submission_id: dreamgen-opus-v1-2-llam_2622_v13
developer_uid: fredi
status: torndown
model_repo: dreamgen/opus-v1.2-llama-3-8b
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 55, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 112}
formatter: {'memory_template': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}. Write {bot_name}\'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}\'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations must be enclosed in asterisks (*). The responses must be long and in third perspective of the story teller.\n\nFor example:\n"""\nMila: *Surrounded by an aura of creativity, Mila carefully places a freshly painted canvas against the wall, the colors vividly depicting a surreal landscape.* Isn\'t it fascinating how art can transport us to entirely different worlds? What kind of worlds do you dream of exploring?\n"""\n\nDescription: {memory}', 'prompt_template': 'Example conversation:\n{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': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-04-21T12:48:26+00:00
model_name: vicgalle-roleplay-llama-3-8b_v2
model_eval_status: success
model_group: dreamgen/opus-v1.2-llama
num_battles: 5482
num_wins: 3004
celo_rating: 1183.84
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: 112
display_name: vicgalle-roleplay-llama-3-8b_v2
ineligible_reason: max_output_tokens!=64
language_model: dreamgen/opus-v1.2-llama-3-8b
model_size: 8B
reward_model: rirv938/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-21
win_ratio: 0.5479751915359358
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name dreamgen-opus-v1-2-llam-2622-v13-mkmlizer
Waiting for job on dreamgen-opus-v1-2-llam-2622-v13-mkmlizer to finish
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ _____ __ __ ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ /___/ ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ Version: 0.8.10 ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ The license key for the current software has been verified as ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ belonging to: ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ Chai Research Corp. ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
dreamgen-opus-v1-2-llam-2622-v13-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.
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: warnings.warn(warning_message, FutureWarning)
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: Downloaded to shared memory in 23.415s
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: quantizing model to /dev/shm/model_cache
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 80.09it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 82.85it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 26.85it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: quantized model in 22.146s
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: Processed model dreamgen/opus-v1.2-llama-3-8b in 46.940s
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: creating bucket guanaco-mkml-models
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v13
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v13/config.json
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v13/special_tokens_map.json
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v13/tokenizer_config.json
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v13/tokenizer.json
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v13/flywheel_model.0.safetensors
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
dreamgen-opus-v1-2-llam-2622-v13-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.
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llam-2622-v13-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.
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llam-2622-v13-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.
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llam-2622-v13-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()
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: return self.fget.__get__(instance, owner)()
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: creating bucket guanaco-reward-models
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: Bucket 's3://guanaco-reward-models/' created
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v13_reward
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v13_reward/config.json
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v13_reward/special_tokens_map.json
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v13_reward/tokenizer_config.json
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v13_reward/merges.txt
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v13_reward/vocab.json
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v13_reward/tokenizer.json
dreamgen-opus-v1-2-llam-2622-v13-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v13_reward/reward.tensors
Job dreamgen-opus-v1-2-llam-2622-v13-mkmlizer completed after 76.13s with status: succeeded
Stopping job with name dreamgen-opus-v1-2-llam-2622-v13-mkmlizer
Pipeline stage MKMLizer completed in 81.67s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service dreamgen-opus-v1-2-llam-2622-v13
Waiting for inference service dreamgen-opus-v1-2-llam-2622-v13 to be ready
Inference service dreamgen-opus-v1-2-llam-2622-v13 ready after 40.22683906555176s
Pipeline stage ISVCDeployer completed in 47.92s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8702197074890137s
Received healthy response to inference request in 2.0418701171875s
Received healthy response to inference request in 2.057845115661621s
Received healthy response to inference request in 3.0625813007354736s
Received healthy response to inference request in 2.0618879795074463s
5 requests
0 failed requests
5th percentile: 2.0450651168823244
10th percentile: 2.0482601165771483
20th percentile: 2.0546501159667967
30th percentile: 2.058653688430786
40th percentile: 2.060270833969116
50th percentile: 2.0618879795074463
60th percentile: 2.385220670700073
70th percentile: 2.7085533618927
80th percentile: 2.9086920261383056
90th percentile: 2.98563666343689
95th percentile: 3.0241089820861817
99th percentile: 3.0548868370056153
mean time: 2.418880844116211
Pipeline stage StressChecker completed in 12.80s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
dreamgen-opus-v1-2-llam_2622_v13 status is now deployed due to DeploymentManager action
dreamgen-opus-v1-2-llam_2622_v13 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of dreamgen-opus-v1-2-llam_2622_v13
Running pipeline stage ISVCDeleter
Checking if service dreamgen-opus-v1-2-llam-2622-v13 is running
Tearing down inference service dreamgen-opus-v1-2-llam-2622-v13
Toredown service dreamgen-opus-v1-2-llam-2622-v13
Pipeline stage ISVCDeleter completed in 3.71s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llam-2622-v13/config.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v13/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v13/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v13/tokenizer.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v13/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llam-2622-v13_reward/config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v13_reward/merges.txt from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v13_reward/reward.tensors from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v13_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v13_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v13_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v13_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.83s
dreamgen-opus-v1-2-llam_2622_v13 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics