developer_uid: ZZYABC
submission_id: zzyabc-llama-3-qlora_v2
model_name: zzyabc-llama-3-qlora_v1
model_group: ZZYABC/llama-3-qlora
status: torndown
timestamp: 2024-12-20T08:33:04+00:00
num_battles: 9906
num_wins: 4251
celo_rating: 1210.29
family_friendly_score: 0.5794
family_friendly_standard_error: 0.0069813414183808545
submission_type: basic
model_repo: ZZYABC/llama-3-qlora
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.8717243159297622, 'latency_mean': 1.1470844745635986, 'latency_p50': 1.150364875793457, 'latency_p90': 1.2710226774215698}, {'batch_size': 4, 'throughput': 1.8595115142436527, 'latency_mean': 2.143397763967514, 'latency_p50': 2.1439863443374634, 'latency_p90': 2.3767537832260133}, {'batch_size': 5, 'throughput': 2.0118292936244475, 'latency_mean': 2.4683276128768923, 'latency_p50': 2.4472079277038574, 'latency_p90': 2.8185751914978026}, {'batch_size': 8, 'throughput': 2.2470807920699634, 'latency_mean': 3.538026611804962, 'latency_p50': 3.5094053745269775, 'latency_p90': 4.00878574848175}, {'batch_size': 10, 'throughput': 2.304784485533021, 'latency_mean': 4.306514847278595, 'latency_p50': 4.294954299926758, 'latency_p90': 4.825851225852966}, {'batch_size': 12, 'throughput': 2.3427310814940765, 'latency_mean': 5.072851274013519, 'latency_p50': 5.107137560844421, 'latency_p90': 5.787620878219604}, {'batch_size': 15, 'throughput': 2.3433155792648184, 'latency_mean': 6.325119345188141, 'latency_p50': 6.306167840957642, 'latency_p90': 7.074692869186401}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: zzyabc-llama-3-qlora_v1
is_internal_developer: False
language_model: ZZYABC/llama-3-qlora
model_size: 8B
ranking_group: single
throughput_3p7s: 2.28
us_pacific_date: 2024-12-20
win_ratio: 0.42913385826771655
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-llama-3-qlora-v2-mkmlizer
Waiting for job on zzyabc-llama-3-qlora-v2-mkmlizer to finish
zzyabc-llama-3-qlora-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zzyabc-llama-3-qlora-v2-mkmlizer: ║     _____            __           __                                ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║       /___/                                                         ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║                                                                     ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║  https://mk1.ai                                                     ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║                                                                     ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║  belonging to:                                                      ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║                                                                     ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║  Chai Research Corp.                                                ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
zzyabc-llama-3-qlora-v2-mkmlizer: ║                                                                     ║
zzyabc-llama-3-qlora-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zzyabc-llama-3-qlora-v2-mkmlizer: Downloaded to shared memory in 31.424s
zzyabc-llama-3-qlora-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpywy5la04, device:0
zzyabc-llama-3-qlora-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zzyabc-llama-3-qlora-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
zzyabc-llama-3-qlora-v2-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
zzyabc-llama-3-qlora-v2-mkmlizer: quantized model in 26.605s
zzyabc-llama-3-qlora-v2-mkmlizer: Processed model ZZYABC/llama-3-qlora in 58.030s
zzyabc-llama-3-qlora-v2-mkmlizer: creating bucket guanaco-mkml-models
zzyabc-llama-3-qlora-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zzyabc-llama-3-qlora-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zzyabc-llama-3-qlora-v2
zzyabc-llama-3-qlora-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zzyabc-llama-3-qlora-v2/config.json
zzyabc-llama-3-qlora-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zzyabc-llama-3-qlora-v2/special_tokens_map.json
zzyabc-llama-3-qlora-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zzyabc-llama-3-qlora-v2/tokenizer_config.json
zzyabc-llama-3-qlora-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zzyabc-llama-3-qlora-v2/tokenizer.json
zzyabc-llama-3-qlora-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zzyabc-llama-3-qlora-v2/flywheel_model.0.safetensors
zzyabc-llama-3-qlora-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 38.45it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 64.84it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 73.82it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 79.51it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 80.20it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 75.94it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 76.32it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 75.03it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:02, 74.44it/s]
Loading 0:  29%|██▉       | 84/291 [00:02<00:10, 20.27it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:08, 23.19it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:06, 28.51it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 36.33it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 44.30it/s]
Loading 0:  43%|████▎     | 125/291 [00:02<00:03, 54.52it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:02, 58.04it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 62.00it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 68.46it/s]
Loading 0:  55%|█████▌    | 161/291 [00:03<00:01, 76.08it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 83.00it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 83.65it/s]
Loading 0:  66%|██████▋   | 193/291 [00:04<00:04, 22.72it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:03, 28.65it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 35.26it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 42.61it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 49.02it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 56.28it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 59.39it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 64.53it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 68.28it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 79.26it/s]
                                                            

Job zzyabc-llama-3-qlora-v2-mkmlizer completed after 84.16s with status: succeeded
Stopping job with name zzyabc-llama-3-qlora-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zzyabc-llama-3-qlora-v2
Waiting for inference service zzyabc-llama-3-qlora-v2 to be ready
Inference service zzyabc-llama-3-qlora-v2 ready after 260.91026616096497s
Pipeline stage MKMLDeployer completed in 261.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6148641109466553s
Received healthy response to inference request in 1.2026312351226807s
Received healthy response to inference request in 1.6799933910369873s
Received healthy response to inference request in 1.4766335487365723s
Received healthy response to inference request in 1.1952388286590576s
5 requests
0 failed requests
5th percentile: 1.1967173099517823
10th percentile: 1.198195791244507
20th percentile: 1.201152753829956
30th percentile: 1.257431697845459
40th percentile: 1.3670326232910157
50th percentile: 1.4766335487365723
60th percentile: 1.5319257736206056
70th percentile: 1.5872179985046386
80th percentile: 1.6278899669647218
90th percentile: 1.6539416790008545
95th percentile: 1.6669675350189208
99th percentile: 1.677388219833374
mean time: 1.4338722229003906
Pipeline stage StressChecker completed in 8.45s
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 2.19s
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 2.03s
Shutdown handler de-registered
zzyabc-llama-3-qlora_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zzyabc-llama-3-qlora-v2-profiler
Waiting for inference service zzyabc-llama-3-qlora-v2-profiler to be ready
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 2152.19s
Shutdown handler de-registered
zzyabc-llama-3-qlora_v2 status is now inactive due to auto deactivation removed underperforming models
zzyabc-llama-3-qlora_v2 status is now torndown due to DeploymentManager action
zzyabc-llama-3-qlora_v2 status is now torndown due to DeploymentManager action
zzyabc-llama-3-qlora_v2 status is now torndown due to DeploymentManager action