submission_id: hastagaras-jamet-8b-l3-mk-1hl_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK.1HL
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.05, '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': "<|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: 2024-06-04T23:38:18+00:00
model_name: jmethl
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 18791
num_wins: 10470
celo_rating: 1207.93
propriety_score: 0.680628272251309
propriety_total_count: 573.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: jmethl
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Jamet-8B-L3-MK.1HL
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-04
win_ratio: 0.5571816295034857
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer to finish
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-mk-1hl-v1-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-mk-1hl-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: Downloaded to shared memory in 32.962s
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission neversleep-noromaid-v0-_8068_v36: ('http://neversleep-noromaid-v0-8068-v36-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'readfrom tcp 127.0.0.1:55716->127.0.0.1:8080: write tcp 127.0.0.1:55716->127.0.0.1:8080: use of closed network connection\n')
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 107.37it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:02, 102.17it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 118.80it/s] Loading 0: 18%|█▊ | 51/291 [00:00<00:02, 116.06it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 123.29it/s] Loading 0: 28%|██▊ | 81/291 [00:00<00:01, 128.44it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:03, 54.01it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:03, 59.79it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:02, 77.07it/s] Loading 0: 46%|████▌ | 134/291 [00:01<00:01, 86.95it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 95.26it/s] Loading 0: 55%|█████▍ | 159/291 [00:01<00:01, 93.82it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:01, 104.29it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 59.47it/s] Loading 0: 68%|██████▊ | 197/291 [00:02<00:01, 65.09it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 76.57it/s] Loading 0: 77%|███████▋ | 225/291 [00:02<00:00, 89.25it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 96.26it/s] Loading 0: 87%|████████▋ | 253/291 [00:02<00:00, 109.04it/s] Loading 0: 91%|█████████▏| 266/291 [00:03<00:00, 107.14it/s] Loading 0: 97%|█████████▋| 281/291 [00:03<00:00, 115.25it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: quantized model in 23.628s
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.1HL in 58.110s
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-1hl-v1
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-1hl-v1/config.json
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-1hl-v1/special_tokens_map.json
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-1hl-v1/tokenizer_config.json
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-1hl-v1/tokenizer.json
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-mk-1hl-v1/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-mk-1hl-v1-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-jamet-8b-l3-mk-1hl-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-1hl-v1-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-mk-1hl-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-1hl-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-jamet-8b-l3-mk-1hl-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-mk-1hl-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-jamet-8b-l3-mk-1hl-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: Saving duration: 0.283s
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.414s
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-1hl-v1_reward
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-1hl-v1_reward/config.json
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-1hl-v1_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-1hl-v1_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-1hl-v1_reward/merges.txt
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-1hl-v1_reward/vocab.json
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-1hl-v1_reward/tokenizer.json
hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-mk-1hl-v1_reward/reward.tensors
Job hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer completed after 83.32s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-mk-1hl-v1-mkmlizer
Pipeline stage MKMLizer completed in 88.44s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-mk-1hl-v1
Waiting for inference service hastagaras-jamet-8b-l3-mk-1hl-v1 to be ready
Inference service hastagaras-jamet-8b-l3-mk-1hl-v1 ready after 40.27371048927307s
Pipeline stage ISVCDeployer completed in 48.54s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.131927728652954s
Received healthy response to inference request in 1.3471293449401855s
Received healthy response to inference request in 1.2956500053405762s
Received healthy response to inference request in 1.2774193286895752s
Received healthy response to inference request in 1.2484078407287598s
5 requests
0 failed requests
5th percentile: 1.2542101383209228
10th percentile: 1.260012435913086
20th percentile: 1.2716170310974122
30th percentile: 1.2810654640197754
40th percentile: 1.2883577346801758
50th percentile: 1.2956500053405762
60th percentile: 1.31624174118042
70th percentile: 1.3368334770202637
80th percentile: 1.5040890216827394
90th percentile: 1.8180083751678469
95th percentile: 1.9749680519104003
99th percentile: 2.1005357933044433
mean time: 1.4601068496704102
Pipeline stage StressChecker completed in 8.07s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-jamet-8b-l3-mk-1hl_v1 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-mk-1hl_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics