submission_id: azazelle-llama-3-nerdy-rp-8b_v1
developer_uid: Azazelle
best_of: 4
celo_rating: 1167.96
display_name: azazelle-llama-3-nerdy-rp-8b_v1
family_friendly_score: 0.0
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 0.5, 'min_p': 0.0, 'top_k': 1000, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Azazelle/Llama-3-Nerdy-RP-8B
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Azazelle/Llama-3-Nerdy-R
model_name: azazelle-llama-3-nerdy-rp-8b_v1
model_num_parameters: 8030261248.0
model_repo: Azazelle/Llama-3-Nerdy-RP-8B
model_size: 8B
num_battles: 24197
num_wins: 11598
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: 2024-06-28T19:31:02+00:00
us_pacific_date: 2024-06-28
win_ratio: 0.47931561763855024
Resubmit model
Running pipeline stage MKMLizer
Starting job with name azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer
Waiting for job on azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer to finish
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ _____ __ __ ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ /___/ ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ Version: 0.8.14 ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ https://mk1.ai ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ belonging to: ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ Chai Research Corp. ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ║ ║
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: Downloaded to shared memory in 33.837s
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<12:38, 2.63s/it] Loading 0: 5%|▌ | 15/291 [00:05<01:12, 3.80it/s] Loading 0: 11%|█ | 32/291 [00:05<00:26, 9.81it/s] Loading 0: 17%|█▋ | 49/291 [00:05<00:13, 17.65it/s] Loading 0: 21%|██▏ | 62/291 [00:06<00:11, 20.36it/s] Loading 0: 26%|██▋ | 77/291 [00:06<00:07, 29.30it/s] Loading 0: 31%|███▏ | 91/291 [00:06<00:05, 39.37it/s] Loading 0: 36%|███▌ | 104/291 [00:06<00:03, 49.39it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 65.01it/s] Loading 0: 48%|████▊ | 139/291 [00:06<00:01, 82.22it/s] Loading 0: 53%|█████▎ | 154/291 [00:06<00:01, 94.85it/s] Loading 0: 58%|█████▊ | 169/291 [00:07<00:01, 67.51it/s] Loading 0: 64%|██████▎ | 185/291 [00:07<00:01, 81.77it/s] Loading 0: 70%|██████▉ | 203/291 [00:07<00:00, 97.70it/s] Loading 0: 76%|███████▌ | 221/291 [00:07<00:00, 111.77it/s] Loading 0: 82%|████████▏ | 238/291 [00:07<00:00, 124.51it/s] Loading 0: 87%|████████▋ | 254/291 [00:07<00:00, 133.01it/s] Loading 0: 93%|█████████▎| 270/291 [00:07<00:00, 83.83it/s] Loading 0: 98%|█████████▊| 284/291 [00:08<00:00, 90.21it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: quantized model in 27.479s
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: Processed model Azazelle/Llama-3-Nerdy-RP-8B in 64.037s
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/azazelle-llama-3-nerdy-rp-8b-v1
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/azazelle-llama-3-nerdy-rp-8b-v1/tokenizer_config.json
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/azazelle-llama-3-nerdy-rp-8b-v1/tokenizer.json
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/azazelle-llama-3-nerdy-rp-8b-v1/config.json
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/azazelle-llama-3-nerdy-rp-8b-v1/flywheel_model.0.safetensors
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: warnings.warn(
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: warnings.warn(
azazelle-llama-3-nerdy-rp-8b-v1-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.
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: warnings.warn(
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: Saving duration: 0.446s
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.736s
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: creating bucket guanaco-reward-models
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/azazelle-llama-3-nerdy-rp-8b-v1_reward
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/azazelle-llama-3-nerdy-rp-8b-v1_reward/special_tokens_map.json
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/azazelle-llama-3-nerdy-rp-8b-v1_reward/tokenizer_config.json
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/azazelle-llama-3-nerdy-rp-8b-v1_reward/config.json
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/azazelle-llama-3-nerdy-rp-8b-v1_reward/merges.txt
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/azazelle-llama-3-nerdy-rp-8b-v1_reward/vocab.json
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/azazelle-llama-3-nerdy-rp-8b-v1_reward/tokenizer.json
azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/azazelle-llama-3-nerdy-rp-8b-v1_reward/reward.tensors
Job azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer completed after 93.98s with status: succeeded
Stopping job with name azazelle-llama-3-nerdy-rp-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.09s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service azazelle-llama-3-nerdy-rp-8b-v1
Waiting for inference service azazelle-llama-3-nerdy-rp-8b-v1 to be ready
Inference service azazelle-llama-3-nerdy-rp-8b-v1 ready after 40.34524178504944s
Pipeline stage ISVCDeployer completed in 47.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 18.371351718902588s
Received healthy response to inference request in 0.5462696552276611s
Received healthy response to inference request in 1.1973247528076172s
Received healthy response to inference request in 4.976345539093018s
Received healthy response to inference request in 1.1247203350067139s
5 requests
0 failed requests
5th percentile: 0.6619597911834717
10th percentile: 0.7776499271392823
20th percentile: 1.0090301990509034
30th percentile: 1.1392412185668945
40th percentile: 1.1682829856872559
50th percentile: 1.1973247528076172
60th percentile: 2.708933067321777
70th percentile: 4.220541381835937
80th percentile: 7.655346775054934
90th percentile: 13.01334924697876
95th percentile: 15.692350482940672
99th percentile: 17.835551471710204
mean time: 5.24320240020752
Pipeline stage StressChecker completed in 26.91s
azazelle-llama-3-nerdy-rp-8b_v1 status is now deployed due to DeploymentManager action
azazelle-llama-3-nerdy-rp-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of azazelle-llama-3-nerdy-rp-8b_v1
Running pipeline stage ISVCDeleter
Checking if service azazelle-llama-3-nerdy-rp-8b-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 10.44s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key azazelle-llama-3-nerdy-rp-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key azazelle-llama-3-nerdy-rp-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key azazelle-llama-3-nerdy-rp-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key azazelle-llama-3-nerdy-rp-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key azazelle-llama-3-nerdy-rp-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key azazelle-llama-3-nerdy-rp-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key azazelle-llama-3-nerdy-rp-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key azazelle-llama-3-nerdy-rp-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key azazelle-llama-3-nerdy-rp-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key azazelle-llama-3-nerdy-rp-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key azazelle-llama-3-nerdy-rp-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key azazelle-llama-3-nerdy-rp-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.43s
azazelle-llama-3-nerdy-rp-8b_v1 status is now torndown due to DeploymentManager action
admin requested tearing down of azazelle-llama-3-nerdy-rp-8b_v1
Running pipeline stage ISVCDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage ISVCDeleter completed in 0.47s
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLModelDeleter completed in 0.34s
azazelle-llama-3-nerdy-rp-8b_v1 status is now torndown due to DeploymentManager action