submission_id: cycy233-l3-base-v2-e2-5_v2
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-base-v2-e2.5
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': True}
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': True}
timestamp: 2024-06-21T14:24:27+00:00
model_name: base
model_group: cycy233/L3-base-v2-e2.5
num_battles: 26233
num_wins: 13545
celo_rating: 1199.36
propriety_score: 0.7127693535514764
propriety_total_count: 12530.0
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
ineligible_reason: None
language_model: cycy233/L3-base-v2-e2.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-21
win_ratio: 0.5163343879845995
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-base-v2-e2-5-v2-mkmlizer
Waiting for job on cycy233-l3-base-v2-e2-5-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', 'upstream connect error or disconnect/reset before headers. reset reason: overflow')
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ /___/ ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ║ ║
cycy233-l3-base-v2-e2-5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-base-v2-e2-5-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-l3-base-v2-e2-5-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-base-v2-e2-5-v2-mkmlizer: Downloaded to shared memory in 18.628s
cycy233-l3-base-v2-e2-5-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-base-v2-e2-5-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-base-v2-e2-5-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 73.48it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 87.33it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 129.20it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-base-v2-e2-5-v2-mkmlizer: quantized model in 23.737s
cycy233-l3-base-v2-e2-5-v2-mkmlizer: Processed model cycy233/L3-base-v2-e2.5 in 44.828s
cycy233-l3-base-v2-e2-5-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-base-v2-e2-5-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-base-v2-e2-5-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-base-v2-e2-5-v2
cycy233-l3-base-v2-e2-5-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-base-v2-e2-5-v2/config.json
cycy233-l3-base-v2-e2-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-base-v2-e2-5-v2/tokenizer_config.json
cycy233-l3-base-v2-e2-5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-base-v2-e2-5-v2/special_tokens_map.json
cycy233-l3-base-v2-e2-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-base-v2-e2-5-v2/tokenizer.json
cycy233-l3-base-v2-e2-5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-base-v2-e2-5-v2/flywheel_model.0.safetensors
cycy233-l3-base-v2-e2-5-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-base-v2-e2-5-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-l3-base-v2-e2-5-v2-mkmlizer: warnings.warn(
cycy233-l3-base-v2-e2-5-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-l3-base-v2-e2-5-v2-mkmlizer: warnings.warn(
cycy233-l3-base-v2-e2-5-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-l3-base-v2-e2-5-v2-mkmlizer: warnings.warn(
cycy233-l3-base-v2-e2-5-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-l3-base-v2-e2-5-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-base-v2-e2-5-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-base-v2-e2-5-v2-mkmlizer: Saving duration: 0.394s
cycy233-l3-base-v2-e2-5-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.881s
cycy233-l3-base-v2-e2-5-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-base-v2-e2-5-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-base-v2-e2-5-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-base-v2-e2-5-v2_reward
cycy233-l3-base-v2-e2-5-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-base-v2-e2-5-v2_reward/config.json
cycy233-l3-base-v2-e2-5-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-base-v2-e2-5-v2_reward/special_tokens_map.json
cycy233-l3-base-v2-e2-5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-base-v2-e2-5-v2_reward/tokenizer_config.json
cycy233-l3-base-v2-e2-5-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-base-v2-e2-5-v2_reward/vocab.json
cycy233-l3-base-v2-e2-5-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-base-v2-e2-5-v2_reward/merges.txt
cycy233-l3-base-v2-e2-5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-base-v2-e2-5-v2_reward/tokenizer.json
cycy233-l3-base-v2-e2-5-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-base-v2-e2-5-v2_reward/reward.tensors
Job cycy233-l3-base-v2-e2-5-v2-mkmlizer completed after 73.35s with status: succeeded
Stopping job with name cycy233-l3-base-v2-e2-5-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-base-v2-e2-5-v2
Waiting for inference service cycy233-l3-base-v2-e2-5-v2 to be ready
Inference service cycy233-l3-base-v2-e2-5-v2 ready after 50.42532229423523s
Pipeline stage ISVCDeployer completed in 56.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1449930667877197s
Received healthy response to inference request in 2.668795585632324s
Received healthy response to inference request in 3.7094407081604004s
Received healthy response to inference request in 2.183093309402466s
Received healthy response to inference request in 1.0900685787200928s
5 requests
0 failed requests
5th percentile: 1.3010534763336181
10th percentile: 1.5120383739471435
20th percentile: 1.9340081691741944
30th percentile: 2.152613115310669
40th percentile: 2.1678532123565675
50th percentile: 2.183093309402466
60th percentile: 2.377374219894409
70th percentile: 2.5716551303863526
80th percentile: 2.8769246101379395
90th percentile: 3.29318265914917
95th percentile: 3.501311683654785
99th percentile: 3.6678149032592775
mean time: 2.3592782497406004
Pipeline stage StressChecker completed in 12.50s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
cycy233-l3-base-v2-e2-5_v2 status is now deployed due to DeploymentManager action
cycy233-l3-base-v2-e2-5_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics