invisietch-etherealrainb-9091-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.56s
invisietch-etherealrainb_9091_v3 status is now torndown due to DeploymentManager action