developer_uid: Hastagaras
submission_id: hastagaras-anjir-8b-l3_v7
model_name: propriety-test
model_group: Hastagaras/Anjir-8B-L3
status: torndown
timestamp: 2024-06-11T06:00:59+00:00
num_battles: 10487
num_wins: 5885
celo_rating: 1222.72
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: propriety-test
is_internal_developer: False
language_model: Hastagaras/Anjir-8B-L3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-10
win_ratio: 0.561170973586345
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: success
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-v7-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-v7-mkmlizer to finish
hastagaras-anjir-8b-l3-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-v7-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-v7-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-v7-mkmlizer: Downloaded to shared memory in 18.948s
hastagaras-anjir-8b-l3-v7-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<12:02, 2.50s/it] Loading 0: 4%|▍ | 13/291 [00:05<01:20, 3.44it/s] Loading 0: 8%|▊ | 24/291 [00:05<00:35, 7.49it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:15, 15.75it/s] Loading 0: 20%|█▉ | 58/291 [00:05<00:08, 26.01it/s] Loading 0: 24%|██▍ | 71/291 [00:05<00:08, 25.03it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:05, 34.98it/s] Loading 0: 35%|███▍ | 101/291 [00:06<00:04, 46.94it/s] Loading 0: 39%|███▉ | 113/291 [00:06<00:03, 56.35it/s] Loading 0: 45%|████▍ | 130/291 [00:06<00:02, 72.45it/s] Loading 0: 49%|████▉ | 143/291 [00:06<00:01, 82.20it/s] Loading 0: 54%|█████▍ | 158/291 [00:06<00:01, 93.58it/s] Loading 0: 59%|█████▉ | 171/291 [00:07<00:01, 62.58it/s] Loading 0: 64%|██████▎ | 185/291 [00:07<00:01, 74.02it/s] Loading 0: 69%|██████▊ | 200/291 [00:07<00:01, 88.13it/s] Loading 0: 73%|███████▎ | 213/291 [00:07<00:00, 93.49it/s] Loading 0: 79%|███████▊ | 229/291 [00:07<00:00, 108.00it/s] Loading 0: 83%|████████▎ | 242/291 [00:07<00:00, 111.11it/s] Loading 0: 88%|████████▊ | 257/291 [00:07<00:00, 116.37it/s] Loading 0: 93%|█████████▎| 270/291 [00:08<00:00, 67.14it/s] Loading 0: 98%|█████████▊| 284/291 [00:08<00:00, 77.58it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-v7-mkmlizer: quantized model in 20.238s
hastagaras-anjir-8b-l3-v7-mkmlizer: Processed model Hastagaras/Anjir-8B-L3 in 40.466s
hastagaras-anjir-8b-l3-v7-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v7
hastagaras-anjir-8b-l3-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v7/special_tokens_map.json
hastagaras-anjir-8b-l3-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v7/config.json
hastagaras-anjir-8b-l3-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v7/tokenizer_config.json
hastagaras-anjir-8b-l3-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v7/tokenizer.json
hastagaras-anjir-8b-l3-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v7/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-v7-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-v7-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-v7-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v7-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-v7-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v7-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-v7-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-v7-mkmlizer: Saving duration: 0.267s
hastagaras-anjir-8b-l3-v7-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.661s
hastagaras-anjir-8b-l3-v7-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v7_reward
hastagaras-anjir-8b-l3-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v7_reward/config.json
hastagaras-anjir-8b-l3-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v7_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v7_reward/vocab.json
hastagaras-anjir-8b-l3-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v7_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v7_reward/merges.txt
hastagaras-anjir-8b-l3-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v7_reward/tokenizer.json
hastagaras-anjir-8b-l3-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v7_reward/reward.tensors
Job hastagaras-anjir-8b-l3-v7-mkmlizer completed after 64.41s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-v7-mkmlizer
Pipeline stage MKMLizer completed in 68.86s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-v7
Waiting for inference service hastagaras-anjir-8b-l3-v7 to be ready
Inference service hastagaras-anjir-8b-l3-v7 ready after 40.280471086502075s
Pipeline stage ISVCDeployer completed in 48.34s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1626839637756348s
Received healthy response to inference request in 1.3356127738952637s
Received healthy response to inference request in 1.2998793125152588s
Received healthy response to inference request in 1.258204460144043s
Received healthy response to inference request in 1.344773292541504s
5 requests
0 failed requests
5th percentile: 1.2665394306182862
10th percentile: 1.2748744010925293
20th percentile: 1.2915443420410155
30th percentile: 1.3070260047912599
40th percentile: 1.3213193893432618
50th percentile: 1.3356127738952637
60th percentile: 1.3392769813537597
70th percentile: 1.3429411888122558
80th percentile: 1.5083554267883303
90th percentile: 1.8355196952819826
95th percentile: 1.9991018295288083
99th percentile: 2.1299675369262694
mean time: 1.4802307605743408
Pipeline stage StressChecker completed in 8.00s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-anjir-8b-l3_v7 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-anjir-8b-l3_v7
Running pipeline stage ISVCDeleter
Checking if service hastagaras-anjir-8b-l3-v7 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.07s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-v7/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-v7_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.33s
hastagaras-anjir-8b-l3_v7 status is now torndown due to DeploymentManager action