developer_uid: Jellywibble
submission_id: jellywibble-lora-120k-p_2801_v27
model_name: jellywibble-lora-120k-p_2801_v27
model_group: Jellywibble/lora_120k_pr
status: torndown
timestamp: 2024-10-29T23:36:12+00:00
num_battles: 8411
num_wins: 4577
celo_rating: 1261.65
family_friendly_score: 0.5726
family_friendly_standard_error: 0.006996130930735931
submission_type: basic
model_repo: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: jellywibble-lora-120k-p_2801_v27
is_internal_developer: True
language_model: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment
model_size: 8B
ranking_group: single
us_pacific_date: 2024-10-29
win_ratio: 0.5441683509689692
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
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}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name jellywibble-lora-120k-p-2801-v27-mkmlizer
Waiting for job on jellywibble-lora-120k-p-2801-v27-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
jellywibble-lora-120k-p-2801-v27-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ _____ __ __ ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ /___/ ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ Version: 0.11.12 ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ https://mk1.ai ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ The license key for the current software has been verified as ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ belonging to: ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ Chai Research Corp. ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ║ ║
jellywibble-lora-120k-p-2801-v27-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
jellywibble-lora-120k-p-2801-v27-mkmlizer: Downloaded to shared memory in 77.062s
jellywibble-lora-120k-p-2801-v27-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwfz9_l86, device:0
jellywibble-lora-120k-p-2801-v27-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
jellywibble-lora-120k-p-2801-v27-mkmlizer: quantized model in 29.167s
jellywibble-lora-120k-p-2801-v27-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment in 106.229s
jellywibble-lora-120k-p-2801-v27-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-p-2801-v27-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-p-2801-v27-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v27
jellywibble-lora-120k-p-2801-v27-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v27/config.json
jellywibble-lora-120k-p-2801-v27-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v27/special_tokens_map.json
jellywibble-lora-120k-p-2801-v27-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v27/tokenizer_config.json
jellywibble-lora-120k-p-2801-v27-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v27/tokenizer.json
jellywibble-lora-120k-p-2801-v27-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v27/flywheel_model.0.safetensors
jellywibble-lora-120k-p-2801-v27-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:11, 24.60it/s] Loading 0: 3%|▎ | 10/291 [00:00<00:08, 34.86it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:10, 26.30it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:08, 31.35it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:08, 31.12it/s] Loading 0: 11%|█ | 31/291 [00:00<00:06, 37.33it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:11, 22.32it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:10, 23.64it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 30.66it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 30.81it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:07, 33.34it/s] Loading 0: 21%|██ | 61/291 [00:02<00:07, 31.62it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 34.60it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 33.42it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 33.59it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 33.85it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:09, 23.20it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 24.28it/s] Loading 0: 31%|███ | 90/291 [00:03<00:07, 28.60it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 29.42it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 33.61it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 32.77it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 35.14it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 33.20it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 33.80it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 38.41it/s] Loading 0: 44%|████▎ | 127/291 [00:04<00:04, 35.72it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 30.64it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 30.41it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 27.63it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.36it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 33.03it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 35.66it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:03, 34.19it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 37.35it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 35.73it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 37.94it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 35.59it/s] Loading 0: 63%|██████▎ | 183/291 [00:05<00:02, 38.86it/s] Loading 0: 64%|██████▍ | 187/291 [00:05<00:03, 27.01it/s] Loading 0: 66%|██████▌ | 191/291 [00:06<00:03, 27.77it/s] Loading 0: 67%|██████▋ | 195/291 [00:06<00:03, 26.18it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 31.99it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 31.17it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.25it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 31.51it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 34.16it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:02, 31.93it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:02, 31.69it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 32.34it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 24.98it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 24.58it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 32.80it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:01, 31.70it/s] Loading 0: 87%|████████▋ | 254/291 [00:08<00:01, 33.29it/s] Loading 0: 89%|████████▊ | 258/291 [00:08<00:01, 30.04it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 35.78it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 33.46it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 35.81it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 34.36it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 35.07it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.57it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.19it/s]
Job jellywibble-lora-120k-p-2801-v27-mkmlizer completed after 186.2s with status: succeeded
Stopping job with name jellywibble-lora-120k-p-2801-v27-mkmlizer
Pipeline stage MKMLizer completed in 186.78s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.24s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jellywibble-lora-120k-p-2801-v27
Waiting for inference service jellywibble-lora-120k-p-2801-v27 to be ready
Failed to get response for submission rica40325-10-14dpo_v2: ('http://rica40325-10-14dpo-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service jellywibble-lora-120k-p-2801-v27 ready after 130.5116903781891s
Pipeline stage MKMLDeployer completed in 131.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.273094892501831s
Received healthy response to inference request in 1.3583505153656006s
Received healthy response to inference request in 1.4285674095153809s
Received healthy response to inference request in 1.3436918258666992s
Received healthy response to inference request in 1.348409652709961s
5 requests
0 failed requests
5th percentile: 1.3446353912353515
10th percentile: 1.345578956604004
20th percentile: 1.3474660873413087
30th percentile: 1.3503978252410889
40th percentile: 1.3543741703033447
50th percentile: 1.3583505153656006
60th percentile: 1.3864372730255128
70th percentile: 1.4145240306854248
80th percentile: 1.5974729061126711
90th percentile: 1.935283899307251
95th percentile: 2.104189395904541
99th percentile: 2.2393137931823732
mean time: 1.5504228591918945
Pipeline stage StressChecker completed in 9.30s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.98s
Shutdown handler de-registered
jellywibble-lora-120k-p_2801_v27 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2105.22s
Shutdown handler de-registered
jellywibble-lora-120k-p_2801_v27 status is now inactive due to auto deactivation removed underperforming models
jellywibble-lora-120k-p_2801_v27 status is now torndown due to DeploymentManager action