alexxi19-ft-v1-nemo-base-lora

developer_uid: leosheng

submission_id: alexxi19-ft-v1-nemo-base-lora_v2

model_name: alexxi19-ft-v1-nemo-base-lora_v2

model_group: alexxi19/ft-v1-nemo-base

status: torndown

timestamp: 2025-02-05T04:01:19+00:00

num_battles: 7002

num_wins: 2814

celo_rating: 1187.29

family_friendly_score: 0.6626000000000001

family_friendly_standard_error: 0.006686721767802217

submission_type: basic

model_repo: alexxi19/ft-v1-nemo-base-lora

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

display_name: alexxi19-ft-v1-nemo-base-lora_v2

is_internal_developer: False

language_model: alexxi19/ft-v1-nemo-base-lora

model_size: 13B

ranking_group: single

us_pacific_date: 2025-02-04

win_ratio: 0.401885175664096

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': '<|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': 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 alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer to finish
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: Downloaded to shared memory in 30.208s
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1nc5m_bu, device:0
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-base-lora-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.
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: quantized model in 35.339s
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-lora in 65.548s
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-lora-v2
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-lora-v2/config.json
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-lora-v2/special_tokens_map.json
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-lora-v2/tokenizer_config.json
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-lora-v2/tokenizer.json
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-lora-v2/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 46.20it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:04, 71.74it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:03, 84.10it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:03, 83.99it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:03, 85.69it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:14, 21.56it/s]
Loading 0:  19%|█▉        | 70/363 [00:01<00:10, 27.04it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 33.85it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:06, 41.27it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:05, 48.78it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:04, 54.65it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 56.37it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 62.84it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 69.05it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:10, 20.88it/s]
Loading 0:  42%|████▏     | 151/363 [00:03<00:07, 26.93it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.13it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:03, 47.11it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 53.63it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:02, 58.89it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:02, 64.52it/s]
Loading 0:  59%|█████▊    | 213/363 [00:04<00:02, 74.51it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:06, 22.20it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:04, 27.75it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 34.47it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 43.25it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:01, 55.05it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 60.23it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 63.66it/s]
Loading 0:  81%|████████  | 293/363 [00:06<00:00, 71.37it/s]
Loading 0:  83%|████████▎ | 302/363 [00:06<00:00, 74.23it/s]
Loading 0:  86%|████████▌ | 311/363 [00:07<00:02, 22.29it/s]
Loading 0:  88%|████████▊ | 319/363 [00:07<00:01, 27.40it/s]
Loading 0:  90%|█████████ | 328/363 [00:08<00:01, 34.44it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 42.03it/s]
Loading 0:  96%|█████████▌| 347/363 [00:08<00:00, 51.58it/s]
Loading 0:  98%|█████████▊| 356/363 [00:08<00:00, 58.12it/s]
                                                            
Job alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer completed after 92.59s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-base-lora-v2-mkmlizer
Pipeline stage MKMLizer completed in 93.07s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexxi19-ft-v1-nemo-base-lora-v2
Waiting for inference service alexxi19-ft-v1-nemo-base-lora-v2 to be ready
Inference service alexxi19-ft-v1-nemo-base-lora-v2 ready after 160.61907958984375s
Pipeline stage MKMLDeployer completed in 161.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4033892154693604s
Received healthy response to inference request in 0.9705288410186768s
Received healthy response to inference request in 1.1232242584228516s
Received healthy response to inference request in 1.3564918041229248s
Received healthy response to inference request in 1.632364273071289s
5 requests
0 failed requests
5th percentile: 1.0010679244995118
10th percentile: 1.0316070079803468
20th percentile: 1.0926851749420166
30th percentile: 1.1698777675628662
40th percentile: 1.2631847858428955
50th percentile: 1.3564918041229248
60th percentile: 1.375250768661499
70th percentile: 1.3940097332000732
80th percentile: 1.4491842269897461
90th percentile: 1.5407742500305175
95th percentile: 1.5865692615509033
99th percentile: 1.623205270767212
mean time: 1.2971996784210205
Pipeline stage StressChecker completed in 7.64s
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 0.63s
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 0.66s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-base-lora_v2 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexxi19-ft-v1-nemo-base-lora-v2-profiler
Waiting for inference service alexxi19-ft-v1-nemo-base-lora-v2-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3942.45s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-base-lora_v2 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-base-lora_v2 status is now torndown due to DeploymentManager action