submission_id: dreamgen-opus-v1-2-llam_2622_v10
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}". 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: 2024-04-20T21:42:04+00:00
model_name: dreamgen-opus-v1-2-llam_2622_v10
model_eval_status: success
model_group: dreamgen/opus-v1.2-llama
num_battles: 6533
num_wins: 3632
celo_rating: 1187.36
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: dreamgen-opus-v1-2-llam_2622_v10
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: 0.5559467319761212
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name dreamgen-opus-v1-2-llam-2622-v10-mkmlizer
Waiting for job on dreamgen-opus-v1-2-llam-2622-v10-mkmlizer to finish
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ _____ __ __ ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ /___/ ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ Version: 0.8.10 ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ The license key for the current software has been verified as ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ belonging to: ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ Chai Research Corp. ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ║ ║
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: Downloaded to shared memory in 16.385s
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: quantizing model to /dev/shm/model_cache
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 80.90it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 87.18it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 28.56it/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-v10-mkmlizer: quantized model in 20.052s
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: Processed model dreamgen/opus-v1.2-llama-3-8b in 37.705s
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: creating bucket guanaco-mkml-models
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v10
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v10/config.json
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v10/tokenizer_config.json
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v10/tokenizer.json
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v10/special_tokens_map.json
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/dreamgen-opus-v1-2-llam-2622-v10/flywheel_model.0.safetensors
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
dreamgen-opus-v1-2-llam-2622-v10-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-v10-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llam-2622-v10-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-v10-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llam-2622-v10-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-v10-mkmlizer: warnings.warn(
dreamgen-opus-v1-2-llam-2622-v10-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-v10-mkmlizer: return self.fget.__get__(instance, owner)()
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: Saving duration: 0.294s
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.698s
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: creating bucket guanaco-reward-models
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v10_reward
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v10_reward/special_tokens_map.json
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v10_reward/merges.txt
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v10_reward/tokenizer_config.json
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v10_reward/config.json
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v10_reward/vocab.json
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v10_reward/tokenizer.json
dreamgen-opus-v1-2-llam-2622-v10-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/dreamgen-opus-v1-2-llam-2622-v10_reward/reward.tensors
Job dreamgen-opus-v1-2-llam-2622-v10-mkmlizer completed after 74.36s with status: succeeded
Stopping job with name dreamgen-opus-v1-2-llam-2622-v10-mkmlizer
Pipeline stage MKMLizer completed in 80.80s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service dreamgen-opus-v1-2-llam-2622-v10
Waiting for inference service dreamgen-opus-v1-2-llam-2622-v10 to be ready
Inference service dreamgen-opus-v1-2-llam-2622-v10 ready after 30.17641854286194s
Pipeline stage ISVCDeployer completed in 37.47s
Running pipeline stage StressChecker
Failed to get response for submission dreamgen-opus-v1-2-llama-3-8b_v7: ('http://dreamgen-opus-v1-2-llama-3-8b-v7-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:50136->127.0.0.1:8080: read: connection reset by peer\n')
Received healthy response to inference request in 2.106464385986328s
Received healthy response to inference request in 1.2709739208221436s
Received healthy response to inference request in 1.3526577949523926s
Received healthy response to inference request in 1.2406599521636963s
Received healthy response to inference request in 1.2377793788909912s
5 requests
0 failed requests
5th percentile: 1.2383554935455323
10th percentile: 1.2389316082000732
20th percentile: 1.2400838375091552
30th percentile: 1.2467227458953858
40th percentile: 1.2588483333587646
50th percentile: 1.2709739208221436
60th percentile: 1.3036474704742431
70th percentile: 1.3363210201263427
80th percentile: 1.5034191131591799
90th percentile: 1.804941749572754
95th percentile: 1.9557030677795408
99th percentile: 2.0763121223449708
mean time: 1.4417070865631103
Pipeline stage StressChecker completed in 7.87s
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 0.06s
M-Eval Dataset for topic stay_in_character is loaded
dreamgen-opus-v1-2-llam_2622_v10 status is now deployed due to DeploymentManager action
dreamgen-opus-v1-2-llam_2622_v10 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of dreamgen-opus-v1-2-llam_2622_v10
Running pipeline stage ISVCDeleter
Checking if service dreamgen-opus-v1-2-llam-2622-v10 is running
Tearing down inference service deverdever-heavenly-goat-v8-v3
Toredown service deverdever-heavenly-goat-v8-v3
Pipeline stage ISVCDeleter completed in 5.20s
Tearing down inference service dreamgen-opus-v1-2-llam-2622-v10
Running pipeline stage MKMLModelDeleter
Toredown service dreamgen-opus-v1-2-llam-2622-v10
Cleaning model data from S3
Pipeline stage ISVCDeleter completed in 4.36s
Cleaning model data from model cache
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key deverdever-heavenly-goat-v8-v3/added_tokens.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v10/config.json from bucket guanaco-mkml-models
Deleting key deverdever-heavenly-goat-v8-v3/config.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key deverdever-heavenly-goat-v8-v3/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key deverdever-heavenly-goat-v8-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key deverdever-heavenly-goat-v8-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key deverdever-heavenly-goat-v8-v3/tokenizer.model from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llam-2622-v10/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key deverdever-heavenly-goat-v8-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llam-2622-v10_reward/config.json from bucket guanaco-reward-models
Deleting key deverdever-heavenly-goat-v8-v3_reward/config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v10_reward/merges.txt from bucket guanaco-reward-models
Deleting key deverdever-heavenly-goat-v8-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v10_reward/reward.tensors from bucket guanaco-reward-models
Deleting key deverdever-heavenly-goat-v8-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v10_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key deverdever-heavenly-goat-v8-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v10_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key deverdever-heavenly-goat-v8-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v10_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key deverdever-heavenly-goat-v8-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llam-2622-v10_reward/vocab.json from bucket guanaco-reward-models
Deleting key deverdever-heavenly-goat-v8-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 4.06s
Pipeline stage MKMLModelDeleter completed in 4.80s
dreamgen-opus-v1-2-llam_2622_v10 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics