submission_id: hastagaras-llama3-8b-ese_7365_v3
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': 0.95, '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': "{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}
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: 2024-05-18T04:05:28+00:00
model_name: one-more-time
model_eval_status: success
model_group: Hastagaras/llama3-8b-ese
num_battles: 31929
num_wins: 17425
celo_rating: 1202.35
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: one-more-time
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: 0.5457421153183626
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-8b-ese-7365-v3-mkmlizer
Waiting for job on hastagaras-llama3-8b-ese-7365-v3-mkmlizer to finish
Stopping job with name hastagaras-llama3-8b-ese-7365-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-llama3-8b-ese-7365-v3-mkmlizer
Waiting for job on hastagaras-llama3-8b-ese-7365-v3-mkmlizer to finish
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ /___/ ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ belonging to: ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ║ ║
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-ese-7365-v3-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-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: Downloaded to shared memory in 13.410s
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:06, 2.10s/it] Loading 0: 5%|▌ | 15/291 [00:04<00:58, 4.73it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:20, 12.54it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:10, 22.43it/s] Loading 0: 22%|██▏ | 65/291 [00:04<00:08, 25.90it/s] Loading 0: 27%|██▋ | 79/291 [00:05<00:05, 35.44it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 49.28it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 65.22it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 81.58it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 97.45it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 70.11it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:01, 85.61it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 100.79it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 114.33it/s] Loading 0: 81%|████████ | 235/291 [00:06<00:00, 116.24it/s] Loading 0: 86%|████████▌ | 250/291 [00:06<00:00, 123.77it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 79.83it/s] Loading 0: 98%|█████████▊| 284/291 [00:06<00:00, 95.55it/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-v3-mkmlizer: quantized model in 18.010s
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: Processed model Hastagaras/llama3-8b-esekuhhwell in 32.461s
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v3
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v3/config.json
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v3/special_tokens_map.json
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v3/tokenizer_config.json
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v3/tokenizer.json
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v3/flywheel_model.0.safetensors
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-ese-7365-v3-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-v3-mkmlizer: warnings.warn(
hastagaras-llama3-8b-ese-7365-v3-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-v3-mkmlizer: warnings.warn(
hastagaras-llama3-8b-ese-7365-v3-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-llama3-8b-ese-7365-v3-mkmlizer: warnings.warn(
hastagaras-llama3-8b-ese-7365-v3-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-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: Saving duration: 0.233s
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.301s
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v3_reward
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v3_reward/config.json
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v3_reward/special_tokens_map.json
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v3_reward/merges.txt
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v3_reward/tokenizer_config.json
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v3_reward/vocab.json
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v3_reward/tokenizer.json
hastagaras-llama3-8b-ese-7365-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v3_reward/reward.tensors
Job hastagaras-llama3-8b-ese-7365-v3-mkmlizer completed after 205.86s with status: succeeded
Stopping job with name hastagaras-llama3-8b-ese-7365-v3-mkmlizer
Pipeline stage MKMLizer completed in 210.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-ese-7365-v3
Waiting for inference service hastagaras-llama3-8b-ese-7365-v3 to be ready
Inference service hastagaras-llama3-8b-ese-7365-v3 ready after 30.18512749671936s
Pipeline stage ISVCDeployer completed in 37.06s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.055548667907715s
Received healthy response to inference request in 1.3016321659088135s
Received healthy response to inference request in 1.2653379440307617s
Received healthy response to inference request in 1.2315354347229004s
Received healthy response to inference request in 1.2287406921386719s
5 requests
0 failed requests
5th percentile: 1.2292996406555177
10th percentile: 1.2298585891723632
20th percentile: 1.2309764862060546
30th percentile: 1.2382959365844726
40th percentile: 1.2518169403076171
50th percentile: 1.2653379440307617
60th percentile: 1.2798556327819823
70th percentile: 1.2943733215332032
80th percentile: 1.452415466308594
90th percentile: 1.7539820671081543
95th percentile: 1.9047653675079343
99th percentile: 2.025392007827759
mean time: 1.4165589809417725
Pipeline stage StressChecker completed in 7.79s
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-llama3-8b-ese_7365_v3 status is now deployed due to DeploymentManager action
hastagaras-llama3-8b-ese_7365_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-8b-ese_7365_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-8b-ese-7365-v3 is running
Tearing down inference service hastagaras-llama3-8b-ese-7365-v3
Toredown service hastagaras-llama3-8b-ese-7365-v3
Pipeline stage ISVCDeleter completed in 3.17s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-ese-7365-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-ese-7365-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-ese-7365-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-ese-7365-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-ese-7365-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-ese-7365-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.99s
hastagaras-llama3-8b-ese_7365_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics