submission_id: hastagaras-jametkuproy64_v1
developer_uid: Hastagaras
best_of: 16
celo_rating: 1203.41
display_name: gf
family_friendly_score: 0.0
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}
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.085, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Hastagaras/JametKuproy64
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Hastagaras/JametKuproy64
model_name: gf
model_num_parameters: 8030261248.0
model_repo: Hastagaras/JametKuproy64
model_size: 8B
num_battles: 12800
num_wins: 6966
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-02T08:25:08+00:00
us_pacific_date: 2024-07-02
win_ratio: 0.54421875
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jametkuproy64-v1-mkmlizer
Waiting for job on hastagaras-jametkuproy64-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s
hastagaras-jametkuproy64-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jametkuproy64-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ /___/ ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ belonging to: ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jametkuproy64-v1-mkmlizer: ║ ║
hastagaras-jametkuproy64-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission neversleep-noromaid-v0-_8068_v108: no entry with id "neversleep-noromaid-v0-_8068_v108" found on database!
hastagaras-jametkuproy64-v1-mkmlizer: Downloaded to shared memory in 33.207s
hastagaras-jametkuproy64-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jametkuproy64-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jametkuproy64-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 106.93it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:02, 101.30it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 120.69it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 118.07it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 124.43it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 121.05it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:03, 65.40it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 72.15it/s] Loading 0: 40%|███▉ | 116/291 [00:01<00:02, 84.08it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 93.08it/s] Loading 0: 49%|████▉ | 144/291 [00:01<00:01, 103.28it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 106.74it/s] Loading 0: 59%|█████▉ | 171/291 [00:01<00:01, 113.95it/s] Loading 0: 63%|██████▎ | 184/291 [00:01<00:00, 117.72it/s] Loading 0: 68%|██████▊ | 197/291 [00:02<00:01, 68.61it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 79.13it/s] Loading 0: 77%|███████▋ | 225/291 [00:02<00:00, 90.95it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 97.45it/s] Loading 0: 87%|████████▋ | 252/291 [00:02<00:00, 106.22it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 108.89it/s] Loading 0: 96%|█████████▌| 279/291 [00:02<00:00, 115.35it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jametkuproy64-v1-mkmlizer: quantized model in 24.151s
hastagaras-jametkuproy64-v1-mkmlizer: Processed model Hastagaras/JametKuproy64 in 57.358s
hastagaras-jametkuproy64-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jametkuproy64-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jametkuproy64-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jametkuproy64-v1
hastagaras-jametkuproy64-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jametkuproy64-v1/special_tokens_map.json
hastagaras-jametkuproy64-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jametkuproy64-v1/config.json
hastagaras-jametkuproy64-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jametkuproy64-v1/tokenizer.json
hastagaras-jametkuproy64-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jametkuproy64-v1/flywheel_model.0.safetensors
hastagaras-jametkuproy64-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jametkuproy64-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-jametkuproy64-v1-mkmlizer: warnings.warn(
hastagaras-jametkuproy64-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
hastagaras-jametkuproy64-v1-mkmlizer: warnings.warn(
hastagaras-jametkuproy64-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-jametkuproy64-v1-mkmlizer: warnings.warn(
hastagaras-jametkuproy64-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-jametkuproy64-v1-mkmlizer: warnings.warn(
hastagaras-jametkuproy64-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-jametkuproy64-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jametkuproy64-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jametkuproy64-v1-mkmlizer: Saving duration: 0.392s
hastagaras-jametkuproy64-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.812s
hastagaras-jametkuproy64-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jametkuproy64-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jametkuproy64-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jametkuproy64-v1_reward
hastagaras-jametkuproy64-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jametkuproy64-v1_reward/config.json
hastagaras-jametkuproy64-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jametkuproy64-v1_reward/tokenizer_config.json
hastagaras-jametkuproy64-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jametkuproy64-v1_reward/merges.txt
hastagaras-jametkuproy64-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jametkuproy64-v1_reward/vocab.json
hastagaras-jametkuproy64-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jametkuproy64-v1_reward/special_tokens_map.json
hastagaras-jametkuproy64-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jametkuproy64-v1_reward/tokenizer.json
hastagaras-jametkuproy64-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jametkuproy64-v1_reward/reward.tensors
Job hastagaras-jametkuproy64-v1-mkmlizer completed after 83.6s with status: succeeded
Stopping job with name hastagaras-jametkuproy64-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jametkuproy64-v1
Waiting for inference service hastagaras-jametkuproy64-v1 to be ready
Failed to get response for submission neversleep-noromaid-v0-_8068_v105: no entry with id "neversleep-noromaid-v0-_8068_v105" found on database!
Failed to get response for submission neversleep-noromaid-v0-_8068_v106: no entry with id "neversleep-noromaid-v0-_8068_v106" found on database!
Failed to get response for submission neversleep-noromaid-v0-_8068_v107: no entry with id "neversleep-noromaid-v0-_8068_v107" found on database!
Failed to get response for submission neversleep-noromaid-v0-_8068_v106: no entry with id "neversleep-noromaid-v0-_8068_v106" found on database!
Failed to get response for submission neversleep-noromaid-v0-_8068_v107: no entry with id "neversleep-noromaid-v0-_8068_v107" found on database!
Failed to get response for submission neversleep-noromaid-v0-_8068_v107: no entry with id "neversleep-noromaid-v0-_8068_v107" found on database!
Failed to get response for submission neversleep-noromaid-v0-_8068_v105: no entry with id "neversleep-noromaid-v0-_8068_v105" found on database!
Inference service hastagaras-jametkuproy64-v1 ready after 40.19338130950928s
Pipeline stage ISVCDeployer completed in 55.84s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0941951274871826s
Received healthy response to inference request in 1.3773491382598877s
Received healthy response to inference request in 1.3681440353393555s
Received healthy response to inference request in 1.3528213500976562s
Received healthy response to inference request in 1.417405605316162s
5 requests
0 failed requests
5th percentile: 1.355885887145996
10th percentile: 1.358950424194336
20th percentile: 1.3650794982910157
30th percentile: 1.3699850559234619
40th percentile: 1.373667097091675
50th percentile: 1.3773491382598877
60th percentile: 1.3933717250823974
70th percentile: 1.4093943119049073
80th percentile: 1.5527635097503663
90th percentile: 1.8234793186187745
95th percentile: 1.9588372230529785
99th percentile: 2.067123546600342
mean time: 1.5219830513000487
Pipeline stage StressChecker completed in 8.48s
hastagaras-jametkuproy64_v1 status is now deployed due to DeploymentManager action
hastagaras-jametkuproy64_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-jametkuproy64_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-jametkuproy64-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.78s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-jametkuproy64-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-jametkuproy64-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-jametkuproy64-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-jametkuproy64-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-jametkuproy64-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-jametkuproy64-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-jametkuproy64-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-jametkuproy64-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-jametkuproy64-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-jametkuproy64-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-jametkuproy64-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-jametkuproy64-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.62s
hastagaras-jametkuproy64_v1 status is now torndown due to DeploymentManager action