submission_id: frank2030-hathor-stable-_7642_v1
developer_uid: frank2030
status: inactive
model_repo: frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-half-k
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-07-09T00:21:30+00:00
model_name: frank2030-hathor-stable-_7642_v1
model_group: frank2030/Hathor_Stable-
num_battles: 32308
num_wins: 16185
celo_rating: 1194.75
propriety_score: 0.698048427900253
propriety_total_count: 5534.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: frank2030-hathor-stable-_7642_v1
ineligible_reason: None
language_model: frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-half-k
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-08
win_ratio: 0.5009595146712889
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name frank2030-hathor-stable-7642-v1-mkmlizer
Waiting for job on frank2030-hathor-stable-7642-v1-mkmlizer to finish
frank2030-hathor-stable-7642-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
frank2030-hathor-stable-7642-v1-mkmlizer: ║ _____ __ __ ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ /___/ ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ Version: 0.8.14 ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ https://mk1.ai ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ The license key for the current software has been verified as ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ belonging to: ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ Chai Research Corp. ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
frank2030-hathor-stable-7642-v1-mkmlizer: ║ ║
frank2030-hathor-stable-7642-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
frank2030-hathor-stable-7642-v1-mkmlizer: Downloaded to shared memory in 29.764s
frank2030-hathor-stable-7642-v1-mkmlizer: quantizing model to /dev/shm/model_cache
frank2030-hathor-stable-7642-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
frank2030-hathor-stable-7642-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 119.93it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 107.55it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 119.25it/s] Loading 0: 18%|█▊ | 51/291 [00:00<00:02, 111.87it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 121.02it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 110.39it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:03, 55.40it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 64.52it/s] Loading 0: 40%|███▉ | 116/291 [00:01<00:02, 76.27it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 86.17it/s] Loading 0: 49%|████▉ | 143/291 [00:01<00:01, 95.39it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 103.28it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 104.21it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:01, 108.96it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 63.52it/s] Loading 0: 71%|███████ | 206/291 [00:02<00:01, 74.98it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 84.90it/s] Loading 0: 80%|████████ | 233/291 [00:02<00:00, 94.35it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 100.64it/s] Loading 0: 89%|████████▉ | 260/291 [00:02<00:00, 107.08it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 112.10it/s] Loading 0: 98%|█████████▊| 286/291 [00:03<00:00, 114.32it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
frank2030-hathor-stable-7642-v1-mkmlizer: quantized model in 24.402s
frank2030-hathor-stable-7642-v1-mkmlizer: Processed model frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-half-k in 54.167s
frank2030-hathor-stable-7642-v1-mkmlizer: creating bucket guanaco-mkml-models
frank2030-hathor-stable-7642-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
frank2030-hathor-stable-7642-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/frank2030-hathor-stable-7642-v1
frank2030-hathor-stable-7642-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/frank2030-hathor-stable-7642-v1/special_tokens_map.json
frank2030-hathor-stable-7642-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/frank2030-hathor-stable-7642-v1/tokenizer_config.json
frank2030-hathor-stable-7642-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/frank2030-hathor-stable-7642-v1/config.json
frank2030-hathor-stable-7642-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/frank2030-hathor-stable-7642-v1/tokenizer.json
frank2030-hathor-stable-7642-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/frank2030-hathor-stable-7642-v1/flywheel_model.0.safetensors
frank2030-hathor-stable-7642-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.
frank2030-hathor-stable-7642-v1-mkmlizer: warnings.warn(
frank2030-hathor-stable-7642-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.
frank2030-hathor-stable-7642-v1-mkmlizer: warnings.warn(
frank2030-hathor-stable-7642-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()
frank2030-hathor-stable-7642-v1-mkmlizer: return self.fget.__get__(instance, owner)()
frank2030-hathor-stable-7642-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
frank2030-hathor-stable-7642-v1-mkmlizer: Saving duration: 0.413s
frank2030-hathor-stable-7642-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.270s
frank2030-hathor-stable-7642-v1-mkmlizer: creating bucket guanaco-reward-models
frank2030-hathor-stable-7642-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
frank2030-hathor-stable-7642-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/frank2030-hathor-stable-7642-v1_reward
frank2030-hathor-stable-7642-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/frank2030-hathor-stable-7642-v1_reward/config.json
frank2030-hathor-stable-7642-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/frank2030-hathor-stable-7642-v1_reward/tokenizer_config.json
frank2030-hathor-stable-7642-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/frank2030-hathor-stable-7642-v1_reward/special_tokens_map.json
frank2030-hathor-stable-7642-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/frank2030-hathor-stable-7642-v1_reward/merges.txt
frank2030-hathor-stable-7642-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/frank2030-hathor-stable-7642-v1_reward/vocab.json
frank2030-hathor-stable-7642-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/frank2030-hathor-stable-7642-v1_reward/tokenizer.json
frank2030-hathor-stable-7642-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/frank2030-hathor-stable-7642-v1_reward/reward.tensors
Job frank2030-hathor-stable-7642-v1-mkmlizer completed after 85.76s with status: succeeded
Stopping job with name frank2030-hathor-stable-7642-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.67s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service frank2030-hathor-stable-7642-v1
Waiting for inference service frank2030-hathor-stable-7642-v1 to be ready
Inference service frank2030-hathor-stable-7642-v1 ready after 50.721824169158936s
Pipeline stage ISVCDeployer completed in 58.19s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9377210140228271s
Received healthy response to inference request in 1.1045327186584473s
Received healthy response to inference request in 1.1202349662780762s
Received healthy response to inference request in 1.1227953433990479s
Received healthy response to inference request in 1.1238813400268555s
5 requests
0 failed requests
5th percentile: 1.107673168182373
10th percentile: 1.1108136177062988
20th percentile: 1.1170945167541504
30th percentile: 1.1207470417022705
40th percentile: 1.1217711925506593
50th percentile: 1.1227953433990479
60th percentile: 1.123229742050171
70th percentile: 1.123664140701294
80th percentile: 1.28664927482605
90th percentile: 1.6121851444244386
95th percentile: 1.7749530792236325
99th percentile: 1.9051674270629881
mean time: 1.2818330764770507
Pipeline stage StressChecker completed in 8.02s
frank2030-hathor-stable-_7642_v1 status is now deployed due to DeploymentManager action
frank2030-hathor-stable-_7642_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics