submission_id: hastagaras-llama3-8b-ese_7365_v1
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/llama3-8b-esekuhhwell
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': "<|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: 2024-05-18T03:14:46+00:00
model_name: lets-go-mergeee
model_eval_status: success
model_group: Hastagaras/llama3-8b-ese
num_battles: 24525
num_wins: 13299
celo_rating: 1205.4
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: lets-go-mergeee
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/llama3-8b-esekuhhwell
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-17
win_ratio: 0.5422629969418961
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-8b-ese-7365-v1-mkmlizer
Waiting for job on hastagaras-llama3-8b-ese-7365-v1-mkmlizer to finish
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ /___/ ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ belonging to: ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ║ ║
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-ese-7365-v1-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-llama3-8b-ese-7365-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: Downloaded to shared memory in 28.559s
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:44, 2.02s/it] Loading 0: 8%|▊ | 22/291 [00:04<00:36, 7.29it/s] Loading 0: 14%|█▍ | 41/291 [00:04<00:15, 15.75it/s] Loading 0: 21%|██ | 60/291 [00:04<00:10, 22.34it/s] Loading 0: 29%|██▊ | 83/291 [00:04<00:05, 36.73it/s] Loading 0: 35%|███▌ | 103/291 [00:04<00:03, 51.30it/s] Loading 0: 42%|████▏ | 122/291 [00:04<00:02, 66.59it/s] Loading 0: 48%|████▊ | 141/291 [00:05<00:01, 83.31it/s] Loading 0: 56%|█████▋ | 164/291 [00:05<00:01, 107.47it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:01, 80.06it/s] Loading 0: 70%|██████▉ | 203/291 [00:05<00:00, 96.30it/s] Loading 0: 77%|███████▋ | 224/291 [00:05<00:00, 116.11it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 137.34it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 92.70it/s] Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 108.52it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: quantized model in 17.146s
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: Processed model Hastagaras/llama3-8b-esekuhhwell in 46.750s
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v1
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v1/tokenizer_config.json
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v1/special_tokens_map.json
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v1/config.json
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v1/tokenizer.json
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v1/flywheel_model.0.safetensors
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-ese-7365-v1-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-llama3-8b-ese-7365-v1-mkmlizer: warnings.warn(
hastagaras-llama3-8b-ese-7365-v1-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-llama3-8b-ese-7365-v1-mkmlizer: warnings.warn(
hastagaras-llama3-8b-ese-7365-v1-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-llama3-8b-ese-7365-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: Saving duration: 0.245s
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.942s
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v1_reward
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v1_reward/config.json
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v1_reward/special_tokens_map.json
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v1_reward/tokenizer_config.json
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v1_reward/merges.txt
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v1_reward/vocab.json
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v1_reward/tokenizer.json
hastagaras-llama3-8b-ese-7365-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v1_reward/reward.tensors
Job hastagaras-llama3-8b-ese-7365-v1-mkmlizer completed after 217.31s with status: succeeded
Stopping job with name hastagaras-llama3-8b-ese-7365-v1-mkmlizer
Pipeline stage MKMLizer completed in 219.94s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-ese-7365-v1
Waiting for inference service hastagaras-llama3-8b-ese-7365-v1 to be ready
Inference service hastagaras-llama3-8b-ese-7365-v1 ready after 40.22288632392883s
Pipeline stage ISVCDeployer completed in 47.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2504007816314697s
Received healthy response to inference request in 1.3454399108886719s
Received healthy response to inference request in 1.3185110092163086s
Received healthy response to inference request in 1.2847745418548584s
Received healthy response to inference request in 1.3558053970336914s
5 requests
0 failed requests
5th percentile: 1.2915218353271485
10th percentile: 1.2982691287994386
20th percentile: 1.3117637157440185
30th percentile: 1.3238967895507812
40th percentile: 1.3346683502197265
50th percentile: 1.3454399108886719
60th percentile: 1.3495861053466798
70th percentile: 1.3537322998046875
80th percentile: 1.5347244739532473
90th percentile: 1.8925626277923584
95th percentile: 2.071481704711914
99th percentile: 2.2146169662475588
mean time: 1.510986328125
Pipeline stage StressChecker completed in 8.19s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama3-8b-ese_7365_v1 status is now deployed due to DeploymentManager action
hastagaras-llama3-8b-ese_7365_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-8b-ese_7365_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-8b-ese-7365-v1 is running
admin requested tearing down of hastagaras-waduh-1-sft-l_7494_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-waduh-1-sft-l-7494-v1 is running
Tearing down inference service hastagaras-llama3-8b-ese-7365-v1
Toredown service hastagaras-llama3-8b-ese-7365-v1
Pipeline stage ISVCDeleter completed in 3.18s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-ese-7365-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-ese-7365-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-ese-7365-v1/special_tokens_map.json from bucket guanaco-mkml-models
Tearing down inference service hastagaras-waduh-1-sft-l-7494-v1
Deleting key hastagaras-llama3-8b-ese-7365-v1/tokenizer.json from bucket guanaco-mkml-models
Toredown service hastagaras-waduh-1-sft-l-7494-v1
Deleting key hastagaras-llama3-8b-ese-7365-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Pipeline stage ISVCDeleter completed in 4.08s
Running pipeline stage MKMLModelDeleter
Deleting key hastagaras-llama3-8b-ese-7365-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v1_reward/merges.txt from bucket guanaco-reward-models
Cleaning model data from S3
Deleting key hastagaras-llama3-8b-ese-7365-v1_reward/reward.tensors from bucket guanaco-reward-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-ese-7365-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-waduh-1-sft-l-7494-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-ese-7365-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-waduh-1-sft-l-7494-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-ese-7365-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.29s
Deleting key hastagaras-waduh-1-sft-l-7494-v1/special_tokens_map.json from bucket guanaco-mkml-models
hastagaras-llama3-8b-ese_7365_v1 status is now torndown due to DeploymentManager action
Deleting key hastagaras-waduh-1-sft-l-7494-v1/tokenizer.json from bucket guanaco-mkml-models

Usage Metrics

Latency Metrics