submission_id: cycy233-l3i-base-v0-e3-0_v2
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3i-base-v0-e3.0
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: 2024-06-22T17:13:49+00:00
model_name: base_f
model_group: cycy233/L3i-base-v0-e3.0
num_battles: 19246
num_wins: 9885
celo_rating: 1201.27
propriety_score: 0.7114406321030414
propriety_total_count: 9239.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: base_f
ineligible_reason: None
language_model: cycy233/L3i-base-v0-e3.0
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-22
win_ratio: 0.5136132183310818
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3i-base-v0-e3-0-v2-mkmlizer
Waiting for job on cycy233-l3i-base-v0-e3-0-v2-mkmlizer to finish
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v33: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:37756->127.0.0.1:8080: read: connection reset by peer\n')
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ /___/ ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ belonging to: ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ║ ║
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3i-base-v0-e3-0-v2-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-l3i-base-v0-e3-0-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: Downloaded to shared memory in 20.287s
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 63.43it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 77.27it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 111.79it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: quantized model in 24.212s
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: Processed model cycy233/L3i-base-v0-e3.0 in 47.176s
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3i-base-v0-e3-0-v2/special_tokens_map.json
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3i-base-v0-e3-0-v2/flywheel_model.0.safetensors
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3i-base-v0-e3-0-v2-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-l3i-base-v0-e3-0-v2-mkmlizer: warnings.warn(
cycy233-l3i-base-v0-e3-0-v2-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-l3i-base-v0-e3-0-v2-mkmlizer: warnings.warn(
cycy233-l3i-base-v0-e3-0-v2-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-l3i-base-v0-e3-0-v2-mkmlizer: warnings.warn(
cycy233-l3i-base-v0-e3-0-v2-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-l3i-base-v0-e3-0-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: Saving duration: 0.400s
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.499s
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3i-base-v0-e3-0-v2_reward
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3i-base-v0-e3-0-v2_reward/config.json
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3i-base-v0-e3-0-v2_reward/special_tokens_map.json
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3i-base-v0-e3-0-v2_reward/tokenizer_config.json
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3i-base-v0-e3-0-v2_reward/vocab.json
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3i-base-v0-e3-0-v2_reward/merges.txt
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3i-base-v0-e3-0-v2_reward/tokenizer.json
cycy233-l3i-base-v0-e3-0-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3i-base-v0-e3-0-v2_reward/reward.tensors
Job cycy233-l3i-base-v0-e3-0-v2-mkmlizer completed after 73.05s with status: succeeded
Stopping job with name cycy233-l3i-base-v0-e3-0-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.45s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3i-base-v0-e3-0-v2
Waiting for inference service cycy233-l3i-base-v0-e3-0-v2 to be ready
Inference service cycy233-l3i-base-v0-e3-0-v2 ready after 40.26602292060852s
Pipeline stage ISVCDeployer completed in 46.08s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2144417762756348s
Received healthy response to inference request in 1.248054027557373s
Received healthy response to inference request in 1.2723972797393799s
Received healthy response to inference request in 1.2769389152526855s
Received healthy response to inference request in 1.2584514617919922s
5 requests
0 failed requests
5th percentile: 1.2501335144042969
10th percentile: 1.2522130012512207
20th percentile: 1.2563719749450684
30th percentile: 1.2612406253814696
40th percentile: 1.2668189525604248
50th percentile: 1.2723972797393799
60th percentile: 1.274213933944702
70th percentile: 1.2760305881500245
80th percentile: 1.4644394874572755
90th percentile: 1.8394406318664551
95th percentile: 2.026941204071045
99th percentile: 2.1769416618347166
mean time: 1.454056692123413
Pipeline stage StressChecker completed in 7.92s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cycy233-l3i-base-v0-e3-0_v2 status is now deployed due to DeploymentManager action
cycy233-l3i-base-v0-e3-0_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics