submission_id: meseca-caspian-1_v3
developer_uid: nguyenzzz
status: inactive
model_repo: meseca/caspian-1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 50, '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{user_name} will roleplay with {bot_name} with persona described as follows:\n{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: 2024-06-03T04:03:29+00:00
model_name: meseca-caspian-11_v1
model_eval_status: success
model_group: meseca/caspian-1
num_battles: 12564
num_wins: 6615
celo_rating: 1200.87
safety_score: 0.95
propriety_score: 0.6217105263157895
propriety_total_count: 304.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: meseca-caspian-11_v1
ineligible_reason: propriety_total_count < 5000
language_model: meseca/caspian-1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-02
win_ratio: 0.5265042979942693
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meseca-caspian-1-v3-mkmlizer
Waiting for job on meseca-caspian-1-v3-mkmlizer to finish
meseca-caspian-1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-caspian-1-v3-mkmlizer: ║ _____ __ __ ║
meseca-caspian-1-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meseca-caspian-1-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meseca-caspian-1-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meseca-caspian-1-v3-mkmlizer: ║ /___/ ║
meseca-caspian-1-v3-mkmlizer: ║ ║
meseca-caspian-1-v3-mkmlizer: ║ Version: 0.8.14 ║
meseca-caspian-1-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meseca-caspian-1-v3-mkmlizer: ║ https://mk1.ai ║
meseca-caspian-1-v3-mkmlizer: ║ ║
meseca-caspian-1-v3-mkmlizer: ║ The license key for the current software has been verified as ║
meseca-caspian-1-v3-mkmlizer: ║ belonging to: ║
meseca-caspian-1-v3-mkmlizer: ║ ║
meseca-caspian-1-v3-mkmlizer: ║ Chai Research Corp. ║
meseca-caspian-1-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meseca-caspian-1-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
meseca-caspian-1-v3-mkmlizer: ║ ║
meseca-caspian-1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-caspian-1-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.
meseca-caspian-1-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
meseca-caspian-1-v3-mkmlizer: Downloaded to shared memory in 17.532s
meseca-caspian-1-v3-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-caspian-1-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-caspian-1-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:02, 2.29s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:03, 4.35it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.59it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.84it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.36it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 36.35it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.10it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 63.24it/s] Loading 0: 44%|████▎ | 127/291 [00:05<00:02, 74.40it/s] Loading 0: 49%|████▉ | 144/291 [00:05<00:01, 91.11it/s] Loading 0: 55%|█████▍ | 159/291 [00:05<00:01, 103.05it/s] Loading 0: 60%|█████▉ | 174/291 [00:06<00:01, 78.50it/s] Loading 0: 65%|██████▌ | 190/291 [00:06<00:01, 92.67it/s] Loading 0: 71%|███████ | 207/291 [00:06<00:00, 108.49it/s] Loading 0: 76%|███████▋ | 222/291 [00:06<00:00, 117.55it/s] Loading 0: 82%|████████▏ | 240/291 [00:06<00:00, 131.70it/s] Loading 0: 89%|████████▊ | 258/291 [00:06<00:00, 142.91it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 94.16it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-caspian-1-v3-mkmlizer: quantized model in 23.050s
meseca-caspian-1-v3-mkmlizer: Processed model meseca/caspian-1 in 43.044s
meseca-caspian-1-v3-mkmlizer: creating bucket guanaco-mkml-models
meseca-caspian-1-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-caspian-1-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-caspian-1-v3
meseca-caspian-1-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-caspian-1-v3/config.json
meseca-caspian-1-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-caspian-1-v3/special_tokens_map.json
meseca-caspian-1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-caspian-1-v3/tokenizer_config.json
meseca-caspian-1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-caspian-1-v3/tokenizer.json
meseca-caspian-1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-caspian-1-v3/flywheel_model.0.safetensors
meseca-caspian-1-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-caspian-1-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.
meseca-caspian-1-v3-mkmlizer: warnings.warn(
meseca-caspian-1-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.
meseca-caspian-1-v3-mkmlizer: warnings.warn(
meseca-caspian-1-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.
meseca-caspian-1-v3-mkmlizer: warnings.warn(
meseca-caspian-1-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()
meseca-caspian-1-v3-mkmlizer: return self.fget.__get__(instance, owner)()
meseca-caspian-1-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-caspian-1-v3-mkmlizer: Saving duration: 0.387s
meseca-caspian-1-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.885s
meseca-caspian-1-v3-mkmlizer: creating bucket guanaco-reward-models
meseca-caspian-1-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-caspian-1-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-caspian-1-v3_reward
meseca-caspian-1-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-caspian-1-v3_reward/config.json
meseca-caspian-1-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-caspian-1-v3_reward/special_tokens_map.json
meseca-caspian-1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-caspian-1-v3_reward/tokenizer_config.json
meseca-caspian-1-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-caspian-1-v3_reward/vocab.json
meseca-caspian-1-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-caspian-1-v3_reward/merges.txt
meseca-caspian-1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-caspian-1-v3_reward/tokenizer.json
meseca-caspian-1-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-caspian-1-v3_reward/reward.tensors
Job meseca-caspian-1-v3-mkmlizer completed after 62.44s with status: succeeded
Stopping job with name meseca-caspian-1-v3-mkmlizer
Pipeline stage MKMLizer completed in 64.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service meseca-caspian-1-v3
Waiting for inference service meseca-caspian-1-v3 to be ready
Inference service meseca-caspian-1-v3 ready after 60.308783531188965s
Pipeline stage ISVCDeployer completed in 66.99s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1142446994781494s
Received healthy response to inference request in 1.369753360748291s
Received healthy response to inference request in 5.714259386062622s
Received healthy response to inference request in 1.2952349185943604s
Received healthy response to inference request in 9.142932176589966s
5 requests
0 failed requests
5th percentile: 1.3101386070251464
10th percentile: 1.3250422954559327
20th percentile: 1.354849672317505
30th percentile: 1.5186516284942626
40th percentile: 1.8164481639862062
50th percentile: 2.1142446994781494
60th percentile: 3.554250574111938
70th percentile: 4.994256448745727
80th percentile: 6.3999939441680915
90th percentile: 7.771463060379029
95th percentile: 8.457197618484496
99th percentile: 9.005785264968871
mean time: 3.927284908294678
Pipeline stage StressChecker completed in 20.23s
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-1_v3 status is now deployed due to DeploymentManager action
meseca-caspian-1_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics