developer_uid: ZZYABC
submission_id: zzyabc-unsloth-llama_v1
model_name: zzyabc-llama-3-qlora_v1
model_group: ZZYABC/unsloth-llama
status: torndown
timestamp: 2024-12-24T11:58:26+00:00
num_battles: 21272
num_wins: 8774
celo_rating: 1201.38
family_friendly_score: 0.5953999999999999
family_friendly_standard_error: 0.006941164743758788
submission_type: basic
model_repo: ZZYABC/unsloth-llama
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.8845531119063065, 'latency_mean': 1.1304545187950135, 'latency_p50': 1.1199396848678589, 'latency_p90': 1.2591072559356689}, {'batch_size': 4, 'throughput': 1.8946072713537554, 'latency_mean': 2.1010054612159728, 'latency_p50': 2.0982013940811157, 'latency_p90': 2.3735704898834227}, {'batch_size': 5, 'throughput': 2.038565834846847, 'latency_mean': 2.4350787317752838, 'latency_p50': 2.452849864959717, 'latency_p90': 2.7103670120239256}, {'batch_size': 8, 'throughput': 2.249402354078863, 'latency_mean': 3.5280766689777376, 'latency_p50': 3.551642894744873, 'latency_p90': 3.975394606590271}, {'batch_size': 10, 'throughput': 2.3344125006532015, 'latency_mean': 4.240629979372025, 'latency_p50': 4.241125822067261, 'latency_p90': 4.7834426164627075}, {'batch_size': 12, 'throughput': 2.3545981917777614, 'latency_mean': 5.047614775896072, 'latency_p50': 5.041549444198608, 'latency_p90': 5.796068096160888}, {'batch_size': 15, 'throughput': 2.3974893715078465, 'latency_mean': 6.185138702392578, 'latency_p50': 6.166069269180298, 'latency_p90': 6.864642930030822}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: zzyabc-llama-3-qlora_v1
is_internal_developer: False
language_model: ZZYABC/unsloth-llama
model_size: 8B
ranking_group: single
throughput_3p7s: 2.29
us_pacific_date: 2024-12-24
win_ratio: 0.4124670928920647
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 zzyabc-unsloth-llama-v1-mkmlizer
Waiting for job on zzyabc-unsloth-llama-v1-mkmlizer to finish
zzyabc-unsloth-llama-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zzyabc-unsloth-llama-v1-mkmlizer: ║ _____ __ __ ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ /___/ ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ Version: 0.11.12 ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ https://mk1.ai ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ The license key for the current software has been verified as ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ belonging to: ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ Chai Research Corp. ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
zzyabc-unsloth-llama-v1-mkmlizer: ║ ║
zzyabc-unsloth-llama-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zzyabc-unsloth-llama-v1-mkmlizer: quantized model in 26.546s
zzyabc-unsloth-llama-v1-mkmlizer: Processed model ZZYABC/unsloth-llama in 62.092s
zzyabc-unsloth-llama-v1-mkmlizer: creating bucket guanaco-mkml-models
zzyabc-unsloth-llama-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zzyabc-unsloth-llama-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zzyabc-unsloth-llama-v1
zzyabc-unsloth-llama-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zzyabc-unsloth-llama-v1/config.json
zzyabc-unsloth-llama-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zzyabc-unsloth-llama-v1/special_tokens_map.json
zzyabc-unsloth-llama-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zzyabc-unsloth-llama-v1/tokenizer_config.json
zzyabc-unsloth-llama-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zzyabc-unsloth-llama-v1/tokenizer.json
zzyabc-unsloth-llama-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zzyabc-unsloth-llama-v1/flywheel_model.0.safetensors
zzyabc-unsloth-llama-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:09, 31.66it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:05, 54.32it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:05, 46.02it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:06, 43.97it/s] Loading 0: 11%|█ | 31/291 [00:00<00:05, 50.47it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 46.95it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 46.21it/s] Loading 0: 17%|█▋ | 49/291 [00:01<00:04, 51.57it/s] Loading 0: 19%|█▉ | 55/291 [00:01<00:05, 47.04it/s] Loading 0: 21%|██ | 60/291 [00:01<00:05, 45.45it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 50.22it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 45.77it/s] Loading 0: 27%|██▋ | 78/291 [00:01<00:04, 44.26it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:06, 32.70it/s] Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 32.39it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:04, 39.71it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 39.78it/s] Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 40.04it/s] Loading 0: 38%|███▊ | 111/291 [00:02<00:04, 44.76it/s] Loading 0: 40%|███▉ | 116/291 [00:02<00:03, 43.95it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 45.36it/s] Loading 0: 44%|████▎ | 127/291 [00:02<00:03, 43.77it/s] Loading 0: 45%|████▌ | 132/291 [00:03<00:03, 42.93it/s] Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 48.84it/s] Loading 0: 50%|████▉ | 145/291 [00:03<00:03, 45.86it/s] Loading 0: 52%|█████▏ | 150/291 [00:03<00:03, 45.67it/s] Loading 0: 54%|█████▎ | 156/291 [00:03<00:02, 49.01it/s] Loading 0: 56%|█████▌ | 162/291 [00:03<00:02, 49.55it/s] Loading 0: 58%|█████▊ | 168/291 [00:03<00:02, 44.06it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:02, 49.74it/s] Loading 0: 62%|██████▏ | 181/291 [00:04<00:02, 41.25it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:02, 35.32it/s] Loading 0: 66%|██████▌ | 192/291 [00:04<00:02, 36.25it/s] Loading 0: 68%|██████▊ | 197/291 [00:04<00:02, 38.83it/s] Loading 0: 70%|██████▉ | 203/291 [00:04<00:02, 38.29it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 47.09it/s] Loading 0: 75%|███████▍ | 217/291 [00:04<00:01, 45.68it/s] Loading 0: 76%|███████▋ | 222/291 [00:05<00:01, 43.33it/s] Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 48.45it/s] Loading 0: 81%|████████ | 235/291 [00:05<00:01, 47.06it/s] Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 44.78it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 50.21it/s] Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 48.49it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 47.76it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 51.36it/s] Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 47.81it/s] Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 47.21it/s] Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 40.93it/s] Loading 0: 99%|█████████▊| 287/291 [00:11<00:01, 3.25it/s]
Job zzyabc-unsloth-llama-v1-mkmlizer completed after 83.7s with status: succeeded
Stopping job with name zzyabc-unsloth-llama-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.17s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zzyabc-unsloth-llama-v1
Waiting for inference service zzyabc-unsloth-llama-v1 to be ready
Inference service zzyabc-unsloth-llama-v1 ready after 271.0713357925415s
Pipeline stage MKMLDeployer completed in 271.64s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6809046268463135s
Received healthy response to inference request in 1.5130653381347656s
Received healthy response to inference request in 1.7191874980926514s
Received healthy response to inference request in 1.3160524368286133s
Received healthy response to inference request in 1.4057528972625732s
5 requests
0 failed requests
5th percentile: 1.3339925289154053
10th percentile: 1.3519326210021974
20th percentile: 1.3878128051757812
30th percentile: 1.4272153854370118
40th percentile: 1.4701403617858886
50th percentile: 1.5130653381347656
60th percentile: 1.5802010536193847
70th percentile: 1.647336769104004
80th percentile: 1.688561201095581
90th percentile: 1.7038743495941162
95th percentile: 1.7115309238433838
99th percentile: 1.717656183242798
mean time: 1.5269925594329834
Pipeline stage StressChecker completed in 9.09s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.68s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.73s
Shutdown handler de-registered
zzyabc-unsloth-llama_v1 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 2226.36s
Shutdown handler de-registered
zzyabc-unsloth-llama_v1 status is now inactive due to auto deactivation removed underperforming models
zzyabc-unsloth-llama_v1 status is now torndown due to DeploymentManager action
admin requested tearing down of function_miset_2024-12-27
zzyabc-unsloth-llama_v1 status is now torndown due to DeploymentManager action
zzyabc-unsloth-llama_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1