submission_id: v000000-l3-8b-poppy-sunspice_v2
developer_uid: v000000
status: inactive
model_repo: v000000/L3-8B-Poppy-Sunspice
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
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}
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: 2024-06-06T12:03:59+00:00
model_name: v000000-l3-8b-poppy-sunspice_v2
model_eval_status: success
model_group: v000000/L3-8B-Poppy-Suns
num_battles: 23811
num_wins: 12553
celo_rating: 1201.84
propriety_score: 0.6808188021228203
propriety_total_count: 1319.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: v000000-l3-8b-poppy-sunspice_v2
ineligible_reason: None
language_model: v000000/L3-8B-Poppy-Sunspice
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-06
win_ratio: 0.5271933140145311
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name v000000-l3-8b-poppy-sunspice-v2-mkmlizer
Waiting for job on v000000-l3-8b-poppy-sunspice-v2-mkmlizer to finish
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ _____ __ __ ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ /___/ ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ Version: 0.8.14 ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ https://mk1.ai ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ The license key for the current software has been verified as ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ belonging to: ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ Chai Research Corp. ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ║ ║
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-poppy-sunspice-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.
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: Downloaded to shared memory in 31.169s
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:21, 2.15s/it] Loading 0: 5%|▌ | 15/291 [00:04<00:59, 4.62it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:21, 12.28it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:10, 22.10it/s] Loading 0: 23%|██▎ | 66/291 [00:04<00:08, 27.27it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 35.24it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 50.45it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 67.00it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 83.20it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 98.55it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 76.27it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:01, 92.58it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 108.41it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 122.93it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 133.83it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 142.89it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 91.55it/s] Loading 0: 99%|█████████▉| 288/291 [00:06<00:00, 101.80it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: quantized model in 22.761s
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: Processed model v000000/L3-8B-Poppy-Sunspice in 56.382s
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: creating bucket guanaco-mkml-models
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-poppy-sunspice-v2
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-sunspice-v2/config.json
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-sunspice-v2/tokenizer_config.json
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-sunspice-v2/special_tokens_map.json
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-sunspice-v2/tokenizer.json
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-poppy-sunspice-v2/flywheel_model.0.safetensors
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-l3-8b-poppy-sunspice-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.
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-sunspice-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.
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-sunspice-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.
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-sunspice-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()
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: return self.fget.__get__(instance, owner)()
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: Saving duration: 0.395s
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.654s
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v2_reward
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v2_reward/special_tokens_map.json
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v2_reward/config.json
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v2_reward/tokenizer_config.json
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v2_reward/vocab.json
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v2_reward/merges.txt
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v2_reward/tokenizer.json
v000000-l3-8b-poppy-sunspice-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v2_reward/reward.tensors
Job v000000-l3-8b-poppy-sunspice-v2-mkmlizer completed after 82.94s with status: succeeded
Stopping job with name v000000-l3-8b-poppy-sunspice-v2-mkmlizer
Pipeline stage MKMLizer completed in 85.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-poppy-sunspice-v2
Waiting for inference service v000000-l3-8b-poppy-sunspice-v2 to be ready
Inference service v000000-l3-8b-poppy-sunspice-v2 ready after 42.17266654968262s
Pipeline stage ISVCDeployer completed in 49.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0446078777313232s
Received healthy response to inference request in 1.159116268157959s
Received healthy response to inference request in 1.1529111862182617s
Received healthy response to inference request in 1.1783337593078613s
Received healthy response to inference request in 1.1495304107666016s
5 requests
0 failed requests
5th percentile: 1.1502065658569336
10th percentile: 1.1508827209472656
20th percentile: 1.1522350311279297
30th percentile: 1.1541522026062012
40th percentile: 1.15663423538208
50th percentile: 1.159116268157959
60th percentile: 1.1668032646179198
70th percentile: 1.174490261077881
80th percentile: 1.3515885829925538
90th percentile: 1.6980982303619385
95th percentile: 1.8713530540466308
99th percentile: 2.009956912994385
mean time: 1.3368999004364013
Pipeline stage StressChecker completed in 7.39s
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
v000000-l3-8b-poppy-sunspice_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
v000000-l3-8b-poppy-sunspice_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics