developer_uid: zonemercy
submission_id: zonemercy-eloquent-user-_7583_v3
model_name: zonemercy-eloquent-user-_7583_v3
model_group: zonemercy/Eloquent-User-
status: torndown
timestamp: 2024-07-30T00:51:13+00:00
num_battles: 13108
num_wins: 5275
celo_rating: 1129.02
family_friendly_score: 0.0
submission_type: basic
model_repo: zonemercy/Eloquent-User-l3-ep4
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
display_name: zonemercy-eloquent-user-_7583_v3
is_internal_developer: True
language_model: zonemercy/Eloquent-User-l3-ep4
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-29
win_ratio: 0.4024259993896857
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###', 'Bot:', 'User:'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64, 'reward_max_token_input': 256}
formatter: {'memory_template': "Bot's Name: {bot_name}\nBot's Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name zonemercy-eloquent-user-7583-v3-mkmlizer
Waiting for job on zonemercy-eloquent-user-7583-v3-mkmlizer to finish
zonemercy-eloquent-user-7583-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ _____ __ __ ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ /___/ ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ Version: 0.9.7 ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ https://mk1.ai ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ belonging to: ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ Chai Research Corp. ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ║ ║
zonemercy-eloquent-user-7583-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-eloquent-user-7583-v3-mkmlizer: Downloaded to shared memory in 43.072s
zonemercy-eloquent-user-7583-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphqh3tyf0, device:0
zonemercy-eloquent-user-7583-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-eloquent-user-7583-v3-mkmlizer: quantized model in 28.693s
zonemercy-eloquent-user-7583-v3-mkmlizer: Processed model zonemercy/Eloquent-User-l3-ep4 in 71.765s
zonemercy-eloquent-user-7583-v3-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-eloquent-user-7583-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-eloquent-user-7583-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-eloquent-user-7583-v3
zonemercy-eloquent-user-7583-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-eloquent-user-7583-v3/config.json
zonemercy-eloquent-user-7583-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-eloquent-user-7583-v3/special_tokens_map.json
zonemercy-eloquent-user-7583-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-eloquent-user-7583-v3/tokenizer_config.json
zonemercy-eloquent-user-7583-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-eloquent-user-7583-v3/tokenizer.json
zonemercy-eloquent-user-7583-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-eloquent-user-7583-v3/flywheel_model.0.safetensors
zonemercy-eloquent-user-7583-v3-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
zonemercy-eloquent-user-7583-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.03it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:06, 42.84it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:06, 39.50it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:06, 39.04it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:06, 39.01it/s] Loading 0: 11%|█ | 32/291 [00:00<00:06, 38.74it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 23.68it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 25.78it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 33.81it/s] Loading 0: 18%|█▊ | 53/291 [00:01<00:06, 34.49it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:06, 35.54it/s] Loading 0: 21%|██▏ | 62/291 [00:01<00:06, 36.19it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:06, 36.90it/s] Loading 0: 24%|██▍ | 71/291 [00:02<00:05, 36.97it/s] Loading 0: 26%|██▌ | 75/291 [00:02<00:07, 30.11it/s] Loading 0: 27%|██▋ | 80/291 [00:02<00:08, 25.89it/s] Loading 0: 29%|██▊ | 83/291 [00:02<00:08, 23.63it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 31.51it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 31.49it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 34.88it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 33.07it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 34.96it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 33.38it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 33.99it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 39.20it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 36.00it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 30.43it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 30.36it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 28.51it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.37it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 32.30it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 34.94it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 33.58it/s] Loading 0: 57%|█████▋ | 165/291 [00:04<00:03, 36.36it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 33.63it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 36.17it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 34.13it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 39.74it/s] Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 24.16it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 25.51it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.24it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 31.63it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 34.49it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 33.41it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:01, 36.50it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:01, 34.72it/s] Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 33.86it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 33.12it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 24.23it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 24.27it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 32.34it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 31.60it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:01, 34.66it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 33.38it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 36.73it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 34.54it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 36.34it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 34.63it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 34.57it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.59it/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.
zonemercy-eloquent-user-7583-v3-mkmlizer: warnings.warn(
zonemercy-eloquent-user-7583-v3-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.
zonemercy-eloquent-user-7583-v3-mkmlizer: warnings.warn(
zonemercy-eloquent-user-7583-v3-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.
zonemercy-eloquent-user-7583-v3-mkmlizer: warnings.warn(
zonemercy-eloquent-user-7583-v3-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.61s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.66s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.96s/it]
zonemercy-eloquent-user-7583-v3-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.44it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 4.00it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.64it/s]
zonemercy-eloquent-user-7583-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
zonemercy-eloquent-user-7583-v3-mkmlizer: Saving duration: 1.350s
zonemercy-eloquent-user-7583-v3-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 15.153s
zonemercy-eloquent-user-7583-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
zonemercy-eloquent-user-7583-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/zonemercy-eloquent-user-7583-v3_reward
zonemercy-eloquent-user-7583-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/zonemercy-eloquent-user-7583-v3_reward/config.json
zonemercy-eloquent-user-7583-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/zonemercy-eloquent-user-7583-v3_reward/special_tokens_map.json
zonemercy-eloquent-user-7583-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/zonemercy-eloquent-user-7583-v3_reward/tokenizer_config.json
zonemercy-eloquent-user-7583-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/zonemercy-eloquent-user-7583-v3_reward/merges.txt
zonemercy-eloquent-user-7583-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/zonemercy-eloquent-user-7583-v3_reward/vocab.json
zonemercy-eloquent-user-7583-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/zonemercy-eloquent-user-7583-v3_reward/tokenizer.json
zonemercy-eloquent-user-7583-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/zonemercy-eloquent-user-7583-v3_reward/reward.tensors
Job zonemercy-eloquent-user-7583-v3-mkmlizer completed after 126.24s with status: succeeded
Stopping job with name zonemercy-eloquent-user-7583-v3-mkmlizer
Pipeline stage MKMLizer completed in 127.29s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service zonemercy-eloquent-user-7583-v3
Waiting for inference service zonemercy-eloquent-user-7583-v3 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service zonemercy-eloquent-user-7583-v3 ready after 110.6951355934143s
Pipeline stage ISVCDeployer completed in 112.45s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.44584059715271s
Received healthy response to inference request in 1.186042308807373s
Received healthy response to inference request in 1.0288903713226318s
Received healthy response to inference request in 1.05303955078125s
Received healthy response to inference request in 0.7949984073638916s
5 requests
0 failed requests
5th percentile: 0.8417768001556396
10th percentile: 0.8885551929473877
20th percentile: 0.9821119785308838
30th percentile: 1.0337202072143554
40th percentile: 1.0433798789978028
50th percentile: 1.05303955078125
60th percentile: 1.1062406539916991
70th percentile: 1.1594417572021485
80th percentile: 1.2380019664764406
90th percentile: 1.3419212818145752
95th percentile: 1.3938809394836424
99th percentile: 1.4354486656188965
mean time: 1.1017622470855712
Pipeline stage StressChecker completed in 6.58s
zonemercy-eloquent-user-_7583_v3 status is now deployed due to DeploymentManager action
zonemercy-eloquent-user-_7583_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of zonemercy-eloquent-user-_7583_v3
Running pipeline stage ISVCDeleter
Checking if service zonemercy-eloquent-user-7583-v3 is running
Tearing down inference service zonemercy-eloquent-user-7583-v3
Service zonemercy-eloquent-user-7583-v3 has been torndown
Pipeline stage ISVCDeleter completed in 4.33s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key zonemercy-eloquent-user-7583-v3/config.json from bucket guanaco-mkml-models
Deleting key zonemercy-eloquent-user-7583-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-eloquent-user-7583-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key zonemercy-eloquent-user-7583-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key zonemercy-eloquent-user-7583-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key zonemercy-eloquent-user-7583-v3_reward/config.json from bucket guanaco-reward-models
Deleting key zonemercy-eloquent-user-7583-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key zonemercy-eloquent-user-7583-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key zonemercy-eloquent-user-7583-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key zonemercy-eloquent-user-7583-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key zonemercy-eloquent-user-7583-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key zonemercy-eloquent-user-7583-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.64s
zonemercy-eloquent-user-_7583_v3 status is now torndown due to DeploymentManager action