submission_id: hastagaras-anjir-8b-l3_v6
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Anjir-8B-L3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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': "<|begin_of_text|><|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: 2024-06-11T05:54:50+00:00
model_name: propriety-test
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3
num_battles: 12728
num_wins: 6992
celo_rating: 1214.11
safety_score: 0.9
propriety_score: 0.6606862525229872
propriety_total_count: 4459.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: propriety-test
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Anjir-8B-L3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-10
win_ratio: 0.5493400377121307
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-v6-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-v6-mkmlizer to finish
hastagaras-anjir-8b-l3-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-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-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-v6-mkmlizer: Downloaded to shared memory in 32.743s
hastagaras-anjir-8b-l3-v6-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:11, 2.12s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:03, 4.34it/s] Loading 0: 11%|█ | 31/291 [00:04<00:22, 11.60it/s] Loading 0: 14%|█▍ | 42/291 [00:04<00:14, 17.41it/s] Loading 0: 20%|██ | 59/291 [00:04<00:07, 29.05it/s] Loading 0: 25%|██▍ | 72/291 [00:05<00:07, 29.12it/s] Loading 0: 30%|██▉ | 86/291 [00:05<00:05, 39.64it/s] Loading 0: 35%|███▌ | 103/291 [00:05<00:03, 54.78it/s] Loading 0: 40%|███▉ | 116/291 [00:05<00:02, 65.23it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:02, 77.74it/s] Loading 0: 51%|█████ | 148/291 [00:05<00:01, 92.82it/s] Loading 0: 56%|█████▌ | 162/291 [00:05<00:01, 96.76it/s] Loading 0: 60%|██████ | 175/291 [00:06<00:01, 62.80it/s] Loading 0: 64%|██████▍ | 186/291 [00:06<00:01, 69.89it/s] Loading 0: 70%|██████▉ | 203/291 [00:06<00:01, 85.42it/s] Loading 0: 74%|███████▍ | 215/291 [00:06<00:00, 91.62it/s] Loading 0: 79%|███████▉ | 230/291 [00:06<00:00, 102.38it/s] Loading 0: 84%|████████▍ | 245/291 [00:06<00:00, 113.70it/s] Loading 0: 89%|████████▊ | 258/291 [00:06<00:00, 109.21it/s] Loading 0: 93%|█████████▎| 271/291 [00:07<00:00, 63.39it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 74.11it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-v6-mkmlizer: quantized model in 20.118s
hastagaras-anjir-8b-l3-v6-mkmlizer: Processed model Hastagaras/Anjir-8B-L3 in 54.011s
hastagaras-anjir-8b-l3-v6-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v6
hastagaras-anjir-8b-l3-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v6/tokenizer_config.json
hastagaras-anjir-8b-l3-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v6/config.json
hastagaras-anjir-8b-l3-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v6/special_tokens_map.json
hastagaras-anjir-8b-l3-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v6/tokenizer.json
hastagaras-anjir-8b-l3-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v6/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-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-v6-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-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-v6-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-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-v6-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-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-v6-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-v6-mkmlizer: Saving duration: 0.278s
hastagaras-anjir-8b-l3-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.480s
hastagaras-anjir-8b-l3-v6-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v6_reward
hastagaras-anjir-8b-l3-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v6_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v6_reward/config.json
hastagaras-anjir-8b-l3-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v6_reward/merges.txt
hastagaras-anjir-8b-l3-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v6_reward/vocab.json
hastagaras-anjir-8b-l3-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v6_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v6_reward/tokenizer.json
hastagaras-anjir-8b-l3-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v6_reward/reward.tensors
Job hastagaras-anjir-8b-l3-v6-mkmlizer completed after 72.66s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-v6-mkmlizer
Pipeline stage MKMLizer completed in 76.59s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-v6
Waiting for inference service hastagaras-anjir-8b-l3-v6 to be ready
Inference service hastagaras-anjir-8b-l3-v6 ready after 40.223973751068115s
Pipeline stage ISVCDeployer completed in 47.43s
Running pipeline stage StressChecker
%s, retrying in %s seconds...
Received healthy response to inference request in 11.241026878356934s
Received healthy response to inference request in 1.327880620956421s
Received healthy response to inference request in 1.2953135967254639s
Received healthy response to inference request in 1.3528509140014648s
Received healthy response to inference request in 1.337096929550171s
5 requests
0 failed requests
5th percentile: 1.3018270015716553
10th percentile: 1.3083404064178468
20th percentile: 1.3213672161102294
30th percentile: 1.329723882675171
40th percentile: 1.3334104061126708
50th percentile: 1.337096929550171
60th percentile: 1.3433985233306884
70th percentile: 1.349700117111206
80th percentile: 3.33048610687256
90th percentile: 7.2857564926147464
95th percentile: 9.263391685485837
99th percentile: 10.845499839782715
mean time: 3.310833787918091
Pipeline stage StressChecker completed in 37.42s
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_v6 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics