submission_id: meseca-05062024-v1_v2
developer_uid: nguyenzzz
status: inactive
model_repo: meseca/05062024-v1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, '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\nYou're {bot_name} in this fictional never-ending roleplay with {user_name}.\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: 2024-06-15T13:44:32+00:00
model_name: meseca-05062024-v1_v1
model_eval_status: success
model_group: meseca/05062024-v1
num_battles: 14646
num_wins: 7694
celo_rating: 1177.7
propriety_score: 0.707094495142773
propriety_total_count: 6794.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: meseca-05062024-v1_v1
ineligible_reason: None
language_model: meseca/05062024-v1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-15
win_ratio: 0.5253311484364331
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meseca-05062024-v1-v2-mkmlizer
Waiting for job on meseca-05062024-v1-v2-mkmlizer to finish
meseca-05062024-v1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-05062024-v1-v2-mkmlizer: ║ _____ __ __ ║
meseca-05062024-v1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meseca-05062024-v1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meseca-05062024-v1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meseca-05062024-v1-v2-mkmlizer: ║ /___/ ║
meseca-05062024-v1-v2-mkmlizer: ║ ║
meseca-05062024-v1-v2-mkmlizer: ║ Version: 0.8.14 ║
meseca-05062024-v1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meseca-05062024-v1-v2-mkmlizer: ║ https://mk1.ai ║
meseca-05062024-v1-v2-mkmlizer: ║ ║
meseca-05062024-v1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
meseca-05062024-v1-v2-mkmlizer: ║ belonging to: ║
meseca-05062024-v1-v2-mkmlizer: ║ ║
meseca-05062024-v1-v2-mkmlizer: ║ Chai Research Corp. ║
meseca-05062024-v1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meseca-05062024-v1-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
meseca-05062024-v1-v2-mkmlizer: ║ ║
meseca-05062024-v1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-05062024-v1-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.
meseca-05062024-v1-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
meseca-05062024-v1-v2-mkmlizer: Downloaded to shared memory in 184.653s
meseca-05062024-v1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-05062024-v1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-05062024-v1-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 120.42it/s] Loading 0: 10%|▉ | 28/291 [00:00<00:01, 136.50it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:01, 125.29it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 130.74it/s] Loading 0: 25%|██▍ | 72/291 [00:00<00:01, 133.70it/s] Loading 0: 30%|██▉ | 86/291 [00:00<00:03, 67.25it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 84.01it/s] Loading 0: 39%|███▉ | 114/291 [00:01<00:01, 90.54it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 103.12it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 114.14it/s] Loading 0: 55%|█████▌ | 161/291 [00:01<00:01, 117.55it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 122.83it/s] Loading 0: 65%|██████▍ | 189/291 [00:01<00:01, 75.46it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 84.73it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 99.14it/s] Loading 0: 80%|███████▉ | 232/291 [00:02<00:00, 105.51it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 112.49it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 122.88it/s] Loading 0: 96%|█████████▌| 278/291 [00:02<00:00, 125.49it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-05062024-v1-v2-mkmlizer: quantized model in 24.170s
meseca-05062024-v1-v2-mkmlizer: creating bucket guanaco-mkml-models
meseca-05062024-v1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-05062024-v1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-05062024-v1-v2
meseca-05062024-v1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-05062024-v1-v2/config.json
meseca-05062024-v1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-05062024-v1-v2/special_tokens_map.json
meseca-05062024-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-05062024-v1-v2/tokenizer_config.json
meseca-05062024-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-05062024-v1-v2/tokenizer.json
meseca-05062024-v1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-05062024-v1-v2/flywheel_model.0.safetensors
meseca-05062024-v1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-05062024-v1-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.
meseca-05062024-v1-v2-mkmlizer: warnings.warn(
meseca-05062024-v1-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.
meseca-05062024-v1-v2-mkmlizer: warnings.warn(
meseca-05062024-v1-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.
meseca-05062024-v1-v2-mkmlizer: warnings.warn(
meseca-05062024-v1-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()
meseca-05062024-v1-v2-mkmlizer: return self.fget.__get__(instance, owner)()
meseca-05062024-v1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-05062024-v1-v2-mkmlizer: Saving duration: 0.475s
meseca-05062024-v1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.725s
meseca-05062024-v1-v2-mkmlizer: creating bucket guanaco-reward-models
meseca-05062024-v1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-05062024-v1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-05062024-v1-v2_reward
meseca-05062024-v1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-05062024-v1-v2_reward/config.json
meseca-05062024-v1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-05062024-v1-v2_reward/special_tokens_map.json
meseca-05062024-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-05062024-v1-v2_reward/tokenizer_config.json
meseca-05062024-v1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-05062024-v1-v2_reward/merges.txt
meseca-05062024-v1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-05062024-v1-v2_reward/vocab.json
meseca-05062024-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-05062024-v1-v2_reward/tokenizer.json
Job meseca-05062024-v1-v2-mkmlizer completed after 247.15s with status: succeeded
Stopping job with name meseca-05062024-v1-v2-mkmlizer
Pipeline stage MKMLizer completed in 247.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service meseca-05062024-v1-v2
Waiting for inference service meseca-05062024-v1-v2 to be ready
Inference service meseca-05062024-v1-v2 ready after 40.23166251182556s
Pipeline stage ISVCDeployer completed in 45.82s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1947593688964844s
Received healthy response to inference request in 1.3074159622192383s
Received healthy response to inference request in 2.6656687259674072s
Received healthy response to inference request in 1.2395780086517334s
Received healthy response to inference request in 1.3260087966918945s
5 requests
0 failed requests
5th percentile: 1.2531455993652343
10th percentile: 1.2667131900787354
20th percentile: 1.2938483715057374
30th percentile: 1.3111345291137695
40th percentile: 1.3185716629028321
50th percentile: 1.3260087966918945
60th percentile: 1.6735090255737304
70th percentile: 2.0210092544555662
80th percentile: 2.288941240310669
90th percentile: 2.477304983139038
95th percentile: 2.5714868545532226
99th percentile: 2.64683235168457
mean time: 1.7466861724853515
Pipeline stage StressChecker completed in 9.35s
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
meseca-05062024-v1_v2 status is now deployed due to DeploymentManager action
meseca-05062024-v1_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics