submission_id: cycy233-l3-base-v5-e1-5_v9
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-base-v5-e1.5
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-06-25T02:01:48+00:00
model_name: cycy233-l3-base-v5-e1-5_v9
model_group: cycy233/L3-base-v5-e1.5
num_battles: 12574
num_wins: 6376
celo_rating: 1191.82
propriety_score: 0.7175444481717544
propriety_total_count: 5962.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cycy233-l3-base-v5-e1-5_v9
ineligible_reason: None
language_model: cycy233/L3-base-v5-e1.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-24
win_ratio: 0.5070780976618419
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-base-v5-e1-5-v9-mkmlizer
Waiting for job on cycy233-l3-base-v5-e1-5-v9-mkmlizer to finish
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ _____ __ __ ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ /___/ ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ belonging to: ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ║ ║
cycy233-l3-base-v5-e1-5-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-base-v5-e1-5-v9-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.
cycy233-l3-base-v5-e1-5-v9-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-base-v5-e1-5-v9-mkmlizer: Downloaded to shared memory in 21.659s
cycy233-l3-base-v5-e1-5-v9-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-base-v5-e1-5-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-base-v5-e1-5-v9-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 73.06it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 83.41it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 123.18it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-base-v5-e1-5-v9-mkmlizer: quantized model in 24.319s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
cycy233-l3-base-v5-e1-5-v9-mkmlizer: Processed model cycy233/L3-base-v5-e1.5 in 48.619s
cycy233-l3-base-v5-e1-5-v9-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-base-v5-e1-5-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-base-v5-e1-5-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-base-v5-e1-5-v9
cycy233-l3-base-v5-e1-5-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-base-v5-e1-5-v9/config.json
cycy233-l3-base-v5-e1-5-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-base-v5-e1-5-v9/special_tokens_map.json
cycy233-l3-base-v5-e1-5-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-base-v5-e1-5-v9/tokenizer_config.json
cycy233-l3-base-v5-e1-5-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-base-v5-e1-5-v9/tokenizer.json
cycy233-l3-base-v5-e1-5-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-base-v5-e1-5-v9/flywheel_model.0.safetensors
cycy233-l3-base-v5-e1-5-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-base-v5-e1-5-v9-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.
cycy233-l3-base-v5-e1-5-v9-mkmlizer: warnings.warn(
cycy233-l3-base-v5-e1-5-v9-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.
cycy233-l3-base-v5-e1-5-v9-mkmlizer: warnings.warn(
cycy233-l3-base-v5-e1-5-v9-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.
cycy233-l3-base-v5-e1-5-v9-mkmlizer: warnings.warn(
cycy233-l3-base-v5-e1-5-v9-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()
cycy233-l3-base-v5-e1-5-v9-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-base-v5-e1-5-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-base-v5-e1-5-v9-mkmlizer: Saving duration: 0.407s
cycy233-l3-base-v5-e1-5-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.363s
cycy233-l3-base-v5-e1-5-v9-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-base-v5-e1-5-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-base-v5-e1-5-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-base-v5-e1-5-v9_reward
cycy233-l3-base-v5-e1-5-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-base-v5-e1-5-v9_reward/config.json
cycy233-l3-base-v5-e1-5-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-base-v5-e1-5-v9_reward/special_tokens_map.json
cycy233-l3-base-v5-e1-5-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-base-v5-e1-5-v9_reward/tokenizer_config.json
cycy233-l3-base-v5-e1-5-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-base-v5-e1-5-v9_reward/vocab.json
cycy233-l3-base-v5-e1-5-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-base-v5-e1-5-v9_reward/merges.txt
cycy233-l3-base-v5-e1-5-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-base-v5-e1-5-v9_reward/tokenizer.json
cycy233-l3-base-v5-e1-5-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-base-v5-e1-5-v9_reward/reward.tensors
Job cycy233-l3-base-v5-e1-5-v9-mkmlizer completed after 73.29s with status: succeeded
Stopping job with name cycy233-l3-base-v5-e1-5-v9-mkmlizer
Pipeline stage MKMLizer completed in 73.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-base-v5-e1-5-v9
Waiting for inference service cycy233-l3-base-v5-e1-5-v9 to be ready
Failed to get response for submission cgato-thesalt-rp-l3-8b-d_2881_v1: ('http://cgato-thesalt-rp-l3-8b-d-2881-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service cycy233-l3-base-v5-e1-5-v9 ready after 40.2045795917511s
Pipeline stage ISVCDeployer completed in 46.00s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1669065952301025s
Received healthy response to inference request in 1.2701070308685303s
Received healthy response to inference request in 1.2565248012542725s
Received healthy response to inference request in 1.269378662109375s
Received healthy response to inference request in 1.2755279541015625s
5 requests
0 failed requests
5th percentile: 1.2590955734252929
10th percentile: 1.2616663455963135
20th percentile: 1.2668078899383546
30th percentile: 1.269524335861206
40th percentile: 1.2698156833648682
50th percentile: 1.2701070308685303
60th percentile: 1.2722754001617431
70th percentile: 1.274443769454956
80th percentile: 1.4538036823272706
90th percentile: 1.8103551387786867
95th percentile: 1.9886308670043944
99th percentile: 2.131251449584961
mean time: 1.4476890087127685
Pipeline stage StressChecker completed in 8.06s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
cycy233-l3-base-v5-e1-5_v9 status is now deployed due to DeploymentManager action
cycy233-l3-base-v5-e1-5_v9 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics