stark2000s-axolotl-test-calm

developer_uid: stark2000s

submission_id: stark2000s-axolotl-test-calm_v2

model_name: stark2000s-axolotl-test-calm_v2

model_group: stark2000s/axolotl_test_

status: inactive

timestamp: 2024-11-28T11:57:47+00:00

num_battles: 13553

num_wins: 5795

celo_rating: 1210.65

family_friendly_score: 0.5628

family_friendly_standard_error: 0.007015071774401171

submission_type: basic

model_repo: stark2000s/axolotl_test_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': 0.8775362874314634, 'latency_mean': 1.139493774175644, 'latency_p50': 1.1383543014526367, 'latency_p90': 1.2638429403305054}, {'batch_size': 4, 'throughput': 1.87529415734472, 'latency_mean': 2.1306417417526244, 'latency_p50': 2.1239354610443115, 'latency_p90': 2.3599506855010985}, {'batch_size': 5, 'throughput': 2.016665037961461, 'latency_mean': 2.463651990890503, 'latency_p50': 2.459979295730591, 'latency_p90': 2.7716994285583496}, {'batch_size': 8, 'throughput': 2.240707724266099, 'latency_mean': 3.5533604550361635, 'latency_p50': 3.571248412132263, 'latency_p90': 3.967246437072754}, {'batch_size': 10, 'throughput': 2.2935508837063416, 'latency_mean': 4.3161403858661656, 'latency_p50': 4.272950172424316, 'latency_p90': 4.889213037490845}, {'batch_size': 12, 'throughput': 2.315092651845361, 'latency_mean': 5.135887514352799, 'latency_p50': 5.149224042892456, 'latency_p90': 5.776059055328369}, {'batch_size': 15, 'throughput': 2.358703447993985, 'latency_mean': 6.2788252758979795, 'latency_p50': 6.284453868865967, 'latency_p90': 7.094165849685669}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: stark2000s-axolotl-test-calm_v2

is_internal_developer: False

language_model: stark2000s/axolotl_test_calm

model_size: 8B

ranking_group: single

throughput_3p7s: 2.27

us_pacific_date: 2024-11-28

win_ratio: 0.4275806094591603

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-test-calm-v2-mkmlizer
Waiting for job on stark2000s-axolotl-test-calm-v2-mkmlizer to finish
stark2000s-axolotl-test-calm-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
stark2000s-axolotl-test-calm-v2-mkmlizer: ║     _____            __           __                                ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║       /___/                                                         ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║                                                                     ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║  https://mk1.ai                                                     ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║                                                                     ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║  belonging to:                                                      ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║                                                                     ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║  Chai Research Corp.                                                ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ║                                                                     ║
stark2000s-axolotl-test-calm-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
stark2000s-axolotl-test-calm-v2-mkmlizer: Downloaded to shared memory in 34.219s
stark2000s-axolotl-test-calm-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp13sva5qf, device:0
stark2000s-axolotl-test-calm-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
stark2000s-axolotl-test-calm-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-test-calm-v2-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
stark2000s-axolotl-test-calm-v2-mkmlizer: quantized model in 27.136s
stark2000s-axolotl-test-calm-v2-mkmlizer: Processed model stark2000s/axolotl_test_calm in 61.355s
stark2000s-axolotl-test-calm-v2-mkmlizer: creating bucket guanaco-mkml-models
stark2000s-axolotl-test-calm-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
stark2000s-axolotl-test-calm-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/stark2000s-axolotl-test-calm-v2
stark2000s-axolotl-test-calm-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/stark2000s-axolotl-test-calm-v2/tokenizer.json
stark2000s-axolotl-test-calm-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/stark2000s-axolotl-test-calm-v2/flywheel_model.0.safetensors
stark2000s-axolotl-test-calm-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 46.23it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 63.55it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 67.62it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 73.34it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 76.94it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 79.18it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 77.76it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 79.75it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 81.24it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:10, 19.78it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 25.22it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 31.82it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 38.62it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 46.19it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 51.18it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 56.32it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 61.79it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 63.83it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 64.29it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 62.81it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:05, 19.48it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 24.99it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 31.69it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:02, 38.37it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 44.60it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 49.62it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 56.58it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 63.08it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 68.35it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 69.68it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 71.37it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 73.75it/s]
                                                            
Job stark2000s-axolotl-test-calm-v2-mkmlizer completed after 83.41s with status: succeeded
Stopping job with name stark2000s-axolotl-test-calm-v2-mkmlizer
Pipeline stage MKMLizer completed in 83.94s
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-test-calm-v2
Waiting for inference service stark2000s-axolotl-test-calm-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service stark2000s-axolotl-test-calm-v2 ready after 130.47429156303406s
Pipeline stage MKMLDeployer completed in 130.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.801558494567871s
Received healthy response to inference request in 1.3608200550079346s
Received healthy response to inference request in 1.396507740020752s
Received healthy response to inference request in 1.3132739067077637s
Received healthy response to inference request in 1.2429797649383545s
5 requests
0 failed requests
5th percentile: 1.2570385932922363
10th percentile: 1.2710974216461182
20th percentile: 1.2992150783538818
30th percentile: 1.3227831363677978
40th percentile: 1.3418015956878662
50th percentile: 1.3608200550079346
60th percentile: 1.3750951290130615
70th percentile: 1.3893702030181885
80th percentile: 1.4775178909301758
90th percentile: 1.6395381927490233
95th percentile: 1.7205483436584472
99th percentile: 1.7853564643859863
mean time: 1.4230279922485352
Pipeline stage StressChecker completed in 8.55s
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 2.30s
Shutdown handler de-registered
stark2000s-axolotl-test-calm_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 2496.12s
Shutdown handler de-registered
stark2000s-axolotl-test-calm_v2 status is now inactive due to auto deactivation removed underperforming models