submission_id: hastagaras-yaelah-8b-lla_4014_v2
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/Yaelah-8B-Llama3-Test
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, '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': "<|start_header_id|>system<|end_header_id|>\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: 2024-06-02T07:36:56+00:00
model_name: t2
model_eval_status: success
model_group: Hastagaras/Yaelah-8B-Lla
num_battles: 7073
num_wins: 3789
celo_rating: 1201.89
propriety_score: 0.7083333333333334
propriety_total_count: 144.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: t2
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/Yaelah-8B-Llama3-Test
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-02
win_ratio: 0.5356991375653896
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-yaelah-8b-lla-4014-v2-mkmlizer
Waiting for job on hastagaras-yaelah-8b-lla-4014-v2-mkmlizer to finish
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ /___/ ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ belonging to: ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ║ ║
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-yaelah-8b-lla-4014-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.
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: Downloaded to shared memory in 15.101s
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 127.73it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 150.74it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 158.99it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 161.22it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 85.19it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 102.36it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 117.85it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 130.63it/s] Loading 0: 53%|█████▎ | 154/291 [00:01<00:01, 132.46it/s] Loading 0: 58%|█████▊ | 169/291 [00:01<00:00, 133.30it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 91.00it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 99.60it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 115.29it/s] Loading 0: 82%|████████▏ | 238/291 [00:01<00:00, 128.36it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 138.59it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 146.81it/s] Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.14it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: quantized model in 22.754s
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: Processed model Hastagaras/Yaelah-8B-Llama3-Test in 40.381s
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v2
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v2/config.json
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v2/tokenizer_config.json
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v2/special_tokens_map.json
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v2/tokenizer.json
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v2/flywheel_model.0.safetensors
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-yaelah-8b-lla-4014-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.
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: warnings.warn(
hastagaras-yaelah-8b-lla-4014-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.
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: warnings.warn(
hastagaras-yaelah-8b-lla-4014-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.
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: warnings.warn(
hastagaras-yaelah-8b-lla-4014-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()
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: Saving duration: 0.410s
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.219s
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v2_reward
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v2_reward/config.json
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v2_reward/tokenizer_config.json
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v2_reward/special_tokens_map.json
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v2_reward/vocab.json
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v2_reward/merges.txt
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v2_reward/tokenizer.json
hastagaras-yaelah-8b-lla-4014-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v2_reward/reward.tensors
Job hastagaras-yaelah-8b-lla-4014-v2-mkmlizer completed after 73.27s with status: succeeded
Stopping job with name hastagaras-yaelah-8b-lla-4014-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.03s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-yaelah-8b-lla-4014-v2
Waiting for inference service hastagaras-yaelah-8b-lla-4014-v2 to be ready
Inference service hastagaras-yaelah-8b-lla-4014-v2 ready after 30.177406311035156s
Pipeline stage ISVCDeployer completed in 37.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 12.276329517364502s
Received healthy response to inference request in 1.369274377822876s
Received healthy response to inference request in 1.3310635089874268s
Received healthy response to inference request in 1.3101575374603271s
Received healthy response to inference request in 1.25583815574646s
5 requests
0 failed requests
5th percentile: 1.2667020320892335
10th percentile: 1.2775659084320068
20th percentile: 1.2992936611175536
30th percentile: 1.3143387317657471
40th percentile: 1.3227011203765868
50th percentile: 1.3310635089874268
60th percentile: 1.3463478565216065
70th percentile: 1.3616322040557862
80th percentile: 3.550685405731203
90th percentile: 7.9135074615478525
95th percentile: 10.094918489456175
99th percentile: 11.840047311782836
mean time: 3.5085326194763184
Pipeline stage StressChecker completed in 18.16s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-yaelah-8b-lla_4014_v2 status is now deployed due to DeploymentManager action
hastagaras-yaelah-8b-lla_4014_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-yaelah-8b-lla_4014_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-yaelah-8b-lla-4014-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.36s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-yaelah-8b-lla-4014-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-yaelah-8b-lla-4014-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-yaelah-8b-lla-4014-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-yaelah-8b-lla-4014-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-yaelah-8b-lla-4014-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-yaelah-8b-lla-4014-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-yaelah-8b-lla-4014-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-yaelah-8b-lla-4014-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-yaelah-8b-lla-4014-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-yaelah-8b-lla-4014-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-yaelah-8b-lla-4014-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-yaelah-8b-lla-4014-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.54s
hastagaras-yaelah-8b-lla_4014_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics