submission_id: rieofawox-l3-8b-stheno-v_2471_v1
developer_uid: la.fey
status: inactive
model_repo: Rieofawox/L3-8B-Stheno-v3.2-X2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.12, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>', '\n\n{user_name}'], '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: 2024-06-06T19:20:53+00:00
model_name: rieofawox-l3-8b-stheno-v_2471_v1
model_eval_status: success
model_group: Rieofawox/L3-8B-Stheno-v
num_battles: 17817
num_wins: 9771
celo_rating: 1214.49
safety_score: 0.96
propriety_score: 0.6890756302521008
propriety_total_count: 1190.0
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-l3-8b-stheno-v_2471_v1
ineligible_reason: propriety_total_count < 5000
language_model: Rieofawox/L3-8B-Stheno-v3.2-X2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-06
win_ratio: 0.5484088230341808
Resubmit model
Running pipeline stage MKMLizer
Starting job with name rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer
Waiting for job on rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer to finish
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ _____ __ __ ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ /___/ ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ Version: 0.8.14 ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ https://mk1.ai ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ belonging to: ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ Chai Research Corp. ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ║ ║
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rieofawox-l3-8b-stheno-v-2471-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-l3-8b-stheno-v-2471-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v45: ('http://mistralai-mixtral-8x7b-3473-v45-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:46120->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v44: ('http://amd-proxy-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ConnectionError : HTTPConnectionPool(host=\'160.72.11.8\', port=8080): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by NewConnectionError(\'<urllib3.connection.HTTPConnection object at 0x7f14d9bb5cd0>: Failed to establish a new connection: [Errno 101] Network is unreachable\'))"}')
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: Downloaded to shared memory in 278.523s
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: quantizing model to /dev/shm/model_cache
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<12:16, 2.55s/it] Loading 0: 4%|▍ | 13/291 [00:05<01:22, 3.37it/s] Loading 0: 8%|▊ | 24/291 [00:05<00:36, 7.31it/s] Loading 0: 12%|█▏ | 36/291 [00:05<00:19, 12.94it/s] Loading 0: 15%|█▌ | 45/291 [00:05<00:13, 18.09it/s] Loading 0: 19%|█▊ | 54/291 [00:05<00:09, 24.26it/s] Loading 0: 22%|██▏ | 63/291 [00:06<00:09, 23.76it/s] Loading 0: 25%|██▌ | 73/291 [00:06<00:06, 31.74it/s] Loading 0: 29%|██▉ | 85/291 [00:06<00:04, 42.02it/s] Loading 0: 33%|███▎ | 95/291 [00:06<00:03, 49.54it/s] Loading 0: 36%|███▌ | 105/291 [00:06<00:03, 58.08it/s] Loading 0: 41%|████ | 118/291 [00:06<00:02, 71.73it/s] Loading 0: 45%|████▍ | 130/291 [00:06<00:01, 80.92it/s] Loading 0: 48%|████▊ | 141/291 [00:06<00:01, 78.49it/s] Loading 0: 53%|█████▎ | 153/291 [00:06<00:01, 86.75it/s] Loading 0: 56%|█████▌ | 163/291 [00:07<00:01, 86.37it/s] Loading 0: 59%|█████▉ | 173/291 [00:07<00:02, 52.96it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 61.26it/s] Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 66.65it/s] Loading 0: 69%|██████▉ | 202/291 [00:07<00:01, 70.97it/s] Loading 0: 73%|███████▎ | 211/291 [00:07<00:01, 74.79it/s] Loading 0: 76%|███████▌ | 220/291 [00:07<00:00, 78.36it/s] Loading 0: 79%|███████▉ | 230/291 [00:08<00:00, 81.88it/s] Loading 0: 82%|████████▏ | 240/291 [00:08<00:00, 84.66it/s] Loading 0: 86%|████████▌ | 249/291 [00:08<00:00, 86.00it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 89.57it/s] Loading 0: 92%|█████████▏| 269/291 [00:08<00:00, 52.00it/s] Loading 0: 96%|█████████▌| 279/291 [00:08<00:00, 60.13it/s] Loading 0: 99%|█████████▉| 289/291 [00:08<00:00, 67.41it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: quantized model in 25.612s
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: Processed model Rieofawox/L3-8B-Stheno-v3.2-X2 in 306.906s
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: creating bucket guanaco-mkml-models
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rieofawox-l3-8b-stheno-v-2471-v1
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rieofawox-l3-8b-stheno-v-2471-v1/special_tokens_map.json
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rieofawox-l3-8b-stheno-v-2471-v1/tokenizer_config.json
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rieofawox-l3-8b-stheno-v-2471-v1/config.json
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rieofawox-l3-8b-stheno-v-2471-v1/tokenizer.json
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rieofawox-l3-8b-stheno-v-2471-v1/flywheel_model.0.safetensors
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
rieofawox-l3-8b-stheno-v-2471-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-l3-8b-stheno-v-2471-v1-mkmlizer: warnings.warn(
rieofawox-l3-8b-stheno-v-2471-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-l3-8b-stheno-v-2471-v1-mkmlizer: warnings.warn(
rieofawox-l3-8b-stheno-v-2471-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-l3-8b-stheno-v-2471-v1-mkmlizer: return self.fget.__get__(instance, owner)()
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: Saving duration: 0.490s
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.450s
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: creating bucket guanaco-reward-models
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/rieofawox-l3-8b-stheno-v-2471-v1_reward
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/rieofawox-l3-8b-stheno-v-2471-v1_reward/merges.txt
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/rieofawox-l3-8b-stheno-v-2471-v1_reward/special_tokens_map.json
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/rieofawox-l3-8b-stheno-v-2471-v1_reward/tokenizer_config.json
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/rieofawox-l3-8b-stheno-v-2471-v1_reward/vocab.json
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/rieofawox-l3-8b-stheno-v-2471-v1_reward/config.json
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/rieofawox-l3-8b-stheno-v-2471-v1_reward/tokenizer.json
rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/rieofawox-l3-8b-stheno-v-2471-v1_reward/reward.tensors
Job rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer completed after 361.0s with status: succeeded
Stopping job with name rieofawox-l3-8b-stheno-v-2471-v1-mkmlizer
Pipeline stage MKMLizer completed in 365.39s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service rieofawox-l3-8b-stheno-v-2471-v1
Waiting for inference service rieofawox-l3-8b-stheno-v-2471-v1 to be ready
Inference service rieofawox-l3-8b-stheno-v-2471-v1 ready after 40.319918155670166s
Pipeline stage ISVCDeployer completed in 48.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2433154582977295s
Received healthy response to inference request in 1.3501715660095215s
Received healthy response to inference request in 1.3063151836395264s
Received healthy response to inference request in 1.2848055362701416s
Received healthy response to inference request in 1.36464524269104s
5 requests
0 failed requests
5th percentile: 1.2891074657440185
10th percentile: 1.2934093952178956
20th percentile: 1.3020132541656495
30th percentile: 1.3150864601135255
40th percentile: 1.3326290130615235
50th percentile: 1.3501715660095215
60th percentile: 1.3559610366821289
70th percentile: 1.3617505073547362
80th percentile: 1.5403792858123782
90th percentile: 1.8918473720550537
95th percentile: 2.0675814151763916
99th percentile: 2.208168649673462
mean time: 1.5098505973815919
Pipeline stage StressChecker completed in 8.20s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
rieofawox-l3-8b-stheno-v_2471_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
rieofawox-l3-8b-stheno-v_2471_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics