submission_id: nousresearch-hermes-2-pr_1418_v2
developer_uid: alexdaoud
status: torndown
model_repo: NousResearch/Hermes-2-Pro-Mistral-7B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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', '<|im_end|>', '</s>', '<|'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>{bot_name}\n{message}<|im_end|>\n', 'user_template': '<|im_start|>{user_name}\n{message}<|im_end|>\n', 'response_template': '<|im_start|>{bot_name}\n', 'truncate_by_message': False}
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}:', 'truncate_by_message': False}
timestamp: 2024-03-22T19:08:12+00:00
model_name: nousresearch-hermes-2-pr_1418_v2
model_eval_status: success
model_group: NousResearch/Hermes-2-Pr
num_battles: 67784
num_wins: 35170
celo_rating: 1170.58
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: None
model_num_parameters: 7241994240.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nousresearch-hermes-2-pr_1418_v2
ineligible_reason: propriety_total_count < 800
language_model: NousResearch/Hermes-2-Pro-Mistral-7B
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-03-22
win_ratio: 0.5188540068452733
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-hermes-2-pr-1418-v2-mkmlizer
Waiting for job on nousresearch-hermes-2-pr-1418-v2-mkmlizer to finish
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ _____ __ __ ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ /___/ ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ Version: 0.6.11 ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ belonging to: ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ Chai Research Corp. ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ║ ║
nousresearch-hermes-2-pr-1418-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-hermes-2-pr-1418-v2-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 15.4MB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: README.md: 0%| | 0.00/18.3k [00:00<?, ?B/s] README.md: 100%|██████████| 18.3k/18.3k [00:00<00:00, 185MB/s]
nousresearch-hermes-2-pr-1418-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, 789kB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: config.json: 0%| | 0.00/642 [00:00<?, ?B/s] config.json: 100%|██████████| 642/642 [00:00<00:00, 8.58MB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: generation_config.json: 0%| | 0.00/136 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 136/136 [00:00<00:00, 1.84MB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: model-00001-of-00004.safetensors: 0%| | 0.00/3.95G [00:00<?, ?B/s] model-00001-of-00004.safetensors: 1%| | 21.0M/3.95G [00:00<00:21, 183MB/s] model-00001-of-00004.safetensors: 2%|▏ | 83.9M/3.95G [00:00<00:12, 307MB/s] model-00001-of-00004.safetensors: 5%|▍ | 178M/3.95G [00:00<00:07, 518MB/s] model-00001-of-00004.safetensors: 6%|▌ | 241M/3.95G [00:00<00:06, 540MB/s] model-00001-of-00004.safetensors: 8%|▊ | 304M/3.95G [00:00<00:06, 546MB/s] model-00001-of-00004.safetensors: 11%|█ | 430M/3.95G [00:00<00:04, 754MB/s] model-00001-of-00004.safetensors: 14%|█▍ | 545M/3.95G [00:00<00:04, 818MB/s] model-00001-of-00004.safetensors: 18%|█▊ | 703M/3.95G [00:00<00:03, 1.02GB/s] model-00001-of-00004.safetensors: 21%|██▏ | 849M/3.95G [00:01<00:02, 1.15GB/s] model-00001-of-00004.safetensors: 25%|██▌ | 1.01G/3.95G [00:01<00:02, 1.23GB/s] model-00001-of-00004.safetensors: 29%|██▊ | 1.13G/3.95G [00:01<00:02, 1.13GB/s] model-00001-of-00004.safetensors: 33%|███▎ | 1.29G/3.95G [00:01<00:02, 1.24GB/s] model-00001-of-00004.safetensors: 38%|███▊ | 1.51G/3.95G [00:01<00:01, 1.49GB/s] model-00001-of-00004.safetensors: 43%|████▎ | 1.69G/3.95G [00:01<00:01, 1.55GB/s] model-00001-of-00004.safetensors: 48%|████▊ | 1.89G/3.95G [00:01<00:01, 1.68GB/s] model-00001-of-00004.safetensors: 52%|█████▏ | 2.07G/3.95G [00:01<00:01, 1.70GB/s] model-00001-of-00004.safetensors: 57%|█████▋ | 2.24G/3.95G [00:01<00:01, 1.70GB/s] model-00001-of-00004.safetensors: 64%|██████▍ | 2.53G/3.95G [00:02<00:00, 1.90GB/s] model-00001-of-00004.safetensors: 69%|██████▉ | 2.74G/3.95G [00:02<00:00, 1.95GB/s] model-00001-of-00004.safetensors: 75%|███████▌ | 2.98G/3.95G [00:02<00:00, 2.07GB/s] model-00001-of-00004.safetensors: 81%|████████ | 3.19G/3.95G [00:02<00:00, 1.98GB/s] model-00001-of-00004.safetensors: 91%|█████████ | 3.60G/3.95G [00:02<00:00, 2.55GB/s] model-00001-of-00004.safetensors: 100%|█████████▉| 3.95G/3.95G [00:02<00:00, 1.54GB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: model-00002-of-00004.safetensors: 0%| | 0.00/3.93G [00:00<?, ?B/s] model-00002-of-00004.safetensors: 0%| | 10.5M/3.93G [00:00<01:26, 45.1MB/s] model-00002-of-00004.safetensors: 1%| | 21.0M/3.93G [00:00<01:11, 54.7MB/s] model-00002-of-00004.safetensors: 2%|▏ | 83.9M/3.93G [00:00<00:19, 202MB/s] model-00002-of-00004.safetensors: 5%|▌ | 199M/3.93G [00:00<00:08, 439MB/s] model-00002-of-00004.safetensors: 7%|▋ | 273M/3.93G [00:00<00:07, 513MB/s] model-00002-of-00004.safetensors: 11%|█ | 440M/3.93G [00:00<00:04, 818MB/s] model-00002-of-00004.safetensors: 16%|█▌ | 629M/3.93G [00:00<00:03, 1.08GB/s] model-00002-of-00004.safetensors: 21%|██ | 818M/3.93G [00:01<00:02, 1.25GB/s] model-00002-of-00004.safetensors: 26%|██▋ | 1.04G/3.93G [00:01<00:01, 1.51GB/s] model-00002-of-00004.safetensors: 31%|███ | 1.21G/3.93G [00:01<00:01, 1.45GB/s] model-00002-of-00004.safetensors: 36%|███▋ | 1.43G/3.93G [00:01<00:01, 1.66GB/s] model-00002-of-00004.safetensors: 41%|████ | 1.60G/3.93G [00:01<00:01, 1.63GB/s] model-00002-of-00004.safetensors: 49%|████▊ | 1.91G/3.93G [00:01<00:00, 2.02GB/s] model-00002-of-00004.safetensors: 56%|█████▋ | 2.21G/3.93G [00:01<00:00, 2.30GB/s] model-00002-of-00004.safetensors: 66%|██████▌ | 2.58G/3.93G [00:01<00:00, 2.69GB/s] model-00002-of-00004.safetensors: 73%|███████▎ | 2.86G/3.93G [00:02<00:00, 1.70GB/s] model-00002-of-00004.safetensors: 79%|███████▊ | 3.09G/3.93G [00:03<00:01, 521MB/s] model-00002-of-00004.safetensors: 83%|████████▎ | 3.25G/3.93G [00:03<00:01, 503MB/s] model-00002-of-00004.safetensors: 86%|████████▌ | 3.38G/3.93G [00:03<00:00, 557MB/s] model-00002-of-00004.safetensors: 89%|████████▉ | 3.51G/3.93G [00:04<00:00, 582MB/s] model-00002-of-00004.safetensors: 100%|█████████▉| 3.93G/3.93G [00:04<00:00, 922MB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: model-00003-of-00004.safetensors: 0%| | 0.00/3.93G [00:00<?, ?B/s] model-00003-of-00004.safetensors: 0%| | 10.5M/3.93G [00:00<00:42, 92.5MB/s] model-00003-of-00004.safetensors: 2%|▏ | 94.4M/3.93G [00:00<00:07, 500MB/s] model-00003-of-00004.safetensors: 5%|▍ | 189M/3.93G [00:00<00:05, 694MB/s] model-00003-of-00004.safetensors: 7%|▋ | 273M/3.93G [00:00<00:05, 654MB/s] model-00003-of-00004.safetensors: 11%|█ | 419M/3.93G [00:00<00:03, 913MB/s] model-00003-of-00004.safetensors: 14%|█▍ | 556M/3.93G [00:00<00:03, 1.04GB/s] model-00003-of-00004.safetensors: 19%|█▉ | 755M/3.93G [00:00<00:02, 1.29GB/s] model-00003-of-00004.safetensors: 24%|██▎ | 923M/3.93G [00:00<00:02, 1.35GB/s] model-00003-of-00004.safetensors: 27%|██▋ | 1.07G/3.93G [00:01<00:02, 1.19GB/s] model-00003-of-00004.safetensors: 31%|███ | 1.21G/3.93G [00:01<00:02, 1.23GB/s] model-00003-of-00004.safetensors: 36%|███▌ | 1.39G/3.93G [00:01<00:01, 1.37GB/s] model-00003-of-00004.safetensors: 39%|███▉ | 1.54G/3.93G [00:01<00:01, 1.28GB/s] model-00003-of-00004.safetensors: 43%|████▎ | 1.68G/3.93G [00:01<00:01, 1.26GB/s] model-00003-of-00004.safetensors: 50%|█████ | 1.98G/3.93G [00:01<00:01, 1.73GB/s] model-00003-of-00004.safetensors: 59%|█████▉ | 2.32G/3.93G [00:01<00:00, 2.15GB/s] model-00003-of-00004.safetensors: 65%|██████▍ | 2.55G/3.93G [00:01<00:00, 2.03GB/s] model-00003-of-00004.safetensors: 70%|███████ | 2.76G/3.93G [00:01<00:00, 1.93GB/s] model-00003-of-00004.safetensors: 75%|███████▌ | 2.96G/3.93G [00:02<00:00, 1.95GB/s] model-00003-of-00004.safetensors: 80%|████████ | 3.16G/3.93G [00:02<00:00, 1.88GB/s] model-00003-of-00004.safetensors: 85%|████████▌ | 3.35G/3.93G [00:02<00:00, 1.88GB/s] model-00003-of-00004.safetensors: 94%|█████████▍| 3.70G/3.93G [00:02<00:00, 2.32GB/s] model-00003-of-00004.safetensors: 100%|█████████▉| 3.93G/3.93G [00:02<00:00, 1.59GB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: model-00004-of-00004.safetensors: 0%| | 0.00/2.68G [00:00<?, ?B/s] model-00004-of-00004.safetensors: 0%| | 10.5M/2.68G [00:00<00:35, 74.3MB/s] model-00004-of-00004.safetensors: 1%| | 31.5M/2.68G [00:00<00:29, 88.8MB/s] model-00004-of-00004.safetensors: 5%|▌ | 147M/2.68G [00:00<00:06, 395MB/s] model-00004-of-00004.safetensors: 12%|█▏ | 315M/2.68G [00:00<00:03, 772MB/s] model-00004-of-00004.safetensors: 20%|█▉ | 535M/2.68G [00:00<00:01, 1.17GB/s] model-00004-of-00004.safetensors: 26%|██▌ | 703M/2.68G [00:00<00:01, 1.31GB/s] model-00004-of-00004.safetensors: 32%|███▏ | 860M/2.68G [00:00<00:01, 1.34GB/s] model-00004-of-00004.safetensors: 40%|████ | 1.08G/2.68G [00:01<00:01, 1.59GB/s] model-00004-of-00004.safetensors: 47%|████▋ | 1.25G/2.68G [00:01<00:01, 1.40GB/s] model-00004-of-00004.safetensors: 54%|█████▍ | 1.45G/2.68G [00:01<00:00, 1.48GB/s] model-00004-of-00004.safetensors: 61%|██████ | 1.63G/2.68G [00:01<00:00, 1.53GB/s] model-00004-of-00004.safetensors: 69%|██████▉ | 1.86G/2.68G [00:01<00:00, 1.72GB/s] model-00004-of-00004.safetensors: 82%|████████▏ | 2.20G/2.68G [00:01<00:00, 2.17GB/s] model-00004-of-00004.safetensors: 100%|█████████▉| 2.68G/2.68G [00:01<00:00, 1.57GB/s]
nousresearch-hermes-2-pr-1418-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, 90.4MB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: special_tokens_map.json: 0%| | 0.00/557 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 557/557 [00:00<00:00, 5.94MB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 61.0MB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/1.60k [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 1.60k/1.60k [00:00<00:00, 17.3MB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: Downloaded to shared memory in 12.448s
nousresearch-hermes-2-pr-1418-v2-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-hermes-2-pr-1418-v2-mkmlizer: Saving mkml model at /dev/shm/model_cache
nousresearch-hermes-2-pr-1418-v2-mkmlizer: Reading /tmp/tmpia_wh0xu/model.safetensors.index.json
nousresearch-hermes-2-pr-1418-v2-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:01<06:55, 1.43s/it] Profiling: 4%|▍ | 13/291 [00:01<00:24, 11.38it/s] Profiling: 8%|▊ | 22/291 [00:01<00:13, 20.30it/s] Profiling: 11%|█ | 32/291 [00:01<00:08, 31.14it/s] Profiling: 16%|█▋ | 48/291 [00:01<00:04, 52.20it/s] Profiling: 20%|██ | 59/291 [00:01<00:03, 62.53it/s] Profiling: 25%|██▌ | 74/291 [00:02<00:02, 80.87it/s] Profiling: 30%|██▉ | 87/291 [00:02<00:03, 65.62it/s] Profiling: 34%|███▍ | 99/291 [00:02<00:02, 75.34it/s] Profiling: 39%|███▉ | 113/291 [00:02<00:02, 88.77it/s] Profiling: 43%|████▎ | 126/291 [00:02<00:01, 97.01it/s] Profiling: 49%|████▉ | 142/291 [00:02<00:01, 108.41it/s] Profiling: 53%|█████▎ | 155/291 [00:02<00:01, 112.03it/s] Profiling: 58%|█████▊ | 168/291 [00:03<00:01, 79.54it/s] Profiling: 63%|██████▎ | 183/291 [00:03<00:01, 90.65it/s] Profiling: 67%|██████▋ | 194/291 [00:03<00:01, 89.54it/s] Profiling: 71%|███████ | 206/291 [00:03<00:00, 96.39it/s] Profiling: 75%|███████▌ | 219/291 [00:03<00:00, 102.87it/s] Profiling: 79%|███████▉ | 231/291 [00:03<00:00, 100.76it/s] Profiling: 83%|████████▎ | 242/291 [00:05<00:02, 21.51it/s] Profiling: 87%|████████▋ | 252/291 [00:05<00:01, 27.07it/s] Profiling: 91%|█████████▏| 266/291 [00:05<00:00, 36.95it/s] Profiling: 95%|█████████▍| 276/291 [00:05<00:00, 43.61it/s] Profiling: 99%|█████████▉| 289/291 [00:05<00:00, 55.25it/s] Profiling: 100%|██████████| 291/291 [00:05<00:00, 49.62it/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-hermes-2-pr-1418-v2-mkmlizer: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-hermes-2-pr-1418-v2-mkmlizer: quantized model in 16.641s
nousresearch-hermes-2-pr-1418-v2-mkmlizer: Processed model NousResearch/Hermes-2-Pro-Mistral-7B in 30.016s
nousresearch-hermes-2-pr-1418-v2-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-hermes-2-pr-1418-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-hermes-2-pr-1418-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v2
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v2/config.json
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v2/special_tokens_map.json
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v2/tokenizer_config.json
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v2/tokenizer.model
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v2/tokenizer.json
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v2/added_tokens.json
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/nousresearch-hermes-2-pr-1418-v2/mkml_model.tensors
nousresearch-hermes-2-pr-1418-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nousresearch-hermes-2-pr-1418-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.
nousresearch-hermes-2-pr-1418-v2-mkmlizer: warnings.warn(
nousresearch-hermes-2-pr-1418-v2-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 9.86MB/s]
nousresearch-hermes-2-pr-1418-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.
nousresearch-hermes-2-pr-1418-v2-mkmlizer: warnings.warn(
nousresearch-hermes-2-pr-1418-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.30MB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 12.0MB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 19.7MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 19.6MB/s]
nousresearch-hermes-2-pr-1418-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.
nousresearch-hermes-2-pr-1418-v2-mkmlizer: warnings.warn(
nousresearch-hermes-2-pr-1418-v2-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:07, 180MB/s] pytorch_model.bin: 4%|▍ | 62.9M/1.44G [00:00<00:05, 257MB/s] pytorch_model.bin: 10%|█ | 147M/1.44G [00:00<00:03, 384MB/s] pytorch_model.bin: 17%|█▋ | 252M/1.44G [00:00<00:02, 576MB/s] pytorch_model.bin: 24%|██▍ | 346M/1.44G [00:00<00:01, 613MB/s] pytorch_model.bin: 31%|███ | 451M/1.44G [00:00<00:01, 733MB/s] pytorch_model.bin: 41%|████▏ | 598M/1.44G [00:00<00:00, 927MB/s] pytorch_model.bin: 52%|█████▏ | 753M/1.44G [00:00<00:00, 1.10GB/s] pytorch_model.bin: 61%|██████ | 878M/1.44G [00:01<00:00, 1.08GB/s] pytorch_model.bin: 77%|███████▋ | 1.11G/1.44G [00:01<00:00, 1.39GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.07GB/s]
nousresearch-hermes-2-pr-1418-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-hermes-2-pr-1418-v2-mkmlizer: Saving duration: 0.276s
nousresearch-hermes-2-pr-1418-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.547s
nousresearch-hermes-2-pr-1418-v2-mkmlizer: creating bucket guanaco-reward-models
nousresearch-hermes-2-pr-1418-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-hermes-2-pr-1418-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v2_reward
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v2_reward/config.json
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v2_reward/special_tokens_map.json
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v2_reward/tokenizer_config.json
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v2_reward/vocab.json
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v2_reward/merges.txt
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v2_reward/tokenizer.json
nousresearch-hermes-2-pr-1418-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-hermes-2-pr-1418-v2_reward/reward.tensors
Job nousresearch-hermes-2-pr-1418-v2-mkmlizer completed after 54.59s with status: succeeded
Stopping job with name nousresearch-hermes-2-pr-1418-v2-mkmlizer
Pipeline stage MKMLizer completed in 59.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-hermes-2-pr-1418-v2
Waiting for inference service nousresearch-hermes-2-pr-1418-v2 to be ready
Inference service nousresearch-hermes-2-pr-1418-v2 ready after 40.27760934829712s
Pipeline stage ISVCDeployer completed in 47.75s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.69818115234375s
Received healthy response to inference request in 1.193892002105713s
Received healthy response to inference request in 1.1840934753417969s
Received healthy response to inference request in 1.1699645519256592s
Received healthy response to inference request in 1.188091516494751s
5 requests
0 failed requests
5th percentile: 1.1727903366088868
10th percentile: 1.1756161212921143
20th percentile: 1.1812676906585693
30th percentile: 1.1848930835723877
40th percentile: 1.1864923000335694
50th percentile: 1.188091516494751
60th percentile: 1.1904117107391357
70th percentile: 1.1927319049835206
80th percentile: 1.2947498321533204
90th percentile: 1.4964654922485352
95th percentile: 1.5973233222961425
99th percentile: 1.6780095863342286
mean time: 1.286844539642334
Pipeline stage StressChecker completed in 7.36s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.06s
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
nousresearch-hermes-2-pr_1418_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nousresearch-hermes-2-pr_1418_v2
Running pipeline stage ISVCDeleter
Checking if service nousresearch-hermes-2-pr-1418-v2 is running
Tearing down inference service nousresearch-hermes-2-pr-1418-v2
Toredown service nousresearch-hermes-2-pr-1418-v2
Pipeline stage ISVCDeleter completed in 2.95s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-hermes-2-pr-1418-v2/added_tokens.json from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v2/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v2/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nousresearch-hermes-2-pr-1418-v2_reward/config.json from bucket guanaco-reward-models
Deleting key nousresearch-hermes-2-pr-1418-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key nousresearch-hermes-2-pr-1418-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nousresearch-hermes-2-pr-1418-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nousresearch-hermes-2-pr-1418-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nousresearch-hermes-2-pr-1418-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nousresearch-hermes-2-pr-1418-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.93s
nousresearch-hermes-2-pr_1418_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics