developer_uid: chace9580
submission_id: jic062-dpo-v1-3_v1
model_name: jic062-dpo-v1-3_v1
model_group: jic062/dpo-v1.3
status: torndown
timestamp: 2024-08-30T00:24:26+00:00
num_battles: 12940
num_wins: 6926
celo_rating: 1261.99
family_friendly_score: 0.0
submission_type: basic
model_repo: jic062/dpo-v1.3
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: jic062-dpo-v1-3_v1
is_internal_developer: False
language_model: jic062/dpo-v1.3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-29
win_ratio: 0.5352395672333848
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', '|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}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-dpo-v1-3-v1-mkmlizer
Waiting for job on jic062-dpo-v1-3-v1-mkmlizer to finish
Stopping job with name jic062-dpo-v1-3-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name jic062-dpo-v1-3-v1-mkmlizer
Waiting for job on jic062-dpo-v1-3-v1-mkmlizer to finish
jic062-dpo-v1-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-dpo-v1-3-v1-mkmlizer: ║ _____ __ __ ║
jic062-dpo-v1-3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-dpo-v1-3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-dpo-v1-3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-dpo-v1-3-v1-mkmlizer: ║ /___/ ║
jic062-dpo-v1-3-v1-mkmlizer: ║ ║
jic062-dpo-v1-3-v1-mkmlizer: ║ Version: 0.10.1 ║
jic062-dpo-v1-3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-dpo-v1-3-v1-mkmlizer: ║ https://mk1.ai ║
jic062-dpo-v1-3-v1-mkmlizer: ║ ║
jic062-dpo-v1-3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-dpo-v1-3-v1-mkmlizer: ║ belonging to: ║
jic062-dpo-v1-3-v1-mkmlizer: ║ ║
jic062-dpo-v1-3-v1-mkmlizer: ║ Chai Research Corp. ║
jic062-dpo-v1-3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-dpo-v1-3-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-dpo-v1-3-v1-mkmlizer: ║ ║
jic062-dpo-v1-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-dpo-v1-3-v1-mkmlizer: quantized model in 26.303s
jic062-dpo-v1-3-v1-mkmlizer: Processed model jic062/dpo-v1.3 in 66.809s
jic062-dpo-v1-3-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-dpo-v1-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-dpo-v1-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-dpo-v1-3-v1
jic062-dpo-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-dpo-v1-3-v1/config.json
jic062-dpo-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-dpo-v1-3-v1/special_tokens_map.json
jic062-dpo-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-dpo-v1-3-v1/tokenizer_config.json
jic062-dpo-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-dpo-v1-3-v1/tokenizer.json
jic062-dpo-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-dpo-v1-3-v1/flywheel_model.0.safetensors
jic062-dpo-v1-3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 36.92it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:05, 55.00it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:05, 46.51it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:05, 46.23it/s] Loading 0: 11%|█ | 31/291 [00:00<00:05, 51.80it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 47.07it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 47.20it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:04, 51.88it/s] Loading 0: 19%|█▉ | 55/291 [00:01<00:04, 48.64it/s] Loading 0: 21%|██ | 60/291 [00:01<00:04, 47.59it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 51.45it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 47.41it/s] Loading 0: 27%|██▋ | 78/291 [00:01<00:04, 45.98it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:05, 35.42it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:05, 34.87it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:04, 41.82it/s] Loading 0: 34%|███▍ | 99/291 [00:02<00:04, 43.76it/s] Loading 0: 36%|███▌ | 104/291 [00:02<00:04, 38.20it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 46.50it/s] Loading 0: 40%|████ | 117/291 [00:02<00:03, 47.18it/s] Loading 0: 42%|████▏ | 122/291 [00:02<00:04, 39.62it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 47.49it/s] Loading 0: 47%|████▋ | 136/291 [00:03<00:03, 43.09it/s] Loading 0: 48%|████▊ | 141/291 [00:03<00:03, 43.07it/s] Loading 0: 51%|█████ | 147/291 [00:03<00:03, 46.95it/s] Loading 0: 52%|█████▏ | 152/291 [00:03<00:02, 46.96it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 47.21it/s] Loading 0: 56%|█████▌ | 163/291 [00:03<00:02, 44.66it/s] Loading 0: 58%|█████▊ | 168/291 [00:03<00:02, 44.09it/s] Loading 0: 59%|█████▉ | 173/291 [00:03<00:02, 45.49it/s] Loading 0: 62%|██████▏ | 179/291 [00:03<00:02, 47.79it/s] Loading 0: 63%|██████▎ | 184/291 [00:04<00:02, 47.75it/s] Loading 0: 65%|██████▍ | 189/291 [00:04<00:03, 30.03it/s] Loading 0: 67%|██████▋ | 194/291 [00:04<00:02, 32.71it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 41.79it/s] Loading 0: 71%|███████▏ | 208/291 [00:04<00:02, 40.45it/s] Loading 0: 73%|███████▎ | 213/291 [00:04<00:01, 40.48it/s] Loading 0: 76%|███████▌ | 220/291 [00:05<00:01, 46.17it/s] Loading 0: 78%|███████▊ | 226/291 [00:05<00:01, 43.87it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 43.23it/s] Loading 0: 81%|████████▏ | 237/291 [00:05<00:01, 46.81it/s] Loading 0: 83%|████████▎ | 242/291 [00:05<00:01, 46.92it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 47.49it/s] Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 43.79it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 42.85it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 48.68it/s] Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 45.51it/s] Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 43.75it/s] Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 40.39it/s] Loading 0: 99%|█████████▊| 287/291 [00:11<00:01, 3.21it/s]
Job jic062-dpo-v1-3-v1-mkmlizer completed after 94.62s with status: succeeded
Stopping job with name jic062-dpo-v1-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 97.25s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jic062-dpo-v1-3-v1
Waiting for inference service jic062-dpo-v1-3-v1 to be ready
Inference service jic062-dpo-v1-3-v1 ready after 181.41999006271362s
Pipeline stage ISVCDeployer completed in 181.97s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4640908241271973s
Received healthy response to inference request in 1.6203067302703857s
Received healthy response to inference request in 2.081829786300659s
Received healthy response to inference request in 2.0684926509857178s
Received healthy response to inference request in 2.1257412433624268s
5 requests
0 failed requests
5th percentile: 1.709943914413452
10th percentile: 1.7995810985565186
20th percentile: 1.9788554668426515
30th percentile: 2.071160078048706
40th percentile: 2.0764949321746826
50th percentile: 2.081829786300659
60th percentile: 2.099394369125366
70th percentile: 2.1169589519500733
80th percentile: 2.193411159515381
90th percentile: 2.328750991821289
95th percentile: 2.396420907974243
99th percentile: 2.4505568408966063
mean time: 2.0720922470092775
Pipeline stage StressChecker completed in 11.10s
jic062-dpo-v1-3_v1 status is now deployed due to DeploymentManager action
jic062-dpo-v1-3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jic062-dpo-v1-3_v1
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
%s, retrying in %s seconds...
%s, retrying in %s seconds...
clean up pipeline due to error=%s
Shutdown handler de-registered
jic062-dpo-v1-3_v1 status is now torndown due to DeploymentManager action