submission_id: cycy233-l3-base-v7-c1_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-base-v7-c1
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: 2024-07-03T03:01:15+00:00
model_name: auto
model_group: cycy233/L3-base-v7-c1
num_battles: 13598
num_wins: 7053
celo_rating: 1193.26
propriety_score: 0.7007481296758105
propriety_total_count: 6416.0
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-base-v7-c1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-02
win_ratio: 0.51867921753199
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-base-v7-c1-v1-mkmlizer
Waiting for job on cycy233-l3-base-v7-c1-v1-mkmlizer to finish
cycy233-l3-base-v7-c1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ /___/ ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ║ ║
cycy233-l3-base-v7-c1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-base-v7-c1-v1-mkmlizer: Downloaded to shared memory in 37.242s
cycy233-l3-base-v7-c1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-base-v7-c1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-base-v7-c1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 63.97it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 74.45it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 108.62it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-base-v7-c1-v1-mkmlizer: quantized model in 22.162s
cycy233-l3-base-v7-c1-v1-mkmlizer: Processed model cycy233/L3-base-v7-c1 in 59.405s
cycy233-l3-base-v7-c1-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-base-v7-c1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-base-v7-c1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-base-v7-c1-v1
cycy233-l3-base-v7-c1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-base-v7-c1-v1/special_tokens_map.json
cycy233-l3-base-v7-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-base-v7-c1-v1/tokenizer_config.json
cycy233-l3-base-v7-c1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-base-v7-c1-v1/config.json
cycy233-l3-base-v7-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-base-v7-c1-v1/tokenizer.json
cycy233-l3-base-v7-c1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-base-v7-c1-v1/flywheel_model.0.safetensors
cycy233-l3-base-v7-c1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-base-v7-c1-v1-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-base-v7-c1-v1-mkmlizer: warnings.warn(
cycy233-l3-base-v7-c1-v1-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-base-v7-c1-v1-mkmlizer: warnings.warn(
cycy233-l3-base-v7-c1-v1-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-base-v7-c1-v1-mkmlizer: warnings.warn(
cycy233-l3-base-v7-c1-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-base-v7-c1-v1-mkmlizer: warnings.warn(
cycy233-l3-base-v7-c1-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-base-v7-c1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-base-v7-c1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-base-v7-c1-v1-mkmlizer: Saving duration: 0.286s
cycy233-l3-base-v7-c1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.231s
cycy233-l3-base-v7-c1-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-base-v7-c1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-base-v7-c1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-base-v7-c1-v1_reward
cycy233-l3-base-v7-c1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-base-v7-c1-v1_reward/special_tokens_map.json
cycy233-l3-base-v7-c1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-base-v7-c1-v1_reward/config.json
cycy233-l3-base-v7-c1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-base-v7-c1-v1_reward/merges.txt
cycy233-l3-base-v7-c1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-base-v7-c1-v1_reward/tokenizer_config.json
cycy233-l3-base-v7-c1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-base-v7-c1-v1_reward/vocab.json
cycy233-l3-base-v7-c1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-base-v7-c1-v1_reward/tokenizer.json
cycy233-l3-base-v7-c1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-base-v7-c1-v1_reward/reward.tensors
Job cycy233-l3-base-v7-c1-v1-mkmlizer completed after 93.87s with status: succeeded
Stopping job with name cycy233-l3-base-v7-c1-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-base-v7-c1-v1
Waiting for inference service cycy233-l3-base-v7-c1-v1 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service cycy233-l3-base-v7-c1-v1 ready after 100.57830762863159s
Pipeline stage ISVCDeployer completed in 107.76s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0885369777679443s
Received healthy response to inference request in 1.238206386566162s
Received healthy response to inference request in 1.2555663585662842s
Received healthy response to inference request in 1.2847261428833008s
Received healthy response to inference request in 1.2456328868865967s
5 requests
0 failed requests
5th percentile: 1.239691686630249
10th percentile: 1.2411769866943358
20th percentile: 1.2441475868225098
30th percentile: 1.2476195812225341
40th percentile: 1.2515929698944093
50th percentile: 1.2555663585662842
60th percentile: 1.2672302722930908
70th percentile: 1.2788941860198975
80th percentile: 1.4454883098602296
90th percentile: 1.767012643814087
95th percentile: 1.9277748107910155
99th percentile: 2.0563845443725586
mean time: 1.4225337505340576
Pipeline stage StressChecker completed in 7.93s
cycy233-l3-base-v7-c1_v1 status is now deployed due to DeploymentManager action
cycy233-l3-base-v7-c1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics