developer_uid: Hastagaras
submission_id: hastagaras-anjir-8b-l3_v3
model_name: test3
model_group: Hastagaras/Anjir-8B-L3
status: torndown
timestamp: 2024-05-30T05:43:55+00:00
num_battles: 6330
num_wins: 3644
celo_rating: 1220.13
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: test3
is_internal_developer: False
language_model: Hastagaras/Anjir-8B-L3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-29
win_ratio: 0.5756714060031596
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': "<|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-v3-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-v3-mkmlizer to finish
hastagaras-anjir-8b-l3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-v3-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-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-v3-mkmlizer: Downloaded to shared memory in 17.752s
hastagaras-anjir-8b-l3-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:43, 2.23s/it] Loading 0: 5%|▌ | 16/291 [00:04<00:57, 4.78it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:21, 11.79it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.35it/s] Loading 0: 23%|██▎ | 66/291 [00:05<00:08, 26.68it/s] Loading 0: 27%|██▋ | 80/291 [00:05<00:05, 36.25it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 49.38it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 66.39it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 83.42it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 100.08it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 77.68it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 93.55it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 108.98it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 122.92it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 132.73it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 141.59it/s] Loading 0: 93%|█████████▎| 272/291 [00:06<00:00, 92.47it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 103.05it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-v3-mkmlizer: quantized model in 22.516s
hastagaras-anjir-8b-l3-v3-mkmlizer: Processed model Hastagaras/Anjir-8B-L3 in 42.694s
hastagaras-anjir-8b-l3-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v3
hastagaras-anjir-8b-l3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v3/tokenizer_config.json
hastagaras-anjir-8b-l3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v3/special_tokens_map.json
hastagaras-anjir-8b-l3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v3/config.json
hastagaras-anjir-8b-l3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v3/tokenizer.json
hastagaras-anjir-8b-l3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v3/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-v3-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-v3-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v3-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-v3-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v3-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-v3-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v3-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-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-v3-mkmlizer: Saving duration: 0.395s
hastagaras-anjir-8b-l3-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.242s
hastagaras-anjir-8b-l3-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v3_reward
hastagaras-anjir-8b-l3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v3_reward/config.json
hastagaras-anjir-8b-l3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v3_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v3_reward/merges.txt
hastagaras-anjir-8b-l3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v3_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v3_reward/vocab.json
hastagaras-anjir-8b-l3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v3_reward/tokenizer.json
Job hastagaras-anjir-8b-l3-v3-mkmlizer completed after 72.74s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-v3-mkmlizer
Pipeline stage MKMLizer completed in 76.59s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-v3
Waiting for inference service hastagaras-anjir-8b-l3-v3 to be ready
Inference service hastagaras-anjir-8b-l3-v3 ready after 30.163817882537842s
Pipeline stage ISVCDeployer completed in 37.82s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.142421007156372s
Received healthy response to inference request in 1.396355390548706s
Received healthy response to inference request in 1.3621981143951416s
Received healthy response to inference request in 1.3195865154266357s
Received healthy response to inference request in 1.2649643421173096s
5 requests
0 failed requests
5th percentile: 1.275888776779175
10th percentile: 1.28681321144104
20th percentile: 1.3086620807647704
30th percentile: 1.328108835220337
40th percentile: 1.3451534748077392
50th percentile: 1.3621981143951416
60th percentile: 1.3758610248565675
70th percentile: 1.3895239353179931
80th percentile: 1.5455685138702393
90th percentile: 1.8439947605133058
95th percentile: 1.9932078838348388
99th percentile: 2.112578382492065
mean time: 1.497105073928833
Pipeline stage StressChecker completed in 8.10s
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_v3 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-anjir-8b-l3_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-anjir-8b-l3-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.59s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.86s
hastagaras-anjir-8b-l3_v3 status is now torndown due to DeploymentManager action