submission_id: meseca-05062024-v1_v1
developer_uid: nguyenzzz
best_of: 16
celo_rating: 1184.59
display_name: meseca-05062024-v1_v1
family_friendly_score: 0.0
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this fictional never-ending roleplay with {user_name}.\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}
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}
is_internal_developer: False
language_model: meseca/05062024-v1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: meseca/05062024-v1
model_name: meseca-05062024-v1_v1
model_num_parameters: 8030261248.0
model_repo: meseca/05062024-v1
model_size: 8B
num_battles: 14723
num_wins: 7710
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-06T14:59:29+00:00
us_pacific_date: 2024-06-06
win_ratio: 0.5236704475989947
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meseca-05062024-v1-v1-mkmlizer
Waiting for job on meseca-05062024-v1-v1-mkmlizer to finish
meseca-05062024-v1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-05062024-v1-v1-mkmlizer: ║ _____ __ __ ║
meseca-05062024-v1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meseca-05062024-v1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meseca-05062024-v1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meseca-05062024-v1-v1-mkmlizer: ║ /___/ ║
meseca-05062024-v1-v1-mkmlizer: ║ ║
meseca-05062024-v1-v1-mkmlizer: ║ Version: 0.8.14 ║
meseca-05062024-v1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meseca-05062024-v1-v1-mkmlizer: ║ https://mk1.ai ║
meseca-05062024-v1-v1-mkmlizer: ║ ║
meseca-05062024-v1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
meseca-05062024-v1-v1-mkmlizer: ║ belonging to: ║
meseca-05062024-v1-v1-mkmlizer: ║ ║
meseca-05062024-v1-v1-mkmlizer: ║ Chai Research Corp. ║
meseca-05062024-v1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meseca-05062024-v1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
meseca-05062024-v1-v1-mkmlizer: ║ ║
meseca-05062024-v1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-05062024-v1-v1-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-05062024-v1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
meseca-05062024-v1-v1-mkmlizer: Downloaded to shared memory in 33.991s
meseca-05062024-v1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-05062024-v1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-05062024-v1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:01, 159.85it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 158.04it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 164.95it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 163.15it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 84.28it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 101.99it/s] Loading 0: 41%|████ | 120/291 [00:00<00:01, 118.35it/s] Loading 0: 46%|████▋ | 135/291 [00:01<00:01, 116.54it/s] Loading 0: 52%|█████▏ | 152/291 [00:01<00:01, 128.98it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 133.46it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 95.94it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 103.87it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 119.20it/s] Loading 0: 82%|████████▏ | 238/291 [00:01<00:00, 132.09it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 140.33it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 141.67it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 10.04it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-05062024-v1-v1-mkmlizer: quantized model in 22.387s
meseca-05062024-v1-v1-mkmlizer: Processed model meseca/05062024-v1 in 58.814s
meseca-05062024-v1-v1-mkmlizer: creating bucket guanaco-mkml-models
meseca-05062024-v1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-05062024-v1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-05062024-v1-v1
meseca-05062024-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-05062024-v1-v1/tokenizer_config.json
meseca-05062024-v1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-05062024-v1-v1/config.json
meseca-05062024-v1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-05062024-v1-v1/special_tokens_map.json
meseca-05062024-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-05062024-v1-v1/tokenizer.json
meseca-05062024-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-05062024-v1-v1/flywheel_model.0.safetensors
meseca-05062024-v1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-05062024-v1-v1-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-05062024-v1-v1-mkmlizer: warnings.warn(
meseca-05062024-v1-v1-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-05062024-v1-v1-mkmlizer: warnings.warn(
meseca-05062024-v1-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.
meseca-05062024-v1-v1-mkmlizer: warnings.warn(
meseca-05062024-v1-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()
meseca-05062024-v1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
meseca-05062024-v1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-05062024-v1-v1-mkmlizer: Saving duration: 0.395s
meseca-05062024-v1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.982s
meseca-05062024-v1-v1-mkmlizer: creating bucket guanaco-reward-models
meseca-05062024-v1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-05062024-v1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-05062024-v1-v1_reward
meseca-05062024-v1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-05062024-v1-v1_reward/config.json
meseca-05062024-v1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-05062024-v1-v1_reward/special_tokens_map.json
meseca-05062024-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-05062024-v1-v1_reward/tokenizer_config.json
meseca-05062024-v1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-05062024-v1-v1_reward/merges.txt
meseca-05062024-v1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-05062024-v1-v1_reward/vocab.json
meseca-05062024-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-05062024-v1-v1_reward/tokenizer.json
meseca-05062024-v1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-05062024-v1-v1_reward/reward.tensors
Job meseca-05062024-v1-v1-mkmlizer completed after 83.6s with status: succeeded
Stopping job with name meseca-05062024-v1-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service meseca-05062024-v1-v1
Waiting for inference service meseca-05062024-v1-v1 to be ready
Inference service meseca-05062024-v1-v1 ready after 40.27346897125244s
Pipeline stage ISVCDeployer completed in 46.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1192588806152344s
Received healthy response to inference request in 1.1877248287200928s
Received healthy response to inference request in 1.2606353759765625s
Received healthy response to inference request in 1.2180285453796387s
Received healthy response to inference request in 1.2940895557403564s
5 requests
0 failed requests
5th percentile: 1.1937855720520019
10th percentile: 1.1998463153839112
20th percentile: 1.2119678020477296
30th percentile: 1.2265499114990235
40th percentile: 1.2435926437377929
50th percentile: 1.2606353759765625
60th percentile: 1.27401704788208
70th percentile: 1.2873987197875976
80th percentile: 1.4591234207153323
90th percentile: 1.7891911506652833
95th percentile: 1.9542250156402585
99th percentile: 2.0862521076202394
mean time: 1.415947437286377
Pipeline stage StressChecker completed in 7.70s
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-05062024-v1_v1 status is now deployed due to DeploymentManager action
meseca-05062024-v1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-05062024-v1_v1
Running pipeline stage ISVCDeleter
Checking if service meseca-05062024-v1-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.76s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-05062024-v1-v1/config.json from bucket guanaco-mkml-models
Deleting key meseca-05062024-v1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-05062024-v1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-05062024-v1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-05062024-v1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-05062024-v1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.83s
meseca-05062024-v1_v1 status is now torndown due to DeploymentManager action