stark2000s-axolotl-augem_8464

developer_uid: stark2000s

submission_id: stark2000s-axolotl-augem_8464_v1

model_name: stark2000s-axolotl-augem_8464_v1

model_group: stark2000s/axolotl_Augem

status: inactive

timestamp: 2024-12-01T15:03:06+00:00

num_battles: 24566

num_wins: 10117

celo_rating: 1198.74

family_friendly_score: 0.5676

family_friendly_standard_error: 0.007006143589736082

submission_type: basic

model_repo: stark2000s/axolotl_Augemental_calm

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8759473911882525, 'latency_mean': 1.141555242538452, 'latency_p50': 1.1484769582748413, 'latency_p90': 1.2591560840606688}, {'batch_size': 4, 'throughput': 1.9072534320820667, 'latency_mean': 2.08766095995903, 'latency_p50': 2.1056262254714966, 'latency_p90': 2.3237064361572264}, {'batch_size': 5, 'throughput': 2.0667486700063935, 'latency_mean': 2.403608844280243, 'latency_p50': 2.389410376548767, 'latency_p90': 2.674973392486572}, {'batch_size': 8, 'throughput': 2.287458873751885, 'latency_mean': 3.4723264825344087, 'latency_p50': 3.487920641899109, 'latency_p90': 3.923646664619446}, {'batch_size': 10, 'throughput': 2.3650843399334627, 'latency_mean': 4.195315600633621, 'latency_p50': 4.201468110084534, 'latency_p90': 4.7741965532302855}, {'batch_size': 12, 'throughput': 2.3847499256802545, 'latency_mean': 4.982240078449249, 'latency_p50': 5.003223538398743, 'latency_p90': 5.665460610389709}, {'batch_size': 15, 'throughput': 2.416394503521507, 'latency_mean': 6.127726961374282, 'latency_p50': 6.111538290977478, 'latency_p90': 6.925012302398682}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: stark2000s-axolotl-augem_8464_v1

is_internal_developer: False

language_model: stark2000s/axolotl_Augemental_calm

model_size: 8B

ranking_group: single

throughput_3p7s: 2.33

us_pacific_date: 2024-12-01

win_ratio: 0.41182935764878287

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 stark2000s-axolotl-augem-8464-v1-mkmlizer
Waiting for job on stark2000s-axolotl-augem-8464-v1-mkmlizer to finish
stark2000s-axolotl-augem-8464-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║     _____            __           __                                ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║       /___/                                                         ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║                                                                     ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║  https://mk1.ai                                                     ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║                                                                     ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║  belonging to:                                                      ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║                                                                     ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║  Chai Research Corp.                                                ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ║                                                                     ║
stark2000s-axolotl-augem-8464-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
stark2000s-axolotl-augem-8464-v1-mkmlizer: Downloaded to shared memory in 36.807s
stark2000s-axolotl-augem-8464-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbbwkk8uj, device:0
stark2000s-axolotl-augem-8464-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
stark2000s-axolotl-augem-8464-v1-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.
stark2000s-axolotl-augem-8464-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
stark2000s-axolotl-augem-8464-v1-mkmlizer: quantized model in 26.715s
stark2000s-axolotl-augem-8464-v1-mkmlizer: Processed model stark2000s/axolotl_Augemental_calm in 63.522s
stark2000s-axolotl-augem-8464-v1-mkmlizer: creating bucket guanaco-mkml-models
stark2000s-axolotl-augem-8464-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
stark2000s-axolotl-augem-8464-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/stark2000s-axolotl-augem-8464-v1
stark2000s-axolotl-augem-8464-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/stark2000s-axolotl-augem-8464-v1/config.json
stark2000s-axolotl-augem-8464-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/stark2000s-axolotl-augem-8464-v1/special_tokens_map.json
stark2000s-axolotl-augem-8464-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/stark2000s-axolotl-augem-8464-v1/tokenizer_config.json
stark2000s-axolotl-augem-8464-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/stark2000s-axolotl-augem-8464-v1/tokenizer.json
stark2000s-axolotl-augem-8464-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/stark2000s-axolotl-augem-8464-v1/flywheel_model.0.safetensors
stark2000s-axolotl-augem-8464-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 48.27it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 66.60it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 74.71it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:03, 83.47it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:02, 89.01it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 86.49it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 82.95it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 73.26it/s]
Loading 0:  29%|██▉       | 84/291 [00:02<00:10, 19.91it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:08, 22.70it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:06, 27.85it/s]
Loading 0:  37%|███▋      | 107/291 [00:02<00:04, 37.53it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 44.20it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 51.28it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:02, 58.37it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 64.19it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 69.66it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:01, 69.89it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 74.02it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 75.00it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:05, 20.37it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 25.87it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 32.64it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 40.24it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 47.41it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 52.22it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 59.42it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 66.05it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 71.71it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 76.12it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 77.54it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 80.49it/s]
                                                            
Job stark2000s-axolotl-augem-8464-v1-mkmlizer completed after 84.05s with status: succeeded
Stopping job with name stark2000s-axolotl-augem-8464-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.55s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service stark2000s-axolotl-augem-8464-v1
Waiting for inference service stark2000s-axolotl-augem-8464-v1 to be ready
Inference service stark2000s-axolotl-augem-8464-v1 ready after 150.53829526901245s
Pipeline stage MKMLDeployer completed in 151.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 6.803676128387451s
Received healthy response to inference request in 2.0085582733154297s
Received healthy response to inference request in 2.060377359390259s
Received healthy response to inference request in 3.385712146759033s
Received healthy response to inference request in 1.4137558937072754s
5 requests
0 failed requests
5th percentile: 1.5327163696289063
10th percentile: 1.651676845550537
20th percentile: 1.8895977973937987
30th percentile: 2.0189220905303955
40th percentile: 2.039649724960327
50th percentile: 2.060377359390259
60th percentile: 2.5905112743377683
70th percentile: 3.1206451892852782
80th percentile: 4.069304943084718
90th percentile: 5.436490535736084
95th percentile: 6.120083332061767
99th percentile: 6.666957569122315
mean time: 3.1344159603118897
Pipeline stage StressChecker completed in 17.23s
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 2.24s
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 2.08s
Shutdown handler de-registered
stark2000s-axolotl-augem_8464_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 2752.13s
Shutdown handler de-registered
stark2000s-axolotl-augem_8464_v1 status is now inactive due to auto deactivation removed underperforming models