submission_id: meseca-caspian-0_v2
developer_uid: nguyenzzz
status: inactive
model_repo: meseca/caspian-0
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, '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': "<|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: 2024-06-08T15:48:53+00:00
model_name: kkk
model_eval_status: success
model_group: meseca/caspian-0
num_battles: 9622
num_wins: 5185
celo_rating: 1208.02
safety_score: 0.94
propriety_score: 0.6623376623376623
propriety_total_count: 770.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: kkk
ineligible_reason: propriety_total_count < 5000
language_model: meseca/caspian-0
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-08
win_ratio: 0.5388692579505301
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meseca-caspian-0-v2-mkmlizer
Waiting for job on meseca-caspian-0-v2-mkmlizer to finish
meseca-caspian-0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-caspian-0-v2-mkmlizer: ║ _____ __ __ ║
meseca-caspian-0-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meseca-caspian-0-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meseca-caspian-0-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meseca-caspian-0-v2-mkmlizer: ║ /___/ ║
meseca-caspian-0-v2-mkmlizer: ║ ║
meseca-caspian-0-v2-mkmlizer: ║ Version: 0.8.14 ║
meseca-caspian-0-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meseca-caspian-0-v2-mkmlizer: ║ https://mk1.ai ║
meseca-caspian-0-v2-mkmlizer: ║ ║
meseca-caspian-0-v2-mkmlizer: ║ The license key for the current software has been verified as ║
meseca-caspian-0-v2-mkmlizer: ║ belonging to: ║
meseca-caspian-0-v2-mkmlizer: ║ ║
meseca-caspian-0-v2-mkmlizer: ║ Chai Research Corp. ║
meseca-caspian-0-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meseca-caspian-0-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
meseca-caspian-0-v2-mkmlizer: ║ ║
meseca-caspian-0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-caspian-0-v2-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.
meseca-caspian-0-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
meseca-caspian-0-v2-mkmlizer: Downloaded to shared memory in 34.577s
meseca-caspian-0-v2-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-caspian-0-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-caspian-0-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:24, 2.37s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:10, 3.90it/s] Loading 0: 11%|█ | 31/291 [00:04<00:24, 10.48it/s] Loading 0: 14%|█▍ | 42/291 [00:05<00:15, 15.82it/s] Loading 0: 20%|██ | 59/291 [00:05<00:08, 26.56it/s] Loading 0: 25%|██▍ | 72/291 [00:05<00:08, 27.06it/s] Loading 0: 30%|██▉ | 86/291 [00:05<00:05, 36.84it/s] Loading 0: 34%|███▍ | 99/291 [00:05<00:04, 47.06it/s] Loading 0: 38%|███▊ | 112/291 [00:05<00:03, 58.42it/s] Loading 0: 43%|████▎ | 124/291 [00:06<00:02, 67.42it/s] Loading 0: 48%|████▊ | 139/291 [00:06<00:01, 82.17it/s] Loading 0: 52%|█████▏ | 152/291 [00:06<00:01, 89.58it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:02, 59.68it/s] Loading 0: 60%|██████ | 176/291 [00:06<00:01, 63.97it/s] Loading 0: 64%|██████▍ | 186/291 [00:06<00:01, 68.98it/s] Loading 0: 69%|██████▉ | 202/291 [00:07<00:01, 85.78it/s] Loading 0: 73%|███████▎ | 213/291 [00:07<00:00, 88.77it/s] Loading 0: 79%|███████▊ | 229/291 [00:07<00:00, 102.42it/s] Loading 0: 83%|████████▎ | 241/291 [00:07<00:00, 103.05it/s] Loading 0: 88%|████████▊ | 256/291 [00:07<00:00, 110.28it/s] Loading 0: 92%|█████████▏| 268/291 [00:07<00:00, 60.29it/s] Loading 0: 97%|█████████▋| 283/291 [00:08<00:00, 73.83it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-caspian-0-v2-mkmlizer: quantized model in 26.791s
meseca-caspian-0-v2-mkmlizer: Processed model meseca/caspian-0 in 64.259s
meseca-caspian-0-v2-mkmlizer: creating bucket guanaco-mkml-models
meseca-caspian-0-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-caspian-0-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-caspian-0-v2
meseca-caspian-0-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-caspian-0-v2/config.json
meseca-caspian-0-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-caspian-0-v2/special_tokens_map.json
meseca-caspian-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-caspian-0-v2/tokenizer_config.json
meseca-caspian-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-caspian-0-v2/tokenizer.json
meseca-caspian-0-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-caspian-0-v2/flywheel_model.0.safetensors
meseca-caspian-0-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-caspian-0-v2-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.
meseca-caspian-0-v2-mkmlizer: warnings.warn(
meseca-caspian-0-v2-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.
meseca-caspian-0-v2-mkmlizer: warnings.warn(
meseca-caspian-0-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.
meseca-caspian-0-v2-mkmlizer: warnings.warn(
meseca-caspian-0-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()
meseca-caspian-0-v2-mkmlizer: return self.fget.__get__(instance, owner)()
meseca-caspian-0-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-caspian-0-v2-mkmlizer: Saving duration: 0.400s
meseca-caspian-0-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.910s
meseca-caspian-0-v2-mkmlizer: creating bucket guanaco-reward-models
meseca-caspian-0-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-caspian-0-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-caspian-0-v2_reward
meseca-caspian-0-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-caspian-0-v2_reward/config.json
meseca-caspian-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-caspian-0-v2_reward/tokenizer_config.json
meseca-caspian-0-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-caspian-0-v2_reward/special_tokens_map.json
meseca-caspian-0-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-caspian-0-v2_reward/merges.txt
meseca-caspian-0-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-caspian-0-v2_reward/vocab.json
meseca-caspian-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-caspian-0-v2_reward/tokenizer.json
meseca-caspian-0-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-caspian-0-v2_reward/reward.tensors
Job meseca-caspian-0-v2-mkmlizer completed after 93.74s with status: succeeded
Stopping job with name meseca-caspian-0-v2-mkmlizer
Pipeline stage MKMLizer completed in 97.01s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service meseca-caspian-0-v2
Waiting for inference service meseca-caspian-0-v2 to be ready
Inference service meseca-caspian-0-v2 ready after 40.24655103683472s
Pipeline stage ISVCDeployer completed in 46.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.182080030441284s
Received healthy response to inference request in 1.3640947341918945s
Received healthy response to inference request in 2.180178165435791s
Received healthy response to inference request in 1.3283662796020508s
Received healthy response to inference request in 1.274472951889038s
5 requests
0 failed requests
5th percentile: 1.2852516174316406
10th percentile: 1.2960302829742432
20th percentile: 1.3175876140594482
30th percentile: 1.3355119705200196
40th percentile: 1.349803352355957
50th percentile: 1.3640947341918945
60th percentile: 1.690528106689453
70th percentile: 2.0169614791870116
80th percentile: 2.1805585384368897
90th percentile: 2.1813192844390867
95th percentile: 2.1816996574401855
99th percentile: 2.1820039558410644
mean time: 1.6658384323120117
Pipeline stage StressChecker completed in 9.23s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
meseca-caspian-0_v2 status is now deployed due to DeploymentManager action
meseca-caspian-0_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics