dans-discountmodels-mist_2208

developer_uid: PocketDoc

submission_id: dans-discountmodels-mist_2208_v2

model_name: Dans-Instruct-7b

model_group: Dans-DiscountModels/mist

status: inactive

timestamp: 2024-12-01T08:00:09+00:00

num_battles: 17443

num_wins: 7729

celo_rating: 1220.04

family_friendly_score: 0.5742

family_friendly_standard_error: 0.00699277284058334

submission_type: basic

model_repo: Dans-DiscountModels/mistral-7b-test-merged

model_architecture: MistralForCausalLM

model_num_parameters: 7248023552.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.9075400847943214, 'latency_mean': 1.101820707321167, 'latency_p50': 1.0996711254119873, 'latency_p90': 1.2108434915542603}, {'batch_size': 4, 'throughput': 1.9689920084270882, 'latency_mean': 2.026159633398056, 'latency_p50': 2.0158298015594482, 'latency_p90': 2.250047135353088}, {'batch_size': 5, 'throughput': 2.1216842123952944, 'latency_mean': 2.352047551870346, 'latency_p50': 2.355575442314148, 'latency_p90': 2.604293775558472}, {'batch_size': 8, 'throughput': 2.3416277744938063, 'latency_mean': 3.3933206474781037, 'latency_p50': 3.37703275680542, 'latency_p90': 3.774171805381775}, {'batch_size': 10, 'throughput': 2.4058782347026537, 'latency_mean': 4.12957312464714, 'latency_p50': 4.116956472396851, 'latency_p90': 4.652850317955017}, {'batch_size': 12, 'throughput': 2.4601016230452633, 'latency_mean': 4.833888108730316, 'latency_p50': 4.815450429916382, 'latency_p90': 5.503431272506714}, {'batch_size': 15, 'throughput': 2.4621765996081537, 'latency_mean': 6.018712298870087, 'latency_p50': 6.002436876296997, 'latency_p90': 6.691913390159607}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: Dans-Instruct-7b

is_internal_developer: False

language_model: Dans-DiscountModels/mistral-7b-test-merged

model_size: 7B

ranking_group: single

throughput_3p7s: 2.39

us_pacific_date: 2024-12-01

win_ratio: 0.44310038410823827

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.02, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}

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 dans-discountmodels-mist-2208-v2-mkmlizer
Waiting for job on dans-discountmodels-mist-2208-v2-mkmlizer to finish
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
dans-discountmodels-mist-2208-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
dans-discountmodels-mist-2208-v2-mkmlizer: ║     _____            __           __                                ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║       /___/                                                         ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║                                                                     ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║  https://mk1.ai                                                     ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║                                                                     ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║  belonging to:                                                      ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║                                                                     ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║  Chai Research Corp.                                                ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
dans-discountmodels-mist-2208-v2-mkmlizer: ║                                                                     ║
dans-discountmodels-mist-2208-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
dans-discountmodels-mist-2208-v2-mkmlizer: Downloaded to shared memory in 19.512s
dans-discountmodels-mist-2208-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcgwpq96u, device:0
dans-discountmodels-mist-2208-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
dans-discountmodels-mist-2208-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.
dans-discountmodels-mist-2208-v2-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
dans-discountmodels-mist-2208-v2-mkmlizer: quantized model in 18.110s
dans-discountmodels-mist-2208-v2-mkmlizer: Processed model Dans-DiscountModels/mistral-7b-test-merged in 37.622s
dans-discountmodels-mist-2208-v2-mkmlizer: creating bucket guanaco-mkml-models
dans-discountmodels-mist-2208-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
dans-discountmodels-mist-2208-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/dans-discountmodels-mist-2208-v2
dans-discountmodels-mist-2208-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/dans-discountmodels-mist-2208-v2/config.json
dans-discountmodels-mist-2208-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/dans-discountmodels-mist-2208-v2/special_tokens_map.json
dans-discountmodels-mist-2208-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/dans-discountmodels-mist-2208-v2/tokenizer_config.json
dans-discountmodels-mist-2208-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/dans-discountmodels-mist-2208-v2/tokenizer.json
dans-discountmodels-mist-2208-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/dans-discountmodels-mist-2208-v2/flywheel_model.0.safetensors
dans-discountmodels-mist-2208-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 43.97it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 64.54it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 74.56it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:03, 82.63it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:03, 81.90it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 88.35it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 86.14it/s]
Loading 0:  27%|██▋       | 80/291 [00:00<00:02, 88.82it/s]
Loading 0:  31%|███       | 89/291 [00:01<00:02, 86.26it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:08, 21.59it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:07, 25.49it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:05, 31.27it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:04, 35.32it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 41.27it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:03, 46.61it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 49.94it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 56.49it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 57.39it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 61.28it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 63.23it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 67.35it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:04, 21.18it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:03, 24.76it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:02, 30.56it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 38.01it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 46.02it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 53.68it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 58.04it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 60.66it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 66.30it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 71.76it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 17.15it/s]
                                                            
Job dans-discountmodels-mist-2208-v2-mkmlizer completed after 63.2s with status: succeeded
Stopping job with name dans-discountmodels-mist-2208-v2-mkmlizer
Pipeline stage MKMLizer completed in 63.67s
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 dans-discountmodels-mist-2208-v2
Waiting for inference service dans-discountmodels-mist-2208-v2 to be ready
Inference service dans-discountmodels-mist-2208-v2 ready after 140.48539686203003s
Pipeline stage MKMLDeployer completed in 140.98s
run pipeline stage %s
Running pipeline stage StressChecker
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.7476706504821777s
Received healthy response to inference request in 1.1912834644317627s
Received healthy response to inference request in 1.7343111038208008s
Received healthy response to inference request in 1.1061255931854248s
Received healthy response to inference request in 1.5274195671081543s
5 requests
0 failed requests
5th percentile: 1.1231571674346923
10th percentile: 1.14018874168396
20th percentile: 1.1742518901824952
30th percentile: 1.258510684967041
40th percentile: 1.3929651260375977
50th percentile: 1.5274195671081543
60th percentile: 1.610176181793213
70th percentile: 1.6929327964782714
80th percentile: 1.7369830131530761
90th percentile: 1.742326831817627
95th percentile: 1.7449987411499024
99th percentile: 1.7471362686157226
mean time: 1.461362075805664
Pipeline stage StressChecker completed in 9.17s
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 2.18s
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
dans-discountmodels-mist_2208_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 2691.35s
Shutdown handler de-registered
dans-discountmodels-mist_2208_v2 status is now inactive due to auto deactivation removed underperforming models