submission_id: fredithefish-harmonyrp-8x7b_v1
developer_uid: fredi
status: torndown
model_repo: Fredithefish/HarmonyRP-8x7B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.92, 'min_p': 0.0, 'top_k': 55, 'presence_penalty': 0.9, 'frequency_penalty': 0.3, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nWrite {bot_name}'s next reply in a fictional roleplay between {bot_name} and {user_name}. Write in a narrative style and use descriptive language. Be proactive, creative, and drive the plot and conversation forward. Always stay in character and avoid repetition. Drive the roleplay forward by initiating actions. Describe {bot_name}'s emotions, thoughts, actions, and sensations. Focus on responding to {user_name} and performing in-character actions.\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '### Input:\n# Introduction:\n{prompt}\n\n# Actual Conversation:\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\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: 2024-04-07T16:59:17+00:00
model_name: fredithefish-harmonyrp-8x7b_v1
model_eval_status: success
model_group: Fredithefish/HarmonyRP-8
num_battles: 72684
num_wins: 34878
celo_rating: 1143.24
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MixtralForCausalLM
model_num_parameters: 46702792704.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: fredithefish-harmonyrp-8x7b_v1
ineligible_reason: propriety_total_count < 800
language_model: Fredithefish/HarmonyRP-8x7B
model_size: 47B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-07
win_ratio: 0.47985801551923396
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name fredithefish-harmonyrp-8x7b-v1-mkmlizer
Waiting for job on fredithefish-harmonyrp-8x7b-v1-mkmlizer to finish
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ _____ __ __ ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ /___/ ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ Version: 0.8.6 ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ belonging to: ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ Chai Research Corp. ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ║ ║
fredithefish-harmonyrp-8x7b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
fredithefish-harmonyrp-8x7b-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.
fredithefish-harmonyrp-8x7b-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
fredithefish-harmonyrp-8x7b-v1-mkmlizer: Downloaded to shared memory in 207.407s
fredithefish-harmonyrp-8x7b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
fredithefish-harmonyrp-8x7b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
fredithefish-harmonyrp-8x7b-v1-mkmlizer: quantized model in 48.819s
fredithefish-harmonyrp-8x7b-v1-mkmlizer: Processed model Fredithefish/HarmonyRP-8x7B in 261.557s
fredithefish-harmonyrp-8x7b-v1-mkmlizer: creating bucket guanaco-mkml-models
fredithefish-harmonyrp-8x7b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
fredithefish-harmonyrp-8x7b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/fredithefish-harmonyrp-8x7b-v1
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/fredithefish-harmonyrp-8x7b-v1/config.json
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/fredithefish-harmonyrp-8x7b-v1/tokenizer_config.json
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/fredithefish-harmonyrp-8x7b-v1/tokenizer.json
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/fredithefish-harmonyrp-8x7b-v1/tokenizer.model
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/fredithefish-harmonyrp-8x7b-v1/special_tokens_map.json
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/fredithefish-harmonyrp-8x7b-v1/flywheel_model.3.safetensors
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/fredithefish-harmonyrp-8x7b-v1/flywheel_model.0.safetensors
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/fredithefish-harmonyrp-8x7b-v1/flywheel_model.2.safetensors
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/fredithefish-harmonyrp-8x7b-v1/flywheel_model.1.safetensors
fredithefish-harmonyrp-8x7b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
fredithefish-harmonyrp-8x7b-v1-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 1%| | 9/995 [00:00<00:11, 87.24it/s] Loading 0: 2%|▏ | 18/995 [00:00<00:11, 82.69it/s] Loading 0: 3%|▎ | 31/995 [00:00<00:09, 102.90it/s] Loading 0: 4%|▍ | 42/995 [00:00<00:10, 93.69it/s] Loading 0: 5%|▌ | 52/995 [00:00<00:10, 90.52it/s] Loading 0: 7%|▋ | 67/995 [00:00<00:08, 108.31it/s] Loading 0: 8%|▊ | 79/995 [00:00<00:09, 96.68it/s] Loading 0: 9%|▉ | 90/995 [00:00<00:09, 97.27it/s] Loading 0: 10%|█ | 102/995 [00:01<00:08, 101.49it/s] Loading 0: 11%|█▏ | 113/995 [00:01<00:22, 40.05it/s] Loading 0: 12%|█▏ | 121/995 [00:01<00:19, 45.27it/s] Loading 0: 14%|█▎ | 135/995 [00:01<00:14, 59.92it/s] Loading 0: 15%|█▍ | 145/995 [00:02<00:12, 65.44it/s] Loading 0: 16%|█▌ | 155/995 [00:02<00:11, 70.33it/s] Loading 0: 17%|█▋ | 170/995 [00:02<00:09, 86.40it/s] Loading 0: 18%|█▊ | 181/995 [00:02<00:09, 83.69it/s] Loading 0: 20%|█▉ | 195/995 [00:02<00:08, 96.56it/s] Loading 0: 21%|██ | 206/995 [00:02<00:08, 95.97it/s] Loading 0: 22%|██▏ | 217/995 [00:03<00:18, 42.33it/s] Loading 0: 23%|██▎ | 230/995 [00:03<00:14, 53.52it/s] Loading 0: 24%|██▍ | 240/995 [00:03<00:13, 56.36it/s] Loading 0: 25%|██▌ | 250/995 [00:03<00:11, 62.73it/s] Loading 0: 26%|██▌ | 259/995 [00:03<00:11, 66.21it/s] Loading 0: 27%|██▋ | 268/995 [00:03<00:10, 68.59it/s] Loading 0: 29%|██▊ | 284/995 [00:03<00:08, 87.31it/s] Loading 0: 30%|██▉ | 295/995 [00:12<02:45, 4.23it/s] Loading 0: 31%|███ | 304/995 [00:12<02:04, 5.55it/s] Loading 0: 32%|███▏ | 319/995 [00:12<01:18, 8.66it/s] Loading 0: 33%|███▎ | 329/995 [00:13<01:06, 10.03it/s] Loading 0: 34%|███▍ | 338/995 [00:13<00:50, 12.92it/s] Loading 0: 35%|███▍ | 347/995 [00:13<00:38, 16.68it/s] Loading 0: 36%|███▋ | 361/995 [00:13<00:25, 24.73it/s] Loading 0: 37%|███▋ | 371/995 [00:13<00:20, 30.81it/s] Loading 0: 39%|███▉ | 387/995 [00:14<00:13, 44.53it/s] Loading 0: 40%|████ | 399/995 [00:14<00:11, 52.66it/s] Loading 0: 41%|████ | 410/995 [00:14<00:09, 60.60it/s] Loading 0: 42%|████▏ | 422/995 [00:14<00:08, 70.23it/s] Loading 0: 44%|████▎ | 433/995 [00:14<00:13, 40.79it/s] Loading 0: 45%|████▍ | 445/995 [00:15<00:10, 50.60it/s] Loading 0: 46%|████▌ | 455/995 [00:15<00:09, 57.45it/s] Loading 0: 47%|████▋ | 465/995 [00:15<00:08, 62.92it/s] Loading 0: 48%|████▊ | 481/995 [00:15<00:06, 80.72it/s] Loading 0: 49%|████▉ | 492/995 [00:15<00:05, 84.03it/s] Loading 0: 51%|█████ | 508/995 [00:15<00:04, 100.40it/s] Loading 0: 52%|█████▏ | 520/995 [00:15<00:04, 96.74it/s] Loading 0: 53%|█████▎ | 531/995 [00:15<00:04, 98.49it/s] Loading 0: 54%|█████▍ | 542/995 [00:16<00:09, 48.20it/s] Loading 0: 55%|█████▌ | 551/995 [00:16<00:08, 54.29it/s] Loading 0: 56%|█████▋ | 560/995 [00:25<01:59, 3.65it/s] Loading 0: 58%|█████▊ | 576/995 [00:25<01:10, 5.96it/s] Loading 0: 59%|█████▉ | 586/995 [00:25<00:51, 7.89it/s] Loading 0: 61%|██████ | 602/995 [00:25<00:32, 12.24it/s] Loading 0: 62%|██████▏ | 613/995 [00:25<00:23, 15.98it/s] Loading 0: 63%|██████▎ | 627/995 [00:26<00:16, 22.52it/s] Loading 0: 64%|██████▍ | 639/995 [00:26<00:12, 29.32it/s] Loading 0: 65%|██████▌ | 651/995 [00:26<00:13, 26.16it/s] Loading 0: 67%|██████▋ | 663/995 [00:26<00:09, 33.53it/s] Loading 0: 68%|██████▊ | 673/995 [00:26<00:08, 40.24it/s] Loading 0: 69%|██████▊ | 683/995 [00:27<00:06, 46.62it/s] Loading 0: 70%|███████ | 699/995 [00:27<00:04, 63.12it/s] Loading 0: 71%|███████▏ | 710/995 [00:27<00:04, 69.47it/s] Loading 0: 73%|███████▎ | 726/995 [00:27<00:03, 87.06it/s] Loading 0: 74%|███████▍ | 738/995 [00:27<00:02, 88.40it/s] Loading 0: 75%|███████▌ | 750/995 [00:28<00:05, 47.40it/s] Loading 0: 76%|███████▋ | 761/995 [00:28<00:04, 55.62it/s] Loading 0: 77%|███████▋ | 771/995 [00:28<00:03, 61.93it/s] Loading 0: 79%|███████▉ | 787/995 [00:28<00:02, 79.46it/s] Loading 0: 80%|████████ | 798/995 [00:28<00:02, 81.28it/s] Loading 0: 81%|████████▏ | 809/995 [00:28<00:02, 79.37it/s] Loading 0: 83%|████████▎ | 823/995 [00:28<00:01, 92.57it/s] Loading 0: 84%|████████▍ | 834/995 [00:28<00:01, 85.66it/s] Loading 0: 85%|████████▍ | 844/995 [00:38<00:37, 4.01it/s] Loading 0: 86%|████████▌ | 854/995 [00:39<00:32, 4.33it/s] Loading 0: 87%|████████▋ | 863/995 [00:40<00:22, 5.75it/s] Loading 0: 88%|████████▊ | 871/995 [00:40<00:16, 7.46it/s] Loading 0: 89%|████████▊ | 881/995 [00:40<00:10, 10.41it/s] Loading 0: 89%|████████▉ | 890/995 [00:40<00:07, 13.85it/s] Loading 0: 90%|█████████ | 899/995 [00:40<00:05, 18.22it/s] Loading 0: 92%|█████████▏| 914/995 [00:40<00:02, 28.21it/s] Loading 0: 93%|█████████▎| 924/995 [00:40<00:02, 34.83it/s] Loading 0: 94%|█████████▍| 940/995 [00:40<00:01, 49.54it/s] Loading 0: 96%|█████████▌| 952/995 [00:40<00:00, 57.63it/s] Loading 0: 97%|█████████▋| 963/995 [00:41<00:00, 37.26it/s] Loading 0: 98%|█████████▊| 979/995 [00:41<00:00, 51.20it/s] Loading 0: 99%|█████████▉| 989/995 [00:41<00:00, 57.44it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1096: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
fredithefish-harmonyrp-8x7b-v1-mkmlizer: warnings.warn(
fredithefish-harmonyrp-8x7b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:720: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
fredithefish-harmonyrp-8x7b-v1-mkmlizer: warnings.warn(
fredithefish-harmonyrp-8x7b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:466: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
fredithefish-harmonyrp-8x7b-v1-mkmlizer: warnings.warn(
fredithefish-harmonyrp-8x7b-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()
fredithefish-harmonyrp-8x7b-v1-mkmlizer: return self.fget.__get__(instance, owner)()
fredithefish-harmonyrp-8x7b-v1-mkmlizer: creating bucket guanaco-reward-models
fredithefish-harmonyrp-8x7b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
fredithefish-harmonyrp-8x7b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/fredithefish-harmonyrp-8x7b-v1_reward
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/fredithefish-harmonyrp-8x7b-v1_reward/tokenizer_config.json
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/fredithefish-harmonyrp-8x7b-v1_reward/special_tokens_map.json
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/fredithefish-harmonyrp-8x7b-v1_reward/vocab.json
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/fredithefish-harmonyrp-8x7b-v1_reward/config.json
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/fredithefish-harmonyrp-8x7b-v1_reward/merges.txt
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/fredithefish-harmonyrp-8x7b-v1_reward/tokenizer.json
fredithefish-harmonyrp-8x7b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/fredithefish-harmonyrp-8x7b-v1_reward/reward.tensors
Job fredithefish-harmonyrp-8x7b-v1-mkmlizer completed after 304.82s with status: succeeded
Stopping job with name fredithefish-harmonyrp-8x7b-v1-mkmlizer
Pipeline stage MKMLizer completed in 309.28s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service fredithefish-harmonyrp-8x7b-v1
Waiting for inference service fredithefish-harmonyrp-8x7b-v1 to be ready
Inference service fredithefish-harmonyrp-8x7b-v1 ready after 60.46263885498047s
Pipeline stage ISVCDeployer completed in 68.33s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4658098220825195s
Received healthy response to inference request in 2.568739652633667s
Received healthy response to inference request in 2.8460865020751953s
Received healthy response to inference request in 2.516066074371338s
Received healthy response to inference request in 2.5411765575408936s
5 requests
0 failed requests
5th percentile: 2.521088171005249
10th percentile: 2.5261102676391602
20th percentile: 2.5361544609069826
30th percentile: 2.546689176559448
40th percentile: 2.557714414596558
50th percentile: 2.568739652633667
60th percentile: 2.6796783924102785
70th percentile: 2.7906171321868896
80th percentile: 2.97003116607666
90th percentile: 3.21792049407959
95th percentile: 3.3418651580810548
99th percentile: 3.4410208892822265
mean time: 2.7875757217407227
Pipeline stage StressChecker completed in 14.61s
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
fredithefish-harmonyrp-8x7b_v1 status is now deployed due to DeploymentManager action
fredithefish-harmonyrp-8x7b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of fredithefish-harmonyrp-8x7b_v1
Running pipeline stage ISVCDeleter
Checking if service fredithefish-harmonyrp-8x7b-v1 is running
Tearing down inference service fredithefish-harmonyrp-8x7b-v1
Toredown service fredithefish-harmonyrp-8x7b-v1
Pipeline stage ISVCDeleter completed in 4.97s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Deleting key fredithefish-harmonyrp-8x7b-v1/config.json from bucket guanaco-mkml-models
Deleting key fredithefish-harmonyrp-8x7b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key fredithefish-harmonyrp-8x7b-v1/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key fredithefish-harmonyrp-8x7b-v1/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key fredithefish-harmonyrp-8x7b-v1/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key fredithefish-harmonyrp-8x7b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key fredithefish-harmonyrp-8x7b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key fredithefish-harmonyrp-8x7b-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key fredithefish-harmonyrp-8x7b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key fredithefish-harmonyrp-8x7b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key fredithefish-harmonyrp-8x7b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key fredithefish-harmonyrp-8x7b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key fredithefish-harmonyrp-8x7b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key fredithefish-harmonyrp-8x7b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key fredithefish-harmonyrp-8x7b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key fredithefish-harmonyrp-8x7b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.20s
fredithefish-harmonyrp-8x7b_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics