rica40325-lora32-secend

developer_uid: rica40325

submission_id: rica40325-lora32-secend_v5

model_name: rica40325-lora32-secend_v1

model_group: rica40325/lora32_secend

status: torndown

timestamp: 2024-08-31T06:54:40+00:00

num_battles: 11679

num_wins: 5974

celo_rating: 1242.96

family_friendly_score: 0.0

submission_type: basic

model_repo: rica40325/lora32_secend

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

display_name: rica40325-lora32-secend_v1

is_internal_developer: False

language_model: rica40325/lora32_secend

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-30

win_ratio: 0.5115163969517939

generation_params: {'temperature': 1.15, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, '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

run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rica40325-lora32-secend-v5-mkmlizer
Waiting for job on rica40325-lora32-secend-v5-mkmlizer to finish
Stopping job with name rica40325-lora32-secend-v5-mkmlizer
%s, retrying in %s seconds...
Starting job with name rica40325-lora32-secend-v5-mkmlizer
Waiting for job on rica40325-lora32-secend-v5-mkmlizer to finish
rica40325-lora32-secend-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-lora32-secend-v5-mkmlizer: ║     _____            __           __                                ║
rica40325-lora32-secend-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-lora32-secend-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-lora32-secend-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-lora32-secend-v5-mkmlizer: ║       /___/                                                         ║
rica40325-lora32-secend-v5-mkmlizer: ║                                                                     ║
rica40325-lora32-secend-v5-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-lora32-secend-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-lora32-secend-v5-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-lora32-secend-v5-mkmlizer: ║                                                                     ║
rica40325-lora32-secend-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-lora32-secend-v5-mkmlizer: ║  belonging to:                                                      ║
rica40325-lora32-secend-v5-mkmlizer: ║                                                                     ║
rica40325-lora32-secend-v5-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-lora32-secend-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-lora32-secend-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-lora32-secend-v5-mkmlizer: ║                                                                     ║
rica40325-lora32-secend-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-lora32-secend-v5-mkmlizer: Downloaded to shared memory in 22.453s
rica40325-lora32-secend-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_fmnjjx7, device:0
rica40325-lora32-secend-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-lora32-secend-v5-mkmlizer: quantized model in 25.556s
rica40325-lora32-secend-v5-mkmlizer: Processed model rica40325/lora32_secend in 48.010s
rica40325-lora32-secend-v5-mkmlizer: creating bucket guanaco-mkml-models
rica40325-lora32-secend-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-lora32-secend-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-lora32-secend-v5
rica40325-lora32-secend-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-lora32-secend-v5/config.json
rica40325-lora32-secend-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-lora32-secend-v5/tokenizer_config.json
rica40325-lora32-secend-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-lora32-secend-v5/special_tokens_map.json
rica40325-lora32-secend-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-lora32-secend-v5/tokenizer.json
rica40325-lora32-secend-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-lora32-secend-v5/flywheel_model.0.safetensors
rica40325-lora32-secend-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 39.88it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 69.80it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 72.95it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 78.03it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:02, 88.10it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 86.54it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 92.83it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 26.08it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 30.84it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:04, 39.53it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 51.89it/s]
Loading 0:  45%|████▌     | 131/291 [00:02<00:02, 59.41it/s]
Loading 0:  48%|████▊     | 140/291 [00:02<00:02, 63.02it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 66.10it/s]
Loading 0:  55%|█████▍    | 160/291 [00:02<00:01, 70.97it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 80.16it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 26.37it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 35.80it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 42.87it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 53.31it/s]
Loading 0:  83%|████████▎ | 241/291 [00:04<00:00, 58.38it/s]
Loading 0:  88%|████████▊ | 256/291 [00:04<00:00, 66.78it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 70.48it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 70.48it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 73.35it/s]
                                                            
Job rica40325-lora32-secend-v5-mkmlizer completed after 64.17s with status: succeeded
Stopping job with name rica40325-lora32-secend-v5-mkmlizer
Pipeline stage MKMLizer completed in 66.07s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-lora32-secend-v5
Waiting for inference service rica40325-lora32-secend-v5 to be ready
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
Inference service rica40325-lora32-secend-v5 ready after 191.84081363677979s
Pipeline stage MKMLDeployer completed in 192.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.218792676925659s
Received healthy response to inference request in 1.9166102409362793s
Received healthy response to inference request in 1.722402811050415s
Received healthy response to inference request in 1.2678217887878418s
Received healthy response to inference request in 1.4692485332489014s
5 requests
0 failed requests
5th percentile: 1.3081071376800537
10th percentile: 1.3483924865722656
20th percentile: 1.4289631843566895
30th percentile: 1.5198793888092041
40th percentile: 1.6211410999298095
50th percentile: 1.722402811050415
60th percentile: 1.8000857830047607
70th percentile: 1.8777687549591064
80th percentile: 1.9770467281341553
90th percentile: 2.0979197025299072
95th percentile: 2.158356189727783
99th percentile: 2.206705379486084
mean time: 1.7189752101898192
Pipeline stage StressChecker completed in 9.75s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.41s
rica40325-lora32-secend_v5 status is now deployed due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-lora32-secend-v5-profiler
Waiting for inference service rica40325-lora32-secend-v5-profiler to be ready
Inference service rica40325-lora32-secend-v5-profiler ready after 190.5988438129425s
Pipeline stage MKMLProfilerDeployer completed in 190.99s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.38s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-lora32-secend-v5-profiler is running
Tearing down inference service rica40325-lora32-secend-v5-profiler
Service rica40325-lora32-secend-v5-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.88s
rica40325-lora32-secend_v5 status is now inactive due to auto deactivation removed underperforming models
rica40325-lora32-secend_v5 status is now torndown due to DeploymentManager action