submission_id: dreamgen-opus-v1-2-llama-3-8b_v7
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': 0.9, '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}". 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: 2024-04-20T20:12:46+00:00
model_name: Dream-8B
model_eval_status: success
model_group: dreamgen/opus-v1.2-llama
num_battles: 6056
num_wins: 3309
celo_rating: 1180.56
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: 0.5464002642007926
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer
Waiting for job on dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer to finish
Stopping job with name dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer
%s, retrying in %s seconds...
Starting job with name dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer
Waiting for job on dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer to finish
Stopping job with name dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer
%s, retrying in %s seconds...
Starting job with name dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer
Failed to get response for submission anhnv125-llama-op-v17-1_v27: HTTPConnectionPool(host='anhnv125-llama-op-v17-1-v27-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud', port=80): Read timed out. (read timeout=5.5)
Waiting for job on dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer to finish
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ _____ __ __ ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ /___/ ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ Version: 0.8.10 ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ The license key for the current software has been verified as ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ belonging to: ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ Chai Research Corp. ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ║ ║
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
dreamgen-opus-v1-2-llama-3-8b-v7-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-v7-mkmlizer: warnings.warn(warning_message, FutureWarning)
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: Downloaded to shared memory in 19.679s
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: quantizing model to /dev/shm/model_cache
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 129.30it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 132.52it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 27.49it/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-v7-mkmlizer: quantized model in 19.429s
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: Processed model dreamgen/opus-v1.2-llama-3-8b in 40.208s
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: creating bucket guanaco-mkml-models
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v7
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v7/config.json
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v7/special_tokens_map.json
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v7/tokenizer_config.json
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v7/tokenizer.json
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/dreamgen-opus-v1-2-llama-3-8b-v7/flywheel_model.0.safetensors
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
dreamgen-opus-v1-2-llama-3-8b-v7-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-v7-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llama-3-8b-v7-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-v7-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llama-3-8b-v7-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-v7-mkmlizer: return self.fget.__get__(instance, owner)()
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: Saving duration: 0.241s
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.903s
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: creating bucket guanaco-reward-models
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v7_reward
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v7_reward/config.json
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v7_reward/tokenizer_config.json
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v7_reward/special_tokens_map.json
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v7_reward/merges.txt
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v7_reward/vocab.json
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v7_reward/tokenizer.json
dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/dreamgen-opus-v1-2-llama-3-8b-v7_reward/reward.tensors
Job dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer completed after 83.32s with status: succeeded
Stopping job with name dreamgen-opus-v1-2-llama-3-8b-v7-mkmlizer
Pipeline stage MKMLizer completed in 89.13s
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-v7
Waiting for inference service dreamgen-opus-v1-2-llama-3-8b-v7 to be ready
Inference service dreamgen-opus-v1-2-llama-3-8b-v7 ready after 30.208847999572754s
Pipeline stage ISVCDeployer completed in 37.62s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0872907638549805s
Received healthy response to inference request in 1.2436318397521973s
Received healthy response to inference request in 1.2421894073486328s
Received healthy response to inference request in 1.2415308952331543s
Received healthy response to inference request in 1.2712759971618652s
5 requests
0 failed requests
5th percentile: 1.24166259765625
10th percentile: 1.2417943000793457
20th percentile: 1.242057704925537
30th percentile: 1.2424778938293457
40th percentile: 1.2430548667907715
50th percentile: 1.2436318397521973
60th percentile: 1.2546895027160645
70th percentile: 1.2657471656799317
80th percentile: 1.4344789505004885
90th percentile: 1.7608848571777345
95th percentile: 1.9240878105163572
99th percentile: 2.0546501731872557
mean time: 1.417183780670166
Pipeline stage StressChecker completed in 7.78s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
dreamgen-opus-v1-2-llama-3-8b_v7 status is now deployed due to DeploymentManager action
dreamgen-opus-v1-2-llama-3-8b_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of dreamgen-opus-v1-2-llama-3-8b_v7
Running pipeline stage ISVCDeleter
Checking if service dreamgen-opus-v1-2-llama-3-8b-v7 is running
Tearing down inference service dreamgen-opus-v1-2-llama-3-8b-v7
Toredown service dreamgen-opus-v1-2-llama-3-8b-v7
Pipeline stage ISVCDeleter completed in 3.83s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llama-3-8b-v7/config.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llama-3-8b-v7_reward/config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.28s
dreamgen-opus-v1-2-llama-3-8b_v7 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics