developer_uid: Hastagaras
submission_id: hastagaras-anjir-8b-l3-m_6487_v4
model_name: tm
model_group: Hastagaras/Anjir-8B-L3-M
status: torndown
timestamp: 2024-06-12T08:29:07+00:00
num_battles: 23998
num_wins: 14452
celo_rating: 1222.62
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Anjir-8B-L3-MK.V-BJ1
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: tm
is_internal_developer: False
language_model: Hastagaras/Anjir-8B-L3-MK.V-BJ1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-12
win_ratio: 0.6022168514042837
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, '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': "<|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}
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: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer to finish
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-m-6487-v4-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-m-6487-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: Downloaded to shared memory in 15.718s
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:50, 2.25s/it] Loading 0: 6%|▌ | 18/291 [00:04<00:51, 5.35it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.43it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.92it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.70it/s] Loading 0: 28%|██▊ | 82/291 [00:05<00:05, 37.75it/s] Loading 0: 34%|███▍ | 100/291 [00:05<00:03, 52.81it/s] Loading 0: 40%|████ | 117/291 [00:05<00:02, 68.14it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 80.80it/s] Loading 0: 51%|█████ | 148/291 [00:05<00:01, 92.06it/s] Loading 0: 56%|█████▌ | 163/291 [00:05<00:01, 100.26it/s] Loading 0: 61%|██████ | 177/291 [00:06<00:01, 72.39it/s] Loading 0: 67%|██████▋ | 195/291 [00:06<00:01, 90.03it/s] Loading 0: 73%|███████▎ | 213/291 [00:06<00:00, 105.94it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:00, 119.10it/s] Loading 0: 86%|████████▌ | 249/291 [00:06<00:00, 132.03it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 89.93it/s] Loading 0: 98%|█████████▊| 284/291 [00:06<00:00, 105.52it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: quantized model in 22.787s
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-MK.V-BJ1 in 40.972s
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v4
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v4/special_tokens_map.json
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v4/tokenizer_config.json
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v4/config.json
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v4/tokenizer.json
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-m-6487-v4-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-m-6487-v4-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-v4-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-m-6487-v4-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-v4-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-m-6487-v4-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-v4-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-m-6487-v4-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: Saving duration: 0.386s
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.030s
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v4_reward
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v4_reward/config.json
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v4_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v4_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v4_reward/vocab.json
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v4_reward/merges.txt
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v4_reward/tokenizer.json
hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v4_reward/reward.tensors
Job hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer completed after 72.76s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-m-6487-v4-mkmlizer
Pipeline stage MKMLizer completed in 73.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-m-6487-v4
Waiting for inference service hastagaras-anjir-8b-l3-m-6487-v4 to be ready
Inference service hastagaras-anjir-8b-l3-m-6487-v4 ready after 40.217750787734985s
Pipeline stage ISVCDeployer completed in 46.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.175013542175293s
Received healthy response to inference request in 1.3357784748077393s
Received healthy response to inference request in 1.3094861507415771s
Received healthy response to inference request in 1.2678627967834473s
Received healthy response to inference request in 1.3277461528778076s
5 requests
0 failed requests
5th percentile: 1.2761874675750733
10th percentile: 1.2845121383666993
20th percentile: 1.3011614799499511
30th percentile: 1.3131381511688232
40th percentile: 1.3204421520233154
50th percentile: 1.3277461528778076
60th percentile: 1.3309590816497803
70th percentile: 1.334172010421753
80th percentile: 1.50362548828125
90th percentile: 1.8393195152282715
95th percentile: 2.007166528701782
99th percentile: 2.141444139480591
mean time: 1.4831774234771729
Pipeline stage StressChecker completed in 8.02s
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-m_6487_v4 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-m_6487_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-anjir-8b-l3-m_6487_v4
Running pipeline stage ISVCDeleter
Checking if service hastagaras-anjir-8b-l3-m-6487-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.22s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-m-6487-v4/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-m-6487-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-m-6487-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-m-6487-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-m-6487-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-m-6487-v4_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-6487-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-6487-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-6487-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-6487-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-6487-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-6487-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.92s
hastagaras-anjir-8b-l3-m_6487_v4 status is now torndown due to DeploymentManager action