submission_id: chaiml-phase2-winner-13b2_v274
developer_uid: chai_backend_admin
status: inactive
model_repo: ChaiML/phase2_winner_13b2
reward_repo: rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
generation_params: {'temperature': 1.0733671330918084, 'top_p': 0.6971846333941389, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.312882778758545, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 156}
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': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:'}
timestamp: 2024-03-31T01:29:04+00:00
model_name: chaiml-phase2-winner-156
model_eval_status: success
safety_score: 0.98
entertaining: 7.14
stay_in_character: 8.4
user_preference: 7.46
double_thumbs_up: 240
thumbs_up: 348
thumbs_down: 175
num_battles: 24913
num_wins: 12957
win_ratio: 0.5200899128968811
celo_rating: 1168.46
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-phase2-winner-13b2-v274-mkmlizer
Waiting for job on chaiml-phase2-winner-13b2-v274-mkmlizer to finish
chaiml-phase2-winner-13b2-v274-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ _____ __ __ ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ /___/ ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ Version: 0.6.11 ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ belonging to: ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ Chai Research Corp. ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v274-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-phase2-winner-13b2-v274-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.1MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: README.md: 0%| | 0.00/1.53k [00:00<?, ?B/s] README.md: 100%|██████████| 1.53k/1.53k [00:00<00:00, 10.2MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: config.json: 0%| | 0.00/651 [00:00<?, ?B/s] config.json: 100%|██████████| 651/651 [00:00<00:00, 10.8MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: generation_config.json: 0%| | 0.00/170 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 170/170 [00:00<00:00, 2.82MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: pytorch_model-00001-of-00003.bin: 0%| | 0.00/9.95G [00:00<?, ?B/s] pytorch_model-00001-of-00003.bin: 0%| | 10.5M/9.95G [00:00<01:51, 89.4MB/s] pytorch_model-00001-of-00003.bin: 1%|▏ | 126M/9.95G [00:00<00:16, 595MB/s] pytorch_model-00001-of-00003.bin: 2%|▏ | 241M/9.95G [00:00<00:12, 770MB/s] pytorch_model-00001-of-00003.bin: 4%|▎ | 357M/9.95G [00:00<00:10, 873MB/s] pytorch_model-00001-of-00003.bin: 5%|▍ | 472M/9.95G [00:00<00:09, 957MB/s] pytorch_model-00001-of-00003.bin: 6%|▌ | 577M/9.95G [00:00<00:10, 879MB/s] pytorch_model-00001-of-00003.bin: 8%|▊ | 797M/9.95G [00:00<00:07, 1.26GB/s] pytorch_model-00001-of-00003.bin: 11%|█ | 1.07G/9.95G [00:00<00:05, 1.68GB/s] pytorch_model-00001-of-00003.bin: 14%|█▍ | 1.43G/9.95G [00:01<00:03, 2.17GB/s] pytorch_model-00001-of-00003.bin: 17%|█▋ | 1.66G/9.95G [00:01<00:04, 1.80GB/s] pytorch_model-00001-of-00003.bin: 19%|█▉ | 1.91G/9.95G [00:01<00:04, 1.93GB/s] pytorch_model-00001-of-00003.bin: 21%|██▏ | 2.12G/9.95G [00:01<00:04, 1.82GB/s] pytorch_model-00001-of-00003.bin: 25%|██▌ | 2.52G/9.95G [00:01<00:03, 2.31GB/s] pytorch_model-00001-of-00003.bin: 28%|██▊ | 2.77G/9.95G [00:01<00:03, 2.34GB/s] pytorch_model-00001-of-00003.bin: 30%|███ | 3.03G/9.95G [00:01<00:02, 2.41GB/s] pytorch_model-00001-of-00003.bin: 33%|███▎ | 3.28G/9.95G [00:01<00:03, 1.91GB/s] pytorch_model-00001-of-00003.bin: 35%|███▌ | 3.50G/9.95G [00:02<00:03, 1.95GB/s] pytorch_model-00001-of-00003.bin: 39%|███▉ | 3.87G/9.95G [00:02<00:02, 2.37GB/s] pytorch_model-00001-of-00003.bin: 42%|████▏ | 4.13G/9.95G [00:02<00:02, 2.13GB/s] pytorch_model-00001-of-00003.bin: 44%|████▍ | 4.37G/9.95G [00:02<00:02, 2.17GB/s] pytorch_model-00001-of-00003.bin: 46%|████▋ | 4.60G/9.95G [00:02<00:02, 2.11GB/s] pytorch_model-00001-of-00003.bin: 48%|████▊ | 4.82G/9.95G [00:02<00:02, 2.09GB/s] pytorch_model-00001-of-00003.bin: 51%|█████ | 5.04G/9.95G [00:02<00:02, 1.95GB/s] pytorch_model-00001-of-00003.bin: 53%|█████▎ | 5.30G/9.95G [00:02<00:02, 2.05GB/s] pytorch_model-00001-of-00003.bin: 56%|█████▋ | 5.61G/9.95G [00:02<00:01, 2.33GB/s] pytorch_model-00001-of-00003.bin: 59%|█████▉ | 5.85G/9.95G [00:03<00:01, 2.17GB/s] pytorch_model-00001-of-00003.bin: 61%|██████ | 6.08G/9.95G [00:03<00:01, 2.18GB/s] pytorch_model-00001-of-00003.bin: 63%|██████▎ | 6.31G/9.95G [00:03<00:01, 2.13GB/s] pytorch_model-00001-of-00003.bin: 67%|██████▋ | 6.62G/9.95G [00:03<00:01, 2.35GB/s] pytorch_model-00001-of-00003.bin: 69%|██████▉ | 6.86G/9.95G [00:03<00:01, 2.22GB/s] pytorch_model-00001-of-00003.bin: 71%|███████ | 7.09G/9.95G [00:03<00:01, 2.19GB/s] pytorch_model-00001-of-00003.bin: 74%|███████▎ | 7.32G/9.95G [00:03<00:01, 2.06GB/s] pytorch_model-00001-of-00003.bin: 76%|███████▌ | 7.53G/9.95G [00:03<00:01, 2.02GB/s] pytorch_model-00001-of-00003.bin: 78%|███████▊ | 7.74G/9.95G [00:04<00:01, 1.97GB/s] pytorch_model-00001-of-00003.bin: 81%|████████ | 8.07G/9.95G [00:04<00:00, 2.33GB/s] pytorch_model-00001-of-00003.bin: 84%|████████▎ | 8.32G/9.95G [00:04<00:00, 2.26GB/s] pytorch_model-00001-of-00003.bin: 86%|████████▌ | 8.55G/9.95G [00:04<00:00, 2.17GB/s] pytorch_model-00001-of-00003.bin: 88%|████████▊ | 8.77G/9.95G [00:04<00:00, 2.05GB/s] pytorch_model-00001-of-00003.bin: 91%|█████████ | 9.01G/9.95G [00:04<00:00, 2.15GB/s] pytorch_model-00001-of-00003.bin: 93%|█████████▎| 9.24G/9.95G [00:04<00:00, 2.16GB/s] pytorch_model-00001-of-00003.bin: 96%|█████████▌| 9.57G/9.95G [00:04<00:00, 2.40GB/s] pytorch_model-00001-of-00003.bin: 99%|█████████▊| 9.82G/9.95G [00:05<00:00, 1.54GB/s] pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.95G/9.95G [00:05<00:00, 1.86GB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: pytorch_model-00002-of-00003.bin: 0%| | 0.00/9.90G [00:00<?, ?B/s] pytorch_model-00002-of-00003.bin: 0%| | 10.5M/9.90G [00:00<02:01, 81.1MB/s] pytorch_model-00002-of-00003.bin: 2%|▏ | 157M/9.90G [00:00<00:13, 726MB/s] pytorch_model-00002-of-00003.bin: 3%|▎ | 294M/9.90G [00:00<00:10, 948MB/s] pytorch_model-00002-of-00003.bin: 4%|▍ | 430M/9.90G [00:00<00:08, 1.07GB/s] pytorch_model-00002-of-00003.bin: 6%|▌ | 598M/9.90G [00:00<00:07, 1.25GB/s] pytorch_model-00002-of-00003.bin: 8%|▊ | 765M/9.90G [00:00<00:06, 1.37GB/s] pytorch_model-00002-of-00003.bin: 10%|▉ | 986M/9.90G [00:00<00:05, 1.62GB/s] pytorch_model-00002-of-00003.bin: 13%|█▎ | 1.30G/9.90G [00:00<00:04, 2.09GB/s] pytorch_model-00002-of-00003.bin: 15%|█▌ | 1.52G/9.90G [00:00<00:03, 2.10GB/s] pytorch_model-00002-of-00003.bin: 18%|█▊ | 1.79G/9.90G [00:01<00:03, 2.25GB/s] pytorch_model-00002-of-00003.bin: 20%|██ | 2.02G/9.90G [00:01<00:03, 2.13GB/s] pytorch_model-00002-of-00003.bin: 23%|██▎ | 2.31G/9.90G [00:01<00:03, 2.32GB/s] pytorch_model-00002-of-00003.bin: 26%|██▌ | 2.59G/9.90G [00:01<00:03, 2.42GB/s] pytorch_model-00002-of-00003.bin: 29%|██▉ | 2.89G/9.90G [00:01<00:02, 2.59GB/s] pytorch_model-00002-of-00003.bin: 32%|███▏ | 3.16G/9.90G [00:01<00:02, 2.41GB/s] pytorch_model-00002-of-00003.bin: 35%|███▍ | 3.42G/9.90G [00:01<00:02, 2.45GB/s] pytorch_model-00002-of-00003.bin: 38%|███▊ | 3.73G/9.90G [00:01<00:02, 2.51GB/s] pytorch_model-00002-of-00003.bin: 40%|████ | 4.00G/9.90G [00:01<00:02, 2.47GB/s] pytorch_model-00002-of-00003.bin: 43%|████▎ | 4.28G/9.90G [00:02<00:02, 2.41GB/s] pytorch_model-00002-of-00003.bin: 47%|████▋ | 4.61G/9.90G [00:02<00:02, 2.62GB/s] pytorch_model-00002-of-00003.bin: 49%|████▉ | 4.89G/9.90G [00:02<00:02, 2.46GB/s] pytorch_model-00002-of-00003.bin: 52%|█████▏ | 5.14G/9.90G [00:02<00:02, 2.25GB/s] pytorch_model-00002-of-00003.bin: 55%|█████▌ | 5.45G/9.90G [00:02<00:01, 2.46GB/s] pytorch_model-00002-of-00003.bin: 58%|█████▊ | 5.76G/9.90G [00:02<00:01, 2.60GB/s] pytorch_model-00002-of-00003.bin: 61%|██████ | 6.03G/9.90G [00:02<00:01, 2.22GB/s] pytorch_model-00002-of-00003.bin: 63%|██████▎ | 6.27G/9.90G [00:02<00:01, 2.08GB/s] pytorch_model-00002-of-00003.bin: 66%|██████▌ | 6.49G/9.90G [00:03<00:01, 1.92GB/s] pytorch_model-00002-of-00003.bin: 68%|██████▊ | 6.75G/9.90G [00:03<00:01, 2.08GB/s] pytorch_model-00002-of-00003.bin: 71%|███████ | 7.01G/9.90G [00:03<00:01, 2.21GB/s] pytorch_model-00002-of-00003.bin: 73%|███████▎ | 7.25G/9.90G [00:03<00:01, 2.05GB/s] pytorch_model-00002-of-00003.bin: 75%|███████▌ | 7.47G/9.90G [00:03<00:01, 2.06GB/s] pytorch_model-00002-of-00003.bin: 78%|███████▊ | 7.69G/9.90G [00:03<00:01, 2.01GB/s] pytorch_model-00002-of-00003.bin: 80%|███████▉ | 7.91G/9.90G [00:03<00:00, 2.05GB/s] pytorch_model-00002-of-00003.bin: 82%|████████▏ | 8.12G/9.90G [00:03<00:00, 1.93GB/s] pytorch_model-00002-of-00003.bin: 84%|████████▍ | 8.34G/9.90G [00:04<00:00, 2.01GB/s] pytorch_model-00002-of-00003.bin: 86%|████████▋ | 8.57G/9.90G [00:04<00:00, 2.08GB/s] pytorch_model-00002-of-00003.bin: 89%|████████▉ | 8.81G/9.90G [00:04<00:00, 2.17GB/s] pytorch_model-00002-of-00003.bin: 91%|█████████▏| 9.06G/9.90G [00:04<00:00, 2.26GB/s] pytorch_model-00002-of-00003.bin: 96%|█████████▌| 9.51G/9.90G [00:04<00:00, 2.90GB/s] pytorch_model-00002-of-00003.bin: 99%|█████████▉| 9.81G/9.90G [00:04<00:00, 2.19GB/s] pytorch_model-00002-of-00003.bin: 100%|█████████▉| 9.90G/9.90G [00:05<00:00, 1.90GB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: pytorch_model-00003-of-00003.bin: 0%| | 0.00/6.18G [00:00<?, ?B/s] pytorch_model-00003-of-00003.bin: 0%| | 10.5M/6.18G [00:00<01:15, 82.0MB/s] pytorch_model-00003-of-00003.bin: 1%| | 73.4M/6.18G [00:00<00:16, 368MB/s] pytorch_model-00003-of-00003.bin: 4%|▎ | 220M/6.18G [00:00<00:07, 815MB/s] pytorch_model-00003-of-00003.bin: 5%|▌ | 325M/6.18G [00:00<00:06, 887MB/s] pytorch_model-00003-of-00003.bin: 7%|▋ | 419M/6.18G [00:00<00:06, 823MB/s] pytorch_model-00003-of-00003.bin: 12%|█▏ | 765M/6.18G [00:00<00:03, 1.63GB/s] pytorch_model-00003-of-00003.bin: 16%|█▌ | 996M/6.18G [00:00<00:02, 1.82GB/s] pytorch_model-00003-of-00003.bin: 21%|██▏ | 1.32G/6.18G [00:00<00:02, 2.23GB/s] pytorch_model-00003-of-00003.bin: 25%|██▌ | 1.55G/6.18G [00:01<00:02, 1.94GB/s] pytorch_model-00003-of-00003.bin: 30%|███ | 1.86G/6.18G [00:01<00:01, 2.22GB/s] pytorch_model-00003-of-00003.bin: 34%|███▍ | 2.11G/6.18G [00:01<00:01, 2.30GB/s] pytorch_model-00003-of-00003.bin: 39%|███▉ | 2.43G/6.18G [00:01<00:01, 2.56GB/s] pytorch_model-00003-of-00003.bin: 44%|████▍ | 2.71G/6.18G [00:01<00:01, 2.39GB/s] pytorch_model-00003-of-00003.bin: 48%|████▊ | 2.96G/6.18G [00:01<00:01, 2.42GB/s] pytorch_model-00003-of-00003.bin: 52%|█████▏ | 3.21G/6.18G [00:01<00:01, 2.31GB/s] pytorch_model-00003-of-00003.bin: 56%|█████▌ | 3.45G/6.18G [00:01<00:01, 1.95GB/s] pytorch_model-00003-of-00003.bin: 62%|██████▏ | 3.82G/6.18G [00:01<00:01, 2.34GB/s] pytorch_model-00003-of-00003.bin: 66%|██████▌ | 4.08G/6.18G [00:02<00:00, 2.39GB/s] pytorch_model-00003-of-00003.bin: 71%|███████ | 4.38G/6.18G [00:02<00:00, 2.52GB/s] pytorch_model-00003-of-00003.bin: 75%|███████▌ | 4.65G/6.18G [00:02<00:00, 2.55GB/s] pytorch_model-00003-of-00003.bin: 79%|███████▉ | 4.91G/6.18G [00:02<00:00, 2.48GB/s] pytorch_model-00003-of-00003.bin: 85%|████████▍ | 5.24G/6.18G [00:02<00:00, 2.71GB/s] pytorch_model-00003-of-00003.bin: 89%|████████▉ | 5.53G/6.18G [00:02<00:00, 2.74GB/s] pytorch_model-00003-of-00003.bin: 94%|█████████▍| 5.81G/6.18G [00:02<00:00, 2.02GB/s] pytorch_model-00003-of-00003.bin: 98%|█████████▊| 6.05G/6.18G [00:03<00:00, 1.17GB/s] pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.18G/6.18G [00:03<00:00, 1.61GB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: pytorch_model.bin.index.json: 0%| | 0.00/33.4k [00:00<?, ?B/s] pytorch_model.bin.index.json: 100%|██████████| 33.4k/33.4k [00:00<00:00, 35.7MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 3.19MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: tokenizer.json: 0%| | 0.00/1.84M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 17.2MB/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 17.1MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: tokenizer.model: 0%| | 0.00/500k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 49.3MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: tokenizer_config.json: 0%| | 0.00/725 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 725/725 [00:00<00:00, 9.08MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: Downloaded to shared memory in 16.759s
chaiml-phase2-winner-13b2-v274-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-phase2-winner-13b2-v274-mkmlizer: Saving mkml model at /dev/shm/model_cache
chaiml-phase2-winner-13b2-v274-mkmlizer: Reading /tmp/tmp8ns6ydxr/pytorch_model.bin.index.json
chaiml-phase2-winner-13b2-v274-mkmlizer: Profiling: 0%| | 0/363 [00:00<?, ?it/s] Profiling: 0%| | 1/363 [00:02<16:56, 2.81s/it] Profiling: 38%|███▊ | 139/363 [00:04<00:05, 39.56it/s] Profiling: 77%|███████▋ | 278/363 [00:05<00:01, 70.62it/s] Profiling: 100%|██████████| 363/363 [00:06<00:00, 65.90it/s] Profiling: 100%|██████████| 363/363 [00:06<00:00, 54.22it/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: quantized model in 23.943s
chaiml-phase2-winner-13b2-v274-mkmlizer: Processed model ChaiML/phase2_winner_13b2 in 42.199s
chaiml-phase2-winner-13b2-v274-mkmlizer: creating bucket guanaco-mkml-models
chaiml-phase2-winner-13b2-v274-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-phase2-winner-13b2-v274-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v274
chaiml-phase2-winner-13b2-v274-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v274/config.json
chaiml-phase2-winner-13b2-v274-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v274/tokenizer.model
chaiml-phase2-winner-13b2-v274-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v274/special_tokens_map.json
chaiml-phase2-winner-13b2-v274-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v274/tokenizer.json
chaiml-phase2-winner-13b2-v274-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v274/tokenizer_config.json
chaiml-phase2-winner-13b2-v274-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v274/mkml_model.tensors
chaiml-phase2-winner-13b2-v274-mkmlizer: loading reward model from rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
chaiml-phase2-winner-13b2-v274-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.
chaiml-phase2-winner-13b2-v274-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v274-mkmlizer: config.json: 0%| | 0.00/983 [00:00<?, ?B/s] config.json: 100%|██████████| 983/983 [00:00<00:00, 9.06MB/s]
chaiml-phase2-winner-13b2-v274-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.
chaiml-phase2-winner-13b2-v274-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v274-mkmlizer: tokenizer_config.json: 0%| | 0.00/445 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 445/445 [00:00<00:00, 5.13MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: vocab.json: 0%| | 0.00/798k [00:00<?, ?B/s] vocab.json: 100%|██████████| 798k/798k [00:00<00:00, 67.6MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: merges.txt: 0%| | 0.00/456k [00:00<?, ?B/s] merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 105MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 34.8MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: special_tokens_map.json: 0%| | 0.00/441 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 441/441 [00:00<00:00, 4.72MB/s]
chaiml-phase2-winner-13b2-v274-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.
chaiml-phase2-winner-13b2-v274-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v274-mkmlizer: model.safetensors.index.json: 0%| | 0.00/10.5k [00:00<?, ?B/s] model.safetensors.index.json: 100%|██████████| 10.5k/10.5k [00:00<00:00, 87.8MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: Downloading shards: 0%| | 0/1 [00:00<?, ?it/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: model-00001-of-00001.safetensors: 0%| | 0.00/249M [00:00<?, ?B/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: model-00001-of-00001.safetensors: 3%|▎ | 7.73M/249M [00:00<00:04, 58.8MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: model-00001-of-00001.safetensors: 79%|███████▉ | 196M/249M [00:00<00:00, 1.01GB/s]  model-00001-of-00001.safetensors: 100%|█████████▉| 249M/249M [00:00<00:00, 982MB/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: Downloading shards: 100%|██████████| 1/1 [00:00<00:00, 2.48it/s] Downloading shards: 100%|██████████| 1/1 [00:00<00:00, 2.48it/s]
chaiml-phase2-winner-13b2-v274-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-phase2-winner-13b2-v274-mkmlizer: Saving duration: 0.085s
chaiml-phase2-winner-13b2-v274-mkmlizer: Processed model rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99 in 1.963s
chaiml-phase2-winner-13b2-v274-mkmlizer: creating bucket guanaco-reward-models
chaiml-phase2-winner-13b2-v274-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-phase2-winner-13b2-v274-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v274_reward
chaiml-phase2-winner-13b2-v274-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v274_reward/special_tokens_map.json
chaiml-phase2-winner-13b2-v274-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v274_reward/config.json
chaiml-phase2-winner-13b2-v274-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v274_reward/tokenizer_config.json
chaiml-phase2-winner-13b2-v274-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v274_reward/vocab.json
chaiml-phase2-winner-13b2-v274-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v274_reward/merges.txt
chaiml-phase2-winner-13b2-v274-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v274_reward/tokenizer.json
chaiml-phase2-winner-13b2-v274-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v274_reward/reward.tensors
Job chaiml-phase2-winner-13b2-v274-mkmlizer completed after 99.98s with status: succeeded
Stopping job with name chaiml-phase2-winner-13b2-v274-mkmlizer
Pipeline stage MKMLizer completed in 103.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-phase2-winner-13b2-v274
Waiting for inference service chaiml-phase2-winner-13b2-v274 to be ready
Inference service chaiml-phase2-winner-13b2-v274 ready after 50.29922533035278s
Pipeline stage ISVCDeployer completed in 57.87s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.205509901046753s
Received healthy response to inference request in 3.5954055786132812s
Received healthy response to inference request in 1.7663960456848145s
Received healthy response to inference request in 1.459604024887085s
Received healthy response to inference request in 2.1628127098083496s
5 requests
0 failed requests
5th percentile: 1.5209624290466308
10th percentile: 1.5823208332061767
20th percentile: 1.7050376415252686
30th percentile: 1.8456793785095216
40th percentile: 2.0042460441589354
50th percentile: 2.1628127098083496
60th percentile: 2.179891586303711
70th percentile: 2.1969704627990723
80th percentile: 2.4834890365600586
90th percentile: 3.03944730758667
95th percentile: 3.3174264430999756
99th percentile: 3.53980975151062
mean time: 2.2379456520080567
Pipeline stage StressChecker completed in 12.11s
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
chaiml-phase2-winner-13b2_v274 status is now deployed due to DeploymentManager action
chaiml-phase2-winner-13b2_v274 status is now inactive due to admin request
chaiml-phase2-winner-13b2_v274 status is now deployed due to admin request
chaiml-phase2-winner-13b2_v274 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics