developer_uid: Hastagaras
submission_id: hastagaras-anjir-8b-l3-mk-ii_v1
model_name: hastagaras-anjir-8b-l3-mk-ii_v1
model_group: Hastagaras/Anjir-8B-L3-M
status: rejected
timestamp: 2024-06-08T02:41:27+00:00
num_battles: 1162
num_wins: 655
celo_rating: 1225.0
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Anjir-8B-L3-MK.II
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-anjir-8b-l3-mk-ii_v1
ineligible_reason: model is not deployable
is_internal_developer: False
language_model: Hastagaras/Anjir-8B-L3-MK.II
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-07
win_ratio: 0.5636833046471601
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, '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': "<|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: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
model_eval_status: error
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer to finish
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-mk-ii-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-anjir-8b-l3-mk-ii-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: Downloaded to shared memory in 35.852s
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 127.23it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 149.27it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 156.00it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 158.84it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 81.92it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 89.55it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 107.08it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 122.05it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 133.24it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 142.53it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 96.46it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 104.01it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 117.72it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 129.01it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 138.85it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 146.90it/s] Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.13it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: quantized model in 22.768s
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-MK.II in 61.230s
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-mk-ii-v1
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-mk-ii-v1/config.json
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-mk-ii-v1/tokenizer_config.json
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-mk-ii-v1/special_tokens_map.json
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-mk-ii-v1/tokenizer.json
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-mk-ii-v1/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-mk-ii-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-anjir-8b-l3-mk-ii-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-mk-ii-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-anjir-8b-l3-mk-ii-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-mk-ii-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-anjir-8b-l3-mk-ii-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-mk-ii-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-anjir-8b-l3-mk-ii-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: Saving duration: 0.399s
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.247s
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v1_reward
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v1_reward/config.json
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v1_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v1_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v1_reward/vocab.json
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v1_reward/tokenizer.json
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v1_reward/merges.txt
hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v1_reward/reward.tensors
Job hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer completed after 94.68s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-mk-ii-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-mk-ii-v1
Waiting for inference service hastagaras-anjir-8b-l3-mk-ii-v1 to be ready
Inference service hastagaras-anjir-8b-l3-mk-ii-v1 ready after 30.2311053276062s
Pipeline stage ISVCDeployer completed in 35.84s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1647260189056396s
Received healthy response to inference request in 1.3237662315368652s
Received healthy response to inference request in 1.2956657409667969s
Received healthy response to inference request in 1.2728352546691895s
Received healthy response to inference request in 1.2245512008666992s
5 requests
0 failed requests
5th percentile: 1.2342080116271972
10th percentile: 1.2438648223876954
20th percentile: 1.2631784439086915
30th percentile: 1.2774013519287108
40th percentile: 1.2865335464477539
50th percentile: 1.2956657409667969
60th percentile: 1.3069059371948242
70th percentile: 1.3181461334228515
80th percentile: 1.4919581890106204
90th percentile: 1.82834210395813
95th percentile: 1.9965340614318845
99th percentile: 2.1310876274108885
mean time: 1.4563088893890381
Pipeline stage StressChecker completed in 7.92s
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-mk-ii_v1 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-mk-ii_v1 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.