submission_id: chaiml-phase2-winner-13b2_v291
developer_uid: FishyCat
alignment_samples: 0
best_of: 4
celo_rating: 844.5
display_name: test
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}:', 'truncate_by_message': False}
generation_params: {'temperature': 64.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
is_internal_developer: False
language_model: ChaiML/phase2_winner_13b2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: ChaiML/phase2_winner_13b
model_name: test
model_num_parameters: 13015864320.0
model_repo: ChaiML/phase2_winner_13b2
model_size: 13B
num_battles: 42951
num_wins: 5408
propriety_score: 0.6507352941176471
propriety_total_count: 2176.0
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: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-17T11:13:43+00:00
us_pacific_date: 2024-07-17
win_ratio: 0.12591092174803847
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-phase2-winner-13b2-v291-mkmlizer
Waiting for job on chaiml-phase2-winner-13b2-v291-mkmlizer to finish
Stopping job with name chaiml-phase2-winner-13b2-v291-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-phase2-winner-13b2-v291-mkmlizer
Waiting for job on chaiml-phase2-winner-13b2-v291-mkmlizer to finish
chaiml-phase2-winner-13b2-v291-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ _____ __ __ ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ /___/ ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ Version: 0.9.5.post2 ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ https://mk1.ai ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ belonging to: ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ Chai Research Corp. ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v291-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-phase2-winner-13b2-v291-mkmlizer: Downloaded to shared memory in 46.743s
chaiml-phase2-winner-13b2-v291-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-phase2-winner-13b2-v291-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-phase2-winner-13b2-v291-mkmlizer: model.embed_tokens.weight torch.Size([43520000])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.0.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.0.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.0.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.0.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.0.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.0.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.1.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.1.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.1.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.1.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.1.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.1.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.2.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.2.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.2.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.2.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.2.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.2.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.3.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.3.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.3.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.3.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.3.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.3.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.4.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.4.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.4.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.4.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.4.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.4.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.5.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.5.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.5.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.5.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.5.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.5.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.6.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.6.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.6.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.6.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.6.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.6.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.7.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.7.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.7.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.7.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.7.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.7.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.8.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.8.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.8.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.8.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.8.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.8.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.9.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.9.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.9.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.9.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.9.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.9.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.10.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.10.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.10.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.10.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.10.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.10.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.11.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.11.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.11.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.11.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.11.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.11.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.12.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.12.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.12.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.12.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.12.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.12.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.13.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.13.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.13.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.13.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.13.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.13.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.14.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.14.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.14.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.14.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.14.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.14.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.15.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.15.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.15.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.15.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.15.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.15.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.16.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.16.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.16.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.16.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.16.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.16.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.17.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.17.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.17.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.17.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.17.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.17.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.18.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.18.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.18.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.18.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.18.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.18.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.19.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.19.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.19.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.19.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.19.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.19.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.20.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.20.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.20.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.20.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.20.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.20.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.21.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.21.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.21.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.21.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.21.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.21.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.22.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.22.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.22.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.22.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.22.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.22.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.23.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.23.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.23.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.23.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.23.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.23.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.24.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.24.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.24.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.24.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.24.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.24.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.25.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.25.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.25.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.25.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.25.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: Loading 0: 0%| | 0/403 [00:00<?, ?it/s] Loading 0: 1%| | 3/403 [00:00<00:03, 101.50it/s] Loading 0: 1%| | 4/403 [00:00<00:03, 132.65it/s] Loading 0: 2%|▏ | 7/403 [00:00<00:01, 226.29it/s] Loading 0: 2%|▏ | 8/403 [00:00<00:01, 254.76it/s] Loading 0: 2%|▏ | 9/403 [00:00<00:01, 285.29it/s] Loading 0: 2%|▏ | 10/403 [00:00<00:01, 315.76it/s] Loading 0: 3%|▎ | 13/403 [00:00<00:00, 405.98it/s] Loading 0: 3%|▎ | 14/403 [00:00<00:00, 431.04it/s] Loading 0: 4%|▍ | 17/403 [00:00<00:00, 511.45it/s] Loading 0: 4%|▍ | 18/403 [00:00<00:00, 534.32it/s] Loading 0: 5%|▍ | 19/403 [00:00<00:00, 561.67it/s] Loading 0: 5%|▍ | 20/403 [00:00<00:00, 589.17it/s] Loading 0: 6%|▌ | 23/403 [00:00<00:00, 670.89it/s] Loading 0: 6%|▌ | 24/403 [00:00<00:00, 691.54it/s] Loading 0: 7%|▋ | 27/403 [00:00<00:00, 765.04it/s] Loading 0: 7%|▋ | 28/403 [00:00<00:00, 783.47it/s] Loading 0: 7%|▋ | 29/403 [00:00<00:00, 808.30it/s] Loading 0: 7%|▋ | 30/403 [00:00<00:00, 833.44it/s] Loading 0: 8%|▊ | 33/403 [00:00<00:00, 908.29it/s] Loading 0: 8%|▊ | 34/403 [00:00<00:00, 924.91it/s] Loading 0: 9%|▉ | 37/403 [00:00<00:00, 990.93it/s] Loading 0: 9%|▉ | 38/403 [00:00<00:00, 1005.19it/s] Loading 0: 10%|▉ | 39/403 [00:00<00:00, 1027.96it/s] Loading 0: 10%|▉ | 40/403 [00:00<00:00, 1050.99it/s] Loading 0: 11%|█ | 43/403 [00:00<00:00, 1119.72it/s] Loading 0: 11%|█ | 44/403 [00:00<00:00, 1133.07it/s] Loading 0: 12%|█▏ | 47/403 [00:00<00:00, 1192.13it/s] Loading 0: 12%|█▏ | 48/403 [00:00<00:00, 1203.42it/s] Loading 0: 12%|█▏ | 49/403 [00:00<00:00, 1224.32it/s] Loading 0: 12%|█▏ | 50/403 [00:00<00:00, 1245.34it/s] Loading 0: 13%|█▎ | 53/403 [00:00<00:00, 1307.88it/s] Loading 0: 13%|█▎ | 54/403 [00:00<00:00, 1318.96it/s] Loading 0: 14%|█▍ | 57/403 [00:00<00:00, 1373.70it/s] Loading 0: 14%|█▍ | 58/403 [00:00<00:00, 1382.98it/s] Loading 0: 15%|█▍ | 59/403 [00:00<00:00, 1402.30it/s] Loading 0: 15%|█▍ | 60/403 [00:00<00:00, 1421.96it/s] Loading 0: 16%|█▌ | 63/403 [00:00<00:00, 1480.50it/s] Loading 0: 16%|█▌ | 64/403 [00:00<00:00, 1489.50it/s] Loading 0: 17%|█▋ | 67/403 [00:00<00:00, 1538.72it/s] Loading 0: 17%|█▋ | 68/403 [00:00<00:00, 1545.98it/s] Loading 0: 17%|█▋ | 69/403 [00:00<00:00, 1563.72it/s] Loading 0: 17%|█▋ | 70/403 [00:00<00:00, 1582.10it/s] Loading 0: 18%|█▊ | 73/403 [00:00<00:00, 1637.20it/s] Loading 0: 18%|█▊ | 74/403 [00:00<00:00, 1643.98it/s] Loading 0: 19%|█▉ | 77/403 [00:00<00:00, 1689.51it/s] Loading 0: 19%|█▉ | 78/403 [00:00<00:00, 1695.03it/s] Loading 0: 20%|█▉ | 79/403 [00:00<00:00, 1711.59it/s] Loading 0: 20%|█▉ | 80/403 [00:00<00:00, 1728.81it/s] Loading 0: 21%|██ | 83/403 [00:00<00:00, 1780.11it/s] Loading 0: 21%|██ | 84/403 [00:00<00:00, 1785.70it/s] Loading 0: 22%|██▏ | 87/403 [00:00<00:00, 1826.79it/s] Loading 0: 22%|██▏ | 88/403 [00:00<00:00, 1830.66it/s] Loading 0: 22%|██▏ | 89/403 [00:00<00:00, 1845.98it/s] Loading 0: 22%|██▏ | 90/403 [00:00<00:00, 1861.15it/s] Loading 0: 23%|██▎ | 93/403 [00:00<00:00, 1909.75it/s] Loading 0: 23%|██▎ | 94/403 [00:00<00:00, 1913.95it/s] Loading 0: 24%|██▍ | 97/403 [00:00<00:00, 1952.89it/s] Loading 0: 24%|██▍ | 98/403 [00:00<00:00, 1955.67it/s] Loading 0: 25%|██▍ | 99/403 [00:00<00:00, 1970.34it/s] Loading 0: 25%|██▍ | 100/403 [00:00<00:00, 1985.55it/s] Loading 0: 26%|██▌ | 103/403 [00:00<00:00, 2031.03it/s] Loading 0: 26%|██▌ | 104/403 [00:00<00:00, 2034.19it/s] Loading 0: 27%|██▋ | 107/403 [00:00<00:00, 2070.07it/s] Loading 0: 27%|██▋ | 108/403 [00:00<00:00, 2072.00it/s] Loading 0: 27%|██▋ | 109/403 [00:00<00:00, 2085.36it/s] Loading 0: 27%|██▋ | 110/403 [00:00<00:00, 2099.65it/s] Loading 0: 28%|██▊ | 113/403 [00:00<00:00, 2142.22it/s] Loading 0: 28%|██▊ | 114/403 [00:00<00:00, 2144.51it/s] Loading 0: 29%|██▉ | 117/403 [00:00<00:00, 2179.47it/s] Loading 0: 29%|██▉ | 118/403 [00:00<00:00, 2179.25it/s] Loading 0: 30%|██▉ | 119/403 [00:00<00:00, 2192.02it/s] Loading 0: 30%|██▉ | 120/403 [00:00<00:00, 2205.62it/s] Loading 0: 31%|███ | 123/403 [00:00<00:00, 2246.50it/s] Loading 0: 31%|███ | 124/403 [00:00<00:00, 2247.45it/s] Loading 0: 32%|███▏ | 127/403 [00:00<00:00, 2278.97it/s] Loading 0: 32%|███▏ | 128/403 [00:00<00:00, 2277.31it/s] Loading 0: 32%|███▏ | 129/403 [00:00<00:00, 2288.55it/s] Loading 0: 32%|███▏ | 130/403 [00:00<00:00, 2301.13it/s] Loading 0: 33%|███▎ | 133/403 [00:00<00:00, 2339.49it/s] Loading 0: 33%|███▎ | 134/403 [00:00<00:00, 2339.88it/s] Loading 0: 34%|███▍ | 137/403 [00:00<00:00, 2370.51it/s] Loading 0: 34%|███▍ | 138/403 [00:00<00:00, 2369.64it/s] Loading 0: 34%|███▍ | 139/403 [00:00<00:00, 2381.25it/s] Loading 0: 35%|███▍ | 140/403 [00:00<00:00, 2392.96it/s] Loading 0: 35%|███▌ | 143/403 [00:00<00:00, 2429.92it/s] Loading 0: 36%|███▌ | 144/403 [00:00<00:00, 2427.90it/s] Loading 0: 36%|███▋ | 147/403 [00:00<00:00, 2456.43it/s] Loading 0: 37%|███▋ | 148/403 [00:00<00:00, 2455.00it/s] Loading 0: 37%|███▋ | 149/403 [00:00<00:00, 2465.94it/s] Loading 0: 37%|███▋ | 150/403 [00:00<00:00, 2477.61it/s] Loading 0: 38%|███▊ | 153/403 [00:02<00:04, 54.85it/s] Loading 0: 38%|███▊ | 154/403 [00:02<00:04, 55.21it/s] Loading 0: 38%|███▊ | 154/403 [00:02<00:04, 55.21it/s] Loading 0: 39%|███▉ | 157/403 [00:02<00:04, 55.21it/s] Loading 0: 39%|███▉ | 158/403 [00:02<00:04, 55.21it/s] Loading 0: 39%|███▉ | 159/403 [00:02<00:04, 55.21it/s] Loading 0: 40%|███▉ | 160/403 [00:02<00:04, 55.21it/s] Loading 0: 40%|████ | 163/403 [00:02<00:04, 55.21it/s] Loading 0: 41%|████ | 164/403 [00:02<00:04, 55.21it/s] Loading 0: 41%|████▏ | 167/403 [00:02<00:04, 55.21it/s] Loading 0: 42%|████▏ | 168/403 [00:02<00:04, 55.21it/s] Loading 0: 42%|████▏ | 169/403 [00:02<00:04, 55.21it/s] Loading 0: 42%|████▏ | 170/403 [00:02<00:04, 55.21it/s] Loading 0: 43%|████▎ | 173/403 [00:02<00:04, 55.21it/s] Loading 0: 43%|████▎ | 174/403 [00:02<00:04, 55.21it/s] Loading 0: 44%|████▍ | 177/403 [00:02<00:04, 55.21it/s] Loading 0: 44%|████▍ | 178/403 [00:02<00:04, 55.21it/s] Loading 0: 44%|████▍ | 179/403 [00:02<00:04, 55.21it/s] Loading 0: 45%|████▍ | 180/403 [00:02<00:04, 55.21it/s] Loading 0: 45%|████▌ | 183/403 [00:02<00:03, 55.21it/s] Loading 0: 46%|████▌ | 184/403 [00:02<00:03, 55.21it/s] Loading 0: 46%|████▋ | 187/403 [00:02<00:03, 55.21it/s] Loading 0: 47%|████▋ | 188/403 [00:02<00:03, 55.21it/s] Loading 0: 47%|████▋ | 189/403 [00:02<00:03, 55.21it/s] Loading 0: 47%|████▋ | 190/403 [00:02<00:03, 55.21it/s] Loading 0: 48%|████▊ | 193/403 [00:02<00:03, 55.21it/s] Loading 0: 48%|████▊ | 194/403 [00:02<00:03, 55.21it/s] Loading 0: 49%|████▉ | 197/403 [00:02<00:03, 55.21it/s] Loading 0: 49%|████▉ | 198/403 [00:02<00:03, 55.21it/s] Loading 0: 49%|████▉ | 199/403 [00:02<00:03, 55.21it/s] Loading 0: 50%|████▉ | 200/403 [00:02<00:03, 55.21it/s] Loading 0: 50%|█████ | 203/403 [00:02<00:03, 55.21it/s] Loading 0: 51%|█████ | 204/403 [00:02<00:03, 55.21it/s] Loading 0: 51%|█████▏ | 207/403 [00:02<00:03, 55.21it/s] Loading 0: 52%|█████▏ | 208/403 [00:02<00:03, 55.21it/s] Loading 0: 52%|███model.layers.25.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.26.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.26.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.26.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.26.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.26.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.26.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.27.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.27.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.27.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.27.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.27.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.27.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.28.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.28.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.28.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.28.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.28.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.28.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.29.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.29.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.29.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.29.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.29.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.29.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.30.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.30.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v291-mkmlizer: model.layers.30.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v291-mkmlizer: quantized model in 31.958s
chaiml-phase2-winner-13b2-v291-mkmlizer: Processed model ChaiML/phase2_winner_13b2 in 78.701s
chaiml-phase2-winner-13b2-v291-mkmlizer: creating bucket guanaco-mkml-models
chaiml-phase2-winner-13b2-v291-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-phase2-winner-13b2-v291-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v291
chaiml-phase2-winner-13b2-v291-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v291/config.json
chaiml-phase2-winner-13b2-v291-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v291/tokenizer_config.json
chaiml-phase2-winner-13b2-v291-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v291/special_tokens_map.json
chaiml-phase2-winner-13b2-v291-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v291/tokenizer.json
chaiml-phase2-winner-13b2-v291-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v291/tokenizer.model
chaiml-phase2-winner-13b2-v291-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v291/flywheel_model.0.safetensors
chaiml-phase2-winner-13b2-v291-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
chaiml-phase2-winner-13b2-v291-mkmlizer: ██▏ | 209/403 [00:02<00:03, 55.21it/s] Loading 0: 52%|█████▏ | 210/403 [00:02<00:03, 55.21it/s] Loading 0: 53%|█████▎ | 213/403 [00:02<00:03, 55.21it/s] Loading 0: 53%|█████▎ | 214/403 [00:02<00:03, 55.21it/s] Loading 0: 54%|█████▍ | 217/403 [00:02<00:03, 55.21it/s] Loading 0: 54%|█████▍ | 218/403 [00:02<00:03, 55.21it/s] Loading 0: 54%|█████▍ | 219/403 [00:02<00:03, 55.21it/s] Loading 0: 55%|█████▍ | 220/403 [00:02<00:03, 55.21it/s] Loading 0: 55%|█████▌ | 223/403 [00:02<00:03, 55.21it/s] Loading 0: 56%|█████▌ | 224/403 [00:02<00:03, 55.21it/s] Loading 0: 56%|█████▋ | 227/403 [00:02<00:03, 55.21it/s] Loading 0: 57%|█████▋ | 228/403 [00:02<00:03, 55.21it/s] Loading 0: 57%|█████▋ | 229/403 [00:02<00:03, 55.21it/s] Loading 0: 57%|█████▋ | 230/403 [00:02<00:03, 55.21it/s] Loading 0: 58%|█████▊ | 233/403 [00:02<00:03, 55.21it/s] Loading 0: 58%|█████▊ | 234/403 [00:02<00:03, 55.21it/s] Loading 0: 59%|█████▉ | 237/403 [00:02<00:03, 55.21it/s] Loading 0: 59%|█████▉ | 238/403 [00:02<00:02, 55.21it/s] Loading 0: 59%|█████▉ | 239/403 [00:02<00:02, 55.21it/s] Loading 0: 60%|█████▉ | 240/403 [00:02<00:02, 55.21it/s] Loading 0: 60%|██████ | 243/403 [00:02<00:02, 55.21it/s] Loading 0: 61%|██████ | 244/403 [00:02<00:02, 55.21it/s] Loading 0: 61%|██████▏ | 247/403 [00:02<00:02, 55.21it/s] Loading 0: 62%|██████▏ | 248/403 [00:02<00:02, 55.21it/s] Loading 0: 62%|██████▏ | 249/403 [00:02<00:02, 55.21it/s] Loading 0: 62%|██████▏ | 250/403 [00:02<00:02, 55.21it/s] Loading 0: 63%|██████▎ | 253/403 [00:02<00:02, 55.21it/s] Loading 0: 63%|██████▎ | 254/403 [00:02<00:02, 55.21it/s] Loading 0: 64%|██████▍ | 257/403 [00:02<00:02, 55.21it/s] Loading 0: 64%|██████▍ | 258/403 [00:02<00:02, 55.21it/s] Loading 0: 64%|██████▍ | 259/403 [00:02<00:01, 103.65it/s] Loading 0: 64%|██████▍ | 259/403 [00:02<00:01, 103.65it/s] Loading 0: 65%|██████▍ | 260/403 [00:02<00:01, 103.65it/s] Loading 0: 65%|██████▌ | 263/403 [00:02<00:01, 103.65it/s] Loading 0: 66%|██████▌ | 264/403 [00:02<00:01, 103.65it/s] Loading 0: 66%|██████▋ | 267/403 [00:02<00:01, 103.65it/s] Loading 0: 67%|██████▋ | 268/403 [00:02<00:01, 103.65it/s] Loading 0: 67%|██████▋ | 269/403 [00:02<00:01, 103.65it/s] Loading 0: 67%|██████▋ | 270/403 [00:02<00:01, 103.65it/s] Loading 0: 68%|██████▊ | 273/403 [00:02<00:01, 103.65it/s] Loading 0: 68%|██████▊ | 274/403 [00:02<00:01, 103.65it/s] Loading 0: 69%|██████▊ | 277/403 [00:02<00:01, 103.65it/s] Loading 0: 69%|██████▉ | 278/403 [00:02<00:01, 103.65it/s] Loading 0: 69%|██████▉ | 279/403 [00:02<00:01, 103.65it/s] Loading 0: 69%|██████▉ | 280/403 [00:02<00:01, 103.65it/s] Loading 0: 70%|███████ | 283/403 [00:02<00:01, 103.65it/s] Loading 0: 70%|███████ | 284/403 [00:02<00:01, 103.65it/s] Loading 0: 71%|███████ | 287/403 [00:02<00:01, 103.65it/s] Loading 0: 71%|███████▏ | 288/403 [00:02<00:01, 103.65it/s] Loading 0: 72%|███████▏ | 289/403 [00:02<00:01, 103.65it/s] Loading 0: 72%|███████▏ | 290/403 [00:02<00:01, 103.65it/s] Loading 0: 73%|███████▎ | 293/403 [00:02<00:01, 103.65it/s] Loading 0: 73%|███████▎ | 294/403 [00:02<00:01, 103.65it/s] Loading 0: 74%|███████▎ | 297/403 [00:02<00:01, 103.65it/s] Loading 0: 74%|███████▍ | 298/403 [00:02<00:01, 103.65it/s] Loading 0: 74%|███████▍ | 299/403 [00:02<00:01, 103.65it/s] Loading 0: 74%|███████▍ | 300/403 [00:02<00:00, 103.65it/s] Loading 0: 75%|███████▌ | 303/403 [00:02<00:00, 103.65it/s] Loading 0: 75%|███████▌ | 304/403 [00:02<00:00, 103.65it/s] Loading 0: 76%|███████▌ | 307/403 [00:02<00:00, 103.65it/s] Loading 0: 76%|███████▋ | 308/403 [00:04<00:00, 103.65it/s] Loading 0: 77%|███████▋ | 309/403 [00:04<00:00, 103.65it/s] Loading 0: 77%|███████▋ | 310/403 [00:04<00:00, 103.65it/s] Loading 0: 78%|███████▊ | 313/403 [00:04<00:00, 103.65it/s] Loading 0: 78%|███████▊ | 314/403 [00:04<00:00, 103.65it/s] Loading 0: 79%|███████▊ | 317/403 [00:04<00:00, 103.65it/s] Loading 0: 79%|███████▉ | 318/403 [00:04<00:00, 103.65it/s] Loading 0: 79%|███████▉ | 319/403 [00:04<00:00, 103.65it/s] Loading 0: 79%|███████▉ | 320/403 [00:04<00:00, 103.65it/s] Loading 0: 80%|████████ | 323/403 [00:04<00:01, 67.44it/s] Loading 0: 80%|████████ | 323/403 [00:04<00:01, 67.44it/s] Loading 0: 80%|████████ | 324/403 [00:04<00:01, 67.44it/s] Loading 0: 81%|████████ | 327/403 [00:04<00:01, 67.44it/s] Loading 0: 81%|████████▏ | 328/403 [00:04<00:01, 67.44it/s] Loading 0: 82%|████████▏ | 329/403 [00:04<00:01, 67.44it/s] Loading 0: 82%|████████▏ | 330/403 [00:04<00:01, 67.44it/s] Loading 0: 83%|████████▎ | 333/403 [00:04<00:01, 67.44it/s] Loading 0: 83%|████████▎ | 334/403 [00:04<00:01, 67.44it/s] Loading 0: 84%|████████▎ | 337/403 [00:04<00:00, 67.44it/s] Loading 0: 84%|████████▍ | 338/403 [00:04<00:00, 67.44it/s] Loading 0: 84%|████████▍ | 339/403 [00:04<00:00, 67.44it/s] Loading 0: 84%|████████▍ | 340/403 [00:04<00:00, 67.44it/s] Loading 0: 85%|████████▌ | 343/403 [00:04<00:00, 67.44it/s] Loading 0: 85%|████████▌ | 344/403 [00:04<00:00, 67.44it/s] Loading 0: 86%|████████▌ | 347/403 [00:04<00:00, 67.44it/s] Loading 0: 86%|████████▋ | 348/403 [00:04<00:00, 67.44it/s] Loading 0: 87%|████████▋ | 349/403 [00:04<00:00, 67.44it/s] Loading 0: 87%|████████▋ | 350/403 [00:04<00:00, 67.44it/s] Loading 0: 88%|████████▊ | 353/403 [00:04<00:00, 67.44it/s] Loading 0: 88%|████████▊ | 354/403 [00:04<00:00, 67.44it/s] Loading 0: 89%|████████▊ | 357/403 [00:04<00:00, 67.44it/s] Loading 0: 89%|████████▉ | 358/403 [00:04<00:00, 67.44it/s] Loading 0: 89%|████████▉ | 359/403 [00:04<00:00, 67.44it/s] Loading 0: 89%|████████▉ | 360/403 [00:04<00:00, 67.44it/s] Loading 0: 90%|█████████ | 363/403 [00:04<00:00, 67.44it/s] Loading 0: 90%|█████████ | 364/403 [00:04<00:00, 67.44it/s] Loading 0: 91%|█████████ | 367/403 [00:04<00:00, 67.44it/s] Loading 0: 91%|█████████▏| 368/403 [00:04<00:00, 67.44it/s] Loading 0: 92%|█████████▏| 369/403 [00:04<00:00, 67.44it/s] Loading 0: 92%|█████████▏| 370/403 [00:04<00:00, 67.44it/s] Loading 0: 93%|█████████▎| 373/403 [00:04<00:00, 67.44it/s] Loading 0: 93%|█████████▎| 374/403 [00:04<00:00, 67.44it/s] Loading 0: 94%|█████████▎| 377/403 [00:04<00:00, 67.44it/s] Loading 0: 94%|█████████▍| 378/403 [00:04<00:00, 67.44it/s] Loading 0: 94%|█████████▍| 379/403 [00:04<00:00, 67.44it/s] Loading 0: 94%|█████████▍| 380/403 [00:04<00:00, 67.44it/s] Loading 0: 95%|█████████▌| 383/403 [00:04<00:00, 67.44it/s] Loading 0: 95%|█████████▌| 384/403 [00:04<00:00, 67.44it/s] Loading 0: 96%|█████████▌| 387/403 [00:04<00:00, 67.44it/s] Loading 0: 96%|█████████▋| 388/403 [00:04<00:00, 67.44it/s] Loading 0: 97%|█████████▋| 389/403 [00:04<00:00, 67.44it/s] Loading 0: 97%|█████████▋| 390/403 [00:04<00:00, 67.44it/s] Loading 0: 98%|█████████▊| 393/403 [00:04<00:00, 67.44it/s] Loading 0: 98%|█████████▊| 394/403 [00:04<00:00, 67.44it/s] Loading 0: 99%|█████████▊| 397/403 [00:04<00:00, 67.44it/s] Loading 0: 99%|█████████▉| 398/403 [00:04<00:00, 67.44it/s] Loading 0: 99%|█████████▉| 399/403 [00:04<00:00, 67.44it/s] Loading 0: 99%|█████████▉| 400/403 [00:04<00:00, 67.44it/s] Loading 0: 100%|█████████▉| 401/403 [00:04<00:00, 67.44it/s] Loading 0: 100%|█████████▉| 402/403 [00:06<00:00, 67.44it/s] Loading 0: 100%|██████████| 403/403 [00:06<00:00, 54.07it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-phase2-winner-13b2-v291-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v291-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-phase2-winner-13b2-v291-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v291-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.
chaiml-phase2-winner-13b2-v291-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v291-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-phase2-winner-13b2-v291-mkmlizer: Saving duration: 0.526s
chaiml-phase2-winner-13b2-v291-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.640s
chaiml-phase2-winner-13b2-v291-mkmlizer: creating bucket guanaco-reward-models
chaiml-phase2-winner-13b2-v291-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-phase2-winner-13b2-v291-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v291_reward
chaiml-phase2-winner-13b2-v291-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v291_reward/config.json
chaiml-phase2-winner-13b2-v291-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v291_reward/merges.txt
chaiml-phase2-winner-13b2-v291-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v291_reward/tokenizer_config.json
chaiml-phase2-winner-13b2-v291-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v291_reward/special_tokens_map.json
chaiml-phase2-winner-13b2-v291-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v291_reward/vocab.json
chaiml-phase2-winner-13b2-v291-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v291_reward/tokenizer.json
chaiml-phase2-winner-13b2-v291-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v291_reward/reward.tensors
Job chaiml-phase2-winner-13b2-v291-mkmlizer completed after 149.41s with status: succeeded
Stopping job with name chaiml-phase2-winner-13b2-v291-mkmlizer
Pipeline stage MKMLizer completed in 150.81s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-phase2-winner-13b2-v291
Waiting for inference service chaiml-phase2-winner-13b2-v291 to be ready
Inference service chaiml-phase2-winner-13b2-v291 ready after 40.164867639541626s
Pipeline stage ISVCDeployer completed in 47.09s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.655134677886963s
Received healthy response to inference request in 1.6045095920562744s
Received healthy response to inference request in 1.6359789371490479s
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
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
Received healthy response to inference request in 1.6236746311187744s
Received healthy response to inference request in 1.6230106353759766s
5 requests
0 failed requests
5th percentile: 1.6082098007202148
10th percentile: 1.6119100093841552
20th percentile: 1.6193104267120362
30th percentile: 1.6231434345245361
40th percentile: 1.6234090328216553
50th percentile: 1.6236746311187744
60th percentile: 1.6285963535308838
70th percentile: 1.6335180759429933
80th percentile: 1.839810085296631
90th percentile: 2.247472381591797
95th percentile: 2.4513035297393797
99th percentile: 2.614368448257446
mean time: 1.8284616947174073
Pipeline stage StressChecker completed in 10.54s
chaiml-phase2-winner-13b2_v291 status is now deployed due to DeploymentManager action
chaiml-phase2-winner-13b2_v291 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-phase2-winner-13b2_v291
Running pipeline stage ISVCDeleter
Checking if service chaiml-phase2-winner-13b2-v291 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.35s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-phase2-winner-13b2-v291/config.json from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v291/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v291/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v291/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v291/tokenizer.model from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v291/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-phase2-winner-13b2-v291_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v291_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v291_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v291_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v291_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v291_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v291_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 8.10s
chaiml-phase2-winner-13b2_v291 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics