submission_id: hastagaras-anjrit_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/anjrit
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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: 2024-05-28T13:02:37+00:00
model_name: mwehehehehehe
model_eval_status: success
model_group: Hastagaras/anjrit
num_battles: 7646
num_wins: 4256
celo_rating: 1217.47
safety_score: 0.76
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: mwehehehehehe
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/anjrit
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-28
win_ratio: 0.5566309181271253
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjrit-v2-mkmlizer
Waiting for job on hastagaras-anjrit-v2-mkmlizer to finish
hastagaras-anjrit-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjrit-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-anjrit-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjrit-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjrit-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjrit-v2-mkmlizer: ║ /___/ ║
hastagaras-anjrit-v2-mkmlizer: ║ ║
hastagaras-anjrit-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjrit-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjrit-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjrit-v2-mkmlizer: ║ ║
hastagaras-anjrit-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjrit-v2-mkmlizer: ║ belonging to: ║
hastagaras-anjrit-v2-mkmlizer: ║ ║
hastagaras-anjrit-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjrit-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjrit-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjrit-v2-mkmlizer: ║ ║
hastagaras-anjrit-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjrit-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.
hastagaras-anjrit-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjrit-v2-mkmlizer: Downloaded to shared memory in 44.853s
hastagaras-anjrit-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjrit-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjrit-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:25, 2.37s/it] Loading 0: 4%|▍ | 13/291 [00:04<01:16, 3.61it/s] Loading 0: 8%|▊ | 23/291 [00:04<00:35, 7.45it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:20, 12.42it/s] Loading 0: 17%|█▋ | 49/291 [00:05<00:10, 22.64it/s] Loading 0: 21%|██ | 60/291 [00:05<00:10, 21.52it/s] Loading 0: 25%|██▌ | 74/291 [00:05<00:06, 31.47it/s] Loading 0: 29%|██▉ | 85/291 [00:05<00:05, 39.19it/s] Loading 0: 33%|███▎ | 95/291 [00:06<00:04, 46.82it/s] Loading 0: 36%|███▌ | 105/291 [00:06<00:03, 54.76it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 71.31it/s] Loading 0: 45%|████▌ | 132/291 [00:06<00:02, 76.91it/s] Loading 0: 51%|█████ | 149/291 [00:06<00:01, 94.57it/s] Loading 0: 56%|█████▋ | 164/291 [00:06<00:01, 107.33it/s] Loading 0: 61%|██████ | 177/291 [00:07<00:01, 62.23it/s] Loading 0: 65%|██████▌ | 190/291 [00:07<00:01, 72.78it/s] Loading 0: 69%|██████▉ | 202/291 [00:07<00:01, 80.96it/s] Loading 0: 73%|███████▎ | 213/291 [00:07<00:00, 82.85it/s] Loading 0: 79%|███████▊ | 229/291 [00:07<00:00, 94.27it/s] Loading 0: 82%|████████▏ | 240/291 [00:07<00:00, 91.79it/s] Loading 0: 88%|████████▊ | 256/291 [00:07<00:00, 104.61it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 62.75it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 74.10it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjrit-v2-mkmlizer: quantized model in 25.284s
hastagaras-anjrit-v2-mkmlizer: Processed model Hastagaras/anjrit in 72.829s
hastagaras-anjrit-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjrit-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjrit-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjrit-v2
hastagaras-anjrit-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjrit-v2/config.json
hastagaras-anjrit-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjrit-v2/tokenizer_config.json
hastagaras-anjrit-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjrit-v2/special_tokens_map.json
hastagaras-anjrit-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjrit-v2/tokenizer.json
hastagaras-anjrit-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjrit-v2/flywheel_model.0.safetensors
hastagaras-anjrit-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjrit-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.
hastagaras-anjrit-v2-mkmlizer: warnings.warn(
hastagaras-anjrit-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.
hastagaras-anjrit-v2-mkmlizer: warnings.warn(
hastagaras-anjrit-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.
hastagaras-anjrit-v2-mkmlizer: warnings.warn(
hastagaras-anjrit-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()
hastagaras-anjrit-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjrit-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjrit-v2-mkmlizer: Saving duration: 0.424s
hastagaras-anjrit-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.397s
hastagaras-anjrit-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjrit-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjrit-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjrit-v2_reward
hastagaras-anjrit-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjrit-v2_reward/special_tokens_map.json
hastagaras-anjrit-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjrit-v2_reward/tokenizer_config.json
hastagaras-anjrit-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjrit-v2_reward/config.json
hastagaras-anjrit-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjrit-v2_reward/merges.txt
hastagaras-anjrit-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjrit-v2_reward/vocab.json
hastagaras-anjrit-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjrit-v2_reward/tokenizer.json
hastagaras-anjrit-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjrit-v2_reward/reward.tensors
Job hastagaras-anjrit-v2-mkmlizer completed after 113.76s with status: succeeded
Stopping job with name hastagaras-anjrit-v2-mkmlizer
Pipeline stage MKMLizer completed in 117.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjrit-v2
Waiting for inference service hastagaras-anjrit-v2 to be ready
Inference service hastagaras-anjrit-v2 ready after 40.2321081161499s
Pipeline stage ISVCDeployer completed in 47.19s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1134252548217773s
Received healthy response to inference request in 1.3679296970367432s
Received healthy response to inference request in 1.3300046920776367s
Received healthy response to inference request in 1.2960090637207031s
Received healthy response to inference request in 1.2334463596343994s
5 requests
0 failed requests
5th percentile: 1.2459589004516602
10th percentile: 1.2584714412689209
20th percentile: 1.2834965229034423
30th percentile: 1.3028081893920898
40th percentile: 1.3164064407348632
50th percentile: 1.3300046920776367
60th percentile: 1.3451746940612792
70th percentile: 1.360344696044922
80th percentile: 1.5170288085937502
90th percentile: 1.8152270317077637
95th percentile: 1.9643261432647703
99th percentile: 2.083605432510376
mean time: 1.468163013458252
Pipeline stage StressChecker completed in 7.95s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-anjrit_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-anjrit_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics