developer_uid: stark2000s
submission_id: stark2000s-axolotl-coupl_9843_v2
model_name: stark2000s-axolotl-coupl_9843_v2
model_group: stark2000s/axolotl_Coupl
status: inactive
timestamp: 2024-12-01T10:45:38+00:00
num_battles: 17290
num_wins: 6810
celo_rating: 1188.95
family_friendly_score: 0.5722
family_friendly_standard_error: 0.006996958767921961
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': 0.8822039196756232, 'latency_mean': 1.1334558320045471, 'latency_p50': 1.1321560144424438, 'latency_p90': 1.2520762920379638}, {'batch_size': 4, 'throughput': 1.9069747219086508, 'latency_mean': 2.0888045239448547, 'latency_p50': 2.080841064453125, 'latency_p90': 2.3318953990936278}, {'batch_size': 5, 'throughput': 2.055504861024471, 'latency_mean': 2.4159501779079435, 'latency_p50': 2.400526762008667, 'latency_p90': 2.6865580558776854}, {'batch_size': 8, 'throughput': 2.260885125575587, 'latency_mean': 3.506121850013733, 'latency_p50': 3.531813383102417, 'latency_p90': 3.878205108642578}, {'batch_size': 10, 'throughput': 2.352662419807385, 'latency_mean': 4.216050661802292, 'latency_p50': 4.2459352016448975, 'latency_p90': 4.7212656259536745}, {'batch_size': 12, 'throughput': 2.4116330979529046, 'latency_mean': 4.926132400035858, 'latency_p50': 4.951519966125488, 'latency_p90': 5.628708839416504}, {'batch_size': 15, 'throughput': 2.4157981772603283, 'latency_mean': 6.128604924678802, 'latency_p50': 6.1417845487594604, 'latency_p90': 6.841614365577698}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: stark2000s-axolotl-coupl_9843_v2
is_internal_developer: False
language_model: stark2000s/axolotl_CoupleRP_calm
model_size: 8B
ranking_group: single
throughput_3p7s: 2.31
us_pacific_date: 2024-12-01
win_ratio: 0.3938692886061307
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-v2-mkmlizer
Waiting for job on stark2000s-axolotl-coupl-9843-v2-mkmlizer to finish
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ _____ __ __ ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ /___/ ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ Version: 0.11.12 ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ https://mk1.ai ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ The license key for the current software has been verified as ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ belonging to: ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ Chai Research Corp. ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
stark2000s-axolotl-coupl-9843-v2-mkmlizer: ║ ║
stark2000s-axolotl-coupl-9843-v2-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
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-coupl-9843-v2-mkmlizer: Downloaded to shared memory in 35.071s
stark2000s-axolotl-coupl-9843-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv_s3_1hq, device:0
stark2000s-axolotl-coupl-9843-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
stark2000s-axolotl-coupl-9843-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.
stark2000s-axolotl-coupl-9843-v2-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
stark2000s-axolotl-coupl-9843-v2-mkmlizer: quantized model in 26.999s
stark2000s-axolotl-coupl-9843-v2-mkmlizer: Processed model stark2000s/axolotl_CoupleRP_calm in 62.070s
stark2000s-axolotl-coupl-9843-v2-mkmlizer: creating bucket guanaco-mkml-models
Connection pool is full, discarding connection: %s. Connection pool size: %s
stark2000s-axolotl-coupl-9843-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
stark2000s-axolotl-coupl-9843-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9843-v2
stark2000s-axolotl-coupl-9843-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9843-v2/config.json
stark2000s-axolotl-coupl-9843-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9843-v2/special_tokens_map.json
stark2000s-axolotl-coupl-9843-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9843-v2/tokenizer_config.json
stark2000s-axolotl-coupl-9843-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9843-v2/tokenizer.json
stark2000s-axolotl-coupl-9843-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9843-v2/flywheel_model.0.safetensors
stark2000s-axolotl-coupl-9843-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 6/291 [00:00<00:04, 58.53it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 59.09it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:03, 69.79it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 76.73it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:03, 77.25it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:03, 76.93it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 78.86it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 80.96it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 81.48it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:10, 19.31it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:07, 24.82it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:06, 31.32it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 37.91it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 44.77it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 51.49it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 58.54it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:02, 64.60it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:01, 67.84it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:01, 72.22it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 76.12it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 75.73it/s] Loading 0: 66%|██████▋ | 193/291 [00:04<00:04, 20.43it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:03, 26.54it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:02, 33.56it/s] Loading 0: 76%|███████▌ | 221/291 [00:04<00:01, 42.70it/s] Loading 0: 79%|███████▉ | 230/291 [00:05<00:01, 49.76it/s] Loading 0: 82%|████████▏ | 239/291 [00:05<00:00, 55.73it/s] Loading 0: 85%|████████▌ | 248/291 [00:05<00:00, 57.05it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 61.00it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 66.76it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 70.30it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 74.70it/s]
Job stark2000s-axolotl-coupl-9843-v2-mkmlizer completed after 83.94s with status: succeeded
Stopping job with name stark2000s-axolotl-coupl-9843-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.49s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service stark2000s-axolotl-coupl-9843-v2
Waiting for inference service stark2000s-axolotl-coupl-9843-v2 to be ready
Inference service stark2000s-axolotl-coupl-9843-v2 ready after 140.48539566993713s
Pipeline stage MKMLDeployer completed in 141.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6679444313049316s
Received healthy response to inference request in 1.3592352867126465s
Received healthy response to inference request in 1.488692045211792s
Received healthy response to inference request in 1.5275003910064697s
Received healthy response to inference request in 1.2111518383026123s
5 requests
0 failed requests
5th percentile: 1.2407685279846192
10th percentile: 1.270385217666626
20th percentile: 1.3296185970306396
30th percentile: 1.3851266384124756
40th percentile: 1.4369093418121337
50th percentile: 1.488692045211792
60th percentile: 1.504215383529663
70th percentile: 1.5197387218475342
80th percentile: 1.555589199066162
90th percentile: 1.6117668151855469
95th percentile: 1.6398556232452393
99th percentile: 1.6623266696929933
mean time: 1.4509047985076904
Pipeline stage StressChecker completed in 9.02s
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 2.23s
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 2.11s
Shutdown handler de-registered
stark2000s-axolotl-coupl_9843_v2 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 2757.43s
Shutdown handler de-registered
stark2000s-axolotl-coupl_9843_v2 status is now inactive due to auto deactivation removed underperforming models