submission_id: cycy233-l3-brw-v0-c2_v2
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-brw-v0-c2
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: 2024-07-04T01:33:44+00:00
model_name: auto
model_group: cycy233/L3-brw-v0-c2
num_battles: 14356
num_wins: 6926
celo_rating: 1172.25
propriety_score: 0.7103145574250183
propriety_total_count: 6835.0
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-brw-v0-c2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-03
win_ratio: 0.48244636388966283
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-brw-v0-c2-v2-mkmlizer
Waiting for job on cycy233-l3-brw-v0-c2-v2-mkmlizer to finish
cycy233-l3-brw-v0-c2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ /___/ ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ║ ║
cycy233-l3-brw-v0-c2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-brw-v0-c2-v2-mkmlizer: Downloaded to shared memory in 53.740s
cycy233-l3-brw-v0-c2-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-brw-v0-c2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
cycy233-l3-brw-v0-c2-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 62.61it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 76.25it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 111.68it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-brw-v0-c2-v2-mkmlizer: quantized model in 24.899s
cycy233-l3-brw-v0-c2-v2-mkmlizer: Processed model cycy233/L3-brw-v0-c2 in 78.640s
cycy233-l3-brw-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c2-v2/config.json
cycy233-l3-brw-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c2-v2/special_tokens_map.json
cycy233-l3-brw-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c2-v2/tokenizer_config.json
cycy233-l3-brw-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c2-v2/tokenizer.json
cycy233-l3-brw-v0-c2-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-brw-v0-c2-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-brw-v0-c2-v2-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c2-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-brw-v0-c2-v2-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c2-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-brw-v0-c2-v2-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c2-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-brw-v0-c2-v2-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c2-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-brw-v0-c2-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-brw-v0-c2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-brw-v0-c2-v2-mkmlizer: Saving duration: 0.417s
cycy233-l3-brw-v0-c2-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.976s
cycy233-l3-brw-v0-c2-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-brw-v0-c2-v2-mkmlizer: WARNING: Retrying failed request: / ([Errno 110] Connection timed out)
cycy233-l3-brw-v0-c2-v2-mkmlizer: WARNING: Waiting 3 sec...
cycy233-l3-brw-v0-c2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-brw-v0-c2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-brw-v0-c2-v2_reward
cycy233-l3-brw-v0-c2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c2-v2_reward/config.json
cycy233-l3-brw-v0-c2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c2-v2_reward/special_tokens_map.json
cycy233-l3-brw-v0-c2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c2-v2_reward/tokenizer_config.json
cycy233-l3-brw-v0-c2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-brw-v0-c2-v2_reward/merges.txt
cycy233-l3-brw-v0-c2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c2-v2_reward/vocab.json
cycy233-l3-brw-v0-c2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c2-v2_reward/tokenizer.json
Job cycy233-l3-brw-v0-c2-v2-mkmlizer completed after 269.01s with status: succeeded
Stopping job with name cycy233-l3-brw-v0-c2-v2-mkmlizer
Pipeline stage MKMLizer completed in 270.03s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-brw-v0-c2-v2
Waiting for inference service cycy233-l3-brw-v0-c2-v2 to be ready
Inference service cycy233-l3-brw-v0-c2-v2 ready after 40.36143779754639s
Pipeline stage ISVCDeployer completed in 47.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9355084896087646s
Received healthy response to inference request in 1.322782278060913s
Received healthy response to inference request in 1.2964627742767334s
Received healthy response to inference request in 1.2696099281311035s
Received healthy response to inference request in 1.3633360862731934s
5 requests
0 failed requests
5th percentile: 1.2749804973602294
10th percentile: 1.2803510665893554
20th percentile: 1.2910922050476075
30th percentile: 1.3017266750335694
40th percentile: 1.3122544765472413
50th percentile: 1.322782278060913
60th percentile: 1.3390038013458252
70th percentile: 1.3552253246307373
80th percentile: 1.4777705669403076
90th percentile: 1.7066395282745361
95th percentile: 1.8210740089416504
99th percentile: 1.9126215934753419
mean time: 1.4375399112701417
Pipeline stage StressChecker completed in 7.91s
cycy233-l3-brw-v0-c2_v2 status is now deployed due to DeploymentManager action
cycy233-l3-brw-v0-c2_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics