trace2333-fd-llama3-v3-f_1924

submission_id: trace2333-fd-llama3-v3-f_1924_v1

developer_uid: Trace2333

best_of: 16

celo_rating: 1194.68

display_name: trace2333-fd-llama3-v3-f_1924_v1

family_friendly_score: 0.0

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}

generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.06, 'top_k': 120, '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}

is_internal_developer: False

language_model: Trace2333/fd_llama3_v3_fdall_r64a128_bs32

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Trace2333/fd_llama3_v3_f

model_name: trace2333-fd-llama3-v3-f_1924_v1

model_num_parameters: 8030261248.0

model_repo: Trace2333/fd_llama3_v3_fdall_r64a128_bs32

model_size: 8B

num_battles: 13839

num_wins: 6751

ranking_group: single

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'}

reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634

status: torndown

submission_type: basic

timestamp: 2024-08-06T09:14:08+00:00

us_pacific_date: 2024-08-06

win_ratio: 0.48782426475901436

Resubmit model

Running pipeline stage MKMLizer
Starting job with name trace2333-fd-llama3-v3-f-1924-v1-mkmlizer
Waiting for job on trace2333-fd-llama3-v3-f-1924-v1-mkmlizer to finish
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║       /___/                                                         ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║  Version: 0.9.9                                                     ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission chaiml-elo-run-3-cp7000_v7: ('http://chaiml-elo-run-3-cp7000-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:43810->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v97: ('http://mistralai-mixtral-8x7b-3473-v97-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:50096->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: Downloaded to shared memory in 54.551s
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwgwvlve5, device:0
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: quantized model in 28.820s
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: Processed model Trace2333/fd_llama3_v3_fdall_r64a128_bs32 in 83.372s
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-fd-llama3-v3-f-1924-v1
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v3-f-1924-v1/config.json
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-fd-llama3-v3-f-1924-v1/special_tokens_map.json
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v3-f-1924-v1/tokenizer_config.json
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-fd-llama3-v3-f-1924-v1/tokenizer.json
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-fd-llama3-v3-f-1924-v1/flywheel_model.0.safetensors
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 24.38it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 35.13it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 33.62it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 37.47it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 34.78it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 41.58it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 24.68it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 26.09it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 32.85it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 32.08it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 35.16it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.66it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 36.64it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 35.07it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 35.59it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:05, 35.55it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 25.56it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 28.05it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 29.93it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 29.64it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 32.33it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 30.80it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 33.76it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 32.15it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 32.79it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 37.18it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 33.98it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 28.58it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 28.89it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 27.79it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.24it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 33.00it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 36.31it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 35.22it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 38.43it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 36.20it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 38.11it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 34.80it/s]
Loading 0:  64%|██████▎   | 185/291 [00:05<00:02, 38.92it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:03, 25.51it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 26.71it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.76it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 33.00it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 35.93it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 33.41it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:02, 35.61it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:02, 33.89it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 33.56it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 33.36it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.98it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 25.48it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.29it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 32.68it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 34.85it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 32.86it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 35.58it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 34.34it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 37.27it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 35.26it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 35.15it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.60it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.22it/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-fd-llama3-v3-f-1924-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v3-f-1924-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-fd-llama3-v3-f-1924-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v3-f-1924-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-fd-llama3-v3-f-1924-v1-mkmlizer:   warnings.warn(
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: Saving duration: 1.471s
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 12.637s
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-fd-llama3-v3-f-1924-v1_reward
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-fd-llama3-v3-f-1924-v1_reward/merges.txt
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-fd-llama3-v3-f-1924-v1_reward/vocab.json
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-fd-llama3-v3-f-1924-v1_reward/tokenizer.json
trace2333-fd-llama3-v3-f-1924-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-fd-llama3-v3-f-1924-v1_reward/reward.tensors
Job trace2333-fd-llama3-v3-f-1924-v1-mkmlizer completed after 125.18s with status: succeeded
Stopping job with name trace2333-fd-llama3-v3-f-1924-v1-mkmlizer
Pipeline stage MKMLizer completed in 126.14s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-fd-llama3-v3-f-1924-v1
Waiting for inference service trace2333-fd-llama3-v3-f-1924-v1 to be ready
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service trace2333-fd-llama3-v3-f-1924-v1 ready after 191.19625878334045s
Pipeline stage ISVCDeployer completed in 193.13s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.293519973754883s
Received healthy response to inference request in 1.5027928352355957s
Received healthy response to inference request in 1.4589977264404297s
Received healthy response to inference request in 0.8301854133605957s
Received healthy response to inference request in 1.290724515914917s
5 requests
0 failed requests
5th percentile: 0.92229323387146
10th percentile: 1.0144010543823243
20th percentile: 1.1986166954040527
30th percentile: 1.3243791580200195
40th percentile: 1.3916884422302247
50th percentile: 1.4589977264404297
60th percentile: 1.476515769958496
70th percentile: 1.4940338134765625
80th percentile: 1.6609382629394533
90th percentile: 1.977229118347168
95th percentile: 2.1353745460510254
99th percentile: 2.2618908882141113
mean time: 1.4752440929412842
Pipeline stage StressChecker completed in 9.03s
trace2333-fd-llama3-v3-f_1924_v1 status is now deployed due to DeploymentManager action
trace2333-fd-llama3-v3-f_1924_v1 status is now inactive due to auto deactivation removed underperforming models
trace2333-fd-llama3-v3-f_1924_v1 status is now torndown due to DeploymentManager action