jellywibble-lora-120k-pr_1572

submission_id: jellywibble-lora-120k-pr_1572_v1

developer_uid: Jellywibble

best_of: 16

celo_rating: 1222.39

display_name: nitral-ai-hathor-l3-8b-v-01_v1

family_friendly_score: 0.0

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}

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

is_internal_developer: True

language_model: Jellywibble/lora_120k_pref_data_ep1

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Jellywibble/lora_120k_pr

model_name: nitral-ai-hathor-l3-8b-v-01_v1

model_num_parameters: 8030261248.0

model_repo: Jellywibble/lora_120k_pref_data_ep1

model_size: 8B

num_battles: 13043

num_wins: 7096

ranking_group: single

reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-07-04T03:50:14+00:00

us_pacific_date: 2024-07-03

win_ratio: 0.5440466150425516

Resubmit model

Running pipeline stage MKMLizer
Starting job with name jellywibble-lora-120k-pr-1572-v1-mkmlizer
Waiting for job on jellywibble-lora-120k-pr-1572-v1-mkmlizer to finish
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║     _____            __           __                                ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║       /___/                                                         ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║  belonging to:                                                      ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-1572-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-lora-120k-pr-1572-v1-mkmlizer: Downloaded to shared memory in 96.697s
jellywibble-lora-120k-pr-1572-v1-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-lora-120k-pr-1572-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-lora-120k-pr-1572-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:08, 35.30it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:05, 46.82it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:06, 42.73it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:06, 41.44it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:05, 51.37it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:09, 26.03it/s]
Loading 0:  14%|█▎        | 40/291 [00:01<00:08, 28.26it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:06, 35.83it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:06, 38.55it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:06, 38.24it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:05, 43.90it/s]
Loading 0:  24%|██▍       | 71/291 [00:01<00:04, 45.02it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 45.63it/s]
Loading 0:  28%|██▊       | 81/291 [00:02<00:07, 29.42it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:06, 31.40it/s]
Loading 0:  31%|███▏      | 91/291 [00:02<00:05, 35.24it/s]
Loading 0:  34%|███▍      | 99/291 [00:02<00:04, 41.83it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:04, 43.59it/s]
Loading 0:  38%|███▊      | 110/291 [00:02<00:04, 43.32it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:02, 57.05it/s]
Loading 0:  44%|████▍     | 128/291 [00:03<00:02, 54.85it/s]
Loading 0:  46%|████▌     | 134/291 [00:03<00:04, 35.42it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:04, 34.94it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:03, 40.65it/s]
Loading 0:  52%|█████▏    | 152/291 [00:03<00:03, 41.28it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:03, 41.15it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:02, 45.30it/s]
Loading 0:  58%|█████▊    | 170/291 [00:04<00:02, 46.25it/s]
Loading 0:  60%|██████    | 176/291 [00:04<00:02, 46.32it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:02, 39.74it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 39.14it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 37.87it/s]
Loading 0:  69%|██████▉   | 202/291 [00:05<00:02, 39.90it/s]
Loading 0:  72%|███████▏  | 210/291 [00:05<00:01, 46.51it/s]
Loading 0:  74%|███████▍  | 215/291 [00:05<00:01, 44.86it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 43.37it/s]
Loading 0:  78%|███████▊  | 227/291 [00:05<00:01, 47.16it/s]
Loading 0:  80%|████████  | 233/291 [00:05<00:01, 33.25it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:01, 33.42it/s]
Loading 0:  85%|████████▍ | 246/291 [00:06<00:01, 39.54it/s]
Loading 0:  86%|████████▋ | 251/291 [00:06<00:01, 39.87it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 39.82it/s]
Loading 0:  91%|█████████ | 264/291 [00:06<00:00, 46.91it/s]
Loading 0:  92%|█████████▏| 269/291 [00:06<00:00, 45.20it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 43.89it/s]
Loading 0:  97%|█████████▋| 281/291 [00:06<00:00, 45.67it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  2.96it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-lora-120k-pr-1572-v1-mkmlizer: quantized model in 29.428s
jellywibble-lora-120k-pr-1572-v1-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep1 in 126.126s
jellywibble-lora-120k-pr-1572-v1-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-pr-1572-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-pr-1572-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-pr-1572-v1
jellywibble-lora-120k-pr-1572-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-1572-v1/tokenizer_config.json
jellywibble-lora-120k-pr-1572-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-1572-v1/config.json
jellywibble-lora-120k-pr-1572-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-1572-v1/special_tokens_map.json
jellywibble-lora-120k-pr-1572-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-1572-v1/tokenizer.json
jellywibble-lora-120k-pr-1572-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-lora-120k-pr-1572-v1/flywheel_model.0.safetensors
jellywibble-lora-120k-pr-1572-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
jellywibble-lora-120k-pr-1572-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-lora-120k-pr-1572-v1-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-1572-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
jellywibble-lora-120k-pr-1572-v1-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-1572-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-lora-120k-pr-1572-v1-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-1572-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.
jellywibble-lora-120k-pr-1572-v1-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-1572-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()
jellywibble-lora-120k-pr-1572-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
jellywibble-lora-120k-pr-1572-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-lora-120k-pr-1572-v1-mkmlizer: Saving duration: 0.441s
jellywibble-lora-120k-pr-1572-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.582s
jellywibble-lora-120k-pr-1572-v1-mkmlizer: creating bucket guanaco-reward-models
jellywibble-lora-120k-pr-1572-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-lora-120k-pr-1572-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-lora-120k-pr-1572-v1_reward
jellywibble-lora-120k-pr-1572-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-1572-v1_reward/config.json
jellywibble-lora-120k-pr-1572-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-1572-v1_reward/special_tokens_map.json
jellywibble-lora-120k-pr-1572-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-1572-v1_reward/tokenizer_config.json
jellywibble-lora-120k-pr-1572-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-1572-v1_reward/vocab.json
jellywibble-lora-120k-pr-1572-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-lora-120k-pr-1572-v1_reward/merges.txt
jellywibble-lora-120k-pr-1572-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-1572-v1_reward/tokenizer.json
jellywibble-lora-120k-pr-1572-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-lora-120k-pr-1572-v1_reward/reward.tensors
Job jellywibble-lora-120k-pr-1572-v1-mkmlizer completed after 166.22s with status: succeeded
Stopping job with name jellywibble-lora-120k-pr-1572-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.07s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-lora-120k-pr-1572-v1
Waiting for inference service jellywibble-lora-120k-pr-1572-v1 to be ready
Inference service jellywibble-lora-120k-pr-1572-v1 ready after 40.2138397693634s
Pipeline stage ISVCDeployer completed in 46.81s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.146315813064575s
Received healthy response to inference request in 1.3610589504241943s
Received healthy response to inference request in 1.3174340724945068s
Received healthy response to inference request in 1.3052010536193848s
Received healthy response to inference request in 1.3505668640136719s
5 requests
0 failed requests
5th percentile: 1.3076476573944091
10th percentile: 1.3100942611694335
20th percentile: 1.3149874687194825
30th percentile: 1.3240606307983398
40th percentile: 1.337313747406006
50th percentile: 1.3505668640136719
60th percentile: 1.3547636985778808
70th percentile: 1.3589605331420898
80th percentile: 1.5181103229522706
90th percentile: 1.832213068008423
95th percentile: 1.989264440536499
99th percentile: 2.11490553855896
mean time: 1.4961153507232665
Pipeline stage StressChecker completed in 8.24s
jellywibble-lora-120k-pr_1572_v1 status is now deployed due to DeploymentManager action
jellywibble-lora-120k-pr_1572_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jellywibble-lora-120k-pr_1572_v1
Running pipeline stage ISVCDeleter
Checking if service jellywibble-lora-120k-pr-1572-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.22s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-1572-v1/config.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-1572-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-1572-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-1572-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-1572-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-1572-v1_reward/config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-1572-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-1572-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-1572-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-1572-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-1572-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-1572-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.67s
jellywibble-lora-120k-pr_1572_v1 status is now torndown due to DeploymentManager action