jellywibble-lora-120k-pr_2827

submission_id: jellywibble-lora-120k-pr_2827_v2

developer_uid: Jellywibble

best_of: 16

celo_rating: 1264.33

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_ep2

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_ep2

model_size: 8B

num_battles: 30751

num_wins: 18446

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/gpt2_xl_pairwise_89m_step_347634

status: torndown

submission_type: basic

timestamp: 2024-07-04T23:04:19+00:00

us_pacific_date: 2024-07-04

win_ratio: 0.599850411368736

Resubmit model

Running pipeline stage MKMLizer
Starting job with name jellywibble-lora-120k-pr-2827-v2-mkmlizer
Waiting for job on jellywibble-lora-120k-pr-2827-v2-mkmlizer to finish
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║     _____            __           __                                ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║       /___/                                                         ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║  belonging to:                                                      ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2827-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-lora-120k-pr-2827-v2-mkmlizer: Downloaded to shared memory in 51.685s
jellywibble-lora-120k-pr-2827-v2-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-lora-120k-pr-2827-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-lora-120k-pr-2827-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:06, 41.73it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 59.10it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:04, 63.63it/s]
Loading 0:  10%|▉         | 28/291 [00:00<00:04, 60.88it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:09, 27.26it/s]
Loading 0:  14%|█▎        | 40/291 [00:01<00:08, 30.21it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:06, 39.05it/s]
Loading 0:  19%|█▊        | 54/291 [00:01<00:05, 43.04it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 44.97it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 50.57it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:03, 54.84it/s]
Loading 0:  28%|██▊       | 81/291 [00:02<00:07, 29.48it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 33.89it/s]
Loading 0:  32%|███▏      | 92/291 [00:02<00:05, 35.26it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 43.88it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:03, 51.58it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 55.04it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:02, 61.22it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:02, 59.95it/s]
Loading 0:  47%|████▋     | 137/291 [00:03<00:04, 32.58it/s]
Loading 0:  49%|████▉     | 143/291 [00:03<00:04, 35.63it/s]
Loading 0:  51%|█████     | 149/291 [00:03<00:03, 38.22it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 46.10it/s]
Loading 0:  57%|█████▋    | 165/291 [00:03<00:02, 52.79it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 55.84it/s]
Loading 0:  62%|██████▏   | 179/291 [00:04<00:02, 55.57it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:03, 33.79it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 36.09it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 37.84it/s]
Loading 0:  70%|██████▉   | 203/291 [00:04<00:02, 41.69it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 50.08it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 55.03it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 56.33it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 34.46it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 36.31it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:01, 42.42it/s]
Loading 0:  88%|████████▊ | 255/291 [00:05<00:00, 50.22it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 54.39it/s]
Loading 0:  92%|█████████▏| 269/291 [00:06<00:00, 54.89it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 54.89it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  3.60it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-lora-120k-pr-2827-v2-mkmlizer: quantized model in 33.596s
jellywibble-lora-120k-pr-2827-v2-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep2 in 85.282s
jellywibble-lora-120k-pr-2827-v2-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-pr-2827-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-pr-2827-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v2
jellywibble-lora-120k-pr-2827-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v2/config.json
jellywibble-lora-120k-pr-2827-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v2/special_tokens_map.json
jellywibble-lora-120k-pr-2827-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v2/tokenizer_config.json
jellywibble-lora-120k-pr-2827-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v2/tokenizer.json
jellywibble-lora-120k-pr-2827-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v2/flywheel_model.0.safetensors
jellywibble-lora-120k-pr-2827-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jellywibble-lora-120k-pr-2827-v2-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-2827-v2-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2827-v2-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-2827-v2-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2827-v2-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-2827-v2-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2827-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.
jellywibble-lora-120k-pr-2827-v2-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2827-v2-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:09<00:09,  9.14s/it]
Downloading shards: 100%|██████████| 2/2 [00:11<00:00,  5.34s/it]
Downloading shards: 100%|██████████| 2/2 [00:11<00:00,  5.91s/it]
jellywibble-lora-120k-pr-2827-v2-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.59it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.59it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.36it/s]
jellywibble-lora-120k-pr-2827-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-lora-120k-pr-2827-v2-mkmlizer: Saving duration: 2.185s
jellywibble-lora-120k-pr-2827-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 16.426s
jellywibble-lora-120k-pr-2827-v2-mkmlizer: creating bucket guanaco-reward-models
jellywibble-lora-120k-pr-2827-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-lora-120k-pr-2827-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v2_reward
jellywibble-lora-120k-pr-2827-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v2_reward/config.json
jellywibble-lora-120k-pr-2827-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v2_reward/special_tokens_map.json
jellywibble-lora-120k-pr-2827-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v2_reward/tokenizer_config.json
jellywibble-lora-120k-pr-2827-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v2_reward/vocab.json
jellywibble-lora-120k-pr-2827-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v2_reward/merges.txt
jellywibble-lora-120k-pr-2827-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v2_reward/tokenizer.json
jellywibble-lora-120k-pr-2827-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v2_reward/reward.tensors
Job jellywibble-lora-120k-pr-2827-v2-mkmlizer completed after 135.02s with status: succeeded
Stopping job with name jellywibble-lora-120k-pr-2827-v2-mkmlizer
Pipeline stage MKMLizer completed in 135.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-lora-120k-pr-2827-v2
Waiting for inference service jellywibble-lora-120k-pr-2827-v2 to be ready
Inference service jellywibble-lora-120k-pr-2827-v2 ready after 70.3964033126831s
Pipeline stage ISVCDeployer completed in 77.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3405394554138184s
Received healthy response to inference request in 1.5941638946533203s
Received healthy response to inference request in 1.5567553043365479s
Received healthy response to inference request in 1.533492088317871s
Received healthy response to inference request in 1.6077618598937988s
5 requests
0 failed requests
5th percentile: 1.5381447315216064
10th percentile: 1.5427973747253418
20th percentile: 1.5521026611328126
30th percentile: 1.5642370223999023
40th percentile: 1.5792004585266113
50th percentile: 1.5941638946533203
60th percentile: 1.5996030807495116
70th percentile: 1.6050422668457032
80th percentile: 1.7543173789978028
90th percentile: 2.0474284172058104
95th percentile: 2.1939839363098144
99th percentile: 2.3112283515930176
mean time: 1.7265425205230713
Pipeline stage StressChecker completed in 9.31s
jellywibble-lora-120k-pr_2827_v2 status is now deployed due to DeploymentManager action
jellywibble-lora-120k-pr_2827_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jellywibble-lora-120k-pr_2827_v2
Running pipeline stage ISVCDeleter
Checking if service jellywibble-lora-120k-pr-2827-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.82s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-2827-v2/config.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2827-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2827-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2827-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2827-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-2827-v2_reward/config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.80s
jellywibble-lora-120k-pr_2827_v2 status is now torndown due to DeploymentManager action