submission_id: cgato-thespice-7b-finver_4042_v2
developer_uid: c.gato
status: torndown
model_repo: cgato/TheSpice-7b-FInvert-v0.1.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 70, 'presence_penalty': 0.9, 'frequency_penalty': 0.9, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n {bot_name} responds in one line.\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}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n {bot_name} gives single line responses.\n{bot_name} gives short responses.\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}
timestamp: 2024-04-18T10:46:01+00:00
model_name: cgato-thespice-7b-finver_4042_v2
model_eval_status: success
model_group: cgato/TheSpice-7b-FInver
num_battles: 5526
num_wins: 2859
celo_rating: 1158.42
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-thespice-7b-finver_4042_v2
ineligible_reason: propriety_total_count < 800
language_model: cgato/TheSpice-7b-FInvert-v0.1.2
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-18
win_ratio: 0.5173724212812161
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespice-7b-finver-4042-v2-mkmlizer
Waiting for job on cgato-thespice-7b-finver-4042-v2-mkmlizer to finish
cgato-thespice-7b-finver-4042-v1-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-finver-4042-v1-mkmlizer:   warnings.warn(
cgato-thespice-7b-finver-4042-v1-mkmlizer: 
pytorch_model.bin:   0%|          | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin:   1%|▏         | 21.0M/1.44G [00:00<00:16, 87.4MB/s]
pytorch_model.bin:   2%|▏         | 31.5M/1.44G [00:00<00:38, 36.3MB/s]
pytorch_model.bin:   4%|▍         | 62.9M/1.44G [00:00<00:16, 82.6MB/s]
pytorch_model.bin:   7%|▋         | 105M/1.44G [00:00<00:09, 143MB/s]  
pytorch_model.bin:  20%|██        | 294M/1.44G [00:01<00:02, 505MB/s]
pytorch_model.bin:  49%|████▊     | 703M/1.44G [00:01<00:00, 1.33GB/s]
pytorch_model.bin:  73%|███████▎  | 1.06G/1.44G [00:01<00:00, 1.87GB/s]
pytorch_model.bin:  91%|█████████ | 1.31G/1.44G [00:01<00:00, 1.89GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:05<00:00, 281MB/s] 
cgato-thespice-7b-finver-4042-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespice-7b-finver-4042-v1-mkmlizer: Saving duration: 0.324s
cgato-thespice-7b-finver-4042-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.578s
cgato-thespice-7b-finver-4042-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thespice-7b-finver-4042-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespice-7b-finver-4042-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v1_reward
cgato-thespice-7b-finver-4042-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v1_reward/config.json
cgato-thespice-7b-finver-4042-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v1_reward/special_tokens_map.json
cgato-thespice-7b-finver-4042-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v1_reward/tokenizer_config.json
cgato-thespice-7b-finver-4042-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v1_reward/merges.txt
cgato-thespice-7b-finver-4042-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v1_reward/vocab.json
cgato-thespice-7b-finver-4042-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v1_reward/tokenizer.json
cgato-thespice-7b-finver-4042-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v1_reward/reward.tensors
cgato-thespice-7b-finver-4042-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║     _____            __           __                                ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║       /___/                                                         ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║                                                                     ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║  Version: 0.6.11                                                    ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║                                                                     ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║  belonging to:                                                      ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║                                                                     ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
Job cgato-thespice-7b-finver-4042-v1-mkmlizer completed after 84.06s with status: succeeded
cgato-thespice-7b-finver-4042-v2-mkmlizer: ║                                                                     ║
Stopping job with name cgato-thespice-7b-finver-4042-v1-mkmlizer
cgato-thespice-7b-finver-4042-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespice-7b-finver-4042-v2-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 14.7MB/s]
Pipeline stage MKMLizer completed in 87.74s
cgato-thespice-7b-finver-4042-v2-mkmlizer: 
README.md:   0%|          | 0.00/30.0 [00:00<?, ?B/s]
README.md: 100%|██████████| 30.0/30.0 [00:00<00:00, 253kB/s]
Running pipeline stage MKMLKubeTemplater
cgato-thespice-7b-finver-4042-v2-mkmlizer: 
config.json:   0%|          | 0.00/653 [00:00<?, ?B/s]
config.json: 100%|██████████| 653/653 [00:00<00:00, 10.1MB/s]
cgato-thespice-7b-finver-4042-v2-mkmlizer: 
generation_config.json:   0%|          | 0.00/137 [00:00<?, ?B/s]
generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 1.16MB/s]
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-7b-finver-4042-v1
Waiting for inference service cgato-thespice-7b-finver-4042-v1 to be ready
cgato-thespice-7b-finver-4042-v2-mkmlizer: 
model-00002-of-00003.safetensors:   0%|          | 0.00/5.00G [00:00<?, ?B/s]
model-00002-of-00003.safetensors:   0%|          | 10.5M/5.00G [00:00<02:26, 34.0MB/s]
model-00002-of-00003.safetensors:   1%|          | 31.5M/5.00G [00:00<01:29, 55.4MB/s]
model-00002-of-00003.safetensors:   2%|▏         | 83.9M/5.00G [00:00<00:31, 158MB/s] 
model-00002-of-00003.safetensors:   3%|▎         | 147M/5.00G [00:00<00:18, 257MB/s] 
model-00002-of-00003.safetensors:   6%|▌         | 283M/5.00G [00:00<00:09, 515MB/s]
model-00002-of-00003.safetensors:   9%|▉         | 461M/5.00G [00:01<00:05, 798MB/s]
model-00002-of-00003.safetensors:  14%|█▍        | 703M/5.00G [00:01<00:03, 1.17GB/s]
model-00002-of-00003.safetensors:  17%|█▋        | 860M/5.00G [00:01<00:03, 1.25GB/s]
model-00002-of-00003.safetensors:  21%|██        | 1.03G/5.00G [00:01<00:02, 1.33GB/s]
model-00002-of-00003.safetensors:  23%|██▎       | 1.17G/5.00G [00:01<00:03, 1.02GB/s]
model-00002-of-00003.safetensors:  26%|██▌       | 1.31G/5.00G [00:01<00:03, 1.09GB/s]
model-00002-of-00003.safetensors:  29%|██▊       | 1.44G/5.00G [00:01<00:03, 1.07GB/s]
model-00002-of-00003.safetensors:  33%|███▎      | 1.64G/5.00G [00:01<00:02, 1.29GB/s]
model-00002-of-00003.safetensors:  37%|███▋      | 1.85G/5.00G [00:02<00:02, 1.46GB/s]
model-00002-of-00003.safetensors:  42%|████▏     | 2.10G/5.00G [00:02<00:01, 1.66GB/s]
model-00002-of-00003.safetensors:  46%|████▌     | 2.29G/5.00G [00:02<00:01, 1.70GB/s]
model-00002-of-00003.safetensors:  50%|█████     | 2.52G/5.00G [00:02<00:01, 1.84GB/s]
model-00002-of-00003.safetensors:  55%|█████▍    | 2.74G/5.00G [00:02<00:01, 1.90GB/s]
model-00002-of-00003.safetensors:  60%|██████    | 3.01G/5.00G [00:02<00:00, 2.13GB/s]
model-00002-of-00003.safetensors:  65%|██████▍   | 3.23G/5.00G [00:02<00:01, 1.60GB/s]
model-00002-of-00003.safetensors:  68%|██████▊   | 3.42G/5.00G [00:02<00:01, 1.47GB/s]
model-00002-of-00003.safetensors:  72%|███████▏  | 3.59G/5.00G [00:03<00:01, 1.33GB/s]
model-00002-of-00003.safetensors:  76%|███████▌  | 3.80G/5.00G [00:03<00:00, 1.47GB/s]
model-00002-of-00003.safetensors:  79%|███████▉  | 3.96G/5.00G [00:03<00:00, 1.28GB/s]
model-00002-of-00003.safetensors:  83%|████████▎ | 4.15G/5.00G [00:03<00:00, 1.39GB/s]
model-00002-of-00003.safetensors:  88%|████████▊ | 4.38G/5.00G [00:03<00:00, 1.59GB/s]
model-00002-of-00003.safetensors:  91%|█████████ | 4.56G/5.00G [00:03<00:00, 1.38GB/s]
model-00002-of-00003.safetensors:  94%|█████████▍| 4.72G/5.00G [00:03<00:00, 1.24GB/s]
model-00002-of-00003.safetensors:  98%|█████████▊| 4.91G/5.00G [00:04<00:00, 1.38GB/s]
model-00002-of-00003.safetensors: 100%|█████████▉| 5.00G/5.00G [00:04<00:00, 1.21GB/s]
cgato-thespice-7b-finver-4042-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<02:24, 31.4MB/s]
model-00003-of-00003.safetensors:   1%|          | 52.4M/4.54G [00:00<00:35, 128MB/s] 
model-00003-of-00003.safetensors:   4%|▎         | 168M/4.54G [00:00<00:11, 393MB/s] 
model-00003-of-00003.safetensors:   8%|▊         | 367M/4.54G [00:00<00:05, 824MB/s]
model-00003-of-00003.safetensors:  14%|█▎        | 619M/4.54G [00:00<00:03, 1.29GB/s]
model-00003-of-00003.safetensors:  17%|█▋        | 786M/4.54G [00:00<00:03, 1.19GB/s]
model-00003-of-00003.safetensors:  22%|██▏       | 996M/4.54G [00:01<00:02, 1.41GB/s]
model-00003-of-00003.safetensors:  26%|██▌       | 1.16G/4.54G [00:01<00:02, 1.24GB/s]
model-00003-of-00003.safetensors:  29%|██▉       | 1.31G/4.54G [00:01<00:02, 1.28GB/s]
model-00003-of-00003.safetensors:  32%|███▏      | 1.46G/4.54G [00:01<00:02, 1.15GB/s]
model-00003-of-00003.safetensors:  37%|███▋      | 1.68G/4.54G [00:01<00:02, 1.40GB/s]
model-00003-of-00003.safetensors:  40%|████      | 1.84G/4.54G [00:01<00:01, 1.42GB/s]
model-00003-of-00003.safetensors:  45%|████▌     | 2.07G/4.54G [00:01<00:01, 1.62GB/s]
model-00003-of-00003.safetensors:  54%|█████▍    | 2.44G/4.54G [00:01<00:00, 2.13GB/s]
model-00003-of-00003.safetensors:  59%|█████▉    | 2.67G/4.54G [00:02<00:00, 1.88GB/s]
model-00003-of-00003.safetensors:  64%|██████▍   | 2.90G/4.54G [00:02<00:00, 1.98GB/s]
model-00003-of-00003.safetensors:  70%|██████▉   | 3.17G/4.54G [00:02<00:00, 2.11GB/s]
model-00003-of-00003.safetensors:  75%|███████▍  | 3.39G/4.54G [00:02<00:00, 1.56GB/s]
model-00003-of-00003.safetensors:  79%|███████▊  | 3.58G/4.54G [00:02<00:00, 1.37GB/s]
model-00003-of-00003.safetensors:  82%|████████▏ | 3.73G/4.54G [00:02<00:00, 1.13GB/s]
model-00003-of-00003.safetensors:  85%|████████▌ | 3.87G/4.54G [00:03<00:00, 696MB/s] 
model-00003-of-00003.safetensors:  88%|████████▊ | 3.98G/4.54G [00:03<00:00, 731MB/s]
model-00003-of-00003.safetensors:  92%|█████████▏| 4.18G/4.54G [00:03<00:00, 878MB/s]
model-00003-of-00003.safetensors:  95%|█████████▍| 4.31G/4.54G [00:03<00:00, 915MB/s]
model-00003-of-00003.safetensors: 100%|█████████▉| 4.54G/4.54G [00:05<00:00, 899MB/s]
cgato-thespice-7b-finver-4042-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, 101MB/s]
cgato-thespice-7b-finver-4042-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, 5.80MB/s]
cgato-thespice-7b-finver-4042-v2-mkmlizer: 
tokenizer.model:   0%|          | 0.00/493k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 17.3MB/s]
cgato-thespice-7b-finver-4042-v2-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/982 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 982/982 [00:00<00:00, 14.7MB/s]
cgato-thespice-7b-finver-4042-v2-mkmlizer: Downloaded to shared memory in 15.231s
cgato-thespice-7b-finver-4042-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespice-7b-finver-4042-v2-mkmlizer: Saving mkml model at /dev/shm/model_cache
cgato-thespice-7b-finver-4042-v2-mkmlizer: Reading /tmp/tmp5ix3maks/model.safetensors.index.json
cgato-thespice-7b-finver-4042-v2-mkmlizer: 
Profiling:   0%|          | 0/291 [00:00<?, ?it/s]
Profiling:   0%|          | 1/291 [00:01<07:43,  1.60s/it]
Profiling:   5%|▍         | 14/291 [00:01<00:24, 11.09it/s]
Profiling:  10%|▉         | 29/291 [00:01<00:10, 25.24it/s]
Profiling:  16%|█▌        | 46/291 [00:01<00:05, 43.07it/s]
Profiling:  22%|██▏       | 63/291 [00:02<00:03, 61.44it/s]
Profiling:  26%|██▋       | 77/291 [00:02<00:02, 75.15it/s]
Profiling:  31%|███▏      | 91/291 [00:02<00:02, 88.03it/s]
Profiling:  36%|███▌      | 105/291 [00:02<00:03, 57.84it/s]
Profiling:  42%|████▏     | 121/291 [00:02<00:02, 73.28it/s]
Profiling:  47%|████▋     | 138/291 [00:02<00:01, 89.71it/s]
Profiling:  53%|█████▎    | 153/291 [00:02<00:01, 101.68it/s]
Profiling:  57%|█████▋    | 167/291 [00:03<00:01, 108.80it/s]
Profiling:  63%|██████▎   | 184/291 [00:03<00:00, 123.09it/s]
Profiling:  68%|██████▊   | 199/291 [00:03<00:00, 128.96it/s]
Profiling:  74%|███████▎  | 214/291 [00:05<00:03, 24.41it/s] 
Profiling:  79%|███████▉  | 231/291 [00:05<00:01, 33.49it/s]
Profiling:  85%|████████▌ | 248/291 [00:05<00:00, 44.89it/s]
Profiling:  91%|█████████ | 265/291 [00:05<00:00, 58.08it/s]
Profiling:  96%|█████████▌| 280/291 [00:05<00:00, 69.96it/s]
Profiling: 100%|██████████| 291/291 [00:05<00:00, 49.90it/s]
cgato-thespice-7b-finver-4042-v2-mkmlizer: quantized model in 17.895s
cgato-thespice-7b-finver-4042-v2-mkmlizer: Processed model cgato/TheSpice-7b-FInvert-v0.1.2 in 34.574s
cgato-thespice-7b-finver-4042-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespice-7b-finver-4042-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespice-7b-finver-4042-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespice-7b-finver-4042-v2
cgato-thespice-7b-finver-4042-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespice-7b-finver-4042-v2/config.json
cgato-thespice-7b-finver-4042-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespice-7b-finver-4042-v2/special_tokens_map.json
cgato-thespice-7b-finver-4042-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespice-7b-finver-4042-v2/tokenizer_config.json
cgato-thespice-7b-finver-4042-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cgato-thespice-7b-finver-4042-v2/tokenizer.model
cgato-thespice-7b-finver-4042-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespice-7b-finver-4042-v2/tokenizer.json
cgato-thespice-7b-finver-4042-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thespice-7b-finver-4042-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-finver-4042-v2-mkmlizer:   warnings.warn(
cgato-thespice-7b-finver-4042-v2-mkmlizer: 
config.json:   0%|          | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 12.3MB/s]
cgato-thespice-7b-finver-4042-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-finver-4042-v2-mkmlizer:   warnings.warn(
cgato-thespice-7b-finver-4042-v2-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.91MB/s]
cgato-thespice-7b-finver-4042-v2-mkmlizer: 
vocab.json:   0%|          | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 53.5MB/s]
cgato-thespice-7b-finver-4042-v2-mkmlizer: 
tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 27.6MB/s]
cgato-thespice-7b-finver-4042-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-finver-4042-v2-mkmlizer:   warnings.warn(
cgato-thespice-7b-finver-4042-v2-mkmlizer: 
pytorch_model.bin:   0%|          | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin:   1%|▏         | 21.0M/1.44G [00:00<00:08, 176MB/s]
pytorch_model.bin:   3%|▎         | 41.9M/1.44G [00:00<00:11, 121MB/s]
pytorch_model.bin:   5%|▌         | 73.4M/1.44G [00:00<00:14, 97.5MB/s]
pytorch_model.bin:  10%|█         | 147M/1.44G [00:00<00:05, 223MB/s]  
pytorch_model.bin:  15%|█▌        | 220M/1.44G [00:00<00:03, 334MB/s]
pytorch_model.bin:  20%|██        | 294M/1.44G [00:01<00:02, 409MB/s]
pytorch_model.bin:  31%|███       | 451M/1.44G [00:01<00:01, 689MB/s]
pytorch_model.bin:  43%|████▎     | 619M/1.44G [00:01<00:00, 940MB/s]
pytorch_model.bin:  58%|█████▊    | 839M/1.44G [00:01<00:00, 1.25GB/s]
pytorch_model.bin:  81%|████████  | 1.16G/1.44G [00:01<00:00, 1.77GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 939MB/s] 
cgato-thespice-7b-finver-4042-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespice-7b-finver-4042-v2-mkmlizer: Saving duration: 0.329s
cgato-thespice-7b-finver-4042-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.216s
cgato-thespice-7b-finver-4042-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-thespice-7b-finver-4042-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespice-7b-finver-4042-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v2_reward
cgato-thespice-7b-finver-4042-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v2_reward/config.json
cgato-thespice-7b-finver-4042-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v2_reward/tokenizer_config.json
cgato-thespice-7b-finver-4042-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v2_reward/merges.txt
cgato-thespice-7b-finver-4042-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v2_reward/special_tokens_map.json
cgato-thespice-7b-finver-4042-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v2_reward/vocab.json
cgato-thespice-7b-finver-4042-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v2_reward/tokenizer.json
cgato-thespice-7b-finver-4042-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thespice-7b-finver-4042-v2_reward/reward.tensors
Inference service cgato-thespice-7b-finver-4042-v1 ready after 40.4051878452301s
Pipeline stage ISVCDeployer completed in 47.83s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.844674825668335s
Received healthy response to inference request in 1.2625396251678467s
Received healthy response to inference request in 1.1934185028076172s
Job cgato-thespice-7b-finver-4042-v2-mkmlizer completed after 66.73s with status: succeeded
Stopping job with name cgato-thespice-7b-finver-4042-v2-mkmlizer
Pipeline stage MKMLizer completed in 67.25s
Running pipeline stage MKMLKubeTemplater
Received healthy response to inference request in 1.2049269676208496s
Pipeline stage MKMLKubeTemplater completed in 0.18s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-7b-finver-4042-v2
Received healthy response to inference request in 1.205693244934082s
5 requests
0 failed requests
5th percentile: 1.1957201957702637
10th percentile: 1.1980218887329102
20th percentile: 1.2026252746582031
30th percentile: 1.205080223083496
40th percentile: 1.2053867340087892
50th percentile: 1.205693244934082
60th percentile: 1.228431797027588
70th percentile: 1.2511703491210937
80th percentile: 1.3789666652679444
90th percentile: 1.6118207454681397
95th percentile: 1.7282477855682372
99th percentile: 1.8213894176483154
mean time: 1.3422506332397461
Pipeline stage StressChecker completed in 9.82s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.10s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.13s
cgato-thespice-7b-finver_4042_v1 status is now deployed due to DeploymentManager action
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Waiting for inference service cgato-thespice-7b-finver-4042-v2 to be ready
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Inference service cgato-thespice-7b-finver-4042-v2 ready after 30.16765832901001s
Received score %s for bot %s
Pipeline stage ISVCDeployer completed in 35.87s
Running pipeline stage StressChecker
Scoring model output for bot %s
Scoring model output for bot %s
Received healthy response to inference request in 1.6353907585144043s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request in 1.2034695148468018s
Scoring model output for bot %s
Scoring model output for bot %s
Received healthy response to inference request in 1.190415382385254s
Received score %s for bot %s
Scoring model output for bot %s
Received healthy response to inference request in 1.1430072784423828s
Received healthy response to inference request in 1.1943485736846924s
5 requests
Received score %s for bot %s
0 failed requests
Received score %s for bot %s
5th percentile: 1.152488899230957
10th percentile: 1.1619705200195312
20th percentile: 1.1809337615966797
30th percentile: 1.1912020206451417
40th percentile: 1.192775297164917
50th percentile: 1.1943485736846924
60th percentile: 1.1979969501495362
70th percentile: 1.2016453266143798
80th percentile: 1.2898537635803224
90th percentile: 1.4626222610473634
95th percentile: 1.5490065097808836
99th percentile: 1.6181139087677001
mean time: 1.273326301574707
Pipeline stage StressChecker completed in 8.79s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Scoring model output for bot %s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.10s
Scoring model output for bot %s
M-Eval Dataset for topic stay_in_character is loaded
cgato-thespice-7b-finver_4042_v2 status is now deployed due to DeploymentManager action
cgato-thespice-7b-finver_4042_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-thespice-7b-finver_4042_v2
Running pipeline stage ISVCDeleter
Checking if service cgato-thespice-7b-finver-4042-v2 is running
Tearing down inference service cgato-thespice-7b-finver-4042-v2
Toredown service cgato-thespice-7b-finver-4042-v2
Pipeline stage ISVCDeleter completed in 5.15s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-thespice-7b-finver-4042-v2/config.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-finver-4042-v2/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-finver-4042-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-finver-4042-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-finver-4042-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key cgato-thespice-7b-finver-4042-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-thespice-7b-finver-4042-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-finver-4042-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-finver-4042-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-finver-4042-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-finver-4042-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-finver-4042-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-7b-finver-4042-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.65s
cgato-thespice-7b-finver_4042_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics