submission_id: rieofawox-h02-l3-8b-73_v2
developer_uid: la.fey
status: inactive
model_repo: Rieofawox/H02-L3-8B-73
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 45, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>'], '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: 2024-06-30T17:43:41+00:00
model_name: rieofawox-h02-l3-8b-00_v1
model_group: Rieofawox/H02-L3-8B-73
num_battles: 18607
num_wins: 9948
celo_rating: 1206.78
propriety_score: 0.7210739159739384
propriety_total_count: 8902.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: rieofawox-h02-l3-8b-00_v1
ineligible_reason: None
language_model: Rieofawox/H02-L3-8B-73
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-30
win_ratio: 0.5346375020153705
Resubmit model
Running pipeline stage MKMLizer
Starting job with name rieofawox-h02-l3-8b-73-v2-mkmlizer
Waiting for job on rieofawox-h02-l3-8b-73-v2-mkmlizer to finish
rieofawox-h02-l3-8b-73-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ _____ __ __ ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ /___/ ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ Version: 0.8.14 ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ https://mk1.ai ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ belonging to: ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ Chai Research Corp. ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ║ ║
rieofawox-h02-l3-8b-73-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rieofawox-h02-l3-8b-73-v2-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.
rieofawox-h02-l3-8b-73-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
rieofawox-h02-l3-8b-73-v2-mkmlizer: Downloaded to shared memory in 21.139s
rieofawox-h02-l3-8b-73-v2-mkmlizer: quantizing model to /dev/shm/model_cache
rieofawox-h02-l3-8b-73-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rieofawox-h02-l3-8b-73-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:53, 2.05s/it] Loading 0: 5%|▌ | 15/291 [00:04<00:57, 4.84it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:20, 12.80it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:10, 22.89it/s] Loading 0: 22%|██▏ | 65/291 [00:04<00:08, 26.67it/s] Loading 0: 27%|██▋ | 78/291 [00:04<00:05, 35.58it/s] Loading 0: 33%|███▎ | 96/291 [00:04<00:03, 50.96it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 67.44it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 84.47it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 100.79it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 73.48it/s] Loading 0: 63%|██████▎ | 182/291 [00:05<00:01, 87.33it/s] Loading 0: 67%|██████▋ | 196/291 [00:05<00:00, 96.27it/s] Loading 0: 73%|███████▎ | 213/291 [00:06<00:00, 108.56it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:00, 120.75it/s] Loading 0: 86%|████████▌ | 249/291 [00:06<00:00, 130.71it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 83.75it/s] Loading 0: 98%|█████████▊| 284/291 [00:06<00:00, 98.13it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
rieofawox-h02-l3-8b-73-v2-mkmlizer: quantized model in 18.487s
rieofawox-h02-l3-8b-73-v2-mkmlizer: Processed model Rieofawox/H02-L3-8B-73 in 40.643s
rieofawox-h02-l3-8b-73-v2-mkmlizer: creating bucket guanaco-mkml-models
rieofawox-h02-l3-8b-73-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rieofawox-h02-l3-8b-73-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rieofawox-h02-l3-8b-73-v2
rieofawox-h02-l3-8b-73-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rieofawox-h02-l3-8b-73-v2/config.json
rieofawox-h02-l3-8b-73-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rieofawox-h02-l3-8b-73-v2/special_tokens_map.json
rieofawox-h02-l3-8b-73-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rieofawox-h02-l3-8b-73-v2/tokenizer_config.json
rieofawox-h02-l3-8b-73-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rieofawox-h02-l3-8b-73-v2/tokenizer.json
rieofawox-h02-l3-8b-73-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rieofawox-h02-l3-8b-73-v2/flywheel_model.0.safetensors
Connection pool is full, discarding connection: %s
rieofawox-h02-l3-8b-73-v2-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.
rieofawox-h02-l3-8b-73-v2-mkmlizer: warnings.warn(
rieofawox-h02-l3-8b-73-v2-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.
rieofawox-h02-l3-8b-73-v2-mkmlizer: warnings.warn(
rieofawox-h02-l3-8b-73-v2-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()
rieofawox-h02-l3-8b-73-v2-mkmlizer: return self.fget.__get__(instance, owner)()
rieofawox-h02-l3-8b-73-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
rieofawox-h02-l3-8b-73-v2-mkmlizer: Saving duration: 0.306s
rieofawox-h02-l3-8b-73-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.244s
rieofawox-h02-l3-8b-73-v2-mkmlizer: creating bucket guanaco-reward-models
rieofawox-h02-l3-8b-73-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
rieofawox-h02-l3-8b-73-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/rieofawox-h02-l3-8b-73-v2_reward
rieofawox-h02-l3-8b-73-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/rieofawox-h02-l3-8b-73-v2_reward/config.json
rieofawox-h02-l3-8b-73-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/rieofawox-h02-l3-8b-73-v2_reward/special_tokens_map.json
rieofawox-h02-l3-8b-73-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/rieofawox-h02-l3-8b-73-v2_reward/tokenizer_config.json
rieofawox-h02-l3-8b-73-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/rieofawox-h02-l3-8b-73-v2_reward/merges.txt
rieofawox-h02-l3-8b-73-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/rieofawox-h02-l3-8b-73-v2_reward/vocab.json
rieofawox-h02-l3-8b-73-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/rieofawox-h02-l3-8b-73-v2_reward/tokenizer.json
rieofawox-h02-l3-8b-73-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/rieofawox-h02-l3-8b-73-v2_reward/reward.tensors
Job rieofawox-h02-l3-8b-73-v2-mkmlizer completed after 74.3s with status: succeeded
Stopping job with name rieofawox-h02-l3-8b-73-v2-mkmlizer
Pipeline stage MKMLizer completed in 75.23s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service rieofawox-h02-l3-8b-73-v2
Waiting for inference service rieofawox-h02-l3-8b-73-v2 to be ready
Inference service rieofawox-h02-l3-8b-73-v2 ready after 40.20113945007324s
Pipeline stage ISVCDeployer completed in 47.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2014267444610596s
Received healthy response to inference request in 1.3642494678497314s
Received healthy response to inference request in 1.295628309249878s
Received healthy response to inference request in 1.2987215518951416s
Received healthy response to inference request in 1.3470382690429688s
5 requests
0 failed requests
5th percentile: 1.2962469577789306
10th percentile: 1.2968656063079833
20th percentile: 1.298102903366089
30th percentile: 1.308384895324707
40th percentile: 1.327711582183838
50th percentile: 1.3470382690429688
60th percentile: 1.3539227485656737
70th percentile: 1.360807228088379
80th percentile: 1.5316849231719973
90th percentile: 1.8665558338165285
95th percentile: 2.0339912891387937
99th percentile: 2.167939653396606
mean time: 1.5014128684997559
Pipeline stage StressChecker completed in 8.13s
rieofawox-h02-l3-8b-73_v2 status is now deployed due to DeploymentManager action
rieofawox-h02-l3-8b-73_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics