submission_id: dreamgen-opus-v1-2-llam_2622_v11
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': 1.0, '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: 2024-04-20T21:44:14+00:00
model_name: opusllama8b
model_eval_status: success
model_group: dreamgen/opus-v1.2-llama
num_battles: 6360
num_wins: 3534
celo_rating: 1187.31
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
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: 0.5556603773584906
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name dreamgen-opus-v1-2-llam-2622-v11-mkmlizer
Waiting for job on dreamgen-opus-v1-2-llam-2622-v11-mkmlizer to finish
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ _____ __ __ ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ /___/ ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ Version: 0.8.10 ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ The license key for the current software has been verified as ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ belonging to: ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ Chai Research Corp. ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
dreamgen-opus-v1-2-llam-2622-v11-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-v11-mkmlizer: warnings.warn(warning_message, FutureWarning)
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: Downloaded to shared memory in 23.263s
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: quantizing model to /dev/shm/model_cache
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:02, 84.26it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 92.02it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 29.38it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: quantized model in 19.629s
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: Processed model dreamgen/opus-v1.2-llama-3-8b in 44.073s
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: creating bucket guanaco-mkml-models
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v11
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v11/config.json
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v11/special_tokens_map.json
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v11/tokenizer_config.json
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v11/tokenizer.json
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v11/flywheel_model.0.safetensors
dreamgen-opus-v1-2-llam-2622-v11-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-v11-mkmlizer: return self.fget.__get__(instance, owner)()
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: Saving duration: 0.290s
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.464s
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: creating bucket guanaco-reward-models
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: Bucket 's3://guanaco-reward-models/' created
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v11_reward
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v11_reward/config.json
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v11_reward/special_tokens_map.json
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v11_reward/tokenizer_config.json
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v11_reward/vocab.json
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v11_reward/merges.txt
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v11_reward/tokenizer.json
dreamgen-opus-v1-2-llam-2622-v11-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v11_reward/reward.tensors
Job dreamgen-opus-v1-2-llam-2622-v11-mkmlizer completed after 76.41s with status: succeeded
Stopping job with name dreamgen-opus-v1-2-llam-2622-v11-mkmlizer
Pipeline stage MKMLizer completed in 77.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service dreamgen-opus-v1-2-llam-2622-v11
Waiting for inference service dreamgen-opus-v1-2-llam-2622-v11 to be ready
Inference service dreamgen-opus-v1-2-llam-2622-v11 ready after 40.21021127700806s
Pipeline stage ISVCDeployer completed in 45.99s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.161827325820923s
Received healthy response to inference request in 1.2472748756408691s
Received healthy response to inference request in 1.2591934204101562s
Received healthy response to inference request in 1.21881103515625s
Received healthy response to inference request in 1.248460054397583s
5 requests
0 failed requests
5th percentile: 1.2245038032531739
10th percentile: 1.2301965713500977
20th percentile: 1.2415821075439453
30th percentile: 1.247511911392212
40th percentile: 1.2479859828948974
50th percentile: 1.248460054397583
60th percentile: 1.2527534008026122
70th percentile: 1.2570467472076416
80th percentile: 1.4397202014923098
90th percentile: 1.8007737636566163
95th percentile: 1.9813005447387693
99th percentile: 2.1257219696044922
mean time: 1.4271133422851563
Pipeline stage StressChecker completed in 7.78s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
dreamgen-opus-v1-2-llam_2622_v11 status is now deployed due to DeploymentManager action
dreamgen-opus-v1-2-llam_2622_v11 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of dreamgen-opus-v1-2-llam_2622_v11
Running pipeline stage ISVCDeleter
Checking if service dreamgen-opus-v1-2-llam-2622-v11 is running
Tearing down inference service dreamgen-opus-v1-2-llam-2622-v11
Toredown service dreamgen-opus-v1-2-llam-2622-v11
Pipeline stage ISVCDeleter completed in 3.94s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llam-2622-v11/config.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v11/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v11/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v11/tokenizer.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v11/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llam-2622-v11_reward/config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v11_reward/merges.txt from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v11_reward/reward.tensors from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v11_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v11_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v11_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v11_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.96s
dreamgen-opus-v1-2-llam_2622_v11 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics