submission_id: cycy233-l3-klee-v0-e2-0_v3
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': "{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: 2024-06-28T06:11:00+00:00
model_name: cycy233-l3-klee-v0-e2-0_v3
model_group: cycy233/L3-klee-v0-e2.0
num_battles: 28156
num_wins: 14768
celo_rating: 1194.91
propriety_score: 0.6951816160118607
propriety_total_count: 13490.0
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_v3
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: 0.5245063219207273
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-klee-v0-e2-0-v3-mkmlizer
Waiting for job on cycy233-l3-klee-v0-e2-0-v3-mkmlizer to finish
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ _____ __ __ ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ /___/ ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ belonging to: ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ║ ║
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-klee-v0-e2-0-v3-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-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: Downloaded to shared memory in 32.546s
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 66.54it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 84.69it/s] Loading 0: 86%|████████▌ | 250/291 [00:02<00:00, 122.16it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 117.59it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: quantized model in 23.660s
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: Processed model cycy233/L3-klee-v0-e2.0 in 58.836s
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-klee-v0-e2-0-v3
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-klee-v0-e2-0-v3/config.json
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-klee-v0-e2-0-v3/tokenizer_config.json
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-klee-v0-e2-0-v3/special_tokens_map.json
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-klee-v0-e2-0-v3/tokenizer.json
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-klee-v0-e2-0-v3/flywheel_model.0.safetensors
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-klee-v0-e2-0-v3-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-v3-mkmlizer: warnings.warn(
cycy233-l3-klee-v0-e2-0-v3-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-v3-mkmlizer: warnings.warn(
cycy233-l3-klee-v0-e2-0-v3-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-v3-mkmlizer: warnings.warn(
cycy233-l3-klee-v0-e2-0-v3-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-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: Saving duration: 0.416s
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.507s
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v3_reward
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v3_reward/special_tokens_map.json
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v3_reward/merges.txt
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v3_reward/tokenizer_config.json
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v3_reward/config.json
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v3_reward/vocab.json
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v3_reward/tokenizer.json
cycy233-l3-klee-v0-e2-0-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-klee-v0-e2-0-v3_reward/reward.tensors
Job cycy233-l3-klee-v0-e2-0-v3-mkmlizer completed after 83.43s with status: succeeded
Stopping job with name cycy233-l3-klee-v0-e2-0-v3-mkmlizer
Pipeline stage MKMLizer completed in 84.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-klee-v0-e2-0-v3
Waiting for inference service cycy233-l3-klee-v0-e2-0-v3 to be ready
Inference service cycy233-l3-klee-v0-e2-0-v3 ready after 40.202836751937866s
Pipeline stage ISVCDeployer completed in 47.19s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1473755836486816s
Received healthy response to inference request in 1.232123851776123s
Received healthy response to inference request in 1.2414205074310303s
Received healthy response to inference request in 2.259800434112549s
Received healthy response to inference request in 1.2575910091400146s
5 requests
0 failed requests
5th percentile: 1.2339831829071044
10th percentile: 1.235842514038086
20th percentile: 1.239561176300049
30th percentile: 1.244654607772827
40th percentile: 1.251122808456421
50th percentile: 1.2575910091400146
60th percentile: 1.6135048389434814
70th percentile: 1.9694186687469482
80th percentile: 2.1698605537414553
90th percentile: 2.214830493927002
95th percentile: 2.237315464019775
99th percentile: 2.255303440093994
mean time: 1.6276622772216798
Pipeline stage StressChecker completed in 8.83s
cycy233-l3-klee-v0-e2-0_v3 status is now deployed due to DeploymentManager action
cycy233-l3-klee-v0-e2-0_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics