submission_id: cycy233-misllm-v9-0-4_v8
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v9.0.4
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, '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: 2024-06-19T07:24:52+00:00
model_name: base_f
model_group: cycy233/misllm_v9.0.4
num_battles: 16714
num_wins: 8453
celo_rating: 1187.34
propriety_score: 0.6904737437056828
propriety_total_count: 9731.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7248023552.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: base_f
ineligible_reason: None
language_model: cycy233/misllm_v9.0.4
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-19
win_ratio: 0.5057436879262893
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v9-0-4-v8-mkmlizer
Waiting for job on cycy233-misllm-v9-0-4-v8-mkmlizer to finish
cycy233-misllm-v9-0-4-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ /___/ ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ belonging to: ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ║ ║
cycy233-misllm-v9-0-4-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v9-0-4-v8-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.
cycy233-misllm-v9-0-4-v8-mkmlizer: warnings.warn(warning_message, FutureWarning)
Failed to get response for submission cycy233-misllm-v9-0-3_v2: ('http://cycy233-misllm-v9-0-3-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission cycy233-misllm-v9-0-3_v2: ('http://cycy233-misllm-v9-0-3-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '')
cycy233-misllm-v9-0-4-v8-mkmlizer: Downloaded to shared memory in 32.176s
cycy233-misllm-v9-0-4-v8-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v9-0-4-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission cycy233-misllm-v9-0-3_v2: ('http://cycy233-misllm-v9-0-3-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission cycy233-misllm-v9-0-3_v2: ('http://cycy233-misllm-v9-0-3-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '')
cycy233-misllm-v9-0-4-v8-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 80.91it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:00, 90.91it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 77.56it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v9-0-4-v8-mkmlizer: quantized model in 15.704s
cycy233-misllm-v9-0-4-v8-mkmlizer: Processed model cycy233/misllm_v9.0.4 in 50.343s
cycy233-misllm-v9-0-4-v8-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v9-0-4-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v9-0-4-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v9-0-4-v8
cycy233-misllm-v9-0-4-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-4-v8/config.json
cycy233-misllm-v9-0-4-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-4-v8/tokenizer_config.json
cycy233-misllm-v9-0-4-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-4-v8/tokenizer.json
cycy233-misllm-v9-0-4-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v9-0-4-v8/special_tokens_map.json
cycy233-misllm-v9-0-4-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v9-0-4-v8/tokenizer.model
cycy233-misllm-v9-0-4-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v9-0-4-v8/flywheel_model.0.safetensors
cycy233-misllm-v9-0-4-v8-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.
cycy233-misllm-v9-0-4-v8-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-4-v8-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.
cycy233-misllm-v9-0-4-v8-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-4-v8-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()
cycy233-misllm-v9-0-4-v8-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v9-0-4-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v9-0-4-v8-mkmlizer: Saving duration: 0.415s
cycy233-misllm-v9-0-4-v8-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.689s
cycy233-misllm-v9-0-4-v8-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v9-0-4-v8-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v9-0-4-v8-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v9-0-4-v8_reward
cycy233-misllm-v9-0-4-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v9-0-4-v8_reward/special_tokens_map.json
cycy233-misllm-v9-0-4-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v9-0-4-v8_reward/config.json
cycy233-misllm-v9-0-4-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v9-0-4-v8_reward/tokenizer_config.json
cycy233-misllm-v9-0-4-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v9-0-4-v8_reward/merges.txt
cycy233-misllm-v9-0-4-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v9-0-4-v8_reward/vocab.json
cycy233-misllm-v9-0-4-v8-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v9-0-4-v8_reward/tokenizer.json
cycy233-misllm-v9-0-4-v8-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v9-0-4-v8_reward/reward.tensors
Job cycy233-misllm-v9-0-4-v8-mkmlizer completed after 93.22s with status: succeeded
Stopping job with name cycy233-misllm-v9-0-4-v8-mkmlizer
Pipeline stage MKMLizer completed in 97.24s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v9-0-4-v8
Waiting for inference service cycy233-misllm-v9-0-4-v8 to be ready
Failed to get response for submission cycy233-misllm-v9-0-3_v2: ('http://cycy233-misllm-v9-0-3-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission cycy233-misllm-v9-0-3_v2: ('http://cycy233-misllm-v9-0-3-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service cycy233-misllm-v9-0-4-v8 ready after 60.308332443237305s
Pipeline stage ISVCDeployer completed in 67.60s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9123663902282715s
Received healthy response to inference request in 1.0129523277282715s
Received healthy response to inference request in 0.9807355403900146s
Received healthy response to inference request in 1.0096125602722168s
Received healthy response to inference request in 0.9846858978271484s
5 requests
0 failed requests
5th percentile: 0.9815256118774414
10th percentile: 0.9823156833648682
20th percentile: 0.9838958263397217
Failed to get response for submission cycy233-misllm-v9-0-3_v2: ('http://cycy233-misllm-v9-0-3-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '')
30th percentile: 0.9896712303161621
40th percentile: 0.9996418952941895
50th percentile: 1.0096125602722168
60th percentile: 1.0109484672546387
70th percentile: 1.0122843742370606
80th percentile: 1.1928351402282718
90th percentile: 1.5526007652282716
95th percentile: 1.7324835777282712
99th percentile: 1.8763898277282713
mean time: 1.1800705432891845
Pipeline stage StressChecker completed in 6.54s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cycy233-misllm-v9-0-4_v8 status is now deployed due to DeploymentManager action
cycy233-misllm-v9-0-4_v8 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics