submission_id: cognitivecomputations-do_5004_v2
developer_uid: chai_backend_admin
status: inactive
model_repo: cognitivecomputations/dolphin-2.8-mistral-7b-v02
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'top_k': 50, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 1, '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}:'}
reward_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}:'}
timestamp: 2024-04-02T17:27:26+00:00
model_name: auto_submit_ricum_guredimatu
model_eval_status: success
safety_score: 0.94
entertaining: 6.6
stay_in_character: 7.92
user_preference: 7.0
double_thumbs_up: 228
thumbs_up: 445
thumbs_down: 271
num_battles: 23642
num_wins: 9495
win_ratio: 0.4016157685475002
celo_rating: 1084.41
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cognitivecomputations-do-5004-v2-mkmlizer
Waiting for job on cognitivecomputations-do-5004-v2-mkmlizer to finish
cognitivecomputations-do-5004-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cognitivecomputations-do-5004-v2-mkmlizer: ║ _____ __ __ ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ /___/ ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ Version: 0.6.11 ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ belonging to: ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ Chai Research Corp. ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cognitivecomputations-do-5004-v2-mkmlizer: ║ ║
cognitivecomputations-do-5004-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cognitivecomputations-do-5004-v2-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 18.4MB/s]
cognitivecomputations-do-5004-v2-mkmlizer: README.md: 0%| | 0.00/7.44k [00:00<?, ?B/s] README.md: 100%|██████████| 7.44k/7.44k [00:00<00:00, 74.0MB/s]
cognitivecomputations-do-5004-v2-mkmlizer: added_tokens.json: 0%| | 0.00/51.0 [00:00<?, ?B/s] added_tokens.json: 100%|██████████| 51.0/51.0 [00:00<00:00, 673kB/s]
cognitivecomputations-do-5004-v2-mkmlizer: config.json: 0%| | 0.00/657 [00:00<?, ?B/s] config.json: 100%|██████████| 657/657 [00:00<00:00, 10.7MB/s]
cognitivecomputations-do-5004-v2-mkmlizer: eval.sh: 0%| | 0.00/1.54k [00:00<?, ?B/s] eval.sh: 100%|██████████| 1.54k/1.54k [00:00<00:00, 20.8MB/s]
cognitivecomputations-do-5004-v2-mkmlizer: eval_results.json: 0%| | 0.00/139k [00:00<?, ?B/s] eval_results.json: 100%|██████████| 139k/139k [00:00<00:00, 5.72MB/s]
cognitivecomputations-do-5004-v2-mkmlizer: generation_config.json: 0%| | 0.00/137 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 1.87MB/s]
cognitivecomputations-do-5004-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<03:07, 26.3MB/s] model-00001-of-00003.safetensors: 0%| | 21.0M/4.94G [00:00<01:54, 43.1MB/s] model-00001-of-00003.safetensors: 3%|▎ | 136M/4.94G [00:00<00:15, 302MB/s] model-00001-of-00003.safetensors: 4%|▍ | 210M/4.94G [00:00<00:11, 405MB/s] model-00001-of-00003.safetensors: 7%|▋ | 346M/4.94G [00:00<00:08, 515MB/s] model-00001-of-00003.safetensors: 8%|▊ | 419M/4.94G [00:01<00:08, 555MB/s] model-00001-of-00003.safetensors: 10%|▉ | 493M/4.94G [00:01<00:09, 462MB/s] model-00001-of-00003.safetensors: 13%|█▎ | 629M/4.94G [00:01<00:07, 610MB/s] model-00001-of-00003.safetensors: 14%|█▍ | 703M/4.94G [00:01<00:08, 500MB/s] model-00001-of-00003.safetensors: 17%|█▋ | 818M/4.94G [00:01<00:08, 483MB/s] model-00001-of-00003.safetensors: 20%|█▉ | 965M/4.94G [00:02<00:06, 628MB/s] model-00001-of-00003.safetensors: 21%|██ | 1.04G/4.94G [00:02<00:06, 630MB/s] model-00001-of-00003.safetensors: 24%|██▎ | 1.16G/4.94G [00:02<00:05, 704MB/s] model-00001-of-00003.safetensors: 25%|██▌ | 1.25G/4.94G [00:02<00:05, 712MB/s] model-00001-of-00003.safetensors: 27%|██▋ | 1.33G/4.94G [00:02<00:04, 723MB/s] model-00001-of-00003.safetensors: 30%|██▉ | 1.48G/4.94G [00:02<00:03, 898MB/s] model-00001-of-00003.safetensors: 32%|███▏ | 1.58G/4.94G [00:02<00:03, 900MB/s] model-00001-of-00003.safetensors: 34%|███▍ | 1.68G/4.94G [00:02<00:03, 825MB/s] model-00001-of-00003.safetensors: 36%|███▌ | 1.77G/4.94G [00:02<00:03, 829MB/s] model-00001-of-00003.safetensors: 38%|███▊ | 1.88G/4.94G [00:03<00:03, 885MB/s] model-00001-of-00003.safetensors: 42%|████▏ | 2.06G/4.94G [00:03<00:02, 1.12GB/s] model-00001-of-00003.safetensors: 46%|████▌ | 2.29G/4.94G [00:03<00:01, 1.45GB/s] model-00001-of-00003.safetensors: 51%|█████▏ | 2.54G/4.94G [00:03<00:01, 1.75GB/s] model-00001-of-00003.safetensors: 57%|█████▋ | 2.82G/4.94G [00:03<00:01, 2.02GB/s] model-00001-of-00003.safetensors: 62%|██████▏ | 3.04G/4.94G [00:03<00:00, 2.06GB/s] model-00001-of-00003.safetensors: 66%|██████▌ | 3.25G/4.94G [00:03<00:00, 1.82GB/s] model-00001-of-00003.safetensors: 71%|███████▏ | 3.53G/4.94G [00:03<00:00, 2.04GB/s] model-00001-of-00003.safetensors: 76%|███████▌ | 3.75G/4.94G [00:04<00:00, 1.58GB/s] model-00001-of-00003.safetensors: 80%|███████▉ | 3.93G/4.94G [00:04<00:00, 1.53GB/s] model-00001-of-00003.safetensors: 83%|████████▎ | 4.10G/4.94G [00:04<00:00, 1.44GB/s] model-00001-of-00003.safetensors: 86%|████████▌ | 4.26G/4.94G [00:04<00:00, 1.33GB/s] model-00001-of-00003.safetensors: 93%|█████████▎| 4.59G/4.94G [00:04<00:00, 1.78GB/s] model-00001-of-00003.safetensors: 100%|█████████▉| 4.94G/4.94G [00:05<00:00, 952MB/s]
cognitivecomputations-do-5004-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<03:02, 27.3MB/s] model-00002-of-00003.safetensors: 5%|▌ | 262M/5.00G [00:00<00:06, 700MB/s] model-00002-of-00003.safetensors: 8%|▊ | 419M/5.00G [00:00<00:06, 754MB/s] model-00002-of-00003.safetensors: 12%|█▏ | 598M/5.00G [00:00<00:04, 1.00GB/s] model-00002-of-00003.safetensors: 15%|█▍ | 744M/5.00G [00:00<00:04, 1.04GB/s] model-00002-of-00003.safetensors: 20%|█▉ | 996M/5.00G [00:01<00:02, 1.41GB/s] model-00002-of-00003.safetensors: 23%|██▎ | 1.17G/5.00G [00:01<00:02, 1.40GB/s] model-00002-of-00003.safetensors: 28%|██▊ | 1.38G/5.00G [00:01<00:02, 1.56GB/s] model-00002-of-00003.safetensors: 31%|███ | 1.56G/5.00G [00:01<00:02, 1.48GB/s] model-00002-of-00003.safetensors: 35%|███▍ | 1.73G/5.00G [00:01<00:02, 1.52GB/s] model-00002-of-00003.safetensors: 38%|███▊ | 1.90G/5.00G [00:01<00:02, 1.39GB/s] model-00002-of-00003.safetensors: 41%|████ | 2.06G/5.00G [00:01<00:02, 1.06GB/s] model-00002-of-00003.safetensors: 46%|████▌ | 2.31G/5.00G [00:01<00:02, 1.33GB/s] model-00002-of-00003.safetensors: 49%|████▉ | 2.46G/5.00G [00:02<00:02, 1.08GB/s] model-00002-of-00003.safetensors: 52%|█████▏ | 2.60G/5.00G [00:02<00:02, 922MB/s] model-00002-of-00003.safetensors: 55%|█████▍ | 2.74G/5.00G [00:02<00:02, 995MB/s] model-00002-of-00003.safetensors: 57%|█████▋ | 2.86G/5.00G [00:02<00:02, 1.05GB/s] model-00002-of-00003.safetensors: 69%|██████▉ | 3.46G/5.00G [00:02<00:00, 2.11GB/s] model-00002-of-00003.safetensors: 74%|███████▍ | 3.70G/5.00G [00:02<00:00, 1.74GB/s] model-00002-of-00003.safetensors: 80%|███████▉ | 4.00G/5.00G [00:03<00:00, 1.67GB/s] model-00002-of-00003.safetensors: 84%|████████▍ | 4.19G/5.00G [00:03<00:00, 1.70GB/s] model-00002-of-00003.safetensors: 88%|████████▊ | 4.38G/5.00G [00:03<00:00, 1.64GB/s] model-00002-of-00003.safetensors: 91%|█████████ | 4.56G/5.00G [00:03<00:00, 1.47GB/s] model-00002-of-00003.safetensors: 95%|█████████▌| 4.76G/5.00G [00:03<00:00, 1.58GB/s] model-00002-of-00003.safetensors: 100%|█████████▉| 5.00G/5.00G [00:03<00:00, 1.33GB/s]
cognitivecomputations-do-5004-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<01:55, 39.1MB/s] model-00003-of-00003.safetensors: 0%| | 21.0M/4.54G [00:00<01:22, 54.8MB/s] model-00003-of-00003.safetensors: 3%|▎ | 157M/4.54G [00:00<00:09, 451MB/s] model-00003-of-00003.safetensors: 9%|▉ | 430M/4.54G [00:00<00:03, 1.11GB/s] model-00003-of-00003.safetensors: 13%|█▎ | 577M/4.54G [00:00<00:03, 1.07GB/s] model-00003-of-00003.safetensors: 17%|█▋ | 755M/4.54G [00:00<00:03, 1.15GB/s] model-00003-of-00003.safetensors: 20%|█▉ | 891M/4.54G [00:01<00:03, 1.05GB/s] model-00003-of-00003.safetensors: 26%|██▌ | 1.17G/4.54G [00:01<00:02, 1.48GB/s] model-00003-of-00003.safetensors: 30%|██▉ | 1.34G/4.54G [00:01<00:02, 1.47GB/s] model-00003-of-00003.safetensors: 33%|███▎ | 1.51G/4.54G [00:01<00:02, 1.39GB/s] model-00003-of-00003.safetensors: 37%|███▋ | 1.68G/4.54G [00:01<00:02, 1.43GB/s] model-00003-of-00003.safetensors: 40%|████ | 1.84G/4.54G [00:01<00:02, 1.19GB/s] model-00003-of-00003.safetensors: 45%|████▌ | 2.07G/4.54G [00:01<00:01, 1.30GB/s] model-00003-of-00003.safetensors: 48%|████▊ | 2.20G/4.54G [00:01<00:01, 1.31GB/s] model-00003-of-00003.safetensors: 52%|█████▏ | 2.35G/4.54G [00:02<00:01, 1.31GB/s] model-00003-of-00003.safetensors: 55%|█████▍ | 2.49G/4.54G [00:02<00:01, 1.25GB/s] model-00003-of-00003.safetensors: 58%|█████▊ | 2.62G/4.54G [00:02<00:01, 1.17GB/s] model-00003-of-00003.safetensors: 61%|██████ | 2.75G/4.54G [00:02<00:01, 1.07GB/s] model-00003-of-00003.safetensors: 73%|███████▎ | 3.29G/4.54G [00:02<00:00, 1.98GB/s] model-00003-of-00003.safetensors: 77%|███████▋ | 3.50G/4.54G [00:02<00:00, 1.96GB/s] model-00003-of-00003.safetensors: 83%|████████▎ | 3.76G/4.54G [00:02<00:00, 2.12GB/s] model-00003-of-00003.safetensors: 89%|████████▊ | 4.03G/4.54G [00:02<00:00, 2.14GB/s] model-00003-of-00003.safetensors: 94%|█████████▍| 4.29G/4.54G [00:03<00:00, 2.09GB/s] model-00003-of-00003.safetensors: 99%|█████████▉| 4.51G/4.54G [00:03<00:00, 1.61GB/s] model-00003-of-00003.safetensors: 100%|█████████▉| 4.54G/4.54G [00:03<00:00, 1.36GB/s]
cognitivecomputations-do-5004-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, 19.4MB/s]
cognitivecomputations-do-5004-v2-mkmlizer: special_tokens_map.json: 0%| | 0.00/443 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 443/443 [00:00<00:00, 7.15MB/s]
cognitivecomputations-do-5004-v2-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 26.2MB/s]
cognitivecomputations-do-5004-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/1.66k [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 1.66k/1.66k [00:00<00:00, 22.0MB/s]
cognitivecomputations-do-5004-v2-mkmlizer: Downloaded to shared memory in 16.643s
cognitivecomputations-do-5004-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cognitivecomputations-do-5004-v2-mkmlizer: Saving mkml model at /dev/shm/model_cache
cognitivecomputations-do-5004-v2-mkmlizer: Reading /tmp/tmpjlv6ffth/model.safetensors.index.json
cognitivecomputations-do-5004-v2-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:01<06:09, 1.27s/it] Profiling: 3%|▎ | 8/291 [00:01<00:36, 7.74it/s] Profiling: 7%|▋ | 20/291 [00:01<00:12, 21.57it/s] Profiling: 10%|▉ | 28/291 [00:01<00:08, 29.44it/s] Profiling: 13%|█▎ | 38/291 [00:01<00:06, 40.29it/s] Profiling: 18%|█▊ | 51/291 [00:01<00:04, 56.74it/s] Profiling: 21%|██ | 61/291 [00:01<00:03, 64.73it/s] Profiling: 25%|██▍ | 72/291 [00:02<00:02, 73.80it/s] Profiling: 28%|██▊ | 82/291 [00:02<00:02, 71.63it/s] Profiling: 31%|███▏ | 91/291 [00:02<00:02, 72.93it/s] Profiling: 34%|███▍ | 100/291 [00:02<00:04, 42.98it/s] Profiling: 37%|███▋ | 108/291 [00:02<00:03, 48.74it/s] Profiling: 41%|████ | 120/291 [00:02<00:02, 60.34it/s] Profiling: 45%|████▍ | 130/291 [00:03<00:02, 67.00it/s] Profiling: 48%|████▊ | 139/291 [00:03<00:02, 70.51it/s] Profiling: 51%|█████ | 149/291 [00:03<00:01, 76.43it/s] Profiling: 56%|█████▌ | 163/291 [00:03<00:01, 91.99it/s] Profiling: 60%|█████▉ | 174/291 [00:03<00:01, 90.25it/s] Profiling: 63%|██████▎ | 184/291 [00:03<00:01, 89.97it/s] Profiling: 67%|██████▋ | 194/291 [00:03<00:01, 91.75it/s] Profiling: 70%|███████ | 204/291 [00:05<00:04, 18.07it/s] Profiling: 73%|███████▎ | 212/291 [00:05<00:03, 22.33it/s] Profiling: 77%|███████▋ | 224/291 [00:05<00:02, 31.12it/s] Profiling: 82%|████████▏ | 238/291 [00:05<00:01, 43.25it/s] Profiling: 86%|████████▌ | 249/291 [00:05<00:00, 50.93it/s] Profiling: 89%|████████▉ | 259/291 [00:05<00:00, 58.11it/s] Profiling: 93%|█████████▎| 272/291 [00:06<00:00, 71.35it/s] Profiling: 98%|█████████▊| 284/291 [00:06<00:00, 78.84it/s] Profiling: 100%|██████████| 291/291 [00:06<00:00, 45.04it/s]
cognitivecomputations-do-5004-v2-mkmlizer: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cognitivecomputations-do-5004-v2-mkmlizer: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cognitivecomputations-do-5004-v2-mkmlizer: quantized model in 17.478s
cognitivecomputations-do-5004-v2-mkmlizer: Processed model cognitivecomputations/dolphin-2.8-mistral-7b-v02 in 35.337s
cognitivecomputations-do-5004-v2-mkmlizer: creating bucket guanaco-mkml-models
cognitivecomputations-do-5004-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cognitivecomputations-do-5004-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cognitivecomputations-do-5004-v2
cognitivecomputations-do-5004-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cognitivecomputations-do-5004-v2/config.json
cognitivecomputations-do-5004-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cognitivecomputations-do-5004-v2/tokenizer_config.json
cognitivecomputations-do-5004-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/cognitivecomputations-do-5004-v2/added_tokens.json
cognitivecomputations-do-5004-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cognitivecomputations-do-5004-v2/special_tokens_map.json
cognitivecomputations-do-5004-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cognitivecomputations-do-5004-v2/tokenizer.model
cognitivecomputations-do-5004-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cognitivecomputations-do-5004-v2/tokenizer.json
cognitivecomputations-do-5004-v2-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/cognitivecomputations-do-5004-v2/mkml_model.tensors
cognitivecomputations-do-5004-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cognitivecomputations-do-5004-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.
cognitivecomputations-do-5004-v2-mkmlizer: warnings.warn(
cognitivecomputations-do-5004-v2-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 11.0MB/s]
cognitivecomputations-do-5004-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.
cognitivecomputations-do-5004-v2-mkmlizer: warnings.warn(
cognitivecomputations-do-5004-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.94MB/s]
cognitivecomputations-do-5004-v2-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 11.1MB/s]
cognitivecomputations-do-5004-v2-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 23.2MB/s]
cognitivecomputations-do-5004-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.
cognitivecomputations-do-5004-v2-mkmlizer: warnings.warn(
cognitivecomputations-do-5004-v2-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:14, 99.0MB/s] pytorch_model.bin: 3%|▎ | 41.9M/1.44G [00:00<00:07, 185MB/s] pytorch_model.bin: 9%|▊ | 126M/1.44G [00:00<00:03, 434MB/s] pytorch_model.bin: 15%|█▍ | 210M/1.44G [00:00<00:02, 553MB/s] pytorch_model.bin: 26%|██▌ | 377M/1.44G [00:00<00:01, 917MB/s] pytorch_model.bin: 33%|███▎ | 482M/1.44G [00:00<00:01, 702MB/s] pytorch_model.bin: 42%|████▏ | 608M/1.44G [00:00<00:00, 837MB/s] pytorch_model.bin: 49%|████▊ | 703M/1.44G [00:00<00:00, 848MB/s] pytorch_model.bin: 57%|█████▋ | 818M/1.44G [00:01<00:00, 916MB/s] pytorch_model.bin: 68%|██████▊ | 983M/1.44G [00:01<00:00, 1.11GB/s] pytorch_model.bin: 86%|████████▌ | 1.25G/1.44G [00:01<00:00, 1.49GB/s] pytorch_model.bin: 97%|█████████▋| 1.40G/1.44G [00:01<00:00, 571MB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:05<00:00, 280MB/s]
cognitivecomputations-do-5004-v2-mkmlizer: creating bucket guanaco-reward-models
cognitivecomputations-do-5004-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cognitivecomputations-do-5004-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cognitivecomputations-do-5004-v2_reward
cognitivecomputations-do-5004-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cognitivecomputations-do-5004-v2_reward/config.json
cognitivecomputations-do-5004-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cognitivecomputations-do-5004-v2_reward/special_tokens_map.json
cognitivecomputations-do-5004-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cognitivecomputations-do-5004-v2_reward/merges.txt
cognitivecomputations-do-5004-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cognitivecomputations-do-5004-v2_reward/vocab.json
cognitivecomputations-do-5004-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cognitivecomputations-do-5004-v2_reward/tokenizer_config.json
cognitivecomputations-do-5004-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cognitivecomputations-do-5004-v2_reward/tokenizer.json
cognitivecomputations-do-5004-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cognitivecomputations-do-5004-v2_reward/reward.tensors
Job cognitivecomputations-do-5004-v2-mkmlizer completed after 65.33s with status: succeeded
Stopping job with name cognitivecomputations-do-5004-v2-mkmlizer
Pipeline stage MKMLizer completed in 68.73s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cognitivecomputations-do-5004-v2
Waiting for inference service cognitivecomputations-do-5004-v2 to be ready
Inference service cognitivecomputations-do-5004-v2 ready after 50.68546462059021s
Pipeline stage ISVCDeployer completed in 57.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.0423030853271484s
Received healthy response to inference request in 1.4744725227355957s
Received healthy response to inference request in 1.6998085975646973s
Received healthy response to inference request in 0.5463969707489014s
Received healthy response to inference request in 0.4440138339996338s
5 requests
0 failed requests
5th percentile: 0.4644904613494873
10th percentile: 0.4849670886993408
20th percentile: 0.5259203433990478
30th percentile: 0.6455781936645507
40th percentile: 0.8439406394958496
50th percentile: 1.0423030853271484
60th percentile: 1.2151708602905273
70th percentile: 1.3880386352539062
80th percentile: 1.5195397377014161
90th percentile: 1.6096741676330566
95th percentile: 1.6547413825988768
99th percentile: 1.6907951545715332
mean time: 1.0413990020751953
Pipeline stage StressChecker completed in 6.07s
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 0.06s
M-Eval Dataset for topic stay_in_character is loaded
cognitivecomputations-do_5004_v2 status is now deployed due to DeploymentManager action
cognitivecomputations-do_5004_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics