submission_id: jellywibble-lora-120k-pr_2827_v7
developer_uid: Jellywibble
best_of: 16
celo_rating: 1172.33
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: 36137
num_wins: 17534
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: Jellywibble/CHAI_alignment_reward_model
status: torndown
submission_type: basic
timestamp: 2024-07-06T03:35:29+00:00
us_pacific_date: 2024-07-05
win_ratio: 0.48520906550073334
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-lora-120k-pr-2827-v7-mkmlizer
Waiting for job on jellywibble-lora-120k-pr-2827-v7-mkmlizer to finish
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║     _____            __           __                                ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║       /___/                                                         ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║  Version: 0.8.14                                                    ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║  belonging to:                                                      ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2827-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-lora-120k-pr-2827-v7-mkmlizer: Downloaded to shared memory in 57.318s
jellywibble-lora-120k-pr-2827-v7-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-lora-120k-pr-2827-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-lora-120k-pr-2827-v7-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 40.73it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 58.79it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:04, 65.25it/s]
Loading 0:  10%|▉         | 28/291 [00:00<00:04, 64.38it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:07, 33.47it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:07, 35.33it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:05, 44.45it/s]
Loading 0:  19%|█▊        | 54/291 [00:01<00:04, 47.46it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:04, 48.04it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 52.60it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:03, 56.06it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:05, 36.60it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:05, 37.43it/s]
Loading 0:  31%|███▏      | 91/291 [00:02<00:04, 41.87it/s]
Loading 0:  34%|███▍      | 99/291 [00:02<00:03, 49.90it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:03, 51.62it/s]
Loading 0:  38%|███▊      | 111/291 [00:02<00:03, 50.71it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:02, 60.95it/s]
Loading 0:  44%|████▍     | 129/291 [00:02<00:02, 59.98it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:04, 37.53it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 38.34it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 44.13it/s]
Loading 0:  54%|█████▎    | 156/291 [00:03<00:02, 51.05it/s]
Loading 0:  56%|█████▌    | 162/291 [00:03<00:02, 52.47it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 51.51it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 55.27it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:02, 42.96it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:02, 42.61it/s]
Loading 0:  68%|██████▊   | 198/291 [00:04<00:02, 45.92it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:01, 47.71it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:01, 51.32it/s]
Loading 0:  76%|███████▌  | 221/291 [00:04<00:01, 55.73it/s]
Loading 0:  79%|███████▉  | 230/291 [00:04<00:00, 62.59it/s]
Loading 0:  81%|████████▏ | 237/291 [00:05<00:01, 40.65it/s]
Loading 0:  85%|████████▍ | 246/291 [00:05<00:00, 46.84it/s]
Loading 0:  88%|████████▊ | 255/291 [00:05<00:00, 51.94it/s]
Loading 0:  91%|█████████ | 264/291 [00:05<00:00, 56.24it/s]
Loading 0:  94%|█████████▍| 273/291 [00:05<00:00, 59.04it/s]
Loading 0:  96%|█████████▌| 280/291 [00:05<00:00, 61.23it/s]
Loading 0:  99%|█████████▊| 287/291 [00:11<00:00,  4.26it/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-v7-mkmlizer: quantized model in 26.751s
jellywibble-lora-120k-pr-2827-v7-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep2 in 84.070s
jellywibble-lora-120k-pr-2827-v7-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-pr-2827-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-pr-2827-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v7
jellywibble-lora-120k-pr-2827-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v7/tokenizer_config.json
jellywibble-lora-120k-pr-2827-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v7/special_tokens_map.json
jellywibble-lora-120k-pr-2827-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v7/config.json
jellywibble-lora-120k-pr-2827-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v7/tokenizer.json
jellywibble-lora-120k-pr-2827-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2827-v7/flywheel_model.0.safetensors
Job jellywibble-lora-120k-pr-2827-v7-mkmlizer completed after 124.21s with status: succeeded
Stopping job with name jellywibble-lora-120k-pr-2827-v7-mkmlizer
Pipeline stage MKMLizer completed in 125.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-lora-120k-pr-2827-v7
Waiting for inference service jellywibble-lora-120k-pr-2827-v7 to be ready
Inference service jellywibble-lora-120k-pr-2827-v7 ready after 40.18766689300537s
Pipeline stage ISVCDeployer completed in 47.54s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9533822536468506s
Received healthy response to inference request in 1.3001835346221924s
Received healthy response to inference request in 1.289438247680664s
Received healthy response to inference request in 1.2361648082733154s
Received healthy response to inference request in 1.3050014972686768s
5 requests
0 failed requests
5th percentile: 1.2468194961547852
10th percentile: 1.2574741840362549
20th percentile: 1.2787835597991943
30th percentile: 1.2915873050689697
40th percentile: 1.2958854198455811
50th percentile: 1.3001835346221924
60th percentile: 1.3021107196807862
70th percentile: 1.30403790473938
80th percentile: 1.4346776485443116
90th percentile: 1.6940299510955812
95th percentile: 1.8237061023712158
99th percentile: 1.9274470233917236
mean time: 1.4168340682983398
Pipeline stage StressChecker completed in 7.78s
jellywibble-lora-120k-pr_2827_v7 status is now deployed due to DeploymentManager action
jellywibble-lora-120k-pr_2827_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jellywibble-lora-120k-pr_2827_v7
Running pipeline stage ISVCDeleter
Checking if service jellywibble-lora-120k-pr-2827-v7 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.95s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-2827-v7/config.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2827-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2827-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2827-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2827-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-2827-v7_reward/config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2827-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.27s
jellywibble-lora-120k-pr_2827_v7 status is now torndown due to DeploymentManager action