submission_id: hastagaras-llama3-8b-dar_7224_v1
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/llama3-8b-darktune-MIX
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.84, 'top_p': 0.9, 'min_p': 0.0, '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\nAct as {bot_name}. {bot_name}'s persona: {memory}<|eot_id|>", 'prompt_template': '<|start_header_id|>Assistant<|end_header_id|>\n\n{bot_name}: {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: {'memory_template': "{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}\n\n', 'bot_template': 'BOT: {message}\n', 'user_template': 'USER: {message}\n', 'response_template': 'BOT:', 'truncate_by_message': False}
timestamp: 2024-05-11T06:06:46+00:00
model_name: hastagaras-lm3-8b-darktune_mix
model_eval_status: success
model_group: Hastagaras/llama3-8b-dar
num_battles: 22254
num_wins: 11105
celo_rating: 1177.51
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-lm3-8b-darktune_mix
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/llama3-8b-darktune-MIX
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-10
win_ratio: 0.4990114136784398
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-8b-dar-7224-v1-mkmlizer
Waiting for job on hastagaras-llama3-8b-dar-7224-v1-mkmlizer to finish
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ /___/ ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ belonging to: ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ║ ║
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-dar-7224-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.
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: Downloaded to shared memory in 30.231s
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 44%|████▍ | 129/291 [00:00<00:01, 129.11it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 141.83it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: quantized model in 17.334s
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: Processed model Hastagaras/llama3-8b-darktune-MIX in 48.598s
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7224-v1
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7224-v1/config.json
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7224-v1/special_tokens_map.json
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7224-v1/tokenizer_config.json
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7224-v1/tokenizer.json
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-dar-7224-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.
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: warnings.warn(
hastagaras-llama3-8b-dar-7224-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.
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: warnings.warn(
hastagaras-llama3-8b-dar-7224-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.
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: warnings.warn(
hastagaras-llama3-8b-dar-7224-v1-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()
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: Saving duration: 0.233s
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.073s
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7224-v1_reward
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7224-v1_reward/config.json
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7224-v1_reward/tokenizer_config.json
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7224-v1_reward/special_tokens_map.json
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7224-v1_reward/merges.txt
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7224-v1_reward/vocab.json
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7224-v1_reward/tokenizer.json
hastagaras-llama3-8b-dar-7224-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7224-v1_reward/reward.tensors
Job hastagaras-llama3-8b-dar-7224-v1-mkmlizer completed after 82.99s with status: succeeded
Stopping job with name hastagaras-llama3-8b-dar-7224-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.96s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-dar-7224-v1
Waiting for inference service hastagaras-llama3-8b-dar-7224-v1 to be ready
Inference service hastagaras-llama3-8b-dar-7224-v1 ready after 40.32407021522522s
Pipeline stage ISVCDeployer completed in 47.59s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3014791011810303s
Received healthy response to inference request in 1.4501125812530518s
Received healthy response to inference request in 1.4695148468017578s
Received healthy response to inference request in 1.4050219058990479s
Received healthy response to inference request in 1.3780817985534668s
5 requests
0 failed requests
5th percentile: 1.383469820022583
10th percentile: 1.3888578414916992
20th percentile: 1.3996338844299316
30th percentile: 1.4140400409698486
40th percentile: 1.4320763111114503
50th percentile: 1.4501125812530518
60th percentile: 1.457873487472534
70th percentile: 1.4656343936920166
80th percentile: 1.6359076976776126
90th percentile: 1.9686933994293214
95th percentile: 2.1350862503051755
99th percentile: 2.2682005310058595
mean time: 1.600842046737671
Pipeline stage StressChecker completed in 8.61s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama3-8b-dar_7224_v1 status is now deployed due to DeploymentManager action
hastagaras-llama3-8b-dar_7224_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-8b-dar_7224_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-8b-dar-7224-v1 is running
Tearing down inference service hastagaras-llama3-8b-dar-7224-v1
Toredown service hastagaras-llama3-8b-dar-7224-v1
Pipeline stage ISVCDeleter completed in 5.90s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-dar-7224-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7224-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7224-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7224-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7224-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-dar-7224-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7224-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7224-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7224-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7224-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7224-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7224-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.14s
hastagaras-llama3-8b-dar_7224_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics