submission_id: frank2030-hathor-stable-_6519_v4
developer_uid: frank2030
status: inactive
model_repo: frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-9k-26
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': 16, '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: 2024-07-09T00:23:38+00:00
model_name: frank2030-hathor-stable-_6519_v4
model_group: frank2030/Hathor_Stable-
num_battles: 32172
num_wins: 17765
celo_rating: 1229.62
propriety_score: 0.6819192293442016
propriety_total_count: 5398.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: frank2030-hathor-stable-_6519_v4
ineligible_reason: None
language_model: frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-9k-26
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-08
win_ratio: 0.5521882382195699
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name frank2030-hathor-stable-6519-v4-mkmlizer
Waiting for job on frank2030-hathor-stable-6519-v4-mkmlizer to finish
frank2030-hathor-stable-6519-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
frank2030-hathor-stable-6519-v4-mkmlizer: ║ _____ __ __ ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ /___/ ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ Version: 0.8.14 ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ https://mk1.ai ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ The license key for the current software has been verified as ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ belonging to: ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ Chai Research Corp. ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
frank2030-hathor-stable-6519-v4-mkmlizer: ║ ║
frank2030-hathor-stable-6519-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
frank2030-hathor-stable-6519-v4-mkmlizer: Downloaded to shared memory in 22.194s
frank2030-hathor-stable-6519-v4-mkmlizer: quantizing model to /dev/shm/model_cache
frank2030-hathor-stable-6519-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
frank2030-hathor-stable-6519-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 108.81it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:02, 116.86it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 117.47it/s] Loading 0: 19%|█▊ | 54/291 [00:00<00:01, 123.20it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 119.58it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 122.13it/s] Loading 0: 32%|███▏ | 93/291 [00:01<00:03, 62.25it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 68.93it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 85.77it/s] Loading 0: 45%|████▌ | 132/291 [00:01<00:01, 90.64it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 102.93it/s] Loading 0: 55%|█████▍ | 159/291 [00:01<00:01, 103.76it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:01, 111.21it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 69.82it/s] Loading 0: 68%|██████▊ | 197/291 [00:02<00:01, 74.56it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:00, 84.89it/s] Loading 0: 77%|███████▋ | 225/291 [00:02<00:00, 95.96it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 101.30it/s] Loading 0: 86%|████████▌ | 250/291 [00:02<00:00, 97.65it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 107.48it/s] Loading 0: 95%|█████████▍| 276/291 [00:02<00:00, 108.08it/s] Loading 0: 99%|█████████▉| 288/291 [00:08<00:00, 7.11it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
frank2030-hathor-stable-6519-v4-mkmlizer: quantized model in 24.089s
frank2030-hathor-stable-6519-v4-mkmlizer: Processed model frank2030/Hathor_Stable-v0.2-L3-8B-DPO-3epoch-9k-26 in 46.283s
frank2030-hathor-stable-6519-v4-mkmlizer: creating bucket guanaco-mkml-models
frank2030-hathor-stable-6519-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
frank2030-hathor-stable-6519-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/frank2030-hathor-stable-6519-v4
frank2030-hathor-stable-6519-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/frank2030-hathor-stable-6519-v4/tokenizer_config.json
frank2030-hathor-stable-6519-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/frank2030-hathor-stable-6519-v4/special_tokens_map.json
frank2030-hathor-stable-6519-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/frank2030-hathor-stable-6519-v4/config.json
frank2030-hathor-stable-6519-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/frank2030-hathor-stable-6519-v4/tokenizer.json
frank2030-hathor-stable-6519-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/frank2030-hathor-stable-6519-v4/flywheel_model.0.safetensors
frank2030-hathor-stable-6519-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
frank2030-hathor-stable-6519-v4-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.
frank2030-hathor-stable-6519-v4-mkmlizer: warnings.warn(
frank2030-hathor-stable-6519-v4-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`.
frank2030-hathor-stable-6519-v4-mkmlizer: warnings.warn(
frank2030-hathor-stable-6519-v4-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-6519-v4-mkmlizer: warnings.warn(
frank2030-hathor-stable-6519-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.
frank2030-hathor-stable-6519-v4-mkmlizer: warnings.warn(
frank2030-hathor-stable-6519-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()
frank2030-hathor-stable-6519-v4-mkmlizer: return self.fget.__get__(instance, owner)()
frank2030-hathor-stable-6519-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
frank2030-hathor-stable-6519-v4-mkmlizer: Saving duration: 0.416s
frank2030-hathor-stable-6519-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.414s
frank2030-hathor-stable-6519-v4-mkmlizer: creating bucket guanaco-reward-models
frank2030-hathor-stable-6519-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
frank2030-hathor-stable-6519-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/frank2030-hathor-stable-6519-v4_reward
frank2030-hathor-stable-6519-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/frank2030-hathor-stable-6519-v4_reward/config.json
frank2030-hathor-stable-6519-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/frank2030-hathor-stable-6519-v4_reward/special_tokens_map.json
frank2030-hathor-stable-6519-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/frank2030-hathor-stable-6519-v4_reward/merges.txt
frank2030-hathor-stable-6519-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/frank2030-hathor-stable-6519-v4_reward/tokenizer_config.json
frank2030-hathor-stable-6519-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/frank2030-hathor-stable-6519-v4_reward/vocab.json
frank2030-hathor-stable-6519-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/frank2030-hathor-stable-6519-v4_reward/tokenizer.json
frank2030-hathor-stable-6519-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/frank2030-hathor-stable-6519-v4_reward/reward.tensors
Job frank2030-hathor-stable-6519-v4-mkmlizer completed after 76.19s with status: succeeded
Stopping job with name frank2030-hathor-stable-6519-v4-mkmlizer
Pipeline stage MKMLizer completed in 77.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service frank2030-hathor-stable-6519-v4
Waiting for inference service frank2030-hathor-stable-6519-v4 to be ready
Inference service frank2030-hathor-stable-6519-v4 ready after 50.23992681503296s
Pipeline stage ISVCDeployer completed in 56.85s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0912110805511475s
Received healthy response to inference request in 1.399059772491455s
Received healthy response to inference request in 1.2834062576293945s
Received healthy response to inference request in 1.2606759071350098s
Received healthy response to inference request in 1.2938885688781738s
5 requests
0 failed requests
5th percentile: 1.2652219772338866
10th percentile: 1.2697680473327637
20th percentile: 1.2788601875305177
30th percentile: 1.2855027198791504
40th percentile: 1.289695644378662
50th percentile: 1.2938885688781738
60th percentile: 1.3359570503234863
70th percentile: 1.3780255317687988
80th percentile: 1.5374900341033937
90th percentile: 1.8143505573272707
95th percentile: 1.9527808189392089
99th percentile: 2.0635250282287596
mean time: 1.465648317337036
Pipeline stage StressChecker completed in 8.03s
frank2030-hathor-stable-_6519_v4 status is now deployed due to DeploymentManager action
frank2030-hathor-stable-_6519_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics