Running pipeline stage MKMLizer
Starting job with name cgato-thespice-7b-ft-ins-1130-v2-mkmlizer
Waiting for job on cgato-thespice-7b-ft-ins-1130-v2-mkmlizer to finish
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ _____ __ __ ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ /___/ ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ Version: 0.6.11 ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ belonging to: ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ║ ║
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
.gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 16.6MB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
README.md: 0%| | 0.00/30.0 [00:00<?, ?B/s]
README.md: 100%|██████████| 30.0/30.0 [00:00<00:00, 248kB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
config.json: 0%| | 0.00/653 [00:00<?, ?B/s]
config.json: 100%|██████████| 653/653 [00:00<00:00, 8.89MB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
generation_config.json: 0%| | 0.00/137 [00:00<?, ?B/s]
generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 1.32MB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
model-00001-of-00003.safetensors: 0%| | 0.00/4.94G [00:00<?, ?B/s]
model-00001-of-00003.safetensors: 0%| | 10.5M/4.94G [00:00<01:21, 60.5MB/s]
model-00001-of-00003.safetensors: 3%|▎ | 126M/4.94G [00:00<00:08, 544MB/s]
model-00001-of-00003.safetensors: 4%|▍ | 199M/4.94G [00:00<00:07, 599MB/s]
model-00001-of-00003.safetensors: 6%|▌ | 294M/4.94G [00:00<00:06, 685MB/s]
model-00001-of-00003.safetensors: 8%|▊ | 419M/4.94G [00:00<00:05, 837MB/s]
model-00001-of-00003.safetensors: 12%|█▏ | 577M/4.94G [00:00<00:04, 1.05GB/s]
model-00001-of-00003.safetensors: 16%|█▋ | 807M/4.94G [00:00<00:02, 1.41GB/s]
model-00001-of-00003.safetensors: 22%|██▏ | 1.09G/4.94G [00:00<00:02, 1.75GB/s]
model-00001-of-00003.safetensors: 26%|██▌ | 1.27G/4.94G [00:01<00:02, 1.54GB/s]
model-00001-of-00003.safetensors: 29%|██▉ | 1.44G/4.94G [00:01<00:02, 1.45GB/s]
model-00001-of-00003.safetensors: 32%|███▏ | 1.59G/4.94G [00:01<00:02, 1.34GB/s]
model-00001-of-00003.safetensors: 37%|███▋ | 1.82G/4.94G [00:01<00:01, 1.57GB/s]
model-00001-of-00003.safetensors: 41%|████ | 2.02G/4.94G [00:01<00:01, 1.62GB/s]
model-00001-of-00003.safetensors: 47%|████▋ | 2.32G/4.94G [00:01<00:01, 1.94GB/s]
model-00001-of-00003.safetensors: 52%|█████▏ | 2.57G/4.94G [00:01<00:01, 2.08GB/s]
model-00001-of-00003.safetensors: 56%|█████▋ | 2.79G/4.94G [00:01<00:01, 1.90GB/s]
model-00001-of-00003.safetensors: 62%|██████▏ | 3.05G/4.94G [00:02<00:00, 2.07GB/s]
model-00001-of-00003.safetensors: 66%|██████▌ | 3.27G/4.94G [00:02<00:00, 2.00GB/s]
model-00001-of-00003.safetensors: 70%|███████ | 3.48G/4.94G [00:02<00:00, 1.85GB/s]
model-00001-of-00003.safetensors: 74%|███████▍ | 3.68G/4.94G [00:02<00:00, 1.62GB/s]
model-00001-of-00003.safetensors: 78%|███████▊ | 3.86G/4.94G [00:02<00:00, 1.49GB/s]
model-00001-of-00003.safetensors: 81%|████████ | 4.02G/4.94G [00:02<00:00, 1.46GB/s]
model-00001-of-00003.safetensors: 87%|████████▋ | 4.28G/4.94G [00:02<00:00, 1.74GB/s]
model-00001-of-00003.safetensors: 94%|█████████▎| 4.63G/4.94G [00:02<00:00, 2.18GB/s]
model-00001-of-00003.safetensors: 100%|█████████▉| 4.94G/4.94G [00:03<00:00, 1.64GB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
model-00003-of-00003.safetensors: 0%| | 0.00/4.54G [00:00<?, ?B/s]
model-00003-of-00003.safetensors: 0%| | 10.5M/4.54G [00:00<00:50, 89.0MB/s]
model-00003-of-00003.safetensors: 2%|▏ | 105M/4.54G [00:00<00:08, 542MB/s]
model-00003-of-00003.safetensors: 5%|▍ | 210M/4.54G [00:00<00:05, 751MB/s]
model-00003-of-00003.safetensors: 8%|▊ | 357M/4.54G [00:00<00:04, 1.00GB/s]
model-00003-of-00003.safetensors: 11%|█ | 503M/4.54G [00:00<00:03, 1.14GB/s]
model-00003-of-00003.safetensors: 17%|█▋ | 755M/4.54G [00:00<00:02, 1.58GB/s]
model-00003-of-00003.safetensors: 24%|██▍ | 1.09G/4.54G [00:00<00:01, 2.13GB/s]
model-00003-of-00003.safetensors: 29%|██▉ | 1.31G/4.54G [00:00<00:01, 2.10GB/s]
model-00003-of-00003.safetensors: 34%|███▎ | 1.53G/4.54G [00:00<00:01, 2.03GB/s]
model-00003-of-00003.safetensors: 39%|███▉ | 1.77G/4.54G [00:01<00:01, 2.09GB/s]
model-00003-of-00003.safetensors: 44%|████▍ | 2.01G/4.54G [00:01<00:01, 2.16GB/s]
model-00003-of-00003.safetensors: 49%|████▉ | 2.23G/4.54G [00:01<00:01, 1.90GB/s]
model-00003-of-00003.safetensors: 55%|█████▍ | 2.47G/4.54G [00:01<00:01, 2.03GB/s]
model-00003-of-00003.safetensors: 59%|█████▉ | 2.68G/4.54G [00:01<00:00, 1.98GB/s]
model-00003-of-00003.safetensors: 65%|██████▌ | 2.96G/4.54G [00:01<00:00, 2.16GB/s]
model-00003-of-00003.safetensors: 70%|███████ | 3.19G/4.54G [00:01<00:00, 2.17GB/s]
model-00003-of-00003.safetensors: 75%|███████▌ | 3.41G/4.54G [00:01<00:00, 1.82GB/s]
model-00003-of-00003.safetensors: 79%|███████▉ | 3.61G/4.54G [00:02<00:00, 1.83GB/s]
model-00003-of-00003.safetensors: 85%|████████▍ | 3.84G/4.54G [00:02<00:00, 1.95GB/s]
model-00003-of-00003.safetensors: 94%|█████████▎| 4.25G/4.54G [00:02<00:00, 2.52GB/s]
model-00003-of-00003.safetensors: 100%|█████████▉| 4.54G/4.54G [00:02<00:00, 1.04GB/s]
model-00003-of-00003.safetensors: 100%|█████████▉| 4.54G/4.54G [00:02<00:00, 1.55GB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
model.safetensors.index.json: 0%| | 0.00/23.9k [00:00<?, ?B/s]
model.safetensors.index.json: 100%|██████████| 23.9k/23.9k [00:00<00:00, 150MB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
special_tokens_map.json: 0%| | 0.00/437 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 437/437 [00:00<00:00, 6.17MB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 61.2MB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
tokenizer_config.json: 0%| | 0.00/982 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 982/982 [00:00<00:00, 8.24MB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: Downloaded to shared memory in 10.089s
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: Saving mkml model at /dev/shm/model_cache
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: Reading /tmp/tmplxt8u_ax/model.safetensors.index.json
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
Profiling: 0%| | 0/291 [00:00<?, ?it/s]
Profiling: 0%| | 1/291 [00:01<06:25, 1.33s/it]
Profiling: 6%|▌ | 17/291 [00:01<00:16, 16.19it/s]
Profiling: 12%|█▏ | 36/291 [00:01<00:06, 37.23it/s]
Profiling: 19%|█▊ | 54/291 [00:01<00:04, 58.32it/s]
Profiling: 25%|██▌ | 73/291 [00:01<00:02, 79.58it/s]
Profiling: 32%|███▏ | 92/291 [00:01<00:02, 99.05it/s]
Profiling: 37%|███▋ | 109/291 [00:02<00:02, 73.28it/s]
Profiling: 44%|████▍ | 129/291 [00:02<00:01, 93.30it/s]
Profiling: 51%|█████ | 148/291 [00:02<00:01, 110.72it/s]
Profiling: 57%|█████▋ | 167/291 [00:02<00:00, 126.69it/s]
Profiling: 65%|██████▍ | 189/291 [00:02<00:00, 147.30it/s]
Profiling: 71%|███████▏ | 208/291 [00:04<00:02, 33.10it/s]
Profiling: 79%|███████▊ | 229/291 [00:04<00:01, 45.05it/s]
Profiling: 85%|████████▌ | 248/291 [00:04<00:00, 57.79it/s]
Profiling: 92%|█████████▏| 267/291 [00:04<00:00, 72.43it/s]
Profiling: 100%|██████████| 291/291 [00:04<00:00, 59.07it/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: quantized model in 15.188s
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: Processed model cgato/TheSpice-7b-FT-InstructExperiment-SlightOvertrain in 26.335s
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-1130-v2
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-1130-v2/tokenizer_config.json
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-1130-v2/special_tokens_map.json
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-1130-v2/config.json
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-1130-v2/tokenizer.model
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-1130-v2/tokenizer.json
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/cgato-thespice-7b-ft-ins-1130-v2/mkml_model.tensors
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1067: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 13.5MB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:690: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.14MB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 35.9MB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 24.2MB/s]
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:472: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer: warnings.warn(
cgato-thespice-7b-ft-ins-1130-v2-mkmlizer:
pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:16, 86.6MB/s]
pytorch_model.bin: 6%|▌ | 83.9M/1.44G [00:00<00:04, 274MB/s]
pytorch_model.bin: 11%|█ | 157M/1.44G [00:00<00:03, 403MB/s]
pytorch_model.bin: 17%|█▋ | 252M/1.44G [00:00<00:02, 561MB/s]
pytorch_model.bin: 24%|██▍ | 346M/1.44G [00:00<00:01, 670MB/s]
pytorch_model.bin: 32%|███▏ | 461M/1.44G [00:00<00:01, 792MB/s]
pytorch_model.bin: 42%|████▏ | 608M/1.44G [00:00<00:00, 971MB/s]
pytorch_model.bin: 52%|█████▏ | 744M/1.44G [00:00<00:00, 1.06GB/s]
pytorch_model.bin: 78%|███████▊ | 1.13G/1.44G [00:01<00:00, 1.86GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:05<00:00, 279MB/s]
Job cgato-thespice-7b-ft-ins-1130-v2-mkmlizer completed after 61.63s with status: succeeded
Stopping job with name cgato-thespice-7b-ft-ins-1130-v2-mkmlizer
Pipeline stage MKMLizer completed in 67.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-7b-ft-ins-1130-v2
Waiting for inference service cgato-thespice-7b-ft-ins-1130-v2 to be ready
Inference service cgato-thespice-7b-ft-ins-1130-v2 ready after 40.28209400177002s
Pipeline stage ISVCDeployer completed in 49.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.711789846420288s
Received healthy response to inference request in 1.2256371974945068s
Received healthy response to inference request in 1.5771410465240479s
Received healthy response to inference request in 3.507158041000366s
Received healthy response to inference request in 2.7251312732696533s
5 requests
0 failed requests
5th percentile: 1.295937967300415
10th percentile: 1.3662387371063232
20th percentile: 1.5068402767181397
30th percentile: 1.6040708065032958
40th percentile: 1.657930326461792
50th percentile: 1.711789846420288
60th percentile: 2.117126417160034
70th percentile: 2.52246298789978
80th percentile: 2.8815366268157963
90th percentile: 3.1943473339080812
95th percentile: 3.3507526874542233
99th percentile: 3.4758769702911376
mean time: 2.1493714809417725
Pipeline stage StressChecker completed in 24.90s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
cgato-thespice-7b-ft-ins_1130_v2 status is now deployed due to DeploymentManager action
cgato-thespice-7b-ft-ins_1130_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-thespice-7b-ft-ins_1130_v2
Running pipeline stage ISVCDeleter
Checking if service cgato-thespice-7b-ft-ins-1130-v2 is running
Tearing down inference service cgato-thespice-7b-ft-ins-1130-v2
Toredown service cgato-thespice-7b-ft-ins-1130-v2
Pipeline stage ISVCDeleter completed in 4.35s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-thespice-7b-ft-ins-1130-v2/config.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-ins-1130-v2/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-ins-1130-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-ins-1130-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-ins-1130-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-ft-ins-1130-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-thespice-7b-ft-ins-1130-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-ins-1130-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-ins-1130-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-ins-1130-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-ins-1130-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-ins-1130-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-ft-ins-1130-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.74s
cgato-thespice-7b-ft-ins_1130_v2 status is now torndown due to DeploymentManager action