submission_id: hastagaras-anjir-8b-l3-test-2_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Anjir-8B-L3-TEST-2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.0, '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: 2024-06-01T09:50:41+00:00
model_name: healing-test2-1
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3-T
num_battles: 12139
num_wins: 6639
celo_rating: 1210.08
safety_score: 0.93
propriety_score: 0.6666666666666666
propriety_total_count: 6.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: healing-test2-1
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Anjir-8B-L3-TEST-2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5469149023807562
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-test-2-v1-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-test-2-v1-mkmlizer to finish
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-test-2-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-anjir-8b-l3-test-2-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: Downloaded to shared memory in 29.634s
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-test-2-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%|▌ | 15/291 [00:04<01:02, 4.39it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.67it/s] Loading 0: 17%|█▋ | 50/291 [00:04<00:11, 20.54it/s] Loading 0: 22%|██▏ | 64/291 [00:05<00:09, 24.40it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.50it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.04it/s] Loading 0: 38%|███▊ | 112/291 [00:05<00:02, 61.52it/s] Loading 0: 43%|████▎ | 126/291 [00:05<00:02, 73.42it/s] Loading 0: 48%|████▊ | 141/291 [00:05<00:01, 86.44it/s] Loading 0: 55%|█████▍ | 159/291 [00:05<00:01, 102.56it/s] Loading 0: 60%|█████▉ | 174/291 [00:06<00:01, 75.61it/s] Loading 0: 64%|██████▍ | 186/291 [00:06<00:01, 82.97it/s] Loading 0: 70%|██████▉ | 203/291 [00:06<00:00, 97.62it/s] Loading 0: 74%|███████▍ | 216/291 [00:06<00:00, 103.43it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:00, 111.18it/s] Loading 0: 85%|████████▌ | 248/291 [00:06<00:00, 124.99it/s] Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 133.57it/s] Loading 0: 96%|█████████▌| 280/291 [00:07<00:00, 82.90it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: quantized model in 23.470s
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-TEST-2 in 55.702s
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-2-v1
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-2-v1/config.json
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-2-v1/special_tokens_map.json
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-2-v1/tokenizer_config.json
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-2-v1/tokenizer.json
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-2-v1/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-test-2-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-anjir-8b-l3-test-2-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-test-2-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-anjir-8b-l3-test-2-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-test-2-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-anjir-8b-l3-test-2-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-test-2-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-anjir-8b-l3-test-2-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: Saving duration: 0.403s
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.612s
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-2-v1_reward
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-2-v1_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-2-v1_reward/vocab.json
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-2-v1_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-2-v1_reward/merges.txt
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-2-v1_reward/config.json
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-2-v1_reward/tokenizer.json
hastagaras-anjir-8b-l3-test-2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-2-v1_reward/reward.tensors
Job hastagaras-anjir-8b-l3-test-2-v1-mkmlizer completed after 82.99s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-test-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-test-2-v1
Waiting for inference service hastagaras-anjir-8b-l3-test-2-v1 to be ready
Inference service hastagaras-anjir-8b-l3-test-2-v1 ready after 30.169809579849243s
Pipeline stage ISVCDeployer completed in 37.63s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.05749249458313s
Received healthy response to inference request in 1.358750581741333s
Received healthy response to inference request in 1.340857744216919s
Received healthy response to inference request in 1.2912392616271973s
Received healthy response to inference request in 1.2325100898742676s
5 requests
0 failed requests
5th percentile: 1.2442559242248534
10th percentile: 1.2560017585754395
20th percentile: 1.2794934272766114
30th percentile: 1.3011629581451416
40th percentile: 1.3210103511810303
50th percentile: 1.340857744216919
60th percentile: 1.3480148792266846
70th percentile: 1.3551720142364503
80th percentile: 1.4984989643096924
90th percentile: 1.7779957294464113
95th percentile: 1.9177441120147705
99th percentile: 2.029542818069458
mean time: 1.4561700344085693
Pipeline stage StressChecker completed in 7.97s
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-anjir-8b-l3-test-2_v1 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-test-2_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics