submission_id: ayalexf-graftmaxx-l3-8b_v1
developer_uid: Ayalexf
status: inactive
model_repo: Ayalexf/Graftmaxx-L3-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.12, 'top_p': 1.0, 'min_p': 0.075, 'top_k': 50, '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: 2024-06-16T16:18:20+00:00
model_name: ayalexf-graftmaxx-l3-8b_v1
model_eval_status: success
model_group: Ayalexf/Graftmaxx-L3-8B
num_battles: 29951
num_wins: 15488
celo_rating: 1184.45
propriety_score: 0.7198603409324297
propriety_total_count: 14607.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: ayalexf-graftmaxx-l3-8b_v1
ineligible_reason: None
language_model: Ayalexf/Graftmaxx-L3-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-16
win_ratio: 0.5171112817602084
Resubmit model
Running pipeline stage MKMLizer
Starting job with name ayalexf-graftmaxx-l3-8b-v1-mkmlizer
Waiting for job on ayalexf-graftmaxx-l3-8b-v1-mkmlizer to finish
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ _____ __ __ ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ /___/ ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ Version: 0.8.14 ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ https://mk1.ai ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ belonging to: ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ Chai Research Corp. ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ║ ║
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
ayalexf-graftmaxx-l3-8b-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.
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: Downloaded to shared memory in 54.994s
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:44, 2.44s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:12, 3.80it/s] Loading 0: 9%|▉ | 27/291 [00:05<00:30, 8.70it/s] Loading 0: 14%|█▎ | 40/291 [00:05<00:16, 15.07it/s] Loading 0: 18%|█▊ | 51/291 [00:05<00:11, 21.51it/s] Loading 0: 21%|██▏ | 62/291 [00:05<00:09, 24.38it/s] Loading 0: 26%|██▌ | 76/291 [00:05<00:06, 35.28it/s] Loading 0: 30%|██▉ | 87/291 [00:05<00:04, 43.59it/s] Loading 0: 35%|███▌ | 103/291 [00:05<00:03, 59.63it/s] Loading 0: 40%|███▉ | 115/291 [00:06<00:02, 67.92it/s] Loading 0: 45%|████▍ | 130/291 [00:06<00:01, 82.41it/s] Loading 0: 49%|████▉ | 142/291 [00:06<00:01, 87.12it/s] Loading 0: 54%|█████▍ | 157/291 [00:06<00:01, 99.21it/s] Loading 0: 58%|█████▊ | 170/291 [00:06<00:01, 65.89it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 77.82it/s] Loading 0: 67%|██████▋ | 195/291 [00:07<00:01, 81.43it/s] Loading 0: 73%|███████▎ | 211/291 [00:07<00:00, 95.78it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:00, 97.54it/s] Loading 0: 82%|████████▏ | 238/291 [00:07<00:00, 107.26it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:00, 106.06it/s] Loading 0: 91%|█████████ | 265/291 [00:07<00:00, 114.63it/s] Loading 0: 96%|█████████▌| 278/291 [00:07<00:00, 71.70it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: quantized model in 24.873s
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: Processed model Ayalexf/Graftmaxx-L3-8B in 82.428s
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: WARNING: Retrying failed request: / ([Errno 110] Connection timed out)
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: WARNING: Waiting 3 sec...
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/ayalexf-graftmaxx-l3-8b-v1
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: DEBUG retryable error: RequestError: send request failed
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: caused by: dial tcp 216.153.53.63:443: i/o timeout
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/ayalexf-graftmaxx-l3-8b-v1/special_tokens_map.json
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/ayalexf-graftmaxx-l3-8b-v1/config.json
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/ayalexf-graftmaxx-l3-8b-v1/tokenizer_config.json
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/ayalexf-graftmaxx-l3-8b-v1/tokenizer.json
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/ayalexf-graftmaxx-l3-8b-v1/flywheel_model.0.safetensors
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
ayalexf-graftmaxx-l3-8b-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.
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: warnings.warn(
ayalexf-graftmaxx-l3-8b-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.
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: warnings.warn(
ayalexf-graftmaxx-l3-8b-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.
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: warnings.warn(
ayalexf-graftmaxx-l3-8b-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()
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: return self.fget.__get__(instance, owner)()
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: Saving duration: 0.393s
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 17.480s
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: creating bucket guanaco-reward-models
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/ayalexf-graftmaxx-l3-8b-v1_reward
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/ayalexf-graftmaxx-l3-8b-v1_reward/config.json
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/ayalexf-graftmaxx-l3-8b-v1_reward/special_tokens_map.json
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/ayalexf-graftmaxx-l3-8b-v1_reward/tokenizer_config.json
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/ayalexf-graftmaxx-l3-8b-v1_reward/vocab.json
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/ayalexf-graftmaxx-l3-8b-v1_reward/merges.txt
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/ayalexf-graftmaxx-l3-8b-v1_reward/tokenizer.json
ayalexf-graftmaxx-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/ayalexf-graftmaxx-l3-8b-v1_reward/reward.tensors
Job ayalexf-graftmaxx-l3-8b-v1-mkmlizer completed after 298.5s with status: succeeded
Stopping job with name ayalexf-graftmaxx-l3-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 302.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service ayalexf-graftmaxx-l3-8b-v1
Waiting for inference service ayalexf-graftmaxx-l3-8b-v1 to be ready
Inference service ayalexf-graftmaxx-l3-8b-v1 ready after 30.227161169052124s
Pipeline stage ISVCDeployer completed in 37.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0349831581115723s
Received healthy response to inference request in 1.1124844551086426s
Received healthy response to inference request in 1.1027531623840332s
Received healthy response to inference request in 1.1300866603851318s
Received healthy response to inference request in 0.9956276416778564s
5 requests
0 failed requests
5th percentile: 1.0170527458190919
10th percentile: 1.038477849960327
20th percentile: 1.0813280582427978
30th percentile: 1.1046994209289551
40th percentile: 1.1085919380187987
50th percentile: 1.1124844551086426
60th percentile: 1.1195253372192382
70th percentile: 1.126566219329834
80th percentile: 1.3110659599304202
90th percentile: 1.6730245590209962
95th percentile: 1.854003858566284
99th percentile: 1.9987872982025146
mean time: 1.2751870155334473
Pipeline stage StressChecker completed in 7.00s
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
ayalexf-graftmaxx-l3-8b_v1 status is now deployed due to DeploymentManager action
ayalexf-graftmaxx-l3-8b_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics