submission_id: hastagaras-anjir-8b-l3-m_6487_v6
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': 0.95, 'top_p': 0.95, 'min_p': 0.06, 'top_k': 60, '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: 2024-06-16T22:52:43+00:00
model_name: t
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3-M
num_battles: 24995
num_wins: 13160
celo_rating: 1212.01
propriety_score: 0.685878728923476
propriety_total_count: 12336.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: t
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: 2024-06-16
win_ratio: 0.5265053010602121
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer to finish
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-m-6487-v6-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-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: Downloaded to shared memory in 18.969s
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:38, 2.42s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:12, 3.84it/s] Loading 0: 11%|█ | 31/291 [00:05<00:25, 10.34it/s] Loading 0: 15%|█▌ | 45/291 [00:05<00:14, 17.18it/s] Loading 0: 21%|██ | 60/291 [00:05<00:11, 20.12it/s] Loading 0: 26%|██▌ | 76/291 [00:05<00:07, 29.99it/s] Loading 0: 31%|███ | 90/291 [00:05<00:05, 40.03it/s] Loading 0: 36%|███▌ | 104/291 [00:06<00:03, 51.23it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 66.61it/s] Loading 0: 46%|████▋ | 135/291 [00:06<00:02, 75.22it/s] Loading 0: 51%|█████ | 148/291 [00:06<00:01, 76.91it/s] Loading 0: 56%|█████▌ | 162/291 [00:06<00:01, 88.28it/s] Loading 0: 60%|█████▉ | 174/291 [00:06<00:01, 60.56it/s] Loading 0: 64%|██████▎ | 185/291 [00:06<00:01, 68.44it/s] Loading 0: 68%|██████▊ | 199/291 [00:07<00:01, 81.14it/s] Loading 0: 73%|███████▎ | 212/291 [00:07<00:00, 90.11it/s] Loading 0: 79%|███████▊ | 229/291 [00:07<00:00, 104.70it/s] Loading 0: 83%|████████▎ | 242/291 [00:07<00:00, 110.33it/s] Loading 0: 88%|████████▊ | 257/291 [00:07<00:00, 116.88it/s] Loading 0: 93%|█████████▎| 270/291 [00:07<00:00, 68.45it/s] Loading 0: 98%|█████████▊| 284/291 [00:08<00:00, 79.48it/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-v6-mkmlizer: quantized model in 27.074s
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-MK.V-BJ1 in 48.778s
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v6
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v6/tokenizer_config.json
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v6/special_tokens_map.json
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v6/config.json
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v6/tokenizer.json
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v6/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-m-6487-v6-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-v6-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-v6-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-v6-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-v6-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-v6-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-v6-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-v6-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: Saving duration: 0.419s
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.385s
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v6_reward
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v6_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v6_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v6_reward/config.json
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v6_reward/merges.txt
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v6_reward/vocab.json
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v6_reward/tokenizer.json
hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v6_reward/reward.tensors
Job hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer completed after 72.63s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-m-6487-v6-mkmlizer
Pipeline stage MKMLizer completed in 75.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-m-6487-v6
Waiting for inference service hastagaras-anjir-8b-l3-m-6487-v6 to be ready
Inference service hastagaras-anjir-8b-l3-m-6487-v6 ready after 30.165855169296265s
Pipeline stage ISVCDeployer completed in 36.82s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.423543691635132s
Received healthy response to inference request in 1.253917932510376s
Received healthy response to inference request in 1.2573983669281006s
Received healthy response to inference request in 1.2404897212982178s
Received healthy response to inference request in 1.2340021133422852s
5 requests
0 failed requests
5th percentile: 1.2352996349334717
10th percentile: 1.2365971565246583
20th percentile: 1.2391921997070312
30th percentile: 1.2431753635406495
40th percentile: 1.2485466480255127
50th percentile: 1.253917932510376
60th percentile: 1.2553101062774659
70th percentile: 1.2567022800445558
80th percentile: 1.490627431869507
90th percentile: 1.9570855617523195
95th percentile: 2.1903146266937252
99th percentile: 2.3768978786468504
mean time: 1.4818703651428222
Pipeline stage StressChecker completed in 8.03s
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_v6 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-m_6487_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics