submission_id: hastagaras-llama-3-8b-okay_v14
developer_uid: Hastagaras
best_of: 16
celo_rating: 1180.55
display_name: hastagaras-llama-3-8b-okay_v14
family_friendly_score: 0.0
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this roleplay chat between {user_name} and {bot_name}. Always write your response as {bot_name} based on the following description.\n\nDescription: {memory}\n", 'prompt_template': 'Previously: {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': True}
generation_params: {'temperature': 0.85, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-okay
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/llama-3-8b-ok
model_name: hastagaras-llama-3-8b-okay_v14
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama-3-8b-okay
model_size: 8B
num_battles: 17629
num_wins: 9131
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': True, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-16T22:44:12+00:00
us_pacific_date: 2024-05-16
win_ratio: 0.5179533722843043
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-okay-v14-mkmlizer
Waiting for job on hastagaras-llama-3-8b-okay-v14-mkmlizer to finish
hastagaras-llama-3-8b-okay-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ _____ __ __ ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ /___/ ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ https://mk1.ai ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ belonging to: ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ║ ║
hastagaras-llama-3-8b-okay-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-okay-v14-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-llama-3-8b-okay-v14-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-okay-v14-mkmlizer: Downloaded to shared memory in 15.802s
hastagaras-llama-3-8b-okay-v14-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v14-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 208.36it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:01, 197.19it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 212.76it/s] Loading 0: 30%|███ | 88/291 [00:00<00:02, 98.09it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 122.98it/s] Loading 0: 45%|████▍ | 130/291 [00:00<00:01, 137.48it/s] Loading 0: 52%|█████▏ | 152/291 [00:01<00:00, 157.12it/s] Loading 0: 59%|█████▉ | 172/291 [00:01<00:00, 134.82it/s] Loading 0: 65%|██████▍ | 189/291 [00:01<00:01, 90.07it/s] Loading 0: 73%|███████▎ | 211/291 [00:01<00:00, 110.82it/s] Loading 0: 80%|████████ | 234/291 [00:01<00:00, 133.11it/s] Loading 0: 88%|████████▊ | 255/291 [00:01<00:00, 146.85it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 156.84it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-okay-v14-mkmlizer: quantized model in 17.408s
hastagaras-llama-3-8b-okay-v14-mkmlizer: Processed model Hastagaras/llama-3-8b-okay in 34.243s
hastagaras-llama-3-8b-okay-v14-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-okay-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-okay-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v14
hastagaras-llama-3-8b-okay-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v14/special_tokens_map.json
hastagaras-llama-3-8b-okay-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v14/config.json
hastagaras-llama-3-8b-okay-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v14/tokenizer_config.json
hastagaras-llama-3-8b-okay-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v14/tokenizer.json
hastagaras-llama-3-8b-okay-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v14/flywheel_model.0.safetensors
hastagaras-llama-3-8b-okay-v14-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-okay-v14-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-llama-3-8b-okay-v14-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-okay-v14-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-llama-3-8b-okay-v14-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-okay-v14-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-llama-3-8b-okay-v14-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-okay-v14-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-llama-3-8b-okay-v14-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-okay-v14-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-okay-v14-mkmlizer: Saving duration: 0.239s
hastagaras-llama-3-8b-okay-v14-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.074s
hastagaras-llama-3-8b-okay-v14-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-okay-v14-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-okay-v14-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v14_reward
hastagaras-llama-3-8b-okay-v14-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v14_reward/config.json
hastagaras-llama-3-8b-okay-v14-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v14_reward/special_tokens_map.json
hastagaras-llama-3-8b-okay-v14-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v14_reward/tokenizer_config.json
hastagaras-llama-3-8b-okay-v14-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v14_reward/vocab.json
hastagaras-llama-3-8b-okay-v14-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v14_reward/tokenizer.json
hastagaras-llama-3-8b-okay-v14-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v14_reward/merges.txt
hastagaras-llama-3-8b-okay-v14-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v14_reward/reward.tensors
Job hastagaras-llama-3-8b-okay-v14-mkmlizer completed after 62.86s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-okay-v14-mkmlizer
Pipeline stage MKMLizer completed in 66.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-okay-v14
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v33: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:53966->127.0.0.1:8080: read: connection reset by peer\n')
Waiting for inference service hastagaras-llama-3-8b-okay-v14 to be ready
Inference service hastagaras-llama-3-8b-okay-v14 ready after 30.17830753326416s
Pipeline stage ISVCDeployer completed in 37.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9851200580596924s
Received healthy response to inference request in 1.1541612148284912s
Received healthy response to inference request in 1.4050426483154297s
Received healthy response to inference request in 1.4544117450714111s
Received healthy response to inference request in 1.125861644744873s
5 requests
0 failed requests
5th percentile: 1.1315215587615968
10th percentile: 1.1371814727783203
20th percentile: 1.1485013008117675
30th percentile: 1.2043375015258788
40th percentile: 1.3046900749206543
50th percentile: 1.4050426483154297
60th percentile: 1.4247902870178222
70th percentile: 1.4445379257202149
80th percentile: 1.5605534076690675
90th percentile: 1.77283673286438
95th percentile: 1.878978395462036
99th percentile: 1.9638917255401611
mean time: 1.4249194622039796
Pipeline stage StressChecker completed in 7.83s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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
hastagaras-llama-3-8b-okay_v14 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-okay_v14 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-okay_v14
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-okay-v14 is running
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Tearing down inference service hastagaras-llama-3-8b-okay-v14
Toredown service hastagaras-llama-3-8b-okay-v14
Pipeline stage ISVCDeleter completed in 8.80s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v14/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v14/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v14/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v14/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v14/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v14_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v14_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v14_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v14_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v14_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v14_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v14_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.94s
hastagaras-llama-3-8b-okay_v14 status is now torndown due to DeploymentManager action