developer_uid: Hastagaras
submission_id: hastagaras-anjir-8b-l3_v9
model_name: t
model_group: Hastagaras/Anjir-8B-L3
status: rejected
timestamp: 2024-06-15T01:36:58+00:00
num_battles: 1274
num_wins: 619
celo_rating: 1188.73
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Anjir-8B-L3
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: t
ineligible_reason: model is not deployable
is_internal_developer: False
language_model: Hastagaras/Anjir-8B-L3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-14
win_ratio: 0.4858712715855573
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, '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': "<|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}
model_eval_status: error
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-v9-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-v9-mkmlizer to finish
hastagaras-anjir-8b-l3-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-v9-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-v9-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-v9-mkmlizer: Downloaded to shared memory in 38.506s
hastagaras-anjir-8b-l3-v9-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-v9-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:52, 2.26s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.41it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.70it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.01it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:09, 24.87it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.34it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.01it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 64.00it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 80.34it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 96.19it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 73.39it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 89.09it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 104.08it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 117.07it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 127.68it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 137.14it/s] Loading 0: 93%|█████████▎| 272/291 [00:07<00:00, 87.85it/s] Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 94.78it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-v9-mkmlizer: quantized model in 23.292s
hastagaras-anjir-8b-l3-v9-mkmlizer: Processed model Hastagaras/Anjir-8B-L3 in 64.462s
hastagaras-anjir-8b-l3-v9-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v9
hastagaras-anjir-8b-l3-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v9/config.json
hastagaras-anjir-8b-l3-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v9/tokenizer_config.json
hastagaras-anjir-8b-l3-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v9/special_tokens_map.json
hastagaras-anjir-8b-l3-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v9/tokenizer.json
hastagaras-anjir-8b-l3-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v9/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-v9-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-v9-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v9-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-v9-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v9-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-v9-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-v9-mkmlizer: Saving duration: 0.419s
hastagaras-anjir-8b-l3-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.411s
hastagaras-anjir-8b-l3-v9-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v9_reward
hastagaras-anjir-8b-l3-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v9_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v9_reward/vocab.json
hastagaras-anjir-8b-l3-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v9_reward/tokenizer.json
hastagaras-anjir-8b-l3-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v9_reward/config.json
hastagaras-anjir-8b-l3-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v9_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v9_reward/merges.txt
hastagaras-anjir-8b-l3-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v9_reward/reward.tensors
Job hastagaras-anjir-8b-l3-v9-mkmlizer completed after 93.54s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-v9-mkmlizer
Pipeline stage MKMLizer completed in 97.96s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-v9
Waiting for inference service hastagaras-anjir-8b-l3-v9 to be ready
Inference service hastagaras-anjir-8b-l3-v9 ready after 40.22875475883484s
Pipeline stage ISVCDeployer completed in 47.76s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2776379585266113s
Received healthy response to inference request in 1.3554954528808594s
Received healthy response to inference request in 1.3042504787445068s
Received healthy response to inference request in 1.2988262176513672s
Received healthy response to inference request in 1.354430913925171s
5 requests
0 failed requests
5th percentile: 1.2999110698699952
10th percentile: 1.3009959220886231
20th percentile: 1.3031656265258789
30th percentile: 1.3142865657806397
40th percentile: 1.3343587398529053
50th percentile: 1.354430913925171
60th percentile: 1.3548567295074463
70th percentile: 1.3552825450897217
80th percentile: 1.53992395401001
90th percentile: 1.9087809562683107
95th percentile: 2.0932094573974607
99th percentile: 2.2407522583007813
mean time: 1.5181282043457032
Pipeline stage StressChecker completed in 8.19s
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_v9 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3_v9 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.