submission_id: rieofawox-h02-l3-8b-73_v1
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: 2024-06-30T16:45:54+00:00
model_name: rieofawox-h02-l3-8b-73_v1
model_group: Rieofawox/H02-L3-8B-73
num_battles: 15479
num_wins: 8142
celo_rating: 1204.36
propriety_score: 0.7215614943332866
propriety_total_count: 7147.0
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-73_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: 0.5260029717682021
Resubmit model
Running pipeline stage MKMLizer
Starting job with name rieofawox-h02-l3-8b-73-v1-mkmlizer
Waiting for job on rieofawox-h02-l3-8b-73-v1-mkmlizer to finish
rieofawox-h02-l3-8b-73-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ _____ __ __ ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ /___/ ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ Version: 0.8.14 ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ https://mk1.ai ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ belonging to: ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ Chai Research Corp. ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ║ ║
rieofawox-h02-l3-8b-73-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rieofawox-h02-l3-8b-73-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.
rieofawox-h02-l3-8b-73-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
rieofawox-h02-l3-8b-73-v1-mkmlizer: Downloaded to shared memory in 61.651s
rieofawox-h02-l3-8b-73-v1-mkmlizer: quantizing model to /dev/shm/model_cache
rieofawox-h02-l3-8b-73-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rieofawox-h02-l3-8b-73-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:16, 2.34s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:04, 4.26it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.33it/s] Loading 0: 18%|█▊ | 51/291 [00:05<00:11, 20.39it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:09, 24.45it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 35.16it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 46.82it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 62.96it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 79.80it/s] Loading 0: 51%|█████ | 149/291 [00:05<00:01, 95.22it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:01, 108.09it/s] Loading 0: 62%|██████▏ | 181/291 [00:06<00:01, 73.36it/s] Loading 0: 67%|██████▋ | 195/291 [00:06<00:01, 83.91it/s] Loading 0: 73%|███████▎ | 213/291 [00:06<00:00, 100.03it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:00, 113.53it/s] Loading 0: 86%|████████▌ | 249/291 [00:06<00:00, 125.64it/s] Loading 0: 91%|█████████▏| 266/291 [00:07<00:00, 84.09it/s] Loading 0: 97%|█████████▋| 283/291 [00:07<00:00, 98.33it/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-v1-mkmlizer: quantized model in 23.671s
rieofawox-h02-l3-8b-73-v1-mkmlizer: Processed model Rieofawox/H02-L3-8B-73 in 87.876s
rieofawox-h02-l3-8b-73-v1-mkmlizer: creating bucket guanaco-mkml-models
rieofawox-h02-l3-8b-73-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rieofawox-h02-l3-8b-73-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rieofawox-h02-l3-8b-73-v1
rieofawox-h02-l3-8b-73-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rieofawox-h02-l3-8b-73-v1/config.json
rieofawox-h02-l3-8b-73-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rieofawox-h02-l3-8b-73-v1/tokenizer.json
rieofawox-h02-l3-8b-73-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rieofawox-h02-l3-8b-73-v1/tokenizer_config.json
rieofawox-h02-l3-8b-73-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rieofawox-h02-l3-8b-73-v1/special_tokens_map.json
rieofawox-h02-l3-8b-73-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rieofawox-h02-l3-8b-73-v1/flywheel_model.0.safetensors
rieofawox-h02-l3-8b-73-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
rieofawox-h02-l3-8b-73-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.
rieofawox-h02-l3-8b-73-v1-mkmlizer: warnings.warn(
rieofawox-h02-l3-8b-73-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.
rieofawox-h02-l3-8b-73-v1-mkmlizer: warnings.warn(
rieofawox-h02-l3-8b-73-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.
rieofawox-h02-l3-8b-73-v1-mkmlizer: warnings.warn(
rieofawox-h02-l3-8b-73-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()
rieofawox-h02-l3-8b-73-v1-mkmlizer: return self.fget.__get__(instance, owner)()
rieofawox-h02-l3-8b-73-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
rieofawox-h02-l3-8b-73-v1-mkmlizer: Saving duration: 0.425s
rieofawox-h02-l3-8b-73-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.524s
rieofawox-h02-l3-8b-73-v1-mkmlizer: creating bucket guanaco-reward-models
rieofawox-h02-l3-8b-73-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/rieofawox-h02-l3-8b-73-v1_reward/reward.tensors
Job rieofawox-h02-l3-8b-73-v1-mkmlizer completed after 114.33s with status: succeeded
Stopping job with name rieofawox-h02-l3-8b-73-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.39s
Running pipeline stage ISVCDeployer
Creating inference service rieofawox-h02-l3-8b-73-v1
Waiting for inference service rieofawox-h02-l3-8b-73-v1 to be ready
Inference service rieofawox-h02-l3-8b-73-v1 ready after 40.200111865997314s
Pipeline stage ISVCDeployer completed in 47.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.237726926803589s
Received healthy response to inference request in 1.332129716873169s
Received healthy response to inference request in 1.312958002090454s
Received healthy response to inference request in 1.297011137008667s
Received healthy response to inference request in 1.3562803268432617s
5 requests
0 failed requests
5th percentile: 1.3002005100250245
10th percentile: 1.303389883041382
20th percentile: 1.3097686290740966
30th percentile: 1.3167923450469972
40th percentile: 1.324461030960083
50th percentile: 1.332129716873169
60th percentile: 1.341789960861206
70th percentile: 1.3514502048492432
80th percentile: 1.5325696468353274
90th percentile: 1.885148286819458
95th percentile: 2.0614376068115234
99th percentile: 2.202469062805176
mean time: 1.5072212219238281
Pipeline stage StressChecker completed in 8.21s
rieofawox-h02-l3-8b-73_v1 status is now deployed due to DeploymentManager action
rieofawox-h02-l3-8b-73_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics