submission_id: hastagaras-anjir-8b-l3_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Anjir-8B-L3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, '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: 2024-05-30T03:32:00+00:00
model_name: test2
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3
num_battles: 7943
num_wins: 4410
celo_rating: 1215.8
safety_score: 0.82
propriety_score: 0.0
propriety_total_count: 2.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: test2
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: 2024-05-29
win_ratio: 0.5552058416215536
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-v2-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-v2-mkmlizer to finish
hastagaras-anjir-8b-l3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-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-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-v2-mkmlizer: Downloaded to shared memory in 16.718s
hastagaras-anjir-8b-l3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:40, 2.22s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:01, 4.49it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:21, 11.94it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.49it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.75it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 36.94it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 48.95it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 65.28it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 82.51it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 99.23it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 76.70it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 93.23it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 109.03it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 121.64it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 133.79it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 142.94it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 93.53it/s] Loading 0: 99%|█████████▉| 288/291 [00:06<00:00, 103.75it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-v2-mkmlizer: quantized model in 22.991s
hastagaras-anjir-8b-l3-v2-mkmlizer: Processed model Hastagaras/Anjir-8B-L3 in 42.222s
hastagaras-anjir-8b-l3-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v2
hastagaras-anjir-8b-l3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v2/config.json
hastagaras-anjir-8b-l3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v2/tokenizer_config.json
hastagaras-anjir-8b-l3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v2/special_tokens_map.json
hastagaras-anjir-8b-l3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v2/tokenizer.json
hastagaras-anjir-8b-l3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v2/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-v2-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-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-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-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-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-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-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-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-v2-mkmlizer: Saving duration: 0.417s
hastagaras-anjir-8b-l3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.512s
hastagaras-anjir-8b-l3-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v2_reward
hastagaras-anjir-8b-l3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v2_reward/config.json
hastagaras-anjir-8b-l3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v2_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v2_reward/merges.txt
hastagaras-anjir-8b-l3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v2_reward/vocab.json
hastagaras-anjir-8b-l3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v2_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v2_reward/tokenizer.json
hastagaras-anjir-8b-l3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v2_reward/reward.tensors
Job hastagaras-anjir-8b-l3-v2-mkmlizer completed after 73.08s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-v2-mkmlizer
Pipeline stage MKMLizer completed in 77.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-v2
Waiting for inference service hastagaras-anjir-8b-l3-v2 to be ready
Inference service hastagaras-anjir-8b-l3-v2 ready after 30.168707370758057s
Pipeline stage ISVCDeployer completed in 37.34s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0664334297180176s
Received healthy response to inference request in 1.3477871417999268s
Received healthy response to inference request in 1.3434903621673584s
Received healthy response to inference request in 1.3332653045654297s
Received healthy response to inference request in 1.2446606159210205s
5 requests
0 failed requests
5th percentile: 1.2623815536499023
10th percentile: 1.2801024913787842
20th percentile: 1.3155443668365479
30th percentile: 1.3353103160858155
40th percentile: 1.339400339126587
50th percentile: 1.3434903621673584
60th percentile: 1.3452090740203857
70th percentile: 1.346927785873413
80th percentile: 1.491516399383545
90th percentile: 1.7789749145507814
95th percentile: 1.9227041721343994
99th percentile: 2.037687578201294
mean time: 1.4671273708343506
Pipeline stage StressChecker completed in 8.00s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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_v2 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics