developer_uid: Trace2333
submission_id: trace2333-duduk-llama3-v5_v1
model_name: trace2333-duduk-llama3-v5_v1
model_group: Trace2333/duduk_llama3_v
status: torndown
timestamp: 2024-07-31T03:39:51+00:00
num_battles: 10086
num_wins: 4460
celo_rating: 1168.35
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/duduk_llama3_v5
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: trace2333-duduk-llama3-v5_v1
is_internal_developer: False
language_model: Trace2333/duduk_llama3_v5
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-30
win_ratio: 0.4421971048978782
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.12, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.1, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\nYou: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name trace2333-duduk-llama3-v5-v1-mkmlizer
Waiting for job on trace2333-duduk-llama3-v5-v1-mkmlizer to finish
trace2333-duduk-llama3-v5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama3-v5-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║       /___/                                                         ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-elo-alignment-run-3_v17: ('http://chaiml-elo-alignment-run-3-v17-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:49388->127.0.0.1:8080: read: connection reset by peer\n')
trace2333-duduk-llama3-v5-v1-mkmlizer: Downloaded to shared memory in 60.954s
trace2333-duduk-llama3-v5-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptd2j0ash, device:0
trace2333-duduk-llama3-v5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Stopping job with name trace2333-duduk-llama3-v5-v1-mkmlizer
%s, retrying in %s seconds...
Stopping job with name trace2333-duduk-llama3-v5-v1-mkmlizer
%s, retrying in %s seconds...
Stopping job with name trace2333-duduk-llama3-v5-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name trace2333-duduk-llama3-v5-v1-mkmlizer
Waiting for job on trace2333-duduk-llama3-v5-v1-mkmlizer to finish
trace2333-duduk-llama3-v5-v1-mkmlizer: quantized model in 29.284s
trace2333-duduk-llama3-v5-v1-mkmlizer: Processed model Trace2333/duduk_llama3_v5 in 90.238s
trace2333-duduk-llama3-v5-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-duduk-llama3-v5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-duduk-llama3-v5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-duduk-llama3-v5-v1
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v5-v1/config.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v5-v1/special_tokens_map.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v5-v1/tokenizer_config.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v5-v1/tokenizer.json
trace2333-duduk-llama3-v5-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-duduk-llama3-v5-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 25.19it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 35.15it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 32.26it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 35.16it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 32.76it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:07, 37.06it/s]
Loading 0:  12%|█▏        | 34/291 [00:01<00:10, 25.26it/s]
Loading 0:  13%|█▎        | 38/291 [00:01<00:09, 26.18it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 23.44it/s]
Loading 0:  16%|█▌        | 46/291 [00:01<00:08, 28.69it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:09, 25.77it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:07, 30.82it/s]
Loading 0:  20%|██        | 59/291 [00:02<00:08, 27.77it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 34.37it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 33.11it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 32.93it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 32.60it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 23.53it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 24.18it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 28.34it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 28.36it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 32.19it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 31.61it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 35.00it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 33.54it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 33.44it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 37.59it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 35.21it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 29.72it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 29.17it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 27.58it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 31.72it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 31.27it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:03, 34.14it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:03, 33.27it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 36.02it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 34.23it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 36.71it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.89it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 39.63it/s]
Loading 0:  65%|██████▍   | 189/291 [00:06<00:04, 24.48it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 25.73it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 32.22it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 31.43it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 33.66it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 32.11it/s]
Loading 0:  75%|███████▌  | 219/291 [00:07<00:02, 34.44it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 32.94it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 34.01it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 33.73it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 26.71it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:01, 26.07it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.54it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 32.55it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 35.78it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 33.46it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 35.75it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 33.89it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 36.65it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 34.33it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 34.45it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.58it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.21it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama3-v5-v1-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v5-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama3-v5-v1-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v5-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama3-v5-v1-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v5-v1-mkmlizer: Saving duration: 1.430s
trace2333-duduk-llama3-v5-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.039s
trace2333-duduk-llama3-v5-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-duduk-llama3-v5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-duduk-llama3-v5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/config.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/special_tokens_map.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/tokenizer_config.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/merges.txt
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/vocab.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/tokenizer.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/reward.tensors
trace2333-duduk-llama3-v5-v1-mkmlizer: Downloaded to shared memory in 41.289s
trace2333-duduk-llama3-v5-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzpi22s0p, device:0
trace2333-duduk-llama3-v5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_nagok_2024-07-30: ('http://mistralai-mixtral-8x7b-3473-v95-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:51700->127.0.0.1:8080: read: connection reset by peer\n')
trace2333-duduk-llama3-v5-v1-mkmlizer: quantized model in 28.851s
trace2333-duduk-llama3-v5-v1-mkmlizer: Processed model Trace2333/duduk_llama3_v5 in 70.140s
trace2333-duduk-llama3-v5-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-duduk-llama3-v5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-duduk-llama3-v5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-duduk-llama3-v5-v1
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v5-v1/config.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v5-v1/special_tokens_map.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v5-v1/tokenizer_config.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v5-v1/tokenizer.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-duduk-llama3-v5-v1/flywheel_model.0.safetensors
trace2333-duduk-llama3-v5-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-duduk-llama3-v5-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.66it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 36.70it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:07, 34.58it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 37.01it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 34.48it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 41.09it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:11, 22.76it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 24.75it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 31.22it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 31.07it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 34.17it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.72it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 36.14it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 34.64it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 34.90it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 35.14it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 23.76it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 24.85it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 29.57it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 30.21it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 34.25it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 33.69it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 36.58it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 34.93it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 34.38it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 38.74it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 36.49it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 30.64it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 31.25it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 28.72it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.35it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 32.31it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 35.27it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 33.86it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 36.76it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 35.42it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 38.05it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 35.58it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 41.67it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:04, 24.73it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 26.44it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 32.99it/s]
Loading 0:  71%|███████   | 206/291 [00:06<00:02, 33.80it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 35.06it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.25it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 37.18it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 35.40it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 35.56it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 35.86it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.94it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 25.96it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.37it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 33.07it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 35.77it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 34.60it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 37.31it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 34.65it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 37.39it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 35.78it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 35.78it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.58it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.21it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama3-v5-v1-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v5-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama3-v5-v1-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v5-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama3-v5-v1-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-duduk-llama3-v5-v1-mkmlizer: Saving duration: 1.356s
trace2333-duduk-llama3-v5-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.694s
trace2333-duduk-llama3-v5-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-duduk-llama3-v5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-duduk-llama3-v5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/special_tokens_map.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/config.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/tokenizer_config.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/merges.txt
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/vocab.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/tokenizer.json
trace2333-duduk-llama3-v5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-duduk-llama3-v5-v1_reward/reward.tensors
Job trace2333-duduk-llama3-v5-v1-mkmlizer completed after 117.61s with status: succeeded
Stopping job with name trace2333-duduk-llama3-v5-v1-mkmlizer
Pipeline stage MKMLizer completed in 222.86s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-duduk-llama3-v5-v1
Waiting for inference service trace2333-duduk-llama3-v5-v1 to be ready
Inference service trace2333-duduk-llama3-v5-v1 ready after 121.08096885681152s
Pipeline stage ISVCDeployer completed in 122.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2552876472473145s
Received healthy response to inference request in 5.306366443634033s
Received healthy response to inference request in 1.4227187633514404s
Received healthy response to inference request in 1.4118304252624512s
Received healthy response to inference request in 1.4073491096496582s
5 requests
0 failed requests
5th percentile: 1.4082453727722168
10th percentile: 1.4091416358947755
20th percentile: 1.4109341621398925
30th percentile: 1.414008092880249
40th percentile: 1.4183634281158448
50th percentile: 1.4227187633514404
60th percentile: 1.75574631690979
70th percentile: 2.0887738704681396
80th percentile: 2.8655034065246587
90th percentile: 4.085934925079346
95th percentile: 4.696150684356689
99th percentile: 5.184323291778564
mean time: 2.3607104778289796
Pipeline stage StressChecker completed in 12.94s
trace2333-duduk-llama3-v5_v1 status is now deployed due to DeploymentManager action
trace2333-duduk-llama3-v5_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-duduk-llama3-v5_v1
Running pipeline stage ISVCDeleter
Checking if service trace2333-duduk-llama3-v5-v1 is running
Tearing down inference service trace2333-duduk-llama3-v5-v1
Service trace2333-duduk-llama3-v5-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.14s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v5-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v5-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v5-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v5-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v5-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v5-v1_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v5-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v5-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v5-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v5-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v5-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v5-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.95s
trace2333-duduk-llama3-v5_v1 status is now torndown due to DeploymentManager action