trace2333-fd-llama3-v2-r64a32

developer_uid: Trace2333

submission_id: trace2333-fd-llama3-v2-r64a32_v1

model_name: trace2333-fd-llama3-v2-r64a32_v1

model_group: Trace2333/fd_llama3_v2_r

status: torndown

timestamp: 2024-08-01T14:33:27+00:00

num_battles: 15354

num_wins: 7661

celo_rating: 1205.07

family_friendly_score: 0.0

submission_type: basic

model_repo: Trace2333/fd_llama3_v2_r64a32

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-fd-llama3-v2-r64a32_v1

is_internal_developer: False

language_model: Trace2333/fd_llama3_v2_r64a32

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-01

win_ratio: 0.49895792627328384

generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.06, 'top_k': 250, '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-fd-llama3-v2-r64a32-v1-mkmlizer
Waiting for job on trace2333-fd-llama3-v2-r64a32-v1-mkmlizer to finish
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║       /___/                                                         ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: Downloaded to shared memory in 62.080s
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3w716l1v, device:0
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: quantized model in 28.430s
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: Processed model Trace2333/fd_llama3_v2_r64a32 in 90.510s
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-fd-llama3-v2-r64a32-v1
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v2-r64a32-v1/config.json
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-fd-llama3-v2-r64a32-v1/special_tokens_map.json
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v2-r64a32-v1/tokenizer_config.json
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-fd-llama3-v2-r64a32-v1/tokenizer.json
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.63it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 37.10it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 34.27it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 37.45it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 34.70it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 41.45it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 24.75it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 26.33it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 33.22it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:07, 33.78it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 35.03it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.89it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 36.70it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 35.14it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 35.67it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:05, 35.93it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 25.43it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 27.81it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 30.32it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 29.71it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 32.90it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 32.44it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 35.37it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 34.03it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 34.55it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 39.00it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 35.88it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:04, 31.67it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 31.08it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 29.27it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 34.55it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 33.52it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 36.37it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 34.85it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 37.50it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 35.60it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 38.14it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 35.51it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 40.78it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:04, 25.37it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 26.80it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.42it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 32.72it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 35.33it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 33.22it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.17it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.88it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 35.22it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:01, 35.58it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 27.28it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:01, 26.38it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 34.12it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 32.64it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 34.82it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 33.59it/s]
Loading 0:  91%|█████████ | 264/291 [00:07<00:00, 36.30it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 34.56it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 37.38it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 35.76it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 35.81it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  2.60it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.23it/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-v2-r64a32-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v2-r64a32-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-v2-r64a32-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v2-r64a32-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-v2-r64a32-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: Saving duration: 1.397s
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 12.054s
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-fd-llama3-v2-r64a32-v1_reward
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-r64a32-v1_reward/config.json
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-r64a32-v1_reward/tokenizer_config.json
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-r64a32-v1_reward/special_tokens_map.json
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-fd-llama3-v2-r64a32-v1_reward/merges.txt
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-r64a32-v1_reward/vocab.json
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-r64a32-v1_reward/tokenizer.json
trace2333-fd-llama3-v2-r64a32-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-fd-llama3-v2-r64a32-v1_reward/reward.tensors
Job trace2333-fd-llama3-v2-r64a32-v1-mkmlizer completed after 135.68s with status: succeeded
Stopping job with name trace2333-fd-llama3-v2-r64a32-v1-mkmlizer
Pipeline stage MKMLizer completed in 136.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-fd-llama3-v2-r64a32-v1
Waiting for inference service trace2333-fd-llama3-v2-r64a32-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service trace2333-fd-llama3-v2-r64a32-v1 ready after 130.95444464683533s
Pipeline stage ISVCDeployer completed in 132.50s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.197582244873047s
Received healthy response to inference request in 1.4947140216827393s
Received healthy response to inference request in 1.4381473064422607s
Received healthy response to inference request in 1.4039273262023926s
Received healthy response to inference request in 1.3813717365264893s
5 requests
0 failed requests
5th percentile: 1.38588285446167
10th percentile: 1.3903939723968506
20th percentile: 1.399416208267212
30th percentile: 1.4107713222503662
40th percentile: 1.4244593143463136
50th percentile: 1.4381473064422607
60th percentile: 1.4607739925384522
70th percentile: 1.4834006786346436
80th percentile: 1.635287666320801
90th percentile: 1.916434955596924
95th percentile: 2.057008600234985
99th percentile: 2.1694675159454344
mean time: 1.5831485271453858
Pipeline stage StressChecker completed in 8.66s
trace2333-fd-llama3-v2-r64a32_v1 status is now deployed due to DeploymentManager action
trace2333-fd-llama3-v2-r64a32_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-fd-llama3-v2-r64a32_v1
Running pipeline stage ISVCDeleter
Checking if service trace2333-fd-llama3-v2-r64a32-v1 is running
Tearing down inference service trace2333-fd-llama3-v2-r64a32-v1
Service trace2333-fd-llama3-v2-r64a32-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.44s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-fd-llama3-v2-r64a32-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v2-r64a32-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v2-r64a32-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v2-r64a32-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v2-r64a32-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-fd-llama3-v2-r64a32-v1_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v2-r64a32-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v2-r64a32-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v2-r64a32-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v2-r64a32-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v2-r64a32-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v2-r64a32-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.39s
trace2333-fd-llama3-v2-r64a32_v1 status is now torndown due to DeploymentManager action