submission_id: hastagaras-llama-3-8b-okay_v1
developer_uid: Hastagaras
best_of: 16
celo_rating: 1189.78
display_name: hastagaras-llama-3-8b-okay_v1
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou're `{bot_name}` in this scenario. Write `{bot_name}`'s next response based on the below information.\n\n{memory}\n\n", 'prompt_template': 'Previous message: {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': 0.88, '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}
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-okay
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/llama-3-8b-ok
model_name: hastagaras-llama-3-8b-okay_v1
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama-3-8b-okay
model_size: 8B
num_battles: 15838
num_wins: 8374
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-12T04:59:48+00:00
us_pacific_date: 2024-05-11
win_ratio: 0.5287283747947973
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-okay-v1-mkmlizer
Waiting for job on hastagaras-llama-3-8b-okay-v1-mkmlizer to finish
hastagaras-llama-3-8b-okay-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ /___/ ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ belonging to: ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-okay-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-llama-3-8b-okay-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-okay-v1-mkmlizer: Downloaded to shared memory in 29.505s
hastagaras-llama-3-8b-okay-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:01, 120.44it/s] Loading 0: 87%|████████▋ | 252/291 [00:02<00:00, 126.01it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 29.67it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-okay-v1-mkmlizer: quantized model in 17.764s
hastagaras-llama-3-8b-okay-v1-mkmlizer: Processed model Hastagaras/llama-3-8b-okay in 48.274s
hastagaras-llama-3-8b-okay-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-okay-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-okay-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v1
hastagaras-llama-3-8b-okay-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v1/config.json
hastagaras-llama-3-8b-okay-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v1/tokenizer_config.json
hastagaras-llama-3-8b-okay-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v1/special_tokens_map.json
hastagaras-llama-3-8b-okay-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v1/tokenizer.json
hastagaras-llama-3-8b-okay-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v1/flywheel_model.0.safetensors
hastagaras-llama-3-8b-okay-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-okay-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-llama-3-8b-okay-v1-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-okay-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-llama-3-8b-okay-v1-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-okay-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-llama-3-8b-okay-v1-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-okay-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-llama-3-8b-okay-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-okay-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-okay-v1-mkmlizer: Saving duration: 0.225s
hastagaras-llama-3-8b-okay-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.719s
hastagaras-llama-3-8b-okay-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-okay-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-okay-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v1_reward
hastagaras-llama-3-8b-okay-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v1_reward/config.json
hastagaras-llama-3-8b-okay-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v1_reward/special_tokens_map.json
hastagaras-llama-3-8b-okay-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v1_reward/merges.txt
hastagaras-llama-3-8b-okay-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v1_reward/vocab.json
hastagaras-llama-3-8b-okay-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v1_reward/tokenizer_config.json
hastagaras-llama-3-8b-okay-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v1_reward/tokenizer.json
hastagaras-llama-3-8b-okay-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v1_reward/reward.tensors
Job hastagaras-llama-3-8b-okay-v1-mkmlizer completed after 83.65s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-okay-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-okay-v1
Waiting for inference service hastagaras-llama-3-8b-okay-v1 to be ready
Inference service hastagaras-llama-3-8b-okay-v1 ready after 30.177937984466553s
Pipeline stage ISVCDeployer completed in 37.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4255692958831787s
Received healthy response to inference request in 1.3207347393035889s
Received healthy response to inference request in 1.288137674331665s
Received healthy response to inference request in 1.2765347957611084s
Received healthy response to inference request in 1.3635046482086182s
5 requests
0 failed requests
5th percentile: 1.2788553714752198
10th percentile: 1.2811759471893311
20th percentile: 1.2858170986175537
30th percentile: 1.29465708732605
40th percentile: 1.3076959133148194
50th percentile: 1.3207347393035889
60th percentile: 1.3378427028656006
70th percentile: 1.3549506664276123
80th percentile: 1.5759175777435304
90th percentile: 2.0007434368133548
95th percentile: 2.2131563663482665
99th percentile: 2.383086709976196
mean time: 1.534896230697632
Pipeline stage StressChecker completed in 9.48s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-llama-3-8b-okay_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-okay_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-okay_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-okay-v1 is running
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Tearing down inference service hastagaras-llama-3-8b-okay-v1
Toredown service hastagaras-llama-3-8b-okay-v1
Pipeline stage ISVCDeleter completed in 7.18s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.99s
hastagaras-llama-3-8b-okay_v1 status is now torndown due to DeploymentManager action