submission_id: hastagaras-jamet-8b-l3-m_8630_v8
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, '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': "<|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: {'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: 2024-06-11T07:31:44+00:00
model_name: p
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 9611
num_wins: 5346
celo_rating: 1220.26
propriety_score: 0.6771929824561403
propriety_total_count: 3420.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: p
ineligible_reason: None
language_model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-11
win_ratio: 0.5562376443658308
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer to finish
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-8630-v8-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-jamet-8b-l3-m-8630-v8-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: Downloaded to shared memory in 20.836s
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 122.70it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 142.80it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 141.09it/s] Loading 0: 22%|██▏ | 63/291 [00:00<00:01, 131.73it/s] Loading 0: 26%|██▋ | 77/291 [00:00<00:01, 120.34it/s] Loading 0: 31%|███ | 90/291 [00:00<00:02, 68.46it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 78.71it/s] Loading 0: 40%|███▉ | 116/291 [00:01<00:01, 89.11it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 97.74it/s] Loading 0: 48%|████▊ | 141/291 [00:01<00:01, 99.44it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 110.19it/s] Loading 0: 58%|█████▊ | 169/291 [00:01<00:01, 110.74it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:00, 111.91it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 64.81it/s] Loading 0: 71%|███████ | 206/291 [00:02<00:01, 76.43it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 87.40it/s] Loading 0: 79%|███████▉ | 231/291 [00:02<00:00, 92.17it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 104.04it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 105.38it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 116.34it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 7.62it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: quantized model in 26.333s
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.V-Blackroot in 49.823s
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v8
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v8/config.json
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v8/tokenizer_config.json
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v8/special_tokens_map.json
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v8/tokenizer.json
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v8/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-8630-v8-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-jamet-8b-l3-m-8630-v8-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8630-v8-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-jamet-8b-l3-m-8630-v8-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8630-v8-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-jamet-8b-l3-m-8630-v8-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: Saving duration: 0.419s
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.581s
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v8_reward
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v8_reward/config.json
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v8_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v8_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v8_reward/merges.txt
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v8_reward/vocab.json
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v8_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v8_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer completed after 73.52s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-8630-v8-mkmlizer
Pipeline stage MKMLizer completed in 74.29s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-8630-v8
Waiting for inference service hastagaras-jamet-8b-l3-m-8630-v8 to be ready
Inference service hastagaras-jamet-8b-l3-m-8630-v8 ready after 110.52227902412415s
Pipeline stage ISVCDeployer completed in 116.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2159011363983154s
Received healthy response to inference request in 1.3062798976898193s
Received healthy response to inference request in 1.293602705001831s
Received healthy response to inference request in 1.2750458717346191s
Received healthy response to inference request in 1.3434922695159912s
5 requests
0 failed requests
5th percentile: 1.2787572383880614
10th percentile: 1.282468605041504
20th percentile: 1.2898913383483888
30th percentile: 1.2961381435394288
40th percentile: 1.301209020614624
50th percentile: 1.3062798976898193
60th percentile: 1.321164846420288
70th percentile: 1.3360497951507568
80th percentile: 1.5179740428924562
90th percentile: 1.866937589645386
95th percentile: 2.0414193630218502
99th percentile: 2.1810047817230225
mean time: 1.4868643760681153
Pipeline stage StressChecker completed in 8.03s
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-jamet-8b-l3-m_8630_v8 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_8630_v8 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics