submission_id: jic062-instruct-unsloth_v1
developer_uid: chace9580
alignment_samples: 11339
alignment_score: -0.16242604165592242
best_of: 16
celo_rating: 1236.87
display_name: jic062-instruct-unsloth_v1
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': 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}
is_internal_developer: False
language_model: jic062/instruct_unsloth
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: jic062/instruct_unsloth
model_name: jic062-instruct-unsloth_v1
model_num_parameters: 8030261248.0
model_repo: jic062/instruct_unsloth
model_size: 8B
num_battles: 11339
num_wins: 5669
propriety_score: 0.7348008385744235
propriety_total_count: 954.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-08-31T23:53:50+00:00
us_pacific_date: 2024-08-31
win_ratio: 0.4999559044007408
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-unsloth-v1-mkmlizer
Waiting for job on jic062-instruct-unsloth-v1-mkmlizer to finish
Stopping job with name jic062-instruct-unsloth-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name jic062-instruct-unsloth-v1-mkmlizer
Waiting for job on jic062-instruct-unsloth-v1-mkmlizer to finish
jic062-instruct-unsloth-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-unsloth-v1-mkmlizer: ║ _____ __ __ ║
jic062-instruct-unsloth-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-instruct-unsloth-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-instruct-unsloth-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-instruct-unsloth-v1-mkmlizer: ║ /___/ ║
jic062-instruct-unsloth-v1-mkmlizer: ║ ║
jic062-instruct-unsloth-v1-mkmlizer: ║ Version: 0.10.1 ║
jic062-instruct-unsloth-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-instruct-unsloth-v1-mkmlizer: ║ https://mk1.ai ║
jic062-instruct-unsloth-v1-mkmlizer: ║ ║
jic062-instruct-unsloth-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-instruct-unsloth-v1-mkmlizer: ║ belonging to: ║
jic062-instruct-unsloth-v1-mkmlizer: ║ ║
jic062-instruct-unsloth-v1-mkmlizer: ║ Chai Research Corp. ║
jic062-instruct-unsloth-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-instruct-unsloth-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-instruct-unsloth-v1-mkmlizer: ║ ║
jic062-instruct-unsloth-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
jic062-instruct-unsloth-v1-mkmlizer: Downloaded to shared memory in 37.947s
jic062-instruct-unsloth-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpshg164pc, device:0
jic062-instruct-unsloth-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-unsloth-v1-mkmlizer: quantized model in 26.250s
jic062-instruct-unsloth-v1-mkmlizer: Processed model jic062/instruct_unsloth in 64.196s
jic062-instruct-unsloth-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-unsloth-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-unsloth-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-unsloth-v1
jic062-instruct-unsloth-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-unsloth-v1/config.json
jic062-instruct-unsloth-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-unsloth-v1/special_tokens_map.json
jic062-instruct-unsloth-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-unsloth-v1/tokenizer_config.json
jic062-instruct-unsloth-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-unsloth-v1/tokenizer.json
jic062-instruct-unsloth-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-unsloth-v1/flywheel_model.0.safetensors
jic062-instruct-unsloth-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 35.80it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:06, 44.90it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:05, 47.07it/s] Loading 0: 11%|█ | 31/291 [00:00<00:04, 55.59it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 47.76it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:04, 50.05it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:05, 46.59it/s] Loading 0: 20%|██ | 59/291 [00:01<00:04, 47.17it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:04, 51.95it/s] Loading 0: 25%|██▍ | 72/291 [00:01<00:04, 52.79it/s] Loading 0: 27%|██▋ | 78/291 [00:01<00:04, 47.63it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:05, 36.69it/s] Loading 0: 30%|███ | 88/291 [00:01<00:05, 37.49it/s] Loading 0: 33%|███▎ | 95/291 [00:02<00:05, 38.70it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 45.88it/s] Loading 0: 37%|███▋ | 108/291 [00:02<00:04, 45.62it/s] Loading 0: 39%|███▉ | 113/291 [00:02<00:04, 39.00it/s] Loading 0: 41%|████ | 120/291 [00:02<00:03, 45.00it/s] Loading 0: 43%|████▎ | 125/291 [00:02<00:03, 44.84it/s] Loading 0: 45%|████▌ | 131/291 [00:02<00:03, 41.36it/s] Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 49.41it/s] Loading 0: 50%|████▉ | 145/291 [00:03<00:03, 47.12it/s] Loading 0: 52%|█████▏ | 150/291 [00:03<00:03, 46.38it/s] Loading 0: 54%|█████▎ | 156/291 [00:03<00:02, 49.01it/s] Loading 0: 56%|█████▌ | 162/291 [00:03<00:02, 49.94it/s] Loading 0: 58%|█████▊ | 168/291 [00:03<00:02, 44.70it/s] Loading 0: 60%|██████ | 176/291 [00:03<00:02, 52.65it/s] Loading 0: 63%|██████▎ | 182/291 [00:03<00:02, 46.05it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:02, 36.85it/s] Loading 0: 66%|██████▌ | 192/291 [00:04<00:02, 38.21it/s] Loading 0: 68%|██████▊ | 197/291 [00:04<00:02, 40.46it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 40.99it/s] Loading 0: 71%|███████▏ | 208/291 [00:04<00:02, 39.64it/s] Loading 0: 73%|███████▎ | 213/291 [00:04<00:01, 40.70it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 46.50it/s] Loading 0: 77%|███████▋ | 225/291 [00:05<00:01, 46.84it/s] Loading 0: 79%|███████▉ | 230/291 [00:05<00:01, 39.59it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 48.66it/s] Loading 0: 84%|████████▍ | 244/291 [00:05<00:01, 46.52it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 46.16it/s] Loading 0: 88%|████████▊ | 255/291 [00:05<00:00, 48.72it/s] Loading 0: 90%|████████▉ | 261/291 [00:05<00:00, 49.88it/s] Loading 0: 92%|█████████▏| 267/291 [00:05<00:00, 45.34it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 50.22it/s] Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 46.46it/s] Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 46.07it/s] Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 3.26it/s]
Job jic062-instruct-unsloth-v1-mkmlizer completed after 85.27s with status: succeeded
Stopping job with name jic062-instruct-unsloth-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.69s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jic062-instruct-unsloth-v1
Waiting for inference service jic062-instruct-unsloth-v1 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
Inference service jic062-instruct-unsloth-v1 ready after 181.59837532043457s
Pipeline stage MKMLDeployer completed in 181.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8613533973693848s
Received healthy response to inference request in 1.8610262870788574s
Received healthy response to inference request in 1.7864158153533936s
Received healthy response to inference request in 1.5634403228759766s
Received healthy response to inference request in 1.666135311126709s
5 requests
0 failed requests
5th percentile: 1.583979320526123
10th percentile: 1.6045183181762694
20th percentile: 1.6455963134765625
30th percentile: 1.6901914119720458
40th percentile: 1.7383036136627197
50th percentile: 1.7864158153533936
60th percentile: 1.816260004043579
70th percentile: 1.8461041927337647
80th percentile: 1.861091709136963
90th percentile: 1.8612225532531739
95th percentile: 1.8612879753112792
99th percentile: 1.8613403129577637
mean time: 1.7476742267608643
Pipeline stage StressChecker completed in 9.59s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.00s
jic062-instruct-unsloth_v1 status is now deployed due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service jic062-instruct-unsloth-v1-profiler
Waiting for inference service jic062-instruct-unsloth-v1-profiler to be ready
Inference service jic062-instruct-unsloth-v1-profiler ready after 190.44984459877014s
Pipeline stage MKMLProfilerDeployer completed in 190.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.40s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-instruct-unsloth-v1-profiler is running
Tearing down inference service jic062-instruct-unsloth-v1-profiler
Service jic062-instruct-unsloth-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.99s
jic062-instruct-unsloth_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics