submission_id: cycy233-l3-klee-v0-e2-0_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-klee-v0-e2.0
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': "<|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: 2024-06-28T04:18:39+00:00
model_name: cycy233-l3-klee-v0-e2-0_v1
model_group: cycy233/L3-klee-v0-e2.0
num_battles: 12817
num_wins: 6376
celo_rating: 1184.69
propriety_score: 0.7049206603622375
propriety_total_count: 6239.0
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-klee-v0-e2-0_v1
ineligible_reason: None
language_model: cycy233/L3-klee-v0-e2.0
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-27
win_ratio: 0.4974643052196302
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-klee-v0-e2-0-v1-mkmlizer
Waiting for job on cycy233-l3-klee-v0-e2-0-v1-mkmlizer to finish
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ /___/ ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ║ ║
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-klee-v0-e2-0-v1-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-klee-v0-e2-0-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: Downloaded to shared memory in 24.231s
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: quantized model in 23.669s
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: Processed model cycy233/L3-klee-v0-e2.0 in 50.528s
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-klee-v0-e2-0-v1
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-klee-v0-e2-0-v1/tokenizer_config.json
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-klee-v0-e2-0-v1/config.json
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-klee-v0-e2-0-v1/tokenizer.json
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-klee-v0-e2-0-v1/special_tokens_map.json
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-klee-v0-e2-0-v1/flywheel_model.0.safetensors
Connection pool is full, discarding connection: %s
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-klee-v0-e2-0-v1-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-klee-v0-e2-0-v1-mkmlizer: warnings.warn(
cycy233-l3-klee-v0-e2-0-v1-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-klee-v0-e2-0-v1-mkmlizer: warnings.warn(
cycy233-l3-klee-v0-e2-0-v1-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-v0-e2-0-v1-mkmlizer: warnings.warn(
cycy233-l3-klee-v0-e2-0-v1-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-v0-e2-0-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: Saving duration: 0.552s
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.527s
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v1_reward
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v1_reward/special_tokens_map.json
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v1_reward/tokenizer_config.json
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v1_reward/merges.txt
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v1_reward/config.json
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v1_reward/vocab.json
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v1_reward/tokenizer.json
cycy233-l3-klee-v0-e2-0-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v1_reward/reward.tensors
Job cycy233-l3-klee-v0-e2-0-v1-mkmlizer completed after 83.25s with status: succeeded
Stopping job with name cycy233-l3-klee-v0-e2-0-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.13s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-klee-v0-e2-0-v1
Waiting for inference service cycy233-l3-klee-v0-e2-0-v1 to be ready
Inference service cycy233-l3-klee-v0-e2-0-v1 ready after 50.69627237319946s
Pipeline stage ISVCDeployer completed in 57.45s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3965158462524414s
Received healthy response to inference request in 1.354163408279419s
Received healthy response to inference request in 1.3269665241241455s
Received healthy response to inference request in 1.310337781906128s
Received healthy response to inference request in 1.3667984008789062s
5 requests
0 failed requests
5th percentile: 1.3136635303497315
10th percentile: 1.316989278793335
20th percentile: 1.323640775680542
30th percentile: 1.3324059009552003
40th percentile: 1.3432846546173096
50th percentile: 1.354163408279419
60th percentile: 1.3592174053192139
70th percentile: 1.3642714023590088
80th percentile: 1.5727418899536134
90th percentile: 1.9846288681030275
95th percentile: 2.190572357177734
99th percentile: 2.3553271484375
mean time: 1.550956392288208
Pipeline stage StressChecker completed in 8.44s
cycy233-l3-klee-v0-e2-0_v1 status is now deployed due to DeploymentManager action
cycy233-l3-klee-v0-e2-0_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics