submission_id: hastagaras-anjrit_v3
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/anjrit
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.85, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 45, '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: 2024-05-28T22:53:06+00:00
model_name: test
model_eval_status: success
model_group: Hastagaras/anjrit
num_battles: 11592
num_wins: 6569
celo_rating: 1218.15
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: test
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/anjrit
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-28
win_ratio: 0.5666839199447895
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjrit-v3-mkmlizer
Waiting for job on hastagaras-anjrit-v3-mkmlizer to finish
hastagaras-anjrit-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjrit-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-anjrit-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjrit-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjrit-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjrit-v3-mkmlizer: ║ /___/ ║
hastagaras-anjrit-v3-mkmlizer: ║ ║
hastagaras-anjrit-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjrit-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjrit-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjrit-v3-mkmlizer: ║ ║
hastagaras-anjrit-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjrit-v3-mkmlizer: ║ belonging to: ║
hastagaras-anjrit-v3-mkmlizer: ║ ║
hastagaras-anjrit-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjrit-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjrit-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjrit-v3-mkmlizer: ║ ║
hastagaras-anjrit-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjrit-v3-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-anjrit-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjrit-v3-mkmlizer: Downloaded to shared memory in 16.322s
hastagaras-anjrit-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjrit-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjrit-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:43, 2.23s/it] Loading 0: 6%|▌ | 17/291 [00:04<00:53, 5.09it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.66it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.23it/s] Loading 0: 23%|██▎ | 66/291 [00:05<00:08, 26.65it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 37.05it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 48.79it/s] Loading 0: 38%|███▊ | 112/291 [00:05<00:02, 62.63it/s] Loading 0: 45%|████▍ | 130/291 [00:05<00:02, 80.02it/s] Loading 0: 51%|█████ | 148/291 [00:05<00:01, 97.03it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 76.44it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 92.68it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 107.63it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 120.34it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 131.72it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 141.55it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 94.10it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 102.51it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjrit-v3-mkmlizer: quantized model in 22.895s
hastagaras-anjrit-v3-mkmlizer: Processed model Hastagaras/anjrit in 41.666s
hastagaras-anjrit-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjrit-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjrit-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjrit-v3
hastagaras-anjrit-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjrit-v3/config.json
hastagaras-anjrit-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjrit-v3/special_tokens_map.json
hastagaras-anjrit-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjrit-v3/tokenizer_config.json
hastagaras-anjrit-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjrit-v3/tokenizer.json
hastagaras-anjrit-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjrit-v3/flywheel_model.0.safetensors
hastagaras-anjrit-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjrit-v3-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-anjrit-v3-mkmlizer: warnings.warn(
hastagaras-anjrit-v3-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-anjrit-v3-mkmlizer: warnings.warn(
hastagaras-anjrit-v3-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-anjrit-v3-mkmlizer: warnings.warn(
hastagaras-anjrit-v3-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-anjrit-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjrit-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjrit-v3-mkmlizer: Saving duration: 0.402s
hastagaras-anjrit-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.115s
hastagaras-anjrit-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjrit-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjrit-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjrit-v3_reward
hastagaras-anjrit-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjrit-v3_reward/config.json
hastagaras-anjrit-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjrit-v3_reward/special_tokens_map.json
hastagaras-anjrit-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjrit-v3_reward/vocab.json
hastagaras-anjrit-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjrit-v3_reward/tokenizer_config.json
hastagaras-anjrit-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjrit-v3_reward/merges.txt
hastagaras-anjrit-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjrit-v3_reward/tokenizer.json
hastagaras-anjrit-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjrit-v3_reward/reward.tensors
Job hastagaras-anjrit-v3-mkmlizer completed after 62.9s with status: succeeded
Stopping job with name hastagaras-anjrit-v3-mkmlizer
Pipeline stage MKMLizer completed in 67.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjrit-v3
Waiting for inference service hastagaras-anjrit-v3 to be ready
Inference service hastagaras-anjrit-v3 ready after 40.24847435951233s
Pipeline stage ISVCDeployer completed in 47.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3083877563476562s
Received healthy response to inference request in 1.3636512756347656s
Received healthy response to inference request in 1.3386023044586182s
Received healthy response to inference request in 1.3500099182128906s
Received healthy response to inference request in 1.2649095058441162s
5 requests
0 failed requests
5th percentile: 1.2796480655670166
10th percentile: 1.294386625289917
20th percentile: 1.3238637447357178
30th percentile: 1.3408838272094727
40th percentile: 1.3454468727111817
50th percentile: 1.3500099182128906
60th percentile: 1.3554664611816407
70th percentile: 1.3609230041503906
80th percentile: 1.5525985717773438
90th percentile: 1.9304931640625
95th percentile: 2.119440460205078
99th percentile: 2.2705982971191405
mean time: 1.5251121520996094
Pipeline stage StressChecker completed in 8.26s
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-anjrit_v3 status is now deployed due to DeploymentManager action
hastagaras-anjrit_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics