submission_id: hastagaras-llama-3-8b-no_7499_v2
developer_uid: Hastagaras
best_of: 16
celo_rating: 1193.45
display_name: with-bos
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|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 persona.\n\n{bot_name}'s Persona: {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': False}
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}
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-not-okay
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/llama-3-8b-no
model_name: with-bos
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama-3-8b-not-okay
model_size: 8B
num_battles: 19786
num_wins: 10551
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-15T06:07:25+00:00
us_pacific_date: 2024-05-14
win_ratio: 0.5332558374608309
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-no-7499-v2-mkmlizer
Waiting for job on hastagaras-llama-3-8b-no-7499-v2-mkmlizer to finish
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ /___/ ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ belonging to: ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ║ ║
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-no-7499-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-llama-3-8b-no-7499-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: Downloaded to shared memory in 14.617s
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:01, 203.67it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 210.06it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 214.12it/s] Loading 0: 30%|███ | 88/291 [00:00<00:01, 102.46it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 125.88it/s] Loading 0: 45%|████▌ | 131/291 [00:00<00:01, 139.18it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 163.04it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 176.87it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:00, 111.36it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 126.27it/s] Loading 0: 83%|████████▎ | 241/291 [00:01<00:00, 143.40it/s] Loading 0: 91%|█████████ | 264/291 [00:01<00:00, 159.64it/s] Loading 0: 98%|█████████▊| 284/291 [00:01<00:00, 169.29it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: quantized model in 16.623s
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: Processed model Hastagaras/llama-3-8b-not-okay in 32.143s
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v2
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v2/special_tokens_map.json
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v2/tokenizer_config.json
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v2/config.json
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v2/tokenizer.json
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v2/flywheel_model.0.safetensors
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-no-7499-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-llama-3-8b-no-7499-v2-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-no-7499-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-llama-3-8b-no-7499-v2-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-no-7499-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-llama-3-8b-no-7499-v2-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-no-7499-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-llama-3-8b-no-7499-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: Saving duration: 0.240s
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 17.650s
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v2_reward
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v2_reward/special_tokens_map.json
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v2_reward/tokenizer_config.json
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v2_reward/config.json
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v2_reward/vocab.json
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v2_reward/merges.txt
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v2_reward/tokenizer.json
hastagaras-llama-3-8b-no-7499-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v2_reward/reward.tensors
Job hastagaras-llama-3-8b-no-7499-v2-mkmlizer completed after 73.58s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-no-7499-v2-mkmlizer
Pipeline stage MKMLizer completed in 79.29s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-no-7499-v2
Waiting for inference service hastagaras-llama-3-8b-no-7499-v2 to be ready
Inference service hastagaras-llama-3-8b-no-7499-v2 ready after 30.174028396606445s
Pipeline stage ISVCDeployer completed in 37.98s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.226976156234741s
Received healthy response to inference request in 1.298638105392456s
Received healthy response to inference request in 1.2600159645080566s
Received healthy response to inference request in 1.3235747814178467s
Received healthy response to inference request in 1.2837860584259033s
5 requests
0 failed requests
5th percentile: 1.264769983291626
10th percentile: 1.2695240020751952
20th percentile: 1.279032039642334
30th percentile: 1.2867564678192138
40th percentile: 1.292697286605835
50th percentile: 1.298638105392456
60th percentile: 1.3086127758026123
70th percentile: 1.3185874462127685
80th percentile: 1.5042550563812258
90th percentile: 1.8656156063079834
95th percentile: 2.0462958812713623
99th percentile: 2.1908401012420655
mean time: 1.4785982131958009
Pipeline stage StressChecker completed in 8.00s
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
hastagaras-llama-3-8b-no_7499_v2 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-no_7499_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-no_7499_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-no-7499-v2 is running
Tearing down inference service hastagaras-llama-3-8b-no-7499-v2
Toredown service hastagaras-llama-3-8b-no-7499-v2
Pipeline stage ISVCDeleter completed in 3.69s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-no-7499-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-no-7499-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.88s
hastagaras-llama-3-8b-no_7499_v2 status is now torndown due to DeploymentManager action