submission_id: hastagaras-anjir-8b-l3-test_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Anjir-8B-L3-TEST
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.85, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 40, '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: 2024-06-01T08:06:03+00:00
model_name: healing-test2
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3-T
num_battles: 10673
num_wins: 5840
celo_rating: 1211.48
safety_score: 0.92
propriety_score: 0.8
propriety_total_count: 5.0
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
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Anjir-8B-L3-TEST
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.547175114775602
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-test-v2-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-test-v2-mkmlizer to finish
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-test-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-test-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-test-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-test-v2-mkmlizer: Downloaded to shared memory in 17.134s
hastagaras-anjir-8b-l3-test-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-test-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-test-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 115.84it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 144.46it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 151.36it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 154.97it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 77.90it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 85.48it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 102.48it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 116.83it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 128.17it/s] Loading 0: 57%|█████▋ | 166/291 [00:01<00:00, 136.63it/s] Loading 0: 63%|██████▎ | 182/291 [00:01<00:00, 142.45it/s] Loading 0: 68%|██████▊ | 198/291 [00:01<00:01, 83.61it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 93.72it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 108.96it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 122.45it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 133.47it/s] Loading 0: 98%|█████████▊| 285/291 [00:02<00:00, 146.35it/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-v2-mkmlizer: quantized model in 23.392s
hastagaras-anjir-8b-l3-test-v2-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-TEST in 43.214s
hastagaras-anjir-8b-l3-test-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-test-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-test-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-v2
hastagaras-anjir-8b-l3-test-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-v2/config.json
hastagaras-anjir-8b-l3-test-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-v2/special_tokens_map.json
hastagaras-anjir-8b-l3-test-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-v2/tokenizer_config.json
hastagaras-anjir-8b-l3-test-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-v2/tokenizer.json
hastagaras-anjir-8b-l3-test-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-v2/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-test-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-test-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-test-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-test-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-test-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-test-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-test-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-test-v2-mkmlizer: Saving duration: 0.457s
hastagaras-anjir-8b-l3-test-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.372s
hastagaras-anjir-8b-l3-test-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-test-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-test-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v2_reward
hastagaras-anjir-8b-l3-test-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v2_reward/config.json
hastagaras-anjir-8b-l3-test-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v2_reward/merges.txt
hastagaras-anjir-8b-l3-test-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v2_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-test-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v2_reward/vocab.json
hastagaras-anjir-8b-l3-test-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v2_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-test-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v2_reward/tokenizer.json
hastagaras-anjir-8b-l3-test-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v2_reward/reward.tensors
Job hastagaras-anjir-8b-l3-test-v2-mkmlizer completed after 76.69s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-test-v2-mkmlizer
Pipeline stage MKMLizer completed in 80.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-test-v2
Waiting for inference service hastagaras-anjir-8b-l3-test-v2 to be ready
Inference service hastagaras-anjir-8b-l3-test-v2 ready after 40.22588658332825s
Pipeline stage ISVCDeployer completed in 48.64s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.127174139022827s
Received healthy response to inference request in 1.33890700340271s
Received healthy response to inference request in 1.3419849872589111s
Received healthy response to inference request in 1.2955691814422607s
Received healthy response to inference request in 1.2171547412872314s
5 requests
0 failed requests
5th percentile: 1.2328376293182373
10th percentile: 1.248520517349243
20th percentile: 1.279886293411255
30th percentile: 1.3042367458343507
40th percentile: 1.3215718746185303
50th percentile: 1.33890700340271
60th percentile: 1.3401381969451904
70th percentile: 1.341369390487671
80th percentile: 1.4990228176116944
90th percentile: 1.8130984783172608
95th percentile: 1.9701363086700439
99th percentile: 2.0957665729522703
mean time: 1.464158010482788
Pipeline stage StressChecker completed in 7.99s
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
hastagaras-anjir-8b-l3-test_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-anjir-8b-l3-test_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics