submission_id: setiaku-run2-modelstock_v2
developer_uid: sao10k
status: inactive
model_repo: Setiaku/Run2-ModelStock
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n,', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], '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|>[{bot_name}]<|end_header_id|>\n\n{message}<|eot_id|>', 'user_template': '<|start_header_id|>[{user_name}]<|end_header_id|>\n\n{message}<|eot_id|>', 'response_template': '<|start_header_id|>[{bot_name}]<|end_header_id|>\n\n', 'truncate_by_message': True}
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: 2024-05-28T15:34:14+00:00
model_name: L3-Run-1-Formatted-Test
model_eval_status: success
model_group: Setiaku/Run2-ModelStock
num_battles: 14421
num_wins: 7627
celo_rating: 1196.67
safety_score: 0.98
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: L3-Run-1-Formatted-Test
ineligible_reason: propriety_total_count < 5000
language_model: Setiaku/Run2-ModelStock
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-28
win_ratio: 0.52888149226822
Resubmit model
Running pipeline stage MKMLizer
Starting job with name setiaku-run2-modelstock-v2-mkmlizer
Waiting for job on setiaku-run2-modelstock-v2-mkmlizer to finish
Stopping job with name setiaku-run2-modelstock-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name setiaku-run2-modelstock-v2-mkmlizer
Waiting for job on setiaku-run2-modelstock-v2-mkmlizer to finish
setiaku-run2-modelstock-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
setiaku-run2-modelstock-v2-mkmlizer: ║ _____ __ __ ║
setiaku-run2-modelstock-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
setiaku-run2-modelstock-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
setiaku-run2-modelstock-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
setiaku-run2-modelstock-v2-mkmlizer: ║ /___/ ║
setiaku-run2-modelstock-v2-mkmlizer: ║ ║
setiaku-run2-modelstock-v2-mkmlizer: ║ Version: 0.8.14 ║
setiaku-run2-modelstock-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
setiaku-run2-modelstock-v2-mkmlizer: ║ https://mk1.ai ║
setiaku-run2-modelstock-v2-mkmlizer: ║ ║
setiaku-run2-modelstock-v2-mkmlizer: ║ The license key for the current software has been verified as ║
setiaku-run2-modelstock-v2-mkmlizer: ║ belonging to: ║
setiaku-run2-modelstock-v2-mkmlizer: ║ ║
setiaku-run2-modelstock-v2-mkmlizer: ║ Chai Research Corp. ║
setiaku-run2-modelstock-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
setiaku-run2-modelstock-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
setiaku-run2-modelstock-v2-mkmlizer: ║ ║
setiaku-run2-modelstock-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
setiaku-run2-modelstock-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.
setiaku-run2-modelstock-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
setiaku-run2-modelstock-v2-mkmlizer: Downloaded to shared memory in 43.638s
setiaku-run2-modelstock-v2-mkmlizer: quantizing model to /dev/shm/model_cache
setiaku-run2-modelstock-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
setiaku-run2-modelstock-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:31, 2.39s/it] Loading 0: 4%|▍ | 13/291 [00:04<01:17, 3.58it/s] Loading 0: 8%|▊ | 23/291 [00:05<00:36, 7.36it/s] Loading 0: 12%|█▏ | 34/291 [00:05<00:20, 12.83it/s] Loading 0: 17%|█▋ | 49/291 [00:05<00:10, 22.23it/s] Loading 0: 21%|██ | 60/291 [00:05<00:09, 23.41it/s] Loading 0: 25%|██▌ | 73/291 [00:05<00:06, 32.94it/s] Loading 0: 29%|██▉ | 85/291 [00:05<00:04, 42.42it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 50.42it/s] Loading 0: 38%|███▊ | 112/291 [00:06<00:02, 66.60it/s] Loading 0: 42%|████▏ | 123/291 [00:06<00:02, 72.18it/s] Loading 0: 47%|████▋ | 136/291 [00:06<00:01, 82.89it/s] Loading 0: 51%|█████ | 148/291 [00:06<00:01, 89.27it/s] Loading 0: 55%|█████▍ | 159/291 [00:06<00:01, 87.20it/s] Loading 0: 58%|█████▊ | 170/291 [00:06<00:02, 58.71it/s] Loading 0: 63%|██████▎ | 182/291 [00:07<00:01, 69.40it/s] Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 76.90it/s] Loading 0: 70%|███████ | 204/291 [00:07<00:01, 81.41it/s] Loading 0: 76%|███████▌ | 220/291 [00:07<00:00, 95.47it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:00, 91.09it/s] Loading 0: 84%|████████▍ | 244/291 [00:07<00:00, 99.90it/s] Loading 0: 88%|████████▊ | 256/291 [00:07<00:00, 102.73it/s] Loading 0: 92%|█████████▏| 267/291 [00:08<00:00, 60.61it/s] Loading 0: 96%|█████████▌| 280/291 [00:08<00:00, 72.30it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
setiaku-run2-modelstock-v2-mkmlizer: quantized model in 24.192s
setiaku-run2-modelstock-v2-mkmlizer: Processed model Setiaku/Run2-ModelStock in 70.331s
setiaku-run2-modelstock-v2-mkmlizer: creating bucket guanaco-mkml-models
setiaku-run2-modelstock-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
setiaku-run2-modelstock-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/setiaku-run2-modelstock-v2
setiaku-run2-modelstock-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/setiaku-run2-modelstock-v2/config.json
setiaku-run2-modelstock-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/setiaku-run2-modelstock-v2/special_tokens_map.json
setiaku-run2-modelstock-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/setiaku-run2-modelstock-v2/tokenizer_config.json
setiaku-run2-modelstock-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/setiaku-run2-modelstock-v2/tokenizer.json
setiaku-run2-modelstock-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/setiaku-run2-modelstock-v2/flywheel_model.0.safetensors
setiaku-run2-modelstock-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
setiaku-run2-modelstock-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.
setiaku-run2-modelstock-v2-mkmlizer: warnings.warn(
setiaku-run2-modelstock-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.
setiaku-run2-modelstock-v2-mkmlizer: warnings.warn(
setiaku-run2-modelstock-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.
setiaku-run2-modelstock-v2-mkmlizer: warnings.warn(
setiaku-run2-modelstock-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()
setiaku-run2-modelstock-v2-mkmlizer: return self.fget.__get__(instance, owner)()
setiaku-run2-modelstock-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
setiaku-run2-modelstock-v2-mkmlizer: Saving duration: 0.419s
setiaku-run2-modelstock-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.590s
setiaku-run2-modelstock-v2-mkmlizer: creating bucket guanaco-reward-models
setiaku-run2-modelstock-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
setiaku-run2-modelstock-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/setiaku-run2-modelstock-v2_reward
setiaku-run2-modelstock-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/setiaku-run2-modelstock-v2_reward/config.json
setiaku-run2-modelstock-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/setiaku-run2-modelstock-v2_reward/tokenizer_config.json
setiaku-run2-modelstock-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/setiaku-run2-modelstock-v2_reward/special_tokens_map.json
setiaku-run2-modelstock-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/setiaku-run2-modelstock-v2_reward/merges.txt
setiaku-run2-modelstock-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/setiaku-run2-modelstock-v2_reward/vocab.json
setiaku-run2-modelstock-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/setiaku-run2-modelstock-v2_reward/tokenizer.json
setiaku-run2-modelstock-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/setiaku-run2-modelstock-v2_reward/reward.tensors
Job setiaku-run2-modelstock-v2-mkmlizer completed after 115.44s with status: succeeded
Stopping job with name setiaku-run2-modelstock-v2-mkmlizer
Pipeline stage MKMLizer completed in 119.86s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service setiaku-run2-modelstock-v2
Waiting for inference service setiaku-run2-modelstock-v2 to be ready
Inference service setiaku-run2-modelstock-v2 ready after 30.29533076286316s
Pipeline stage ISVCDeployer completed in 37.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3350090980529785s
Received healthy response to inference request in 1.3582208156585693s
Received healthy response to inference request in 1.3230524063110352s
Received healthy response to inference request in 1.3050026893615723s
Received healthy response to inference request in 1.2542412281036377s
5 requests
0 failed requests
5th percentile: 1.2643935203552246
10th percentile: 1.2745458126068114
20th percentile: 1.2948503971099854
30th percentile: 1.3086126327514649
40th percentile: 1.31583251953125
50th percentile: 1.3230524063110352
60th percentile: 1.3371197700500488
70th percentile: 1.3511871337890624
80th percentile: 1.5535784721374513
90th percentile: 1.9442937850952149
95th percentile: 2.1396514415740966
99th percentile: 2.295937566757202
mean time: 1.5151052474975586
Pipeline stage StressChecker completed in 8.20s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.07s
setiaku-run2-modelstock_v2 status is now deployed due to DeploymentManager action
setiaku-run2-modelstock_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics