jellywibble-lora-120k-pr_2827

developer_uid: kay5555
submission_id: jellywibble-lora-120k-pr_2827_v4
model_name: nitral-ai-hathor-l3-8b-v-01_v1
model_group: Jellywibble/lora_120k_pr
status: torndown
timestamp: 2024-07-05T04:01:08+00:00
num_battles: 40196
num_wins: 23356
celo_rating: 1259.68
family_friendly_score: 0.0
submission_type: basic
model_repo: Jellywibble/lora_120k_pref_data_ep2
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-l3-8b-v-01_v1
is_internal_developer: False
language_model: Jellywibble/lora_120k_pref_data_ep2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-04
win_ratio: 0.5810528410787144
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}
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: {'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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-lora-120k-pr-2827-v4-mkmlizer
Waiting for job on jellywibble-lora-120k-pr-2827-v4-mkmlizer to finish
Stopping job with name jellywibble-lora-120k-pr-2827-v4-mkmlizer
%s, retrying in %s seconds...
Starting job with name jellywibble-lora-120k-pr-2827-v4-mkmlizer
Waiting for job on jellywibble-lora-120k-pr-2827-v4-mkmlizer to finish
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║     _____            __           __                                ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║       /___/                                                         ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║  belonging to:                                                      ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2827-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-lora-120k-pr-2827-v4-mkmlizer: Downloaded to shared memory in 72.672s
jellywibble-lora-120k-pr-2827-v4-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-lora-120k-pr-2827-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-lora-120k-pr-2827-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/291 [00:06<10:59,  2.29s/it]
Loading 0:   1%|▏         | 4/291 [00:09<12:11,  2.55s/it]
Loading 0:   2%|▏         | 5/291 [00:10<08:45,  1.84s/it]
Loading 0:   3%|▎         | 8/291 [00:10<03:46,  1.25it/s]
Loading 0:   3%|▎         | 10/291 [00:10<02:30,  1.86it/s]
Loading 0:   4%|▍         | 12/291 [00:10<01:54,  2.43it/s]
Loading 0:   5%|▍         | 14/291 [00:11<01:47,  2.57it/s]
Loading 0:   6%|▌         | 17/291 [00:11<01:07,  4.07it/s]
Loading 0:   7%|▋         | 19/291 [00:11<00:52,  5.17it/s]
Loading 0:   7%|▋         | 21/291 [00:12<00:49,  5.40it/s]
Loading 0:   8%|▊         | 23/291 [00:12<01:05,  4.09it/s]
Loading 0:   9%|▉         | 26/291 [00:12<00:45,  5.87it/s]
Loading 0:  10%|▉         | 28/291 [00:13<00:38,  6.84it/s]
Loading 0:  10%|█         | 30/291 [00:13<00:33,  7.76it/s]
Loading 0:  11%|█         | 32/291 [00:13<00:30,  8.59it/s]
Loading 0:  12%|█▏        | 34/291 [00:14<00:51,  4.97it/s]
Loading 0:  12%|█▏        | 35/291 [00:14<01:00,  4.22it/s]
Loading 0:  12%|█▏        | 36/291 [00:15<01:08,  3.72it/s]
Loading 0:  13%|█▎        | 39/291 [00:15<00:52,  4.78it/s]
Loading 0:  14%|█▎        | 40/291 [00:15<01:01,  4.09it/s]
Loading 0:  14%|█▍        | 41/291 [00:16<01:05,  3.80it/s]
Loading 0:  15%|█▌        | 44/291 [00:16<00:39,  6.25it/s]
Loading 0:  16%|█▌        | 46/291 [00:16<00:32,  7.61it/s]
Loading 0:  16%|█▋        | 48/291 [00:16<00:35,  6.83it/s]
Loading 0:  17%|█▋        | 49/291 [00:17<00:45,  5.28it/s]
Loading 0:  17%|█▋        | 50/291 [00:17<00:51,  4.66it/s]
Loading 0:  19%|█▊        | 54/291 [00:17<00:27,  8.54it/s]
Loading 0:  20%|█▉        | 57/291 [00:17<00:21, 10.83it/s]
Loading 0:  20%|██        | 59/291 [00:18<00:19, 11.64it/s]
Loading 0:  23%|██▎       | 67/291 [00:18<00:09, 22.47it/s]
Loading 0:  25%|██▌       | 74/291 [00:18<00:07, 30.64it/s]
Loading 0:  27%|██▋       | 80/291 [00:18<00:08, 25.03it/s]
Loading 0:  29%|██▉       | 84/291 [00:18<00:07, 26.37it/s]
Loading 0:  31%|███▏      | 91/291 [00:18<00:05, 33.86it/s]
Loading 0:  34%|███▍      | 99/291 [00:18<00:04, 41.65it/s]
Loading 0:  36%|███▌      | 104/291 [00:19<00:04, 40.80it/s]
Loading 0:  37%|███▋      | 109/291 [00:19<00:05, 35.56it/s]
Loading 0:  40%|███▉      | 116/291 [00:19<00:04, 39.79it/s]
Loading 0:  43%|████▎     | 125/291 [00:19<00:03, 45.17it/s]
Loading 0:  45%|████▍     | 130/291 [00:19<00:03, 44.09it/s]
Loading 0:  46%|████▋     | 135/291 [00:20<00:05, 28.15it/s]
Loading 0:  48%|████▊     | 140/291 [00:20<00:04, 30.54it/s]
Loading 0:  51%|█████     | 148/291 [00:20<00:03, 38.53it/s]
Loading 0:  54%|█████▎    | 156/291 [00:20<00:02, 45.70it/s]
Loading 0:  56%|█████▌    | 162/291 [00:20<00:02, 47.89it/s]
Loading 0:  58%|█████▊    | 168/291 [00:20<00:02, 47.64it/s]
Loading 0:  60%|██████    | 175/291 [00:20<00:02, 50.76it/s]
Loading 0:  63%|██████▎   | 184/291 [00:20<00:01, 60.26it/s]
Loading 0:  66%|██████▌   | 191/291 [00:21<00:02, 35.51it/s]
Loading 0:  68%|██████▊   | 197/291 [00:21<00:02, 37.29it/s]
Loading 0:  70%|██████▉   | 203/291 [00:21<00:02, 38.81it/s]
Loading 0:  73%|███████▎  | 211/291 [00:21<00:01, 45.83it/s]
Loading 0:  75%|███████▌  | 219/291 [00:21<00:01, 51.42it/s]
Loading 0:  77%|███████▋  | 225/291 [00:21<00:01, 51.65it/s]
Loading 0:  79%|███████▉  | 231/291 [00:21<00:01, 51.69it/s]
Loading 0:  81%|████████▏ | 237/291 [00:22<00:01, 33.68it/s]
Loading 0:  83%|████████▎ | 242/291 [00:22<00:01, 36.43it/s]
Loading 0:  85%|████████▍ | 247/291 [00:22<00:01, 39.02it/s]
Loading 0:  88%|████████▊ | 255/291 [00:22<00:00, 46.65it/s]
Loading 0:  90%|████████▉ | 261/291 [00:22<00:00, 48.47it/s]
Loading 0:  92%|█████████▏| 267/291 [00:22<00:00, 47.93it/s]
Loading 0:  94%|█████████▍| 274/291 [00:23<00:00, 51.05it/s]
Loading 0:  97%|█████████▋| 281/291 [00:23<00:00, 53.92it/s]
Loading 0:  99%|█████████▊| 287/291 [00:29<00:01,  3.33it/s]
Loading 0: 100%|██████████| 291/291 [00:29<00:00,  4.13it/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-v4-mkmlizer: quantized model in 95.152s
jellywibble-lora-120k-pr-2827-v4-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep2 in 167.824s
jellywibble-lora-120k-pr-2827-v4-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-pr-2827-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-pr-2827-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v4
jellywibble-lora-120k-pr-2827-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v4/config.json
jellywibble-lora-120k-pr-2827-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v4/special_tokens_map.json
jellywibble-lora-120k-pr-2827-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v4/tokenizer_config.json
jellywibble-lora-120k-pr-2827-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v4/tokenizer.json
jellywibble-lora-120k-pr-2827-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v4/flywheel_model.0.safetensors
jellywibble-lora-120k-pr-2827-v4-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jellywibble-lora-120k-pr-2827-v4-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-v4-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2827-v4-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-v4-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2827-v4-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-v4-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2827-v4-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-v4-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2827-v4-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:10<00:10, 10.28s/it]
Downloading shards: 100%|██████████| 2/2 [00:20<00:00, 10.22s/it]
Downloading shards: 100%|██████████| 2/2 [00:20<00:00, 10.23s/it]
jellywibble-lora-120k-pr-2827-v4-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.77it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.92it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.66it/s]
jellywibble-lora-120k-pr-2827-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-lora-120k-pr-2827-v4-mkmlizer: Saving duration: 1.873s
jellywibble-lora-120k-pr-2827-v4-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 24.645s
jellywibble-lora-120k-pr-2827-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-lora-120k-pr-2827-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v4_reward
jellywibble-lora-120k-pr-2827-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v4_reward/config.json
jellywibble-lora-120k-pr-2827-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v4_reward/special_tokens_map.json
jellywibble-lora-120k-pr-2827-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v4_reward/tokenizer_config.json
jellywibble-lora-120k-pr-2827-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v4_reward/vocab.json
jellywibble-lora-120k-pr-2827-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v4_reward/merges.txt
jellywibble-lora-120k-pr-2827-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2827-v4_reward/tokenizer.json
Job jellywibble-lora-120k-pr-2827-v4-mkmlizer completed after 227.55s with status: succeeded
Stopping job with name jellywibble-lora-120k-pr-2827-v4-mkmlizer
Pipeline stage MKMLizer completed in 229.35s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-lora-120k-pr-2827-v4
Waiting for inference service jellywibble-lora-120k-pr-2827-v4 to be ready
Inference service jellywibble-lora-120k-pr-2827-v4 ready after 50.42552733421326s
Pipeline stage ISVCDeployer completed in 57.63s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3338465690612793s
Received healthy response to inference request in 1.5829353332519531s
Received healthy response to inference request in 1.5495185852050781s
Received healthy response to inference request in 1.5027964115142822s
Received healthy response to inference request in 1.5863428115844727s
5 requests
0 failed requests
5th percentile: 1.5121408462524415
10th percentile: 1.5214852809906005
20th percentile: 1.5401741504669189
30th percentile: 1.5562019348144531
40th percentile: 1.5695686340332031
50th percentile: 1.5829353332519531
60th percentile: 1.584298324584961
70th percentile: 1.5856613159179687
80th percentile: 1.7358435630798341
90th percentile: 2.034845066070557
95th percentile: 2.1843458175659176
99th percentile: 2.303946418762207
mean time: 1.711087942123413
Pipeline stage StressChecker completed in 9.28s
jellywibble-lora-120k-pr_2827_v4 status is now deployed due to DeploymentManager action
jellywibble-lora-120k-pr_2827_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jellywibble-lora-120k-pr_2827_v4
Running pipeline stage ISVCDeleter
Checking if service jellywibble-lora-120k-pr-2827-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.57s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-2827-v4/config.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2827-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2827-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2827-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2827-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-2827-v4_reward/config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.88s
jellywibble-lora-120k-pr_2827_v4 status is now torndown due to DeploymentManager action