submission_id: dreamgen-opus-v1-2-llam_2622_v12
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': 0.8, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 70, 'presence_penalty': 0.9, '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}". {bot_name}\'s 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: 2024-04-21T08:08:40+00:00
model_name: opusllama8b_v2
model_eval_status: success
model_group: dreamgen/opus-v1.2-llama
num_battles: 6073
num_wins: 3380
celo_rating: 1185.57
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: opusllama8b_v2
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: 2024-04-21
win_ratio: 0.5565618310554915
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name dreamgen-opus-v1-2-llam-2622-v12-mkmlizer
Waiting for job on dreamgen-opus-v1-2-llam-2622-v12-mkmlizer to finish
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ _____ __ __ ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ /___/ ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ Version: 0.8.10 ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ The license key for the current software has been verified as ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ belonging to: ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ Chai Research Corp. ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
dreamgen-opus-v1-2-llam-2622-v12-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-v12-mkmlizer: warnings.warn(warning_message, FutureWarning)
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▉ | 84/291 [00:01<00:02, 82.82it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 85.11it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 28.24it/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-v12-mkmlizer: quantized model in 19.871s
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: Processed model dreamgen/opus-v1.2-llama-3-8b in 38.885s
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: creating bucket guanaco-mkml-models
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v12
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v12/tokenizer_config.json
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v12/config.json
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v12/special_tokens_map.json
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v12/tokenizer.json
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v12/flywheel_model.0.safetensors
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
dreamgen-opus-v1-2-llam-2622-v12-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-v12-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llam-2622-v12-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-v12-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llam-2622-v12-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-v12-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llam-2622-v12-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-v12-mkmlizer: return self.fget.__get__(instance, owner)()
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: Saving duration: 0.267s
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.486s
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: creating bucket guanaco-reward-models
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: Bucket 's3://guanaco-reward-models/' created
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v12_reward
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v12_reward/special_tokens_map.json
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v12_reward/config.json
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v12_reward/tokenizer_config.json
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v12_reward/vocab.json
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v12_reward/merges.txt
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v12_reward/tokenizer.json
dreamgen-opus-v1-2-llam-2622-v12-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v12_reward/reward.tensors
Job dreamgen-opus-v1-2-llam-2622-v12-mkmlizer completed after 63.24s with status: succeeded
Stopping job with name dreamgen-opus-v1-2-llam-2622-v12-mkmlizer
Pipeline stage MKMLizer completed in 68.65s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service dreamgen-opus-v1-2-llam-2622-v12
Waiting for inference service dreamgen-opus-v1-2-llam-2622-v12 to be ready
Inference service dreamgen-opus-v1-2-llam-2622-v12 ready after 30.173523664474487s
Pipeline stage ISVCDeployer completed in 37.63s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0822126865386963s
Received healthy response to inference request in 1.2840337753295898s
Received healthy response to inference request in 1.268949270248413s
Received healthy response to inference request in 1.2827317714691162s
Received healthy response to inference request in 1.2951974868774414s
5 requests
0 failed requests
5th percentile: 1.2717057704925536
10th percentile: 1.2744622707366944
20th percentile: 1.2799752712249757
30th percentile: 1.282992172241211
40th percentile: 1.2835129737854003
50th percentile: 1.2840337753295898
60th percentile: 1.2884992599487304
70th percentile: 1.2929647445678711
80th percentile: 1.4526005268096924
90th percentile: 1.7674066066741945
95th percentile: 1.9248096466064453
99th percentile: 2.050732078552246
mean time: 1.4426249980926513
Pipeline stage StressChecker completed in 7.80s
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_v12 status is now deployed due to DeploymentManager action
dreamgen-opus-v1-2-llam_2622_v12 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of dreamgen-opus-v1-2-llam_2622_v12
Running pipeline stage ISVCDeleter
Checking if service dreamgen-opus-v1-2-llam-2622-v12 is running
Tearing down inference service dreamgen-opus-v1-2-llam-2622-v12
Toredown service dreamgen-opus-v1-2-llam-2622-v12
Pipeline stage ISVCDeleter completed in 3.56s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llam-2622-v12/config.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v12/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v12/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v12/tokenizer.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v12/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llam-2622-v12_reward/config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v12_reward/merges.txt from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v12_reward/reward.tensors from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v12_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v12_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v12_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v12_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.86s
dreamgen-opus-v1-2-llam_2622_v12 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics