submission_id: cycy233-l3-klee-v2-e1-5_v2
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-klee-v2-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', '<|end_header_id|>', '<|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\n{bot_name}'s 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\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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: 2024-07-02T02:51:27+00:00
model_name: auto
model_group: cycy233/L3-klee-v2-e1.5
num_battles: 11262
num_wins: 5777
celo_rating: 1183.45
propriety_score: 0.7055439330543933
propriety_total_count: 5736.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
ineligible_reason: None
language_model: cycy233/L3-klee-v2-e1.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-01
win_ratio: 0.5129639495649085
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-klee-v2-e1-5-v2-mkmlizer
Waiting for job on cycy233-l3-klee-v2-e1-5-v2-mkmlizer to finish
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ /___/ ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ║ ║
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: Downloaded to shared memory in 23.125s
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 77.12it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 87.70it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 129.02it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: quantized model in 23.650s
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: Processed model cycy233/L3-klee-v2-e1.5 in 46.776s
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-klee-v2-e1-5-v2
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-klee-v2-e1-5-v2/flywheel_model.0.safetensors
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: warnings.warn(
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: warnings.warn(
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: warnings.warn(
cycy233-l3-klee-v2-e1-5-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-klee-v2-e1-5-v2-mkmlizer: warnings.warn(
cycy233-l3-klee-v2-e1-5-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-klee-v2-e1-5-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: Saving duration: 1.615s
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.450s
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-klee-v2-e1-5-v2_reward
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-klee-v2-e1-5-v2_reward/special_tokens_map.json
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-klee-v2-e1-5-v2_reward/tokenizer_config.json
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-klee-v2-e1-5-v2_reward/merges.txt
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-klee-v2-e1-5-v2_reward/config.json
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-klee-v2-e1-5-v2_reward/vocab.json
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-klee-v2-e1-5-v2_reward/tokenizer.json
cycy233-l3-klee-v2-e1-5-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-klee-v2-e1-5-v2_reward/reward.tensors
Job cycy233-l3-klee-v2-e1-5-v2-mkmlizer completed after 140.9s with status: succeeded
Stopping job with name cycy233-l3-klee-v2-e1-5-v2-mkmlizer
Pipeline stage MKMLizer completed in 141.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-klee-v2-e1-5-v2
Waiting for inference service cycy233-l3-klee-v2-e1-5-v2 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service cycy233-l3-klee-v2-e1-5-v2 ready after 50.244877099990845s
Pipeline stage ISVCDeployer completed in 57.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.163104295730591s
Received healthy response to inference request in 1.4228589534759521s
Received healthy response to inference request in 1.376718282699585s
Received healthy response to inference request in 1.3536522388458252s
Received healthy response to inference request in 1.4161410331726074s
5 requests
0 failed requests
5th percentile: 1.3582654476165772
10th percentile: 1.3628786563873292
20th percentile: 1.372105073928833
30th percentile: 1.3846028327941895
40th percentile: 1.4003719329833983
50th percentile: 1.4161410331726074
60th percentile: 1.4188282012939453
70th percentile: 1.4215153694152831
80th percentile: 1.57090802192688
90th percentile: 1.8670061588287354
95th percentile: 2.015055227279663
99th percentile: 2.133494482040405
mean time: 1.546494960784912
Pipeline stage StressChecker completed in 8.51s
cycy233-l3-klee-v2-e1-5_v2 status is now deployed due to DeploymentManager action
cycy233-l3-klee-v2-e1-5_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics