submission_id: hastagaras-haluanjir-8b-l3-dd_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/HaluAnjir-8B-L3-DD
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, '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}
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: 2024-05-30T15:08:56+00:00
model_name: dah-ah
model_eval_status: success
model_group: Hastagaras/HaluAnjir-8B-
num_battles: 11541
num_wins: 6436
celo_rating: 1214.47
propriety_score: 1.0
propriety_total_count: 3.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: dah-ah
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/HaluAnjir-8B-L3-DD
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-30
win_ratio: 0.5576639805909367
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer
Waiting for job on hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer to finish
Stopping job with name hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer
Waiting for job on hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer to finish
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ /___/ ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ belonging to: ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ║ ║
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-haluanjir-8b-l3-dd-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-haluanjir-8b-l3-dd-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: Downloaded to shared memory in 32.947s
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:47, 2.45s/it] Loading 0: 8%|▊ | 22/291 [00:05<00:44, 6.05it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:19, 13.13it/s] Loading 0: 21%|██ | 60/291 [00:05<00:12, 18.85it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:06, 30.11it/s] Loading 0: 35%|███▍ | 101/291 [00:05<00:04, 43.32it/s] Loading 0: 42%|████▏ | 121/291 [00:05<00:02, 58.60it/s] Loading 0: 48%|████▊ | 140/291 [00:05<00:02, 74.58it/s] Loading 0: 55%|█████▍ | 159/291 [00:06<00:01, 91.67it/s] Loading 0: 61%|██████ | 177/291 [00:06<00:01, 70.36it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 94.55it/s] Loading 0: 76%|███████▌ | 221/291 [00:06<00:00, 109.82it/s] Loading 0: 82%|████████▏ | 240/291 [00:06<00:00, 125.05it/s] Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 148.93it/s] Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 98.54it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: quantized model in 19.107s
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: Processed model Hastagaras/HaluAnjir-8B-L3-DD in 53.402s
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-haluanjir-8b-l3-dd-v1
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-haluanjir-8b-l3-dd-v1/config.json
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-haluanjir-8b-l3-dd-v1/special_tokens_map.json
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-haluanjir-8b-l3-dd-v1/tokenizer_config.json
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-haluanjir-8b-l3-dd-v1/tokenizer.json
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-haluanjir-8b-l3-dd-v1/flywheel_model.0.safetensors
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-haluanjir-8b-l3-dd-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-haluanjir-8b-l3-dd-v1-mkmlizer: warnings.warn(
hastagaras-haluanjir-8b-l3-dd-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-haluanjir-8b-l3-dd-v1-mkmlizer: warnings.warn(
hastagaras-haluanjir-8b-l3-dd-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-haluanjir-8b-l3-dd-v1-mkmlizer: warnings.warn(
hastagaras-haluanjir-8b-l3-dd-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-haluanjir-8b-l3-dd-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: Saving duration: 0.306s
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.532s
hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer: creating bucket guanaco-reward-models
Job hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer completed after 83.61s with status: succeeded
Stopping job with name hastagaras-haluanjir-8b-l3-dd-v1-mkmlizer
Pipeline stage MKMLizer completed in 89.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-haluanjir-8b-l3-dd-v1
Waiting for inference service hastagaras-haluanjir-8b-l3-dd-v1 to be ready
Inference service hastagaras-haluanjir-8b-l3-dd-v1 ready after 60.466747760772705s
Pipeline stage ISVCDeployer completed in 68.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.190662384033203s
Received healthy response to inference request in 1.4196367263793945s
Received healthy response to inference request in 1.3192470073699951s
Received healthy response to inference request in 1.323225975036621s
Received healthy response to inference request in 1.2440874576568604s
5 requests
0 failed requests
5th percentile: 1.2591193675994874
10th percentile: 1.2741512775421142
20th percentile: 1.304215097427368
30th percentile: 1.3200428009033203
40th percentile: 1.3216343879699708
50th percentile: 1.323225975036621
60th percentile: 1.3617902755737306
70th percentile: 1.4003545761108398
80th percentile: 1.5738418579101563
90th percentile: 1.8822521209716798
95th percentile: 2.036457252502441
99th percentile: 2.1598213577270506
mean time: 1.4993719100952148
Pipeline stage StressChecker completed in 8.11s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.02s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-haluanjir-8b-l3-dd_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-haluanjir-8b-l3-dd_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics