submission_id: dreamgen-opus-v1-2-llama-3-8b_v6
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}". Your 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: 2024-04-20T17:20:11+00:00
model_name: Dream-8B
model_eval_status: success
model_group: dreamgen/opus-v1.2-llama
num_battles: 5886
num_wins: 3241
celo_rating: 1181.47
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: 0.5506286102616378
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer
Waiting for job on dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer to finish
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ _____ __ __ ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ /___/ ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ Version: 0.8.10 ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ The license key for the current software has been verified as ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ belonging to: ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ Chai Research Corp. ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ║ ║
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
dreamgen-opus-v1-2-llama-3-8b-v6-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-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: Downloaded to shared memory in 19.222s
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: quantizing model to /dev/shm/model_cache
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 63.74it/s] Loading 0: 57%|█████▋ | 166/291 [00:02<00:01, 73.51it/s] Loading 0: 73%|███████▎ | 212/291 [00:03<00:01, 61.31it/s] Loading 0: 99%|█████████▊| 287/291 [00:09<00:00, 21.39it/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-v6-mkmlizer: quantized model in 23.765s
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: Processed model dreamgen/opus-v1.2-llama-3-8b in 44.604s
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: creating bucket guanaco-mkml-models
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v6
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v6/config.json
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v6/special_tokens_map.json
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v6/tokenizer_config.json
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v6/tokenizer.json
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v6/flywheel_model.0.safetensors
dreamgen-opus-v1-2-llama-3-8b-v6-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-v6-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llama-3-8b-v6-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-v6-mkmlizer: return self.fget.__get__(instance, owner)()
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: Saving duration: 0.316s
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.206s
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: creating bucket guanaco-reward-models
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v6_reward
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v6_reward/config.json
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v6_reward/special_tokens_map.json
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v6_reward/tokenizer_config.json
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v6_reward/vocab.json
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v6_reward/merges.txt
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v6_reward/tokenizer.json
dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v6_reward/reward.tensors
Job dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer completed after 76.91s with status: succeeded
Stopping job with name dreamgen-opus-v1-2-llama-3-8b-v6-mkmlizer
Pipeline stage MKMLizer completed in 82.14s
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-v6
Waiting for inference service dreamgen-opus-v1-2-llama-3-8b-v6 to be ready
Inference service dreamgen-opus-v1-2-llama-3-8b-v6 ready after 40.32349681854248s
Pipeline stage ISVCDeployer completed in 48.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.113241672515869s
Received healthy response to inference request in 1.2782723903656006s
Received healthy response to inference request in 1.2720603942871094s
Received healthy response to inference request in 1.3108267784118652s
Received healthy response to inference request in 1.2807693481445312s
5 requests
0 failed requests
5th percentile: 1.2733027935028076
10th percentile: 1.2745451927185059
20th percentile: 1.2770299911499023
30th percentile: 1.2787717819213866
40th percentile: 1.279770565032959
50th percentile: 1.2807693481445312
60th percentile: 1.2927923202514648
70th percentile: 1.3048152923583984
80th percentile: 1.471309757232666
90th percentile: 1.7922757148742676
95th percentile: 1.9527586936950683
99th percentile: 2.081145076751709
mean time: 1.4510341167449952
Pipeline stage StressChecker completed in 7.89s
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_v6 status is now deployed due to DeploymentManager action
dreamgen-opus-v1-2-llama-3-8b_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of dreamgen-opus-v1-2-llama-3-8b_v6
Running pipeline stage ISVCDeleter
Checking if service dreamgen-opus-v1-2-llama-3-8b-v6 is running
Tearing down inference service dreamgen-opus-v1-2-llama-3-8b-v6
Toredown service dreamgen-opus-v1-2-llama-3-8b-v6
Pipeline stage ISVCDeleter completed in 5.14s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llama-3-8b-v6/config.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llama-3-8b-v6_reward/config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.55s
dreamgen-opus-v1-2-llama-3-8b_v6 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics