submission_id: inv-konstanta-v4-alpha-7b_v2
developer_uid: Inv
status: torndown
model_repo: Inv/Konstanta-V4-Alpha-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'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': 'This is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nPlay the role of {bot_name}. Engage in a chat with {user_name} while staying in character. You should create a fun dialogue which entertains {user_name}.\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####\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: 2024-03-24T15:37:11+00:00
model_name: inv-konstanta-v4-alpha-7b_v2
model_eval_status: success
model_group: Inv/Konstanta-V4-Alpha-7
num_battles: 112002
num_wins: 59851
celo_rating: 1181.81
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: None
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: inv-konstanta-v4-alpha-7b_v2
ineligible_reason: propriety_total_count < 800
language_model: Inv/Konstanta-V4-Alpha-7B
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-03-24
win_ratio: 0.5343743861716755
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name inv-konstanta-v4-alpha-7b-v2-mkmlizer
Waiting for job on inv-konstanta-v4-alpha-7b-v2-mkmlizer to finish
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.8MB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
README.md:   0%|          | 0.00/1.17k [00:00<?, ?B/s]
README.md: 100%|██████████| 1.17k/1.17k [00:00<00:00, 15.5MB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
config.json:   0%|          | 0.00/632 [00:00<?, ?B/s]
config.json: 100%|██████████| 632/632 [00:00<00:00, 8.47MB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
mergekit_config.yml:   0%|          | 0.00/410 [00:00<?, ?B/s]
mergekit_config.yml: 100%|██████████| 410/410 [00:00<00:00, 5.49MB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
model-00001-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]
model-00001-of-00008.safetensors:   1%|          | 10.5M/1.98G [00:00<00:27, 70.6MB/s]
model-00001-of-00008.safetensors:   1%|          | 21.0M/1.98G [00:00<00:45, 43.1MB/s]
model-00001-of-00008.safetensors:   3%|▎         | 52.4M/1.98G [00:00<00:17, 113MB/s] 
model-00001-of-00008.safetensors:   4%|▍         | 83.9M/1.98G [00:00<00:13, 142MB/s]
model-00001-of-00008.safetensors:   6%|▋         | 126M/1.98G [00:00<00:09, 195MB/s] 
model-00001-of-00008.safetensors:  11%|█         | 210M/1.98G [00:00<00:05, 344MB/s]
model-00001-of-00008.safetensors:  13%|█▎        | 252M/1.98G [00:01<00:05, 340MB/s]
model-00001-of-00008.safetensors:  17%|█▋        | 336M/1.98G [00:01<00:04, 375MB/s]
model-00001-of-00008.safetensors:  22%|██▏       | 440M/1.98G [00:01<00:02, 526MB/s]
model-00001-of-00008.safetensors:  26%|██▌       | 514M/1.98G [00:01<00:02, 554MB/s]
model-00001-of-00008.safetensors:  29%|██▉       | 577M/1.98G [00:01<00:02, 562MB/s]
model-00001-of-00008.safetensors:  32%|███▏      | 640M/1.98G [00:01<00:02, 569MB/s]
model-00001-of-00008.safetensors:  37%|███▋      | 724M/1.98G [00:01<00:02, 575MB/s]
model-00001-of-00008.safetensors:  41%|████      | 807M/1.98G [00:01<00:01, 629MB/s]
model-00001-of-00008.safetensors:  44%|████▍     | 881M/1.98G [00:02<00:01, 638MB/s]
model-00001-of-00008.safetensors:  49%|████▊     | 963M/1.98G [00:02<00:01, 602MB/s]
model-00001-of-00008.safetensors:  56%|█████▌    | 1.11G/1.98G [00:02<00:01, 802MB/s]
model-00001-of-00008.safetensors:  64%|██████▍   | 1.27G/1.98G [00:02<00:00, 949MB/s]
model-00001-of-00008.safetensors:  74%|███████▎  | 1.46G/1.98G [00:02<00:00, 1.18GB/s]
model-00001-of-00008.safetensors:  80%|████████  | 1.59G/1.98G [00:02<00:00, 1.23GB/s]
model-00001-of-00008.safetensors:  97%|█████████▋| 1.92G/1.98G [00:02<00:00, 1.79GB/s]
model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:03<00:00, 619MB/s] 
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
model-00002-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]
model-00002-of-00008.safetensors:   1%|          | 10.5M/1.95G [00:00<01:12, 26.7MB/s]
model-00002-of-00008.safetensors:   2%|▏         | 31.5M/1.95G [00:00<00:32, 59.5MB/s]
model-00002-of-00008.safetensors:   4%|▍         | 83.9M/1.95G [00:00<00:11, 164MB/s] 
model-00002-of-00008.safetensors:   8%|▊         | 157M/1.95G [00:00<00:06, 260MB/s] 
model-00002-of-00008.safetensors:  12%|█▏        | 231M/1.95G [00:00<00:04, 370MB/s]
model-00002-of-00008.safetensors:  15%|█▍        | 283M/1.95G [00:01<00:04, 391MB/s]
model-00002-of-00008.safetensors:  19%|█▉        | 367M/1.95G [00:01<00:03, 472MB/s]
model-00002-of-00008.safetensors:  24%|██▎       | 461M/1.95G [00:01<00:02, 568MB/s]
model-00002-of-00008.safetensors:  27%|██▋       | 524M/1.95G [00:01<00:02, 556MB/s]
model-00002-of-00008.safetensors:  31%|███       | 608M/1.95G [00:01<00:02, 576MB/s]
model-00002-of-00008.safetensors:  35%|███▌      | 682M/1.95G [00:01<00:02, 555MB/s]
model-00002-of-00008.safetensors:  38%|███▊      | 744M/1.95G [00:01<00:02, 554MB/s]
model-00002-of-00008.safetensors:  45%|████▌     | 881M/1.95G [00:01<00:01, 744MB/s]
model-00002-of-00008.safetensors:  50%|████▉     | 965M/1.95G [00:02<00:01, 765MB/s]
model-00002-of-00008.safetensors:  54%|█████▍    | 1.05G/1.95G [00:02<00:01, 787MB/s]
model-00002-of-00008.safetensors:  62%|██████▏   | 1.20G/1.95G [00:02<00:00, 949MB/s]
model-00002-of-00008.safetensors:  71%|███████   | 1.38G/1.95G [00:02<00:00, 1.17GB/s]
model-00002-of-00008.safetensors:  77%|███████▋  | 1.51G/1.95G [00:02<00:00, 1.18GB/s]
model-00002-of-00008.safetensors:  90%|█████████ | 1.76G/1.95G [00:02<00:00, 1.55GB/s]
model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:02<00:00, 734MB/s] 
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
model-00004-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]
model-00004-of-00008.safetensors:   1%|          | 10.5M/1.95G [00:00<01:26, 22.4MB/s]
model-00004-of-00008.safetensors:   2%|▏         | 31.5M/1.95G [00:00<00:29, 66.0MB/s]
model-00004-of-00008.safetensors:   4%|▍         | 83.9M/1.95G [00:00<00:12, 150MB/s] 
model-00004-of-00008.safetensors:   8%|▊         | 147M/1.95G [00:00<00:06, 258MB/s] 
model-00004-of-00008.safetensors:  27%|██▋       | 524M/1.95G [00:00<00:01, 1.12GB/s]
model-00004-of-00008.safetensors:  47%|████▋     | 912M/1.95G [00:01<00:00, 1.82GB/s]
model-00004-of-00008.safetensors:  60%|██████    | 1.17G/1.95G [00:01<00:00, 2.04GB/s]
model-00004-of-00008.safetensors:  74%|███████▎  | 1.43G/1.95G [00:01<00:00, 2.18GB/s]
model-00004-of-00008.safetensors:  87%|████████▋ | 1.68G/1.95G [00:01<00:00, 2.21GB/s]
model-00004-of-00008.safetensors:  99%|█████████▉| 1.93G/1.95G [00:01<00:00, 1.98GB/s]
model-00004-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.20GB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
model-00005-of-00008.safetensors:   0%|          | 0.00/1.89G [00:00<?, ?B/s]
model-00005-of-00008.safetensors:   1%|          | 10.5M/1.89G [00:00<01:58, 15.8MB/s]
model-00005-of-00008.safetensors:   4%|▍         | 83.9M/1.89G [00:00<00:14, 125MB/s] 
model-00005-of-00008.safetensors:  11%|█         | 210M/1.89G [00:00<00:05, 323MB/s] 
model-00005-of-00008.safetensors:  15%|█▍        | 283M/1.89G [00:01<00:04, 347MB/s]
model-00005-of-00008.safetensors:  23%|██▎       | 440M/1.89G [00:01<00:02, 571MB/s]
model-00005-of-00008.safetensors:  28%|██▊       | 524M/1.89G [00:01<00:02, 557MB/s]
model-00005-of-00008.safetensors:  33%|███▎      | 619M/1.89G [00:01<00:02, 624MB/s]
model-00005-of-00008.safetensors:  37%|███▋      | 703M/1.89G [00:01<00:01, 616MB/s]
model-00005-of-00008.safetensors:  45%|████▍     | 849M/1.89G [00:01<00:01, 798MB/s]
model-00005-of-00008.safetensors:  53%|█████▎    | 1.01G/1.89G [00:01<00:00, 981MB/s]
model-00005-of-00008.safetensors:  62%|██████▏   | 1.17G/1.89G [00:01<00:00, 1.10GB/s]
model-00005-of-00008.safetensors:  70%|███████   | 1.32G/1.89G [00:02<00:00, 1.22GB/s]
model-00005-of-00008.safetensors:  82%|████████▏ | 1.54G/1.89G [00:02<00:00, 1.45GB/s]
model-00005-of-00008.safetensors:  98%|█████████▊| 1.85G/1.89G [00:02<00:00, 1.84GB/s]
model-00005-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:02<00:00, 750MB/s] 
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
model-00006-of-00008.safetensors:   0%|          | 0.00/1.92G [00:00<?, ?B/s]
model-00006-of-00008.safetensors:   1%|          | 10.5M/1.92G [00:00<01:11, 26.8MB/s]
model-00006-of-00008.safetensors:   5%|▌         | 105M/1.92G [00:00<00:10, 181MB/s]  
model-00006-of-00008.safetensors:  16%|█▋        | 315M/1.92G [00:00<00:02, 567MB/s]
model-00006-of-00008.safetensors:  29%|██▉       | 556M/1.92G [00:00<00:01, 978MB/s]
model-00006-of-00008.safetensors:  38%|███▊      | 724M/1.92G [00:01<00:01, 841MB/s]
model-00006-of-00008.safetensors:  44%|████▍     | 849M/1.92G [00:01<00:01, 799MB/s]
model-00006-of-00008.safetensors:  52%|█████▏    | 996M/1.92G [00:01<00:01, 919MB/s]
model-00006-of-00008.safetensors:  59%|█████▊    | 1.13G/1.92G [00:01<00:00, 1.00GB/s]
model-00006-of-00008.safetensors:  65%|██████▌   | 1.25G/1.92G [00:01<00:00, 947MB/s] 
model-00006-of-00008.safetensors:  73%|███████▎  | 1.41G/1.92G [00:01<00:00, 1.09GB/s]
model-00006-of-00008.safetensors:  96%|█████████▌| 1.84G/1.92G [00:01<00:00, 1.89GB/s]
model-00006-of-00008.safetensors: 100%|█████████▉| 1.92G/1.92G [00:05<00:00, 379MB/s] 
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
model-00007-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]
model-00007-of-00008.safetensors:   1%|          | 10.5M/1.95G [00:00<01:03, 30.6MB/s]
model-00007-of-00008.safetensors:   5%|▍         | 94.4M/1.95G [00:00<00:07, 256MB/s] 
model-00007-of-00008.safetensors:   8%|▊         | 147M/1.95G [00:00<00:05, 301MB/s] 
model-00007-of-00008.safetensors:  11%|█         | 210M/1.95G [00:00<00:04, 389MB/s]
model-00007-of-00008.safetensors:  16%|█▌        | 315M/1.95G [00:00<00:03, 505MB/s]
model-00007-of-00008.safetensors:  19%|█▉        | 377M/1.95G [00:01<00:03, 457MB/s]
model-00007-of-00008.safetensors:  28%|██▊       | 545M/1.95G [00:01<00:01, 715MB/s]
model-00007-of-00008.safetensors:  32%|███▏      | 629M/1.95G [00:01<00:01, 735MB/s]
model-00007-of-00008.safetensors:  37%|███▋      | 713M/1.95G [00:01<00:01, 631MB/s]
model-00007-of-00008.safetensors:  43%|████▎     | 828M/1.95G [00:01<00:01, 747MB/s]
model-00007-of-00008.safetensors:  47%|████▋     | 912M/1.95G [00:01<00:01, 721MB/s]
model-00007-of-00008.safetensors:  55%|█████▌    | 1.08G/1.95G [00:01<00:00, 870MB/s]
model-00007-of-00008.safetensors:  61%|██████    | 1.18G/1.95G [00:01<00:00, 886MB/s]
model-00007-of-00008.safetensors:  66%|██████▌   | 1.28G/1.95G [00:01<00:00, 900MB/s]
model-00007-of-00008.safetensors:  74%|███████▍  | 1.44G/1.95G [00:02<00:00, 1.10GB/s]
model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:02<00:00, 1.79GB/s]
model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:02<00:00, 838MB/s] 
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
model-00008-of-00008.safetensors:   0%|          | 0.00/872M [00:00<?, ?B/s]
model-00008-of-00008.safetensors:   1%|          | 10.5M/872M [00:00<00:13, 62.3MB/s]
model-00008-of-00008.safetensors:   8%|▊         | 73.4M/872M [00:00<00:03, 260MB/s] 
model-00008-of-00008.safetensors:  12%|█▏        | 107M/872M [00:00<00:02, 265MB/s] 
model-00008-of-00008.safetensors:  22%|██▏       | 191M/872M [00:00<00:01, 441MB/s]
model-00008-of-00008.safetensors:  36%|███▋      | 317M/872M [00:00<00:00, 681MB/s]
model-00008-of-00008.safetensors:  59%|█████▉    | 516M/872M [00:00<00:00, 1.06GB/s]
model-00008-of-00008.safetensors:  82%|████████▏ | 715M/872M [00:00<00:00, 1.26GB/s]
model-00008-of-00008.safetensors:  98%|█████████▊| 851M/872M [00:01<00:00, 561MB/s] 
model-00008-of-00008.safetensors: 100%|█████████▉| 872M/872M [00:02<00:00, 326MB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
model.safetensors.index.json:   0%|          | 0.00/22.8k [00:00<?, ?B/s]
model.safetensors.index.json: 100%|██████████| 22.8k/22.8k [00:00<00:00, 149MB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/414 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 6.22MB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
tokenizer.json:   0%|          | 0.00/1.80M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 17.7MB/s]
tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 17.6MB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
tokenizer.model:   0%|          | 0.00/493k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 25.4MB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/967 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 15.8MB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: Downloaded to shared memory in 26.219s
inv-konstanta-v4-alpha-7b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
inv-konstanta-v4-alpha-7b-v2-mkmlizer: Saving mkml model at /dev/shm/model_cache
inv-konstanta-v4-alpha-7b-v2-mkmlizer: Reading /tmp/tmpjaxe198m/model.safetensors.index.json
inv-konstanta-v4-alpha-7b-v2-mkmlizer: quantized model in 15.873s
inv-konstanta-v4-alpha-7b-v2-mkmlizer: Processed model Inv/Konstanta-V4-Alpha-7B in 43.066s
inv-konstanta-v4-alpha-7b-v2-mkmlizer: creating bucket guanaco-mkml-models
inv-konstanta-v4-alpha-7b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
inv-konstanta-v4-alpha-7b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v2
inv-konstanta-v4-alpha-7b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v2/config.json
inv-konstanta-v4-alpha-7b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v2/special_tokens_map.json
inv-konstanta-v4-alpha-7b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v2/tokenizer_config.json
inv-konstanta-v4-alpha-7b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v2/tokenizer.json
inv-konstanta-v4-alpha-7b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v2/tokenizer.model
inv-konstanta-v4-alpha-7b-v2-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v2/mkml_model.tensors
inv-konstanta-v4-alpha-7b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
inv-konstanta-v4-alpha-7b-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.
inv-konstanta-v4-alpha-7b-v2-mkmlizer:   warnings.warn(
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
config.json:   0%|          | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 9.20MB/s]
inv-konstanta-v4-alpha-7b-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.
inv-konstanta-v4-alpha-7b-v2-mkmlizer:   warnings.warn(
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.80MB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
vocab.json:   0%|          | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 23.7MB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 21.6MB/s]
inv-konstanta-v4-alpha-7b-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.
inv-konstanta-v4-alpha-7b-v2-mkmlizer:   warnings.warn(
inv-konstanta-v4-alpha-7b-v2-mkmlizer: 
pytorch_model.bin:   0%|          | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin:   1%|          | 10.5M/1.44G [00:00<00:18, 77.6MB/s]
pytorch_model.bin:   4%|▎         | 52.4M/1.44G [00:00<00:05, 236MB/s] 
pytorch_model.bin:   6%|▌         | 83.9M/1.44G [00:00<00:09, 139MB/s]
pytorch_model.bin:  11%|█         | 157M/1.44G [00:00<00:05, 253MB/s] 
pytorch_model.bin:  25%|██▌       | 367M/1.44G [00:00<00:01, 673MB/s]
pytorch_model.bin:  39%|███▉      | 566M/1.44G [00:00<00:00, 997MB/s]
pytorch_model.bin:  49%|████▊     | 703M/1.44G [00:01<00:00, 900MB/s]
pytorch_model.bin:  60%|██████    | 868M/1.44G [00:01<00:00, 1.07GB/s]
pytorch_model.bin:  86%|████████▌ | 1.25G/1.44G [00:01<00:00, 1.74GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.04GB/s]
inv-konstanta-v4-alpha-7b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
inv-konstanta-v4-alpha-7b-v2-mkmlizer: Saving duration: 0.240s
inv-konstanta-v4-alpha-7b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.095s
inv-konstanta-v4-alpha-7b-v2-mkmlizer: creating bucket guanaco-reward-models
inv-konstanta-v4-alpha-7b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
inv-konstanta-v4-alpha-7b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v2_reward
inv-konstanta-v4-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v2_reward/config.json
inv-konstanta-v4-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v2_reward/tokenizer_config.json
inv-konstanta-v4-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v2_reward/special_tokens_map.json
inv-konstanta-v4-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v2_reward/merges.txt
inv-konstanta-v4-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v2_reward/tokenizer.json
inv-konstanta-v4-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v2_reward/vocab.json
inv-konstanta-v4-alpha-7b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v2_reward/reward.tensors
Job inv-konstanta-v4-alpha-7b-v2-mkmlizer completed after 127.36s with status: succeeded
Stopping job with name inv-konstanta-v4-alpha-7b-v2-mkmlizer
Pipeline stage MKMLizer completed in 130.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service inv-konstanta-v4-alpha-7b-v2
Waiting for inference service inv-konstanta-v4-alpha-7b-v2 to be ready
Inference service inv-konstanta-v4-alpha-7b-v2 ready after 60.455589294433594s
Pipeline stage ISVCDeployer completed in 67.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.712597131729126s
Received healthy response to inference request in 1.2016839981079102s
Received healthy response to inference request in 1.2010955810546875s
Received healthy response to inference request in 1.1842072010040283s
Received healthy response to inference request in 1.1766860485076904s
5 requests
0 failed requests
5th percentile: 1.178190279006958
10th percentile: 1.1796945095062257
20th percentile: 1.1827029705047607
30th percentile: 1.1875848770141602
40th percentile: 1.1943402290344238
50th percentile: 1.2010955810546875
60th percentile: 1.2013309478759766
70th percentile: 1.2015663146972657
80th percentile: 1.3038666248321533
90th percentile: 1.5082318782806396
95th percentile: 1.6104145050048828
99th percentile: 1.6921606063842773
mean time: 1.2952539920806885
Pipeline stage StressChecker completed in 7.82s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
inv-konstanta-v4-alpha-7b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of inv-konstanta-v4-alpha-7b_v2
Running pipeline stage ISVCDeleter
Checking if service inv-konstanta-v4-alpha-7b-v2 is running
Tearing down inference service inv-konstanta-v4-alpha-7b-v2
Toredown service inv-konstanta-v4-alpha-7b-v2
Pipeline stage ISVCDeleter completed in 3.83s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key inv-konstanta-v4-alpha-7b-v2/config.json from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v2/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key inv-konstanta-v4-alpha-7b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.75s
inv-konstanta-v4-alpha-7b_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics