submission_id: v000000-l3-8b-poppy-sunspice_v3
developer_uid: v000000
status: inactive
model_repo: v000000/L3-8B-Poppy-Sunspice
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.22, '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': 16, '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: 2024-06-06T13:01:22+00:00
model_name: v000000-l3-8b-poppy-sunspice_v3
model_eval_status: success
model_group: v000000/L3-8B-Poppy-Suns
num_battles: 20741
num_wins: 11281
celo_rating: 1215.44
propriety_score: 0.6825817860300619
propriety_total_count: 1131.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: v000000-l3-8b-poppy-sunspice_v3
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: 0.543898558410877
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name v000000-l3-8b-poppy-sunspice-v3-mkmlizer
Waiting for job on v000000-l3-8b-poppy-sunspice-v3-mkmlizer to finish
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ _____ __ __ ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ /___/ ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ Version: 0.8.14 ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ https://mk1.ai ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ The license key for the current software has been verified as ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ belonging to: ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ Chai Research Corp. ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ║ ║
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-poppy-sunspice-v3-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-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: Downloaded to shared memory in 43.582s
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:41, 2.43s/it] Loading 0: 3%|▎ | 9/291 [00:04<01:57, 2.40it/s] Loading 0: 7%|▋ | 19/291 [00:05<00:43, 6.22it/s] Loading 0: 11%|█ | 32/291 [00:05<00:20, 12.66it/s] Loading 0: 15%|█▌ | 45/291 [00:05<00:11, 20.83it/s] Loading 0: 20%|█▉ | 58/291 [00:05<00:07, 30.61it/s] Loading 0: 24%|██▎ | 69/291 [00:06<00:08, 24.83it/s] Loading 0: 27%|██▋ | 79/291 [00:06<00:06, 31.78it/s] Loading 0: 30%|███ | 88/291 [00:06<00:05, 38.52it/s] Loading 0: 35%|███▌ | 103/291 [00:06<00:03, 53.12it/s] Loading 0: 39%|███▉ | 113/291 [00:06<00:03, 58.75it/s] Loading 0: 42%|████▏ | 123/291 [00:06<00:02, 63.66it/s] Loading 0: 46%|████▌ | 134/291 [00:06<00:02, 73.01it/s] Loading 0: 49%|████▉ | 144/291 [00:06<00:01, 77.94it/s] Loading 0: 53%|█████▎ | 154/291 [00:06<00:01, 81.12it/s] Loading 0: 56%|█████▋ | 164/291 [00:06<00:01, 84.97it/s] Loading 0: 60%|█████▉ | 174/291 [00:07<00:02, 49.69it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 56.48it/s] Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 62.70it/s] Loading 0: 70%|██████▉ | 203/291 [00:07<00:01, 67.67it/s] Loading 0: 73%|███████▎ | 213/291 [00:07<00:01, 71.96it/s] Loading 0: 77%|███████▋ | 225/291 [00:07<00:00, 82.62it/s] Loading 0: 81%|████████ | 235/291 [00:08<00:00, 86.65it/s] Loading 0: 85%|████████▍ | 247/291 [00:08<00:00, 90.28it/s] Loading 0: 88%|████████▊ | 257/291 [00:08<00:00, 87.92it/s] Loading 0: 92%|█████████▏| 267/291 [00:08<00:00, 50.59it/s] Loading 0: 96%|█████████▌| 279/291 [00:08<00:00, 62.15it/s] Loading 0: 99%|█████████▉| 289/291 [00:08<00:00, 69.07it/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-v3-mkmlizer: quantized model in 25.500s
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: Processed model v000000/L3-8B-Poppy-Sunspice in 72.308s
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: creating bucket guanaco-mkml-models
Retrying (%r) after connection broken by '%r': %s
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: WARNING: Retrying failed request: /?location ([Errno 110] Connection timed out)
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: WARNING: Waiting 3 sec...
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-poppy-sunspice-v3
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-sunspice-v3/config.json
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-sunspice-v3/special_tokens_map.json
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-sunspice-v3/tokenizer_config.json
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-sunspice-v3/tokenizer.json
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-poppy-sunspice-v3/flywheel_model.0.safetensors
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-l3-8b-poppy-sunspice-v3-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-v3-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-sunspice-v3-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-v3-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-sunspice-v3-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-v3-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-sunspice-v3-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-v3-mkmlizer: return self.fget.__get__(instance, owner)()
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: Saving duration: 0.540s
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.974s
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v3_reward
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v3_reward/config.json
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v3_reward/tokenizer_config.json
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v3_reward/special_tokens_map.json
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v3_reward/vocab.json
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v3_reward/merges.txt
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v3_reward/tokenizer.json
v000000-l3-8b-poppy-sunspice-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-l3-8b-poppy-sunspice-v3_reward/reward.tensors
Job v000000-l3-8b-poppy-sunspice-v3-mkmlizer completed after 257.03s with status: succeeded
Stopping job with name v000000-l3-8b-poppy-sunspice-v3-mkmlizer
Pipeline stage MKMLizer completed in 260.47s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-poppy-sunspice-v3
Waiting for inference service v000000-l3-8b-poppy-sunspice-v3 to be ready
Inference service v000000-l3-8b-poppy-sunspice-v3 ready after 40.26051926612854s
Pipeline stage ISVCDeployer completed in 47.48s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.196361780166626s
Received healthy response to inference request in 1.2572247982025146s
Received healthy response to inference request in 1.2759037017822266s
Received healthy response to inference request in 1.254894733428955s
Received healthy response to inference request in 1.250718116760254s
5 requests
0 failed requests
5th percentile: 1.251553440093994
10th percentile: 1.2523887634277344
20th percentile: 1.254059410095215
30th percentile: 1.255360746383667
40th percentile: 1.2562927722930908
50th percentile: 1.2572247982025146
60th percentile: 1.2646963596343994
70th percentile: 1.2721679210662842
80th percentile: 1.4599953174591067
90th percentile: 1.8281785488128663
95th percentile: 2.012270164489746
99th percentile: 2.15954345703125
mean time: 1.4470206260681153
Pipeline stage StressChecker completed in 7.83s
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-sunspice_v3 status is now deployed due to DeploymentManager action
v000000-l3-8b-poppy-sunspice_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics