submission_id: hastagaras-halu-8b-llama_9226_v1
developer_uid: Hastagaras
best_of: 16
celo_rating: 1213.55
display_name: experiment-2
family_friendly_score: 0.0
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}
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, '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/HALU-8B-LLAMA3-EXP-2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/HALU-8B-LLAMA
model_name: experiment-2
model_num_parameters: 8030261248.0
model_repo: Hastagaras/HALU-8B-LLAMA3-EXP-2
model_size: 8B
num_battles: 8790
num_wins: 4622
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': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-31T11:22:02+00:00
us_pacific_date: 2024-05-31
win_ratio: 0.5258248009101252
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-9226-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-9226-v1-mkmlizer to finish
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-9226-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-9226-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-halu-8b-llama-9226-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-9226-v1-mkmlizer: Downloaded to shared memory in 28.147s
hastagaras-halu-8b-llama-9226-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-9226-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-9226-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:55, 2.27s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:08, 4.07it/s] Loading 0: 9%|▉ | 27/291 [00:04<00:28, 9.30it/s] Loading 0: 14%|█▎ | 40/291 [00:04<00:15, 16.07it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:10, 22.80it/s] Loading 0: 21%|██▏ | 62/291 [00:05<00:10, 22.57it/s] Loading 0: 26%|██▋ | 77/291 [00:05<00:06, 33.48it/s] Loading 0: 31%|███▏ | 91/291 [00:05<00:04, 45.33it/s] Loading 0: 36%|███▌ | 104/291 [00:05<00:03, 56.65it/s] Loading 0: 41%|████ | 119/291 [00:05<00:02, 71.83it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 81.80it/s] Loading 0: 52%|█████▏ | 150/291 [00:06<00:01, 99.75it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:02, 61.97it/s] Loading 0: 61%|██████ | 177/291 [00:06<00:01, 68.57it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:01, 84.02it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:00, 98.92it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:00, 101.07it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:00, 111.91it/s] Loading 0: 88%|████████▊ | 256/291 [00:07<00:00, 125.88it/s] Loading 0: 93%|█████████▎| 271/291 [00:07<00:00, 74.65it/s] Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 85.12it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-9226-v1-mkmlizer: quantized model in 22.256s
hastagaras-halu-8b-llama-9226-v1-mkmlizer: Processed model Hastagaras/HALU-8B-LLAMA3-EXP-2 in 51.726s
hastagaras-halu-8b-llama-9226-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-9226-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-9226-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-9226-v1
hastagaras-halu-8b-llama-9226-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-9226-v1/config.json
hastagaras-halu-8b-llama-9226-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-9226-v1/special_tokens_map.json
hastagaras-halu-8b-llama-9226-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-9226-v1/tokenizer_config.json
hastagaras-halu-8b-llama-9226-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-9226-v1/tokenizer.json
hastagaras-halu-8b-llama-9226-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-9226-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-9226-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-9226-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-halu-8b-llama-9226-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-9226-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-halu-8b-llama-9226-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-9226-v1-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-halu-8b-llama-9226-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-9226-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-halu-8b-llama-9226-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-9226-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-9226-v1-mkmlizer: Saving duration: 0.287s
hastagaras-halu-8b-llama-9226-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.317s
hastagaras-halu-8b-llama-9226-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-9226-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-9226-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v1_reward
hastagaras-halu-8b-llama-9226-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v1_reward/config.json
hastagaras-halu-8b-llama-9226-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama-9226-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama-9226-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v1_reward/merges.txt
hastagaras-halu-8b-llama-9226-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v1_reward/vocab.json
hastagaras-halu-8b-llama-9226-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v1_reward/tokenizer.json
hastagaras-halu-8b-llama-9226-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama-9226-v1-mkmlizer completed after 83.16s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-9226-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-9226-v1
Waiting for inference service hastagaras-halu-8b-llama-9226-v1 to be ready
Inference service hastagaras-halu-8b-llama-9226-v1 ready after 40.20598387718201s
Pipeline stage ISVCDeployer completed in 45.98s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1485064029693604s
Received healthy response to inference request in 1.3407251834869385s
Received healthy response to inference request in 1.3348877429962158s
Received healthy response to inference request in 1.294001579284668s
Received healthy response to inference request in 1.2354333400726318s
5 requests
0 failed requests
5th percentile: 1.247146987915039
10th percentile: 1.2588606357574463
20th percentile: 1.2822879314422608
30th percentile: 1.3021788120269775
40th percentile: 1.3185332775115968
50th percentile: 1.3348877429962158
60th percentile: 1.3372227191925048
70th percentile: 1.339557695388794
80th percentile: 1.502281427383423
90th percentile: 1.8253939151763916
95th percentile: 1.9869501590728758
99th percentile: 2.1161951541900637
mean time: 1.470710849761963
Pipeline stage StressChecker completed in 7.96s
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-halu-8b-llama_9226_v1 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_9226_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama_9226_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama-9226-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.08s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-9226-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-9226-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-9226-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-9226-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-9226-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-9226-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-9226-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-9226-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-9226-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-9226-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-9226-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-9226-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.65s
hastagaras-halu-8b-llama_9226_v1 status is now torndown due to DeploymentManager action