submission_id: v000000-l3-8b-poppy-suns_5460_v1
developer_uid: v000000
status: inactive
model_repo: v000000/L3-8B-Poppy-Sunspice-experiment-c
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: 2024-06-06T11:57:20+00:00
model_name: v000000-l3-8b-poppy-suns_5460_v1
model_eval_status: success
model_group: v000000/L3-8B-Poppy-Suns
num_battles: 7844
num_wins: 4083
celo_rating: 1196.74
propriety_score: 0.69377990430622
propriety_total_count: 418.0
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-suns_5460_v1
ineligible_reason: propriety_total_count < 800
language_model: v000000/L3-8B-Poppy-Sunspice-experiment-c
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-06
win_ratio: 0.5205252422233554
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name v000000-l3-8b-poppy-suns-5460-v1-mkmlizer
Waiting for job on v000000-l3-8b-poppy-suns-5460-v1-mkmlizer to finish
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ _____ __ __ ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ /___/ ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ Version: 0.8.14 ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ https://mk1.ai ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ The license key for the current software has been verified as ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ belonging to: ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ Chai Research Corp. ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ║ ║
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-poppy-suns-5460-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.
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: Downloaded to shared memory in 33.585s
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:41, 2.22s/it] Loading 0: 6%|▌ | 18/291 [00:04<00:50, 5.42it/s] Loading 0: 12%|█▏ | 36/291 [00:04<00:19, 12.85it/s] Loading 0: 19%|█▊ | 54/291 [00:04<00:10, 22.38it/s] Loading 0: 24%|██▎ | 69/291 [00:05<00:08, 26.96it/s] Loading 0: 30%|██▉ | 87/291 [00:05<00:05, 39.58it/s] Loading 0: 36%|███▌ | 105/291 [00:05<00:03, 54.29it/s] Loading 0: 42%|████▏ | 123/291 [00:05<00:02, 70.64it/s] Loading 0: 48%|████▊ | 141/291 [00:05<00:01, 87.06it/s] Loading 0: 55%|█████▍ | 159/291 [00:05<00:01, 102.74it/s] Loading 0: 60%|██████ | 176/291 [00:05<00:01, 79.34it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:01, 94.64it/s] Loading 0: 73%|███████▎ | 212/291 [00:06<00:00, 108.51it/s] Loading 0: 79%|███████▉ | 230/291 [00:06<00:00, 122.13it/s] Loading 0: 85%|████████▌ | 248/291 [00:06<00:00, 132.67it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 91.05it/s] Loading 0: 96%|█████████▌| 279/291 [00:06<00:00, 95.87it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: quantized model in 22.629s
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: Processed model v000000/L3-8B-Poppy-Sunspice-experiment-c in 58.629s
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: creating bucket guanaco-mkml-models
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-poppy-suns-5460-v1
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-suns-5460-v1/tokenizer_config.json
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-suns-5460-v1/special_tokens_map.json
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-suns-5460-v1/tokenizer.json
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-suns-5460-v1/config.json
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-poppy-suns-5460-v1/flywheel_model.0.safetensors
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-l3-8b-poppy-suns-5460-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.
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-suns-5460-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.
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-suns-5460-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.
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-suns-5460-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()
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: return self.fget.__get__(instance, owner)()
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: Saving duration: 0.407s
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.762s
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-poppy-suns-5460-v1_reward
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-poppy-suns-5460-v1_reward/config.json
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-poppy-suns-5460-v1_reward/merges.txt
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-poppy-suns-5460-v1_reward/special_tokens_map.json
v000000-l3-8b-poppy-suns-5460-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-poppy-suns-5460-v1_reward/vocab.json
Job v000000-l3-8b-poppy-suns-5460-v1-mkmlizer completed after 85.58s with status: succeeded
Stopping job with name v000000-l3-8b-poppy-suns-5460-v1-mkmlizer
Pipeline stage MKMLizer completed in 89.30s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-poppy-suns-5460-v1
Waiting for inference service v000000-l3-8b-poppy-suns-5460-v1 to be ready
Inference service v000000-l3-8b-poppy-suns-5460-v1 ready after 50.56072759628296s
Pipeline stage ISVCDeployer completed in 58.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.125916004180908s
Received healthy response to inference request in 1.1972427368164062s
Received healthy response to inference request in 1.1848671436309814s
Received healthy response to inference request in 1.189481258392334s
Received healthy response to inference request in 1.1714134216308594s
5 requests
0 failed requests
5th percentile: 1.1741041660308837
10th percentile: 1.1767949104309081
20th percentile: 1.182176399230957
30th percentile: 1.1857899665832519
40th percentile: 1.187635612487793
50th percentile: 1.189481258392334
60th percentile: 1.1925858497619628
70th percentile: 1.1956904411315918
80th percentile: 1.3829773902893068
90th percentile: 1.7544466972351076
95th percentile: 1.9401813507080077
99th percentile: 2.0887690734863282
mean time: 1.373784112930298
Pipeline stage StressChecker completed in 7.45s
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
v000000-l3-8b-poppy-suns_5460_v1 status is now deployed due to DeploymentManager action
v000000-l3-8b-poppy-suns_5460_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics