submission_id: meseca-07062024-m1_v3
developer_uid: nguyenzzz
status: inactive
model_repo: meseca/07062024-m1
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\nThis is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nEngage in a chat with {user_name} while staying in character. Try to flirt with {user_name}. Engage in *roleplay* actions. Describe the scene dramatically.\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: 2024-06-18T01:45:36+00:00
model_name: 07062024-m1-sft
model_group: meseca/07062024-m1
num_battles: 18336
num_wins: 9942
celo_rating: 1208.81
propriety_score: 0.6659741458910434
propriety_total_count: 8664.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: 07062024-m1-sft
ineligible_reason: None
language_model: meseca/07062024-m1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-17
win_ratio: 0.5422120418848168
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meseca-07062024-m1-v3-mkmlizer
Waiting for job on meseca-07062024-m1-v3-mkmlizer to finish
meseca-07062024-m1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-07062024-m1-v3-mkmlizer: ║ _____ __ __ ║
meseca-07062024-m1-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meseca-07062024-m1-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meseca-07062024-m1-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meseca-07062024-m1-v3-mkmlizer: ║ /___/ ║
meseca-07062024-m1-v3-mkmlizer: ║ ║
meseca-07062024-m1-v3-mkmlizer: ║ Version: 0.8.14 ║
meseca-07062024-m1-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meseca-07062024-m1-v3-mkmlizer: ║ https://mk1.ai ║
meseca-07062024-m1-v3-mkmlizer: ║ ║
meseca-07062024-m1-v3-mkmlizer: ║ The license key for the current software has been verified as ║
meseca-07062024-m1-v3-mkmlizer: ║ belonging to: ║
meseca-07062024-m1-v3-mkmlizer: ║ ║
meseca-07062024-m1-v3-mkmlizer: ║ Chai Research Corp. ║
meseca-07062024-m1-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meseca-07062024-m1-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
meseca-07062024-m1-v3-mkmlizer: ║ ║
meseca-07062024-m1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-07062024-m1-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-07062024-m1-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
meseca-07062024-m1-v3-mkmlizer: Downloaded to shared memory in 30.968s
meseca-07062024-m1-v3-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-07062024-m1-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-07062024-m1-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:01, 159.50it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 158.07it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 163.86it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 165.87it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 88.58it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 105.54it/s] Loading 0: 41%|████ | 120/291 [00:00<00:01, 119.86it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 131.81it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 140.20it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 142.65it/s] Loading 0: 65%|██████▍ | 189/291 [00:01<00:01, 89.74it/s] Loading 0: 71%|███████ | 206/291 [00:01<00:00, 104.40it/s] Loading 0: 77%|███████▋ | 223/291 [00:01<00:00, 118.15it/s] Loading 0: 82%|████████▏ | 239/291 [00:01<00:00, 127.27it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 137.49it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 146.34it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 9.91it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-07062024-m1-v3-mkmlizer: quantized model in 22.821s
meseca-07062024-m1-v3-mkmlizer: Processed model meseca/07062024-m1 in 56.302s
meseca-07062024-m1-v3-mkmlizer: creating bucket guanaco-mkml-models
meseca-07062024-m1-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-07062024-m1-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-07062024-m1-v3
meseca-07062024-m1-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-07062024-m1-v3/config.json
meseca-07062024-m1-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-07062024-m1-v3/special_tokens_map.json
meseca-07062024-m1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-07062024-m1-v3/tokenizer_config.json
meseca-07062024-m1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-07062024-m1-v3/tokenizer.json
meseca-07062024-m1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-07062024-m1-v3/flywheel_model.0.safetensors
meseca-07062024-m1-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-07062024-m1-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-07062024-m1-v3-mkmlizer: warnings.warn(
meseca-07062024-m1-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-07062024-m1-v3-mkmlizer: warnings.warn(
meseca-07062024-m1-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-07062024-m1-v3-mkmlizer: warnings.warn(
meseca-07062024-m1-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-07062024-m1-v3-mkmlizer: return self.fget.__get__(instance, owner)()
meseca-07062024-m1-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-07062024-m1-v3-mkmlizer: Saving duration: 0.387s
meseca-07062024-m1-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.272s
meseca-07062024-m1-v3-mkmlizer: creating bucket guanaco-reward-models
meseca-07062024-m1-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-07062024-m1-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-07062024-m1-v3_reward
meseca-07062024-m1-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-07062024-m1-v3_reward/config.json
meseca-07062024-m1-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-07062024-m1-v3_reward/special_tokens_map.json
meseca-07062024-m1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-07062024-m1-v3_reward/tokenizer_config.json
meseca-07062024-m1-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-07062024-m1-v3_reward/vocab.json
meseca-07062024-m1-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-07062024-m1-v3_reward/merges.txt
meseca-07062024-m1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-07062024-m1-v3_reward/tokenizer.json
meseca-07062024-m1-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-07062024-m1-v3_reward/reward.tensors
Job meseca-07062024-m1-v3-mkmlizer completed after 83.24s with status: succeeded
Stopping job with name meseca-07062024-m1-v3-mkmlizer
Pipeline stage MKMLizer completed in 85.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service meseca-07062024-m1-v3
Waiting for inference service meseca-07062024-m1-v3 to be ready
Inference service meseca-07062024-m1-v3 ready after 50.44266438484192s
Pipeline stage ISVCDeployer completed in 57.38s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3329434394836426s
Received healthy response to inference request in 1.3446731567382812s
Received healthy response to inference request in 1.336298942565918s
Received healthy response to inference request in 1.8063397407531738s
Received healthy response to inference request in 1.3742244243621826s
5 requests
0 failed requests
5th percentile: 1.3379737854003906
10th percentile: 1.3396486282348632
20th percentile: 1.3429983139038086
30th percentile: 1.3505834102630616
40th percentile: 1.3624039173126221
50th percentile: 1.3742244243621826
60th percentile: 1.5470705509185791
70th percentile: 1.7199166774749755
80th percentile: 1.9116604804992676
90th percentile: 2.122301959991455
95th percentile: 2.2276226997375486
99th percentile: 2.311879291534424
mean time: 1.6388959407806396
Pipeline stage StressChecker completed in 8.82s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
meseca-07062024-m1_v3 status is now deployed due to DeploymentManager action
meseca-07062024-m1_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics