submission_id: dreamgen-opus-v1-2-llama-3-8b_v5
developer_uid: fredi
status: torndown
model_repo: dreamgen/opus-v1.2-llama-3-8b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 55, 'presence_penalty': 0.0, 'frequency_penalty': 0.9, '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\nYou are roleplaying "{bot_name}" in an entertaining chat between "{bot_name}" and User. \nYour 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\nUser: {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: 2024-04-20T13:23:52+00:00
model_name: Dream-8B
model_eval_status: success
model_group: dreamgen/opus-v1.2-llama
num_battles: 6028
num_wins: 3189
celo_rating: 1169.41
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: Dream-8B
ineligible_reason: propriety_total_count < 800
language_model: dreamgen/opus-v1.2-llama-3-8b
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-20
win_ratio: 0.5290311877903119
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer
Waiting for job on dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer to finish
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ _____ __ __ ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ /___/ ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ Version: 0.8.10 ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ The license key for the current software has been verified as ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ belonging to: ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ Chai Research Corp. ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ║ ║
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
dreamgen-opus-v1-2-llama-3-8b-v5-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-llama-3-8b-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: Downloaded to shared memory in 21.200s
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: quantizing model to /dev/shm/model_cache
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 61.63it/s] Loading 0: 64%|██████▍ | 186/291 [00:02<00:01, 82.92it/s] Loading 0: 82%|████████▏ | 238/291 [00:03<00:00, 69.77it/s] Loading 0: 99%|█████████▊| 287/291 [00:09<00:00, 20.38it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: quantized model in 21.945s
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: Processed model dreamgen/opus-v1.2-llama-3-8b in 44.858s
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: creating bucket guanaco-mkml-models
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v5
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v5/config.json
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v5/tokenizer_config.json
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v5/special_tokens_map.json
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v5/tokenizer.json
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
dreamgen-opus-v1-2-llama-3-8b-v5-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-llama-3-8b-v5-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llama-3-8b-v5-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-llama-3-8b-v5-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llama-3-8b-v5-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-llama-3-8b-v5-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llama-3-8b-v5-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-llama-3-8b-v5-mkmlizer: return self.fget.__get__(instance, owner)()
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: Saving duration: 0.309s
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.475s
dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v5_reward/reward.tensors
Job dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer completed after 74.42s with status: succeeded
Stopping job with name dreamgen-opus-v1-2-llama-3-8b-v5-mkmlizer
Pipeline stage MKMLizer completed in 76.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service dreamgen-opus-v1-2-llama-3-8b-v5
Waiting for inference service dreamgen-opus-v1-2-llama-3-8b-v5 to be ready
Inference service dreamgen-opus-v1-2-llama-3-8b-v5 ready after 40.24758315086365s
Pipeline stage ISVCDeployer completed in 46.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1252048015594482s
Received healthy response to inference request in 1.259566307067871s
Received healthy response to inference request in 1.2925512790679932s
Received healthy response to inference request in 1.2764358520507812s
Received healthy response to inference request in 1.3000667095184326s
5 requests
0 failed requests
5th percentile: 1.2629402160644532
10th percentile: 1.2663141250610352
20th percentile: 1.2730619430541992
30th percentile: 1.2796589374542235
40th percentile: 1.2861051082611084
50th percentile: 1.2925512790679932
60th percentile: 1.295557451248169
70th percentile: 1.2985636234283446
80th percentile: 1.465094327926636
90th percentile: 1.795149564743042
95th percentile: 1.960177183151245
99th percentile: 2.092199277877808
mean time: 1.4507649898529054
Pipeline stage StressChecker completed in 7.90s
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-llama-3-8b_v5 status is now deployed due to DeploymentManager action
dreamgen-opus-v1-2-llama-3-8b_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of dreamgen-opus-v1-2-llama-3-8b_v5
Running pipeline stage ISVCDeleter
Checking if service dreamgen-opus-v1-2-llama-3-8b-v5 is running
Tearing down inference service dreamgen-opus-v1-2-llama-3-8b-v5
Toredown service dreamgen-opus-v1-2-llama-3-8b-v5
Pipeline stage ISVCDeleter completed in 4.11s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llama-3-8b-v5/config.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llama-3-8b-v5_reward/config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.96s
dreamgen-opus-v1-2-llama-3-8b_v5 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics