submission_id: hastagaras-anjir-8b-l3-m_6487_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Anjir-8B-L3-MK.V-BJ1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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: 2024-06-10T23:24:30+00:00
model_name: 1
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3-M
num_battles: 9901
num_wins: 5572
celo_rating: 1224.59
propriety_score: 0.668364099299809
propriety_total_count: 3142.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: 1
ineligible_reason: None
language_model: Hastagaras/Anjir-8B-L3-MK.V-BJ1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-10
win_ratio: 0.5627714372285628
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer to finish
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-m-6487-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-anjir-8b-l3-m-6487-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: Downloaded to shared memory in 19.764s
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:56, 2.27s/it] Loading 0: 6%|▌ | 18/291 [00:04<00:51, 5.30it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.31it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.65it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.36it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 36.48it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.32it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 64.96it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:01, 81.27it/s] Loading 0: 51%|█████ | 148/291 [00:05<00:01, 97.24it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 75.54it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 91.19it/s] Loading 0: 69%|██████▊ | 200/291 [00:06<00:00, 103.93it/s] Loading 0: 74%|███████▍ | 215/291 [00:06<00:00, 111.87it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:00, 120.26it/s] Loading 0: 86%|████████▌ | 249/291 [00:06<00:00, 132.26it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 90.30it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 105.25it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: quantized model in 22.825s
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-MK.V-BJ1 in 45.057s
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v2
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v2/special_tokens_map.json
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v2/config.json
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v2/tokenizer_config.json
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v2/tokenizer.json
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v2/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-m-6487-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-anjir-8b-l3-m-6487-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-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-anjir-8b-l3-m-6487-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-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-anjir-8b-l3-m-6487-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-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-anjir-8b-l3-m-6487-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v2_reward
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v2_reward/config.json
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v2_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v2_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v2_reward/merges.txt
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v2_reward/vocab.json
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v2_reward/tokenizer.json
hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v2_reward/reward.tensors
Job hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer completed after 73.09s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-m-6487-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.92s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-m-6487-v2
Waiting for inference service hastagaras-anjir-8b-l3-m-6487-v2 to be ready
Inference service hastagaras-anjir-8b-l3-m-6487-v2 ready after 40.34753608703613s
Pipeline stage ISVCDeployer completed in 46.20s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.138160467147827s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.3321263790130615s
Received healthy response to inference request in 1.3327968120574951s
Received healthy response to inference request in 1.3280706405639648s
Received healthy response to inference request in 1.2901525497436523s
Received healthy response to inference request in 1.2474935054779053s
5 requests
0 failed requests
5th percentile: 1.2560253143310547
10th percentile: 1.264557123184204
20th percentile: 1.281620740890503
30th percentile: 1.2977361679077148
40th percentile: 1.3129034042358398
50th percentile: 1.3280706405639648
60th percentile: 1.3296929359436036
70th percentile: 1.3313152313232421
80th percentile: 1.3322604656219483
90th percentile: 1.3325286388397217
95th percentile: 1.3326627254486083
99th percentile: 1.3327699947357177
mean time: 1.3061279773712158
Pipeline stage StressChecker completed in 29.42s
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-anjir-8b-l3-m_6487_v2 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-m_6487_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics