stark2000s-axolotl-coupl_9843

developer_uid: stark2000s

submission_id: stark2000s-axolotl-coupl_9843_v1

model_name: stark2000s-axolotl-coupl_9843_v1

model_group: stark2000s/axolotl_Coupl

status: inactive

timestamp: 2024-12-01T06:55:08+00:00

num_battles: 16498

num_wins: 6686

celo_rating: 1196.65

family_friendly_score: 0.5734

family_friendly_standard_error: 0.006994461237293406

submission_type: basic

model_repo: stark2000s/axolotl_CoupleRP_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': 0.8771326297970815, 'latency_mean': 1.1400122451782226, 'latency_p50': 1.1434619426727295, 'latency_p90': 1.2616287469863892}, {'batch_size': 4, 'throughput': 1.9033656728434916, 'latency_mean': 2.0904364621639253, 'latency_p50': 2.0927813053131104, 'latency_p90': 2.3295702934265137}, {'batch_size': 5, 'throughput': 2.042110072938724, 'latency_mean': 2.42921848654747, 'latency_p50': 2.434988021850586, 'latency_p90': 2.7560423612594604}, {'batch_size': 8, 'throughput': 2.2968490295682464, 'latency_mean': 3.4623105251789092, 'latency_p50': 3.472258687019348, 'latency_p90': 3.8709691762924194}, {'batch_size': 10, 'throughput': 2.347335152994375, 'latency_mean': 4.2236045348644256, 'latency_p50': 4.195646166801453, 'latency_p90': 4.77425627708435}, {'batch_size': 12, 'throughput': 2.3962426302383593, 'latency_mean': 4.956626950502396, 'latency_p50': 4.964157581329346, 'latency_p90': 5.675876641273499}, {'batch_size': 15, 'throughput': 2.41692751654083, 'latency_mean': 6.124833184480667, 'latency_p50': 6.156020164489746, 'latency_p90': 6.794467282295227}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: stark2000s-axolotl-coupl_9843_v1

is_internal_developer: False

language_model: stark2000s/axolotl_CoupleRP_calm

model_size: 8B

ranking_group: single

throughput_3p7s: 2.33

us_pacific_date: 2024-11-30

win_ratio: 0.4052612437871257

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-coupl-9843-v1-mkmlizer
Waiting for job on stark2000s-axolotl-coupl-9843-v1-mkmlizer to finish
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║     _____            __           __                                ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║       /___/                                                         ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║                                                                     ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║  https://mk1.ai                                                     ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║                                                                     ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║  belonging to:                                                      ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║                                                                     ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║  Chai Research Corp.                                                ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ║                                                                     ║
stark2000s-axolotl-coupl-9843-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
stark2000s-axolotl-coupl-9843-v1-mkmlizer: Downloaded to shared memory in 35.014s
stark2000s-axolotl-coupl-9843-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzacn9_fg, device:0
stark2000s-axolotl-coupl-9843-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
stark2000s-axolotl-coupl-9843-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-coupl-9843-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
stark2000s-axolotl-coupl-9843-v1-mkmlizer: quantized model in 27.270s
stark2000s-axolotl-coupl-9843-v1-mkmlizer: Processed model stark2000s/axolotl_CoupleRP_calm in 62.284s
stark2000s-axolotl-coupl-9843-v1-mkmlizer: creating bucket guanaco-mkml-models
stark2000s-axolotl-coupl-9843-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
stark2000s-axolotl-coupl-9843-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9843-v1
stark2000s-axolotl-coupl-9843-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9843-v1/config.json
stark2000s-axolotl-coupl-9843-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9843-v1/special_tokens_map.json
stark2000s-axolotl-coupl-9843-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9843-v1/tokenizer_config.json
stark2000s-axolotl-coupl-9843-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9843-v1/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
stark2000s-axolotl-coupl-9843-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9843-v1/flywheel_model.0.safetensors
stark2000s-axolotl-coupl-9843-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 38.30it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 61.12it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 67.77it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 70.10it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 69.78it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 71.59it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 72.99it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:03, 69.71it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 71.30it/s]
Loading 0:  29%|██▉       | 84/291 [00:02<00:10, 19.15it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:09, 21.74it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 26.66it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 34.60it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 42.58it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 48.74it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:02, 55.08it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:02, 57.50it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 63.44it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 64.68it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 66.58it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 69.15it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:05, 19.62it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 25.10it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:02, 31.60it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:01, 38.57it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 45.13it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 51.27it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 56.61it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 59.83it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 64.62it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 66.45it/s]
Loading 0:  95%|█████████▌| 277/291 [00:06<00:00, 68.24it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 70.52it/s]
                                                            
Job stark2000s-axolotl-coupl-9843-v1-mkmlizer completed after 89.26s with status: succeeded
Stopping job with name stark2000s-axolotl-coupl-9843-v1-mkmlizer
Pipeline stage MKMLizer completed in 89.74s
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 stark2000s-axolotl-coupl-9843-v1
Waiting for inference service stark2000s-axolotl-coupl-9843-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service stark2000s-axolotl-coupl-9843-v1 ready after 140.579252243042s
Pipeline stage MKMLDeployer completed in 141.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4067656993865967s
Received healthy response to inference request in 1.2570819854736328s
Received healthy response to inference request in 1.6950488090515137s
Received healthy response to inference request in 1.7711451053619385s
Received healthy response to inference request in 1.21311616897583s
5 requests
0 failed requests
5th percentile: 1.2219093322753907
10th percentile: 1.2307024955749513
20th percentile: 1.2482888221740722
30th percentile: 1.344675350189209
40th percentile: 1.5198620796203615
50th percentile: 1.6950488090515137
60th percentile: 1.7254873275756837
70th percentile: 1.7559258460998535
80th percentile: 1.8982692241668702
90th percentile: 2.1525174617767333
95th percentile: 2.2796415805816648
99th percentile: 2.3813408756256105
mean time: 1.6686315536499023
Pipeline stage StressChecker completed in 9.68s
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 2.22s
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
stark2000s-axolotl-coupl_9843_v1 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service stark2000s-axolotl-coupl-9843-v1-profiler
Waiting for inference service stark2000s-axolotl-coupl-9843-v1-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 2766.09s
Shutdown handler de-registered
stark2000s-axolotl-coupl_9843_v1 status is now inactive due to auto deactivation removed underperforming models