submission_id: hastagaras-anjrit_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/anjrit
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, '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: 2024-05-28T12:54:17+00:00
model_name: mweheh
model_eval_status: success
model_group: Hastagaras/anjrit
num_battles: 8023
num_wins: 4287
celo_rating: 1203.13
safety_score: 0.83
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: mweheh
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: 0.5343387760189455
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjrit-v1-mkmlizer
Waiting for job on hastagaras-anjrit-v1-mkmlizer to finish
hastagaras-anjrit-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjrit-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-anjrit-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjrit-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjrit-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjrit-v1-mkmlizer: ║ /___/ ║
hastagaras-anjrit-v1-mkmlizer: ║ ║
hastagaras-anjrit-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjrit-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjrit-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjrit-v1-mkmlizer: ║ ║
hastagaras-anjrit-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjrit-v1-mkmlizer: ║ belonging to: ║
hastagaras-anjrit-v1-mkmlizer: ║ ║
hastagaras-anjrit-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjrit-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjrit-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjrit-v1-mkmlizer: ║ ║
hastagaras-anjrit-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjrit-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-anjrit-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjrit-v1-mkmlizer: Downloaded to shared memory in 49.376s
hastagaras-anjrit-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjrit-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjrit-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:46, 2.44s/it] Loading 0: 4%|▍ | 13/291 [00:04<01:19, 3.52it/s] Loading 0: 8%|▊ | 24/291 [00:05<00:35, 7.61it/s] Loading 0: 13%|█▎ | 38/291 [00:05<00:17, 14.53it/s] Loading 0: 17%|█▋ | 49/291 [00:05<00:11, 21.15it/s] Loading 0: 21%|██ | 60/291 [00:05<00:10, 21.66it/s] Loading 0: 26%|██▌ | 76/291 [00:05<00:06, 33.37it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:05, 40.51it/s] Loading 0: 34%|███▍ | 99/291 [00:06<00:03, 52.35it/s] Loading 0: 38%|███▊ | 112/291 [00:06<00:02, 64.26it/s] Loading 0: 43%|████▎ | 124/291 [00:06<00:02, 71.69it/s] Loading 0: 48%|████▊ | 139/291 [00:06<00:01, 85.33it/s] Loading 0: 52%|█████▏ | 151/291 [00:06<00:01, 88.73it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:02, 61.10it/s] Loading 0: 60%|██████ | 176/291 [00:07<00:01, 67.31it/s] Loading 0: 64%|██████▍ | 186/291 [00:07<00:01, 73.24it/s] Loading 0: 69%|██████▊ | 200/291 [00:07<00:01, 87.35it/s] Loading 0: 73%|███████▎ | 212/291 [00:07<00:00, 92.16it/s] Loading 0: 77%|███████▋ | 224/291 [00:07<00:00, 98.80it/s] Loading 0: 82%|████████▏ | 238/291 [00:07<00:00, 107.69it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:00, 107.02it/s] Loading 0: 91%|█████████ | 265/291 [00:07<00:00, 113.30it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 62.51it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjrit-v1-mkmlizer: quantized model in 24.731s
hastagaras-anjrit-v1-mkmlizer: Processed model Hastagaras/anjrit in 76.908s
hastagaras-anjrit-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjrit-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjrit-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjrit-v1
hastagaras-anjrit-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjrit-v1/config.json
hastagaras-anjrit-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjrit-v1/tokenizer_config.json
hastagaras-anjrit-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjrit-v1/special_tokens_map.json
hastagaras-anjrit-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjrit-v1/tokenizer.json
hastagaras-anjrit-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjrit-v1/flywheel_model.0.safetensors
hastagaras-anjrit-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjrit-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-anjrit-v1-mkmlizer: warnings.warn(
hastagaras-anjrit-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-anjrit-v1-mkmlizer: warnings.warn(
hastagaras-anjrit-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-anjrit-v1-mkmlizer: warnings.warn(
hastagaras-anjrit-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-anjrit-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjrit-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjrit-v1-mkmlizer: Saving duration: 0.427s
hastagaras-anjrit-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 13.494s
hastagaras-anjrit-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjrit-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjrit-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjrit-v1_reward
hastagaras-anjrit-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjrit-v1_reward/tokenizer_config.json
hastagaras-anjrit-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjrit-v1_reward/config.json
hastagaras-anjrit-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjrit-v1_reward/special_tokens_map.json
hastagaras-anjrit-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjrit-v1_reward/vocab.json
hastagaras-anjrit-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjrit-v1_reward/merges.txt
hastagaras-anjrit-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjrit-v1_reward/tokenizer.json
hastagaras-anjrit-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjrit-v1_reward/reward.tensors
Job hastagaras-anjrit-v1-mkmlizer completed after 124.09s with status: succeeded
Stopping job with name hastagaras-anjrit-v1-mkmlizer
Pipeline stage MKMLizer completed in 124.86s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjrit-v1
Waiting for inference service hastagaras-anjrit-v1 to be ready
Inference service hastagaras-anjrit-v1 ready after 160.8714301586151s
Pipeline stage ISVCDeployer completed in 166.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1762287616729736s
Received healthy response to inference request in 1.3233821392059326s
Received healthy response to inference request in 1.3187248706817627s
Received healthy response to inference request in 1.2776854038238525s
Received healthy response to inference request in 1.23008131980896s
5 requests
0 failed requests
5th percentile: 1.2396021366119385
10th percentile: 1.249122953414917
20th percentile: 1.268164587020874
30th percentile: 1.2858932971954347
40th percentile: 1.3023090839385987
50th percentile: 1.3187248706817627
60th percentile: 1.3205877780914306
70th percentile: 1.3224506855010987
80th percentile: 1.493951463699341
90th percentile: 1.8350901126861574
95th percentile: 2.005659437179565
99th percentile: 2.142114896774292
mean time: 1.4652204990386963
Pipeline stage StressChecker completed in 7.95s
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_v1 status is now deployed due to DeploymentManager action
hastagaras-anjrit_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics